This paper proposes a robust control scheme based on the sequential convex programming and learning-based model for nonlinear system subjected to additive uncertainties.For the problem of system nonlinearty and unknow...This paper proposes a robust control scheme based on the sequential convex programming and learning-based model for nonlinear system subjected to additive uncertainties.For the problem of system nonlinearty and unknown uncertainties,we study the tube-based model predictive control scheme that makes use of feedforward neural network.Based on the characteristics of the bounded limit of the average cost function while time approaching infinity,a min-max optimization problem(referred to as min-max OP)is formulated to design the controller.The feasibility of this optimization problem and the practical stability of the controlled system are ensured.To demonstrate the efficacy of the proposed approach,a numerical simulation on a double-tank system is conducted.The results of the simulation serve as verification of the effectualness of the proposed scheme.展开更多
The rapid prediction of aerodynamic performance is critical in the conceptual and preliminary design of hypersonic vehicles. This study focused on axisymmetric body configurations commonly used in such vehicles and pr...The rapid prediction of aerodynamic performance is critical in the conceptual and preliminary design of hypersonic vehicles. This study focused on axisymmetric body configurations commonly used in such vehicles and proposed a multi-fidelity neural network (MFNN) framework to fuse aerodynamic data of varying quality. A data-driven prediction model was constructed using a pointwise modeling method based on generating lines to input geometric features into the network. The MFNN framework combined low-fidelity and high-fidelity networks, trained on aerodynamic performance data from engineering rapid computation methods and CFD, respectively, using spherically blunted cones as examples. The results showed that the MFNN effectively integrated multi-fidelity data, achieving prediction accuracy close to CFD results in most regions, with errors under 5% in key stagnation areas. The model demonstrated strong generalization capabilities for varying cone dimensions and flight conditions. Furthermore, it significantly reduced dependence on high-fidelity data, enabling efficient aerodynamic performance predictions with limited datasets. This study provides a novel methodology for rapid aerodynamic performance prediction, offering both accuracy and efficiency, and contributes to the design of hypersonic vehicles.展开更多
Over 1.3 million people die annually in traffic accidents,and this tragic fact highlights the urgent need to enhance the intelligence of traffic safety and control systems.In modern industrial and technological applic...Over 1.3 million people die annually in traffic accidents,and this tragic fact highlights the urgent need to enhance the intelligence of traffic safety and control systems.In modern industrial and technological applications and collaborative edge intelligence,control systems are crucial for ensuring efficiency and safety.However,deficiencies in these systems can lead to significant operational risks.This paper uses edge intelligence to address the challenges of achieving target speeds and improving efficiency in vehicle control,particularly the limitations of traditional Proportional-Integral-Derivative(PID)controllers inmanaging nonlinear and time-varying dynamics,such as varying road conditions and vehicle behavior,which often result in substantial discrepancies between desired and actual speeds,as well as inefficiencies due to manual parameter adjustments.The paper uses edge intelligence to propose a novel PID control algorithm that integrates Backpropagation(BP)neural networks to enhance robustness and adaptability.The BP neural network is first trained to capture the nonlinear dynamic characteristics of the vehicle.Thetrained network is then combined with the PID controller to forma hybrid control strategy.The output layer of the neural network directly adjusts the PIDparameters(k_(p),k_(i),k_(d)),optimizing performance for specific driving scenarios through self-learning and weight adjustments.Simulation experiments demonstrate that our BP neural network-based PID design significantly outperforms traditional methods,with the response time for acceleration from 0 to 1 m/s improved from 0.25 s to just 0.065 s.Furthermore,real-world tests on an intelligent vehicle show its ability to make timely adjustments in response to complex road conditions,ensuring consistent speed maintenance and enhancing overall system performance.展开更多
A distributionally robust model predictive control(DRMPC)scheme is proposed based on neural network(NN)modeling to achieve the trajectory tracking control of robot manipulators with state and control torque constraint...A distributionally robust model predictive control(DRMPC)scheme is proposed based on neural network(NN)modeling to achieve the trajectory tracking control of robot manipulators with state and control torque constraints.First,an NN is used to fit the motion data of robot manipulators for data-driven dynamic modeling,converting it into a linear prediction model through gradients.Then,by statistically analyzing the stochastic characteristics of the NN modeling errors,a distributionally robust model predictive controller is designed based on the chance constraints,and the optimization problem is transformed into a tractable quadratic programming(QP)problem under the distributionally robust optimization(DRO)framework.The recursive feasibility and convergence of the proposed algorithm are proven.Finally,the effectiveness of the proposed algorithm is verified through numerical simulation.展开更多
In the realm of engineering practice,various factors such as limited availability of measurement data and complex working conditions pose significant challenges to obtaining accurate load spectra.Thus,accurately predi...In the realm of engineering practice,various factors such as limited availability of measurement data and complex working conditions pose significant challenges to obtaining accurate load spectra.Thus,accurately predicting the fatigue life of structures becomes notably arduous.This paper proposed an approach to predict the fatigue life of structure based on the optimized load spectra,which is accurately estimated by an efficient hinging hyperplane neural network(EHH-NN)model.The construction of the EHH-NN model includes initial network generation and parameter optimization.Through the combination of working conditions design,multi-body dynamics analysis and structural static mechanics analysis,the simulated load spectra of the structure are obtained.The simulated load spectra are taken as the input variables for the optimized EHH-NN model,while the measurement load spectra are used as the output variables.The prediction results of case structure indicate that the optimized EHH-NN model can achieve the high-accuracy load spectra,in comparison with support vector machine(SVM),random forest(RF)model and back propagation(BP)neural network.The error rate between the prediction values and the measurement values of the optimized EHH-NN model is 4.61%.In the Cauchy-Lorentz distribution,the absolute error data of 92%with EHH-NN model appear in the intermediate range of±1.65%.Also,the fatigue life analysis is performed for the case structure,based on the accurately predicted load spectra.The fatigue life of the case structure is calculated based on the comparison between the measured and predicted load spectra,with an accuracy of 93.56%.This research proposes the optimized EHH-NN model can more accurately reflect the measurement load spectra,enabling precise calculation of fatigue life.Additionally,the optimized EHH-NN model provides reliability assessment for industrial engineering equipment.展开更多
