This paper presents the fault diagnosis of face milling tool based on machine learning approach.While machining,spindle vibration signals in feed direction under healthy and faulty conditions of the milling tool are a...This paper presents the fault diagnosis of face milling tool based on machine learning approach.While machining,spindle vibration signals in feed direction under healthy and faulty conditions of the milling tool are acquired.A set of discrete wavelet features is extracted from the vibration signals using discrete wavelet transform(DWT)technique.The decision tree technique is used to select significant features out of all extracted wavelet features.C-support vector classification(C-SVC)andν-support vector classification(ν-SVC)models with different kernel functions of support vector machine(SVM)are used to study and classify the tool condition based on selected features.From the results obtained,C-SVC is the best model thanν-SVC and it can be able to give 94.5%classification accuracy for face milling of special steel alloy 42CrMo4.展开更多
This paper describes an analytical investigation into synchrophasing,a vibration control strategy on a machinery installation in which two rotational machines are attached to a beam-like raft by discrete resilient iso...This paper describes an analytical investigation into synchrophasing,a vibration control strategy on a machinery installation in which two rotational machines are attached to a beam-like raft by discrete resilient isolators.Forces and moments introduced by sources are considered,which effectively represent a practical engineering system.Adjusting the relative phase angle between the machines has been theoretically demonstrated to greatly reduce the cost function,which is defined as the sum of velocity squares of attaching points on the raft at each frequency of interest.The effect of the position of the machine is also investigated.Results show that altering the position of the secondary source may cause a slight change to the mode shape of the composite system and therefore change the optimum phase between the two machines.Although the analysis is based on a one-dimensional Euler– Bernoulli beam and each machine is considered as a rigid-body,a key principle can be derived from the results.However,the factors that can influence the synchrophasing control performance would become coupled and highly complicated.This condition has to be considered in practice.展开更多
Congenital Long QT Syndrome (LQTS) is a genetic disease and associated with significant arrhythmias and sudden cardiac death. We introduce a noninva-sive procedure in which Discrete Wavelet Trans-form (DWT) is used to...Congenital Long QT Syndrome (LQTS) is a genetic disease and associated with significant arrhythmias and sudden cardiac death. We introduce a noninva-sive procedure in which Discrete Wavelet Trans-form (DWT) is used to extract features from elec-trocardiogram (ECG) time-series data first, then the extracted features data is classified as either abnormal or unaffected using Support Vector Machines (SVM). A total of 26 genetically identified patients with LQTS and 19 healthy controls were studied. Due to the limited number of samples, model selection was done by training 44 instances and testing it on remaining one in each run. The proposed method shows reasonably high average accuracy in LQTS diagnosis when combined with best parameter selection process in the classifica-tion stage. An accuracy of 80%is achieved when Sigmoid kernel is used in v-SVM with parameters v = 0.58 and r = 0.5. The corresponding SVM model showed a classification rate of 21/26 for LQTS pa-tients and 15/19 for controls. Since the diagnosis of LQTS can be challenging, the proposed method is promising and can be a potential tool in the correct diagnosis. The method may be improved further if larger data sets can be obtained and used.展开更多