For a class of complex industrial processes with strong nonlinearity, serious coupling and uncertainty, a nonlinear decoupling proportional-integral-differential （PID） controller is proposed, which consists of a tra...For a class of complex industrial processes with strong nonlinearity, serious coupling and uncertainty, a nonlinear decoupling proportional-integral-differential （PID） controller is proposed, which consists of a traditional PID controller, a decoupling compensator and a feedforward compensator for the unmodeled dynamics. The parameters of such controller is selected based on the generalized minimum variance control law. The unmodeled dynamics is estimated and compensated by neural networks, a switching mechanism is introduced to improve tracking performance, then a nonlinear decoupling PID control algorithm is proposed. All signals in such switching system are globally bounded and the tracking error is convergent. Simulations show effectiveness of the algorithm.展开更多
Pneumatic muscle actuators(PMAs)are compliant and suitable for robotic devices that have been shown to be effective in assisting patients with neurologic injuries,such as strokes,spinal cord injuries,etc.,to accomplis...Pneumatic muscle actuators(PMAs)are compliant and suitable for robotic devices that have been shown to be effective in assisting patients with neurologic injuries,such as strokes,spinal cord injuries,etc.,to accomplish rehabilitation tasks.However,because PMAs have nonlinearities,hysteresis,and uncertainties,etc.,complex mechanisms are rarely involved in the study of PMA-driven robotic systems.In this paper,we use nonlinear model predictive control(NMPC)and an extension of the echo state network called an echo state Gaussian process(ESGP)to design a tracking controller for a PMA-driven lower limb exoskeleton.The dynamics of the system include the PMA actuation and mechanism of the leg orthoses;thus,the system is represented by two nonlinear uncertain subsystems.To facilitate the design of the controller,joint angles of leg orthoses are forecasted based on the universal approximation ability of the ESGP.A gradient descent algorithm is employed to solve the optimization problem and generate the control signal.The stability of the closed-loop system is guaranteed when the ESGP is capable of approximating system dynamics.Simulations and experiments are conducted to verify the approximation ability of the ESGP and achieve gait pattern training with four healthy subjects.展开更多
The performance of the model algorithm control method is partially based on the accuracy of the system＇s model. It is difficult to obtain a good model of a nonlinear system, especially when the nonlinearity is high. ...The performance of the model algorithm control method is partially based on the accuracy of the system＇s model. It is difficult to obtain a good model of a nonlinear system, especially when the nonlinearity is high. Neural networks have the ability to ＂learn＂the characteristics of a system through nonlinear mapping to represent nonlinear functions as well as their inverse functions. This paper presents a model algorithm control method using neural networks for nonlinear time delay systems. Two neural networks are used in the control scheme. One neural network is trained as the model of the nonlinear time delay system, and the other one produces the control inputs. The neural networks are combined with the model algorithm control method to control the nonlinear time delay systems. Three examples are used to illustrate the proposed control method. The simulation results show that the proposed control method has a good control performance for nonlinear time delay systems.展开更多
Nonlinear model predictive controllers(NMPC)can predict the future behavior of the under-controlled system using a nonlinear predictive model.Here,an array of hyper chaotic diagonal recurrent neural network(HCDRNN)was...Nonlinear model predictive controllers(NMPC)can predict the future behavior of the under-controlled system using a nonlinear predictive model.Here,an array of hyper chaotic diagonal recurrent neural network(HCDRNN)was proposed for modeling and predicting the behavior of the under-controller nonlinear system in a moving forward window.In order to improve the convergence of the parameters of the HCDRNN to improve system’s modeling,the extent of chaos is adjusted using a logistic map in the hidden layer.A novel NMPC based on the HCDRNN array(HCDRNN-NMPC)was proposed that the control signal with the help of an improved gradient descent method was obtained.The controller was used to control a continuous stirred tank reactor(CSTR)with hard-nonlinearities and input constraints,in the presence of uncertainties including external disturbance.The results of the simulations show the superior performance of the proposed method in trajectory tracking and disturbance rejection.Parameter convergence and neglectable prediction error of the neural network(NN),guaranteed stability and high tracking performance are the most significant advantages of the proposed scheme.展开更多
An adaptive inverse controller for nonliear discrete-time system is proposed in this paper. A compound neural network is constructed to identify the nonlinear system, which includes a linear part to approximate the no...An adaptive inverse controller for nonliear discrete-time system is proposed in this paper. A compound neural network is constructed to identify the nonlinear system, which includes a linear part to approximate the nonlinear system and a recurrent neural network to minimize the difference between the linear model and the real nonlinear system. Because the current control input is not included in the input vector of recurrent neural network (RNN), the inverse control law can be calculated directly. This scheme can be used in real-time nonlinear single-input single-output (SISO) and multi-input multi-output (MIMO) system control with less computation work. Simulation studies have shown that this scheme is simple and affects good control accuracy and robustness.展开更多
The pneumatic artificial muscles are widely used in the fields of medicalrobots, etc. Neural networks are applied to modeling and controlling of artificial muscle system. Asingle-joint artificial muscle test system is...The pneumatic artificial muscles are widely used in the fields of medicalrobots, etc. Neural networks are applied to modeling and controlling of artificial muscle system. Asingle-joint artificial muscle test system is designed. The recursive prediction error (RPE)algorithm which yields faster convergence than back propagation (BP) algorithm is applied to trainthe neural networks. The realization of RPE algorithm is given. The difference of modeling ofartificial muscles using neural networks with different input nodes and different hidden layer nodesis discussed. On this basis the nonlinear control scheme using neural networks for artificialmuscle system has been introduced. The experimental results show that the nonlinear control schemeyields faster response and higher control accuracy than the traditional linear control scheme.展开更多
A multivariable adaptive controller feasible for implementation on distributed computer systems （DCS） is presented for a class of uncertain nonlinear multivariable discrete time systems. The adaptive controller is c...A multivariable adaptive controller feasible for implementation on distributed computer systems （DCS） is presented for a class of uncertain nonlinear multivariable discrete time systems. The adaptive controller is composed of a linear adaptive controller, a neural network nonlinear adaptive controller and a switching mechanism. The linear controller can provide boundedness of the input and output signals, and the nonlinear controller can improve the performance of the system. The purpose of using the switching mechanism is to obtain the improved system performance and stability simultaneously. Theory analysis and simulation results are presented to show the effectiveness of the proposed method.展开更多
A nonlinear model predictive control problem based on pseudo-linear neural network (PNN) is discussed, in which the second order on-line optimization method is adopted. The recursive computation of Jacobian matrix is ...A nonlinear model predictive control problem based on pseudo-linear neural network (PNN) is discussed, in which the second order on-line optimization method is adopted. The recursive computation of Jacobian matrix is investigated. The stability of the closed loop model predictive control system is analyzed based on Lyapunov theory to obtain the sufficient condition for the asymptotical stability of the neural predictive control system. A simulation was carried out for an exothermic first-order reaction in a continuous stirred tank reactor.It is demonstrated that the proposed control strategy is applicable to some of nonlinear systems.展开更多
The effective and timely diagnosis and treatment of ocular diseases are key to the rapid recovery of patients.Today,the mass disease that needs attention in this context is cataracts.Although deep learning has signifi...The effective and timely diagnosis and treatment of ocular diseases are key to the rapid recovery of patients.Today,the mass disease that needs attention in this context is cataracts.Although deep learning has significantly advanced the analysis of ocular disease images,there is a need for a probabilistic model to generate the distributions of potential outcomes and thusmake decisions related to uncertainty quantification.Therefore,this study implements a Bayesian Convolutional Neural Networks(BCNN)model for predicting cataracts by assigning probability values to the predictions.It prepares convolutional neural network(CNN)and BCNN models.The proposed BCNN model is CNN-based in which reparameterization is in the first and last layers of the CNN model.This study then trains them on a dataset of cataract images filtered from the ocular disease fundus images fromKaggle.The deep CNN model has an accuracy of 95%,while the BCNN model has an accuracy of 93.75% along with information on uncertainty estimation of cataracts and normal eye conditions.When compared with other methods,the proposed work reveals that it can be a promising solution for cataract prediction with uncertainty estimation.展开更多
This paper concerns ultimately bounded output-feedback control problems for networked systems with unknown nonlinear dynamics. Sensor-to-observer signal transmission is facilitated over networks that has communication...This paper concerns ultimately bounded output-feedback control problems for networked systems with unknown nonlinear dynamics. Sensor-to-observer signal transmission is facilitated over networks that has communication constraints.These transmissions are carried out over an unreliable communication channel. In order to enhance the utilization rate of measurement data, a buffer-aided strategy is novelly employed to store historical measurements when communication networks are inaccessible. Using the neural network technique, a novel observer-based controller is introduced to address effects of signal transmission behaviors and unknown nonlinear dynamics.Through the application of stochastic analysis and Lyapunov stability, a joint framework is constructed for analyzing resultant system performance under the introduced controller. Subsequently, existence conditions for the desired output-feedback controller are delineated. The required parameters for the observerbased controller are then determined by resolving some specific matrix inequalities. Finally, a simulation example is showcased to confirm method efficacy.展开更多
Since chemical processes are highly non-linear and multiscale,it is vital to deeply mine the multiscale coupling relationships embedded in the massive process data for the prediction and anomaly tracing of crucial pro...Since chemical processes are highly non-linear and multiscale,it is vital to deeply mine the multiscale coupling relationships embedded in the massive process data for the prediction and anomaly tracing of crucial process parameters and production indicators.While the integrated method of adaptive signal decomposition combined with time series models could effectively predict process variables,it does have limitations in capturing the high-frequency detail of the operation state when applied to complex chemical processes.In light of this,a novel Multiscale Multi-radius Multi-step Convolutional Neural Network(Msrt Net)is proposed for mining spatiotemporal multiscale information.First,the industrial data from the Fluid Catalytic Cracking(FCC)process decomposition using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)extract the multi-energy scale information of the feature subset.Then,convolution kernels with varying stride and padding structures are established to decouple the long-period operation process information encapsulated within the multi-energy scale data.Finally,a reconciliation network is trained to reconstruct the multiscale prediction results and obtain the final output.Msrt Net is initially assessed for its capability to untangle the spatiotemporal multiscale relationships among variables in the Tennessee Eastman Process(TEP).Subsequently,the performance of Msrt Net is evaluated in predicting product yield for a 2.80×10^(6) t/a FCC unit,taking diesel and gasoline yield as examples.In conclusion,Msrt Net can decouple and effectively extract spatiotemporal multiscale information from chemical process data and achieve a approximately reduction of 30%in prediction error compared to other time-series models.Furthermore,its robustness and transferability underscore its promising potential for broader applications.展开更多
Polylactic acid(PLA)is a potential polymer material used as a substitute for traditional plastics,and the accurate molecular weight distribution range of PLA is strictly required in practical applications.Therefore,ex...Polylactic acid(PLA)is a potential polymer material used as a substitute for traditional plastics,and the accurate molecular weight distribution range of PLA is strictly required in practical applications.Therefore,exploring the relationship between synthetic conditions and PLA molecular weight is crucially important.In this work,direct polycondensation combined with overlay sampling uniform design(OSUD)was applied to synthesize the low molecular weight PLA.Then a multiple regression model and two artificial neural network models on PLA molecular weight versus reaction temperature,reaction time,and catalyst dosage were developed for PLA molecular weight prediction.The characterization results indicated that the low molecular weight PLA was efficiently synthesized under this method.Meanwhile,the experimental dataset acquired from OSUD successfully established three predictive models for PLA molecular weight.Among them,both artificial neural network models had significantly better predictive performance than the regression model.Notably,the radial basis function neural network model had the best predictive accuracy with only 11.9%of mean relative error on the validation dataset,which improved by 67.7%compared with the traditional multiple regression model.This work successfully predicted PLA molecular weight in a direct polycondensation process using artificial neural network models combined with OSUD,which provided guidance for the future implementation of molecular weight-controlled polymer's synthesis.展开更多
This paper presents a Nonlinear Model Predictive Controller(NMPC)for the path following of autonomous vehicles and an algorithm to adaptively adjust the preview distance.The prediction model includes vehicle dynamics,...This paper presents a Nonlinear Model Predictive Controller(NMPC)for the path following of autonomous vehicles and an algorithm to adaptively adjust the preview distance.The prediction model includes vehicle dynamics,path following dynamics,and system input dynamics.The single-track vehicle model considers the vehicle’s coupled lateral and longitudinal dynamics,as well as nonlinear tire forces.The tracking error dynamics are derived based on the curvilinear coordinates.The cost function is designed to minimize path tracking errors and control effort while considering constraints such as actuator bounds and tire grip limits.An algorithm that utilizes the optimal preview distance vector to query the corresponding reference curvature and reference speed.The length of the preview path is adaptively adjusted based on the vehicle speed,heading error,and path curvature.We validate the controller performance in a simulation environment with the autonomous racing scenario.The simulation results show that the vehicle accurately follows the highly dynamic path with small tracking errors.The maximum preview distance can be prior estimated and guidance the selection of the prediction horizon for NMPC.展开更多
In this paper, platoons of autonomous vehicles operating in urban road networks are considered. From a methodological point of view, the problem of interest consists of formally characterizing vehicle state trajectory...In this paper, platoons of autonomous vehicles operating in urban road networks are considered. From a methodological point of view, the problem of interest consists of formally characterizing vehicle state trajectory tubes by means of routing decisions complying with traffic congestion criteria. To this end, a novel distributed control architecture is conceived by taking advantage of two methodologies: deep reinforcement learning and model predictive control. On one hand, the routing decisions are obtained by using a distributed reinforcement learning algorithm that exploits available traffic data at each road junction. On the other hand, a bank of model predictive controllers is in charge of computing the more adequate control action for each involved vehicle. Such tasks are here combined into a single framework:the deep reinforcement learning output(action) is translated into a set-point to be tracked by the model predictive controller;conversely, the current vehicle position, resulting from the application of the control move, is exploited by the deep reinforcement learning unit for improving its reliability. The main novelty of the proposed solution lies in its hybrid nature: on one hand it fully exploits deep reinforcement learning capabilities for decisionmaking purposes;on the other hand, time-varying hard constraints are always satisfied during the dynamical platoon evolution imposed by the computed routing decisions. To efficiently evaluate the performance of the proposed control architecture, a co-design procedure, involving the SUMO and MATLAB platforms, is implemented so that complex operating environments can be used, and the information coming from road maps(links,junctions, obstacles, semaphores, etc.) and vehicle state trajectories can be shared and exchanged. Finally by considering as operating scenario a real entire city block and a platoon of eleven vehicles described by double-integrator models, several simulations have been performed with the aim to put in light the main f eatures of the proposed approach. Moreover, it is important to underline that in different operating scenarios the proposed reinforcement learning scheme is capable of significantly reducing traffic congestion phenomena when compared with well-reputed competitors.展开更多
The goals of this study are to assess the viability of waste tire-derived char(WTDC)as a sustainable,low-cost fine aggregate surrogate material for asphalt mixtures and to develop the statistically coupled neural netw...The goals of this study are to assess the viability of waste tire-derived char(WTDC)as a sustainable,low-cost fine aggregate surrogate material for asphalt mixtures and to develop the statistically coupled neural network(SCNN)model for predicting volumetric and Marshall properties of asphalt mixtures modified with WTDC.The study is based on experimental data acquired from laboratory volumetric and Marshall properties testing on WTDCmodified asphalt mixtures(WTDC-MAM).The input variables comprised waste tire char content and asphalt binder content.The output variables comprised mixture unit weight,total voids,voids filled with asphalt,Marshall stability,and flow.Statistical coupled neural networks were utilized to predict the volumetric and Marshall properties of asphalt mixtures.For predictive modeling,the SCNN model is employed,incorporating a three-layer neural network and preprocessing techniques to enhance accuracy and reliability.The optimal network architecture,using the collected dataset,was a 2:6:5 structure,and the neural network was trained with 60%of the data,whereas the other 20%was used for cross-validation and testing respectively.The network employed a hyperbolic tangent(tanh)activation function and a feed-forward backpropagation.According to the results,the network model could accurately predict the volumetric and Marshall properties.The predicted accuracy of SCNN was found to be as high value>98%and low prediction errors for both volumetric and Marshall properties.This study demonstrates WTDC's potential as a low-cost,sustainable aggregate replacement.The SCNN-based predictive model proves its efficiency and versatility and promotes sustainable practices.展开更多
文摘This paper proposes a robust control scheme based on the sequential convex programming and learning-based model for nonlinear system subjected to additive uncertainties.For the problem of system nonlinearty and unknown uncertainties,we study the tube-based model predictive control scheme that makes use of feedforward neural network.Based on the characteristics of the bounded limit of the average cost function while time approaching infinity,a min-max optimization problem(referred to as min-max OP)is formulated to design the controller.The feasibility of this optimization problem and the practical stability of the controlled system are ensured.To demonstrate the efficacy of the proposed approach,a numerical simulation on a double-tank system is conducted.The results of the simulation serve as verification of the effectualness of the proposed scheme.
文摘The rapid prediction of aerodynamic performance is critical in the conceptual and preliminary design of hypersonic vehicles. This study focused on axisymmetric body configurations commonly used in such vehicles and proposed a multi-fidelity neural network (MFNN) framework to fuse aerodynamic data of varying quality. A data-driven prediction model was constructed using a pointwise modeling method based on generating lines to input geometric features into the network. The MFNN framework combined low-fidelity and high-fidelity networks, trained on aerodynamic performance data from engineering rapid computation methods and CFD, respectively, using spherically blunted cones as examples. The results showed that the MFNN effectively integrated multi-fidelity data, achieving prediction accuracy close to CFD results in most regions, with errors under 5% in key stagnation areas. The model demonstrated strong generalization capabilities for varying cone dimensions and flight conditions. Furthermore, it significantly reduced dependence on high-fidelity data, enabling efficient aerodynamic performance predictions with limited datasets. This study provides a novel methodology for rapid aerodynamic performance prediction, offering both accuracy and efficiency, and contributes to the design of hypersonic vehicles.
基金supported by the National Key Research and Development Program of China(No.2023YFF0715103)-financial supportNational Natural Science Foundation of China(Grant Nos.62306237 and 62006191)-financial support+1 种基金Key Research and Development Program of Shaanxi(Nos.2024GX-YBXM-149 and 2021ZDLGY15-04)-financial support,NorthwestUniversity Graduate Innovation Project(No.CX2023194)-financial supportNatural Science Foundation of Shaanxi(No.2023-JC-QN-0750)-financial support.
文摘Over 1.3 million people die annually in traffic accidents,and this tragic fact highlights the urgent need to enhance the intelligence of traffic safety and control systems.In modern industrial and technological applications and collaborative edge intelligence,control systems are crucial for ensuring efficiency and safety.However,deficiencies in these systems can lead to significant operational risks.This paper uses edge intelligence to address the challenges of achieving target speeds and improving efficiency in vehicle control,particularly the limitations of traditional Proportional-Integral-Derivative(PID)controllers inmanaging nonlinear and time-varying dynamics,such as varying road conditions and vehicle behavior,which often result in substantial discrepancies between desired and actual speeds,as well as inefficiencies due to manual parameter adjustments.The paper uses edge intelligence to propose a novel PID control algorithm that integrates Backpropagation(BP)neural networks to enhance robustness and adaptability.The BP neural network is first trained to capture the nonlinear dynamic characteristics of the vehicle.Thetrained network is then combined with the PID controller to forma hybrid control strategy.The output layer of the neural network directly adjusts the PIDparameters(k_(p),k_(i),k_(d)),optimizing performance for specific driving scenarios through self-learning and weight adjustments.Simulation experiments demonstrate that our BP neural network-based PID design significantly outperforms traditional methods,with the response time for acceleration from 0 to 1 m/s improved from 0.25 s to just 0.065 s.Furthermore,real-world tests on an intelligent vehicle show its ability to make timely adjustments in response to complex road conditions,ensuring consistent speed maintenance and enhancing overall system performance.
基金Project supported by the National Natural Science Foundation of China(Nos.62273245 and 62173033)the Sichuan Science and Technology Program of China(No.2024NSFSC1486)the Opening Project of Robotic Satellite Key Laboratory of Sichuan Province of China。
文摘A distributionally robust model predictive control(DRMPC)scheme is proposed based on neural network(NN)modeling to achieve the trajectory tracking control of robot manipulators with state and control torque constraints.First,an NN is used to fit the motion data of robot manipulators for data-driven dynamic modeling,converting it into a linear prediction model through gradients.Then,by statistically analyzing the stochastic characteristics of the NN modeling errors,a distributionally robust model predictive controller is designed based on the chance constraints,and the optimization problem is transformed into a tractable quadratic programming(QP)problem under the distributionally robust optimization(DRO)framework.The recursive feasibility and convergence of the proposed algorithm are proven.Finally,the effectiveness of the proposed algorithm is verified through numerical simulation.
基金Supported by National Natural Science Foundation of China(Grant No.51805447)Natural Science Foundation of Jiangsu Higher Education of China(Grant No.22KJB460010)+2 种基金Jiangsu Provincial Innovation and Promotion Project of Forestry Science and Technology of China(Grant No.LYKJ[2023]06)Yangzhou Science and Technology Plan(City School Cooperation Project)of China(Grant No.YZ2022193)Cyan Blue Project of Yangzhou University of China。
文摘In the realm of engineering practice,various factors such as limited availability of measurement data and complex working conditions pose significant challenges to obtaining accurate load spectra.Thus,accurately predicting the fatigue life of structures becomes notably arduous.This paper proposed an approach to predict the fatigue life of structure based on the optimized load spectra,which is accurately estimated by an efficient hinging hyperplane neural network(EHH-NN)model.The construction of the EHH-NN model includes initial network generation and parameter optimization.Through the combination of working conditions design,multi-body dynamics analysis and structural static mechanics analysis,the simulated load spectra of the structure are obtained.The simulated load spectra are taken as the input variables for the optimized EHH-NN model,while the measurement load spectra are used as the output variables.The prediction results of case structure indicate that the optimized EHH-NN model can achieve the high-accuracy load spectra,in comparison with support vector machine(SVM),random forest(RF)model and back propagation(BP)neural network.The error rate between the prediction values and the measurement values of the optimized EHH-NN model is 4.61%.In the Cauchy-Lorentz distribution,the absolute error data of 92%with EHH-NN model appear in the intermediate range of±1.65%.Also,the fatigue life analysis is performed for the case structure,based on the accurately predicted load spectra.The fatigue life of the case structure is calculated based on the comparison between the measured and predicted load spectra,with an accuracy of 93.56%.This research proposes the optimized EHH-NN model can more accurately reflect the measurement load spectra,enabling precise calculation of fatigue life.Additionally,the optimized EHH-NN model provides reliability assessment for industrial engineering equipment.
基金This paper is supported by the National Foundamental Research Program of China (No. 2002CB312201), the State Key Program of NationalNatural Science of China (No. 60534010), the Funds for Creative Research Groups of China (No. 60521003), and Program for Changjiang Scholarsand Innovative Research Team in University (No. IRT0421).
文摘For a class of complex industrial processes with strong nonlinearity, serious coupling and uncertainty, a nonlinear decoupling proportional-integral-differential （PID） controller is proposed, which consists of a traditional PID controller, a decoupling compensator and a feedforward compensator for the unmodeled dynamics. The parameters of such controller is selected based on the generalized minimum variance control law. The unmodeled dynamics is estimated and compensated by neural networks, a switching mechanism is introduced to improve tracking performance, then a nonlinear decoupling PID control algorithm is proposed. All signals in such switching system are globally bounded and the tracking error is convergent. Simulations show effectiveness of the algorithm.
基金supported in part by the National Natural Science Foundation of China(U1913207)the International Science and Technology Cooperation Program of China(2017YFE0128300)the Fundamental Research Funds for the Central Universities(HUST 2019kfyRCPY014)。
文摘Pneumatic muscle actuators(PMAs)are compliant and suitable for robotic devices that have been shown to be effective in assisting patients with neurologic injuries,such as strokes,spinal cord injuries,etc.,to accomplish rehabilitation tasks.However,because PMAs have nonlinearities,hysteresis,and uncertainties,etc.,complex mechanisms are rarely involved in the study of PMA-driven robotic systems.In this paper,we use nonlinear model predictive control(NMPC)and an extension of the echo state network called an echo state Gaussian process(ESGP)to design a tracking controller for a PMA-driven lower limb exoskeleton.The dynamics of the system include the PMA actuation and mechanism of the leg orthoses;thus,the system is represented by two nonlinear uncertain subsystems.To facilitate the design of the controller,joint angles of leg orthoses are forecasted based on the universal approximation ability of the ESGP.A gradient descent algorithm is employed to solve the optimization problem and generate the control signal.The stability of the closed-loop system is guaranteed when the ESGP is capable of approximating system dynamics.Simulations and experiments are conducted to verify the approximation ability of the ESGP and achieve gait pattern training with four healthy subjects.
基金supported by the Brain Korea 21 PLUS Project,National Research Foundation of Korea(NRF-2013R1A2A2A01068127NRF-2013R1A1A2A10009458)Jiangsu Province University Natural Science Research Project(13KJB510003)
文摘The performance of the model algorithm control method is partially based on the accuracy of the system＇s model. It is difficult to obtain a good model of a nonlinear system, especially when the nonlinearity is high. Neural networks have the ability to ＂learn＂the characteristics of a system through nonlinear mapping to represent nonlinear functions as well as their inverse functions. This paper presents a model algorithm control method using neural networks for nonlinear time delay systems. Two neural networks are used in the control scheme. One neural network is trained as the model of the nonlinear time delay system, and the other one produces the control inputs. The neural networks are combined with the model algorithm control method to control the nonlinear time delay systems. Three examples are used to illustrate the proposed control method. The simulation results show that the proposed control method has a good control performance for nonlinear time delay systems.
文摘Nonlinear model predictive controllers(NMPC)can predict the future behavior of the under-controlled system using a nonlinear predictive model.Here,an array of hyper chaotic diagonal recurrent neural network(HCDRNN)was proposed for modeling and predicting the behavior of the under-controller nonlinear system in a moving forward window.In order to improve the convergence of the parameters of the HCDRNN to improve system’s modeling,the extent of chaos is adjusted using a logistic map in the hidden layer.A novel NMPC based on the HCDRNN array(HCDRNN-NMPC)was proposed that the control signal with the help of an improved gradient descent method was obtained.The controller was used to control a continuous stirred tank reactor(CSTR)with hard-nonlinearities and input constraints,in the presence of uncertainties including external disturbance.The results of the simulations show the superior performance of the proposed method in trajectory tracking and disturbance rejection.Parameter convergence and neglectable prediction error of the neural network(NN),guaranteed stability and high tracking performance are the most significant advantages of the proposed scheme.
基金Supported by the National Natural Science Foundation of China (60575009, 60574036)
文摘An adaptive inverse controller for nonliear discrete-time system is proposed in this paper. A compound neural network is constructed to identify the nonlinear system, which includes a linear part to approximate the nonlinear system and a recurrent neural network to minimize the difference between the linear model and the real nonlinear system. Because the current control input is not included in the input vector of recurrent neural network (RNN), the inverse control law can be calculated directly. This scheme can be used in real-time nonlinear single-input single-output (SISO) and multi-input multi-output (MIMO) system control with less computation work. Simulation studies have shown that this scheme is simple and affects good control accuracy and robustness.
基金This project is supported by Foundation of Public Laboratory on Robotics of Chinese Academy of Sciences.
文摘The pneumatic artificial muscles are widely used in the fields of medicalrobots, etc. Neural networks are applied to modeling and controlling of artificial muscle system. Asingle-joint artificial muscle test system is designed. The recursive prediction error (RPE)algorithm which yields faster convergence than back propagation (BP) algorithm is applied to trainthe neural networks. The realization of RPE algorithm is given. The difference of modeling ofartificial muscles using neural networks with different input nodes and different hidden layer nodesis discussed. On this basis the nonlinear control scheme using neural networks for artificialmuscle system has been introduced. The experimental results show that the nonlinear control schemeyields faster response and higher control accuracy than the traditional linear control scheme.
基金the National Fundamental Research Program of China (No. 2002CB312201)the State Key Program of National Natural Science of China (No. 60534010)+1 种基金the Funds for Creative Research Groups of China (No. 60521003)the Program for Changjiang Scholars and Innovative Research Team in University (No. IRT0421)
文摘A multivariable adaptive controller feasible for implementation on distributed computer systems （DCS） is presented for a class of uncertain nonlinear multivariable discrete time systems. The adaptive controller is composed of a linear adaptive controller, a neural network nonlinear adaptive controller and a switching mechanism. The linear controller can provide boundedness of the input and output signals, and the nonlinear controller can improve the performance of the system. The purpose of using the switching mechanism is to obtain the improved system performance and stability simultaneously. Theory analysis and simulation results are presented to show the effectiveness of the proposed method.
文摘A nonlinear model predictive control problem based on pseudo-linear neural network (PNN) is discussed, in which the second order on-line optimization method is adopted. The recursive computation of Jacobian matrix is investigated. The stability of the closed loop model predictive control system is analyzed based on Lyapunov theory to obtain the sufficient condition for the asymptotical stability of the neural predictive control system. A simulation was carried out for an exothermic first-order reaction in a continuous stirred tank reactor.It is demonstrated that the proposed control strategy is applicable to some of nonlinear systems.
基金Saudi Arabia for funding this work through Small Research Group Project under Grant Number RGP.1/316/45.
文摘The effective and timely diagnosis and treatment of ocular diseases are key to the rapid recovery of patients.Today,the mass disease that needs attention in this context is cataracts.Although deep learning has significantly advanced the analysis of ocular disease images,there is a need for a probabilistic model to generate the distributions of potential outcomes and thusmake decisions related to uncertainty quantification.Therefore,this study implements a Bayesian Convolutional Neural Networks(BCNN)model for predicting cataracts by assigning probability values to the predictions.It prepares convolutional neural network(CNN)and BCNN models.The proposed BCNN model is CNN-based in which reparameterization is in the first and last layers of the CNN model.This study then trains them on a dataset of cataract images filtered from the ocular disease fundus images fromKaggle.The deep CNN model has an accuracy of 95%,while the BCNN model has an accuracy of 93.75% along with information on uncertainty estimation of cataracts and normal eye conditions.When compared with other methods,the proposed work reveals that it can be a promising solution for cataract prediction with uncertainty estimation.
基金supported in part by the National Natural Science Foundation of China (61933007,62273087,U22A2044,61973102,62073180)the Shanghai Pujiang Program of China (22PJ1400400)+1 种基金the Royal Society of the UKthe Alexander von Humboldt Foundation of Germany。
文摘This paper concerns ultimately bounded output-feedback control problems for networked systems with unknown nonlinear dynamics. Sensor-to-observer signal transmission is facilitated over networks that has communication constraints.These transmissions are carried out over an unreliable communication channel. In order to enhance the utilization rate of measurement data, a buffer-aided strategy is novelly employed to store historical measurements when communication networks are inaccessible. Using the neural network technique, a novel observer-based controller is introduced to address effects of signal transmission behaviors and unknown nonlinear dynamics.Through the application of stochastic analysis and Lyapunov stability, a joint framework is constructed for analyzing resultant system performance under the introduced controller. Subsequently, existence conditions for the desired output-feedback controller are delineated. The required parameters for the observerbased controller are then determined by resolving some specific matrix inequalities. Finally, a simulation example is showcased to confirm method efficacy.
文摘Since chemical processes are highly non-linear and multiscale,it is vital to deeply mine the multiscale coupling relationships embedded in the massive process data for the prediction and anomaly tracing of crucial process parameters and production indicators.While the integrated method of adaptive signal decomposition combined with time series models could effectively predict process variables,it does have limitations in capturing the high-frequency detail of the operation state when applied to complex chemical processes.In light of this,a novel Multiscale Multi-radius Multi-step Convolutional Neural Network(Msrt Net)is proposed for mining spatiotemporal multiscale information.First,the industrial data from the Fluid Catalytic Cracking(FCC)process decomposition using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)extract the multi-energy scale information of the feature subset.Then,convolution kernels with varying stride and padding structures are established to decouple the long-period operation process information encapsulated within the multi-energy scale data.Finally,a reconciliation network is trained to reconstruct the multiscale prediction results and obtain the final output.Msrt Net is initially assessed for its capability to untangle the spatiotemporal multiscale relationships among variables in the Tennessee Eastman Process(TEP).Subsequently,the performance of Msrt Net is evaluated in predicting product yield for a 2.80×10^(6) t/a FCC unit,taking diesel and gasoline yield as examples.In conclusion,Msrt Net can decouple and effectively extract spatiotemporal multiscale information from chemical process data and achieve a approximately reduction of 30%in prediction error compared to other time-series models.Furthermore,its robustness and transferability underscore its promising potential for broader applications.
基金funded by the Zhejiang Provincial Natural Science Foundation of China(LD21B060001)the National Natural Science Foundation of China(22078296,21576240).
文摘Polylactic acid(PLA)is a potential polymer material used as a substitute for traditional plastics,and the accurate molecular weight distribution range of PLA is strictly required in practical applications.Therefore,exploring the relationship between synthetic conditions and PLA molecular weight is crucially important.In this work,direct polycondensation combined with overlay sampling uniform design(OSUD)was applied to synthesize the low molecular weight PLA.Then a multiple regression model and two artificial neural network models on PLA molecular weight versus reaction temperature,reaction time,and catalyst dosage were developed for PLA molecular weight prediction.The characterization results indicated that the low molecular weight PLA was efficiently synthesized under this method.Meanwhile,the experimental dataset acquired from OSUD successfully established three predictive models for PLA molecular weight.Among them,both artificial neural network models had significantly better predictive performance than the regression model.Notably,the radial basis function neural network model had the best predictive accuracy with only 11.9%of mean relative error on the validation dataset,which improved by 67.7%compared with the traditional multiple regression model.This work successfully predicted PLA molecular weight in a direct polycondensation process using artificial neural network models combined with OSUD,which provided guidance for the future implementation of molecular weight-controlled polymer's synthesis.
基金“National Science and Technology Council”(NSTC 111-2221-E-027-088)。
文摘This paper presents a Nonlinear Model Predictive Controller(NMPC)for the path following of autonomous vehicles and an algorithm to adaptively adjust the preview distance.The prediction model includes vehicle dynamics,path following dynamics,and system input dynamics.The single-track vehicle model considers the vehicle’s coupled lateral and longitudinal dynamics,as well as nonlinear tire forces.The tracking error dynamics are derived based on the curvilinear coordinates.The cost function is designed to minimize path tracking errors and control effort while considering constraints such as actuator bounds and tire grip limits.An algorithm that utilizes the optimal preview distance vector to query the corresponding reference curvature and reference speed.The length of the preview path is adaptively adjusted based on the vehicle speed,heading error,and path curvature.We validate the controller performance in a simulation environment with the autonomous racing scenario.The simulation results show that the vehicle accurately follows the highly dynamic path with small tracking errors.The maximum preview distance can be prior estimated and guidance the selection of the prediction horizon for NMPC.
文摘In this paper, platoons of autonomous vehicles operating in urban road networks are considered. From a methodological point of view, the problem of interest consists of formally characterizing vehicle state trajectory tubes by means of routing decisions complying with traffic congestion criteria. To this end, a novel distributed control architecture is conceived by taking advantage of two methodologies: deep reinforcement learning and model predictive control. On one hand, the routing decisions are obtained by using a distributed reinforcement learning algorithm that exploits available traffic data at each road junction. On the other hand, a bank of model predictive controllers is in charge of computing the more adequate control action for each involved vehicle. Such tasks are here combined into a single framework:the deep reinforcement learning output(action) is translated into a set-point to be tracked by the model predictive controller;conversely, the current vehicle position, resulting from the application of the control move, is exploited by the deep reinforcement learning unit for improving its reliability. The main novelty of the proposed solution lies in its hybrid nature: on one hand it fully exploits deep reinforcement learning capabilities for decisionmaking purposes;on the other hand, time-varying hard constraints are always satisfied during the dynamical platoon evolution imposed by the computed routing decisions. To efficiently evaluate the performance of the proposed control architecture, a co-design procedure, involving the SUMO and MATLAB platforms, is implemented so that complex operating environments can be used, and the information coming from road maps(links,junctions, obstacles, semaphores, etc.) and vehicle state trajectories can be shared and exchanged. Finally by considering as operating scenario a real entire city block and a platoon of eleven vehicles described by double-integrator models, several simulations have been performed with the aim to put in light the main f eatures of the proposed approach. Moreover, it is important to underline that in different operating scenarios the proposed reinforcement learning scheme is capable of significantly reducing traffic congestion phenomena when compared with well-reputed competitors.
基金the University of Teknologi PETRONAS(UTP),Malaysia,and Ahmadu Bello University,Nigeria,for their vital help and availability of laboratory facilities that allowed this work to be conducted successfully.
文摘The goals of this study are to assess the viability of waste tire-derived char(WTDC)as a sustainable,low-cost fine aggregate surrogate material for asphalt mixtures and to develop the statistically coupled neural network(SCNN)model for predicting volumetric and Marshall properties of asphalt mixtures modified with WTDC.The study is based on experimental data acquired from laboratory volumetric and Marshall properties testing on WTDCmodified asphalt mixtures(WTDC-MAM).The input variables comprised waste tire char content and asphalt binder content.The output variables comprised mixture unit weight,total voids,voids filled with asphalt,Marshall stability,and flow.Statistical coupled neural networks were utilized to predict the volumetric and Marshall properties of asphalt mixtures.For predictive modeling,the SCNN model is employed,incorporating a three-layer neural network and preprocessing techniques to enhance accuracy and reliability.The optimal network architecture,using the collected dataset,was a 2:6:5 structure,and the neural network was trained with 60%of the data,whereas the other 20%was used for cross-validation and testing respectively.The network employed a hyperbolic tangent(tanh)activation function and a feed-forward backpropagation.According to the results,the network model could accurately predict the volumetric and Marshall properties.The predicted accuracy of SCNN was found to be as high value>98%and low prediction errors for both volumetric and Marshall properties.This study demonstrates WTDC's potential as a low-cost,sustainable aggregate replacement.The SCNN-based predictive model proves its efficiency and versatility and promotes sustainable practices.