Support vector machine (SVM) has become an increasingly popular tool for machine learning tasks involving classification. In this paper, we present a simple and effective method of detect and classify hard exudates. A...Support vector machine (SVM) has become an increasingly popular tool for machine learning tasks involving classification. In this paper, we present a simple and effective method of detect and classify hard exudates. Automatic detection of hard exudates from retinal images is worth-studying problem since hard exudates are associated with diabetic retinopathy and have been found to be one of the most prevalent earliest signs of retinopathy. The algorithm is based on Discrete Cosine Transform (DCT) analysis and SVM makes use of color information to perform the classification of retinal exudates. We prospectively assessed the algorithm performance using a database containing 1200 retinal images with variable color, brightness, and quality. Results of the proposed system can achieve a diagnostic accuracy with 97.0% sensitivity and 98.7% specificity for the identification of images containing any evidence of retinopathy.展开更多
为解决传统数字滤波器在有限精度实现时因有限字长(Finite Word Length,FWL)效应导致滤波器性能下降的问题,提出一种L_(2)灵敏度最小化的数字滤波器状态空间实现稀疏化方法.推导前向差分算子数字滤波器结构传输函数及其等效状态空间实现...为解决传统数字滤波器在有限精度实现时因有限字长(Finite Word Length,FWL)效应导致滤波器性能下降的问题,提出一种L_(2)灵敏度最小化的数字滤波器状态空间实现稀疏化方法.推导前向差分算子数字滤波器结构传输函数及其等效状态空间实现,根据可控及可观格莱姆矩阵得到基于相似变换矩阵的L_(2)灵敏度表达式,并进行稀疏化校准,将L_(2)灵敏度最小化问题转换为凸函数求最值问题,求导得到L_(2)灵敏度最小化表达式,代回即得前向差分算子数字滤波器的稀疏化状态空间实现.仿真结果表明,所提方法设计的数字滤波器具有更好的抗FWL效应.展开更多
针对如何充分利用空间特征来达到较高的高光谱图像分类精度的问题,提出了一种基于三维离散小波变换(3D-DWT)与随机补丁网络(RPNet)结合的高光谱图像的地物属性分类算法。在分类过程中,综合3D-DWT提取的特征和RPNet深度学习框架提取的特...针对如何充分利用空间特征来达到较高的高光谱图像分类精度的问题,提出了一种基于三维离散小波变换(3D-DWT)与随机补丁网络(RPNet)结合的高光谱图像的地物属性分类算法。在分类过程中,综合3D-DWT提取的特征和RPNet深度学习框架提取的特征,利用支持向量机(SVM)对特征向量进行分类。所提出的方法在Indian Pines和University of Pavia两个数据集上进行测试,结果表明该方法比现有方法有显著的分类性能的提高。展开更多
Ground control in underground mines employs rock reinforcement and surface support to maintain the integrity of excavations for their anticipated working life.The performance of a ground support system,however,is more...Ground control in underground mines employs rock reinforcement and surface support to maintain the integrity of excavations for their anticipated working life.The performance of a ground support system,however,is more complex and relies on effective load distribution between reinforcement and surface support elements.Typically,failure of the ground support system is along its weakest link,often the surface support.Consequently,the degradation of any ground support element over time will compromise the structural integrity of the ground support system.Degradation of ground support can be due to multiple factors.This paper focuses on the role of corrosion in the long-term performance of mesh.It presents a comprehensive methodology for quantifying the impact of degradation on bolted welded wire mesh over time.This is an important aspect,as the mesh is often the first element that fails in a ground support system.This paper combines information from extensive field and laboratory studies on mesh corrosion with calibrated numerical models to capture the long-term performance of different bolting patterns under a range of corrosion environments.A series of three-dimensional(3D)distinct element models(DEM)were constructed to quantify the impact of different corrosion rate scenarios on the loading capacity,displacement,and failure mechanisms of bolted welded wire mesh in diamond and square bolting patterns.This work can contribute to the management of long-term hazards associated with corrosion of mesh in corrosive environments under non-seismic mining conditions.展开更多
The cross-level and twist irregularities are the most dangerous irregularity types that could cause wheel unloading with the risk of derailments and additional maintenance expenses.However,the mechanism of the irregul...The cross-level and twist irregularities are the most dangerous irregularity types that could cause wheel unloading with the risk of derailments and additional maintenance expenses.However,the mechanism of the irregularities initiation and development is unclear.The motivation of the present study was the previous experimental studies on the application of wide sleepers in the ballasted track.The long-term track geometry measurements with wide sleepers show an enormous reduction of the vertical longitudinal irregularities compared to the conventional track.However,wide sleepers had higher twist and cross-section level irregularities.The present paper aims to explain the phenomenon by discrete element method(DEM)modeling the development process of sleeper inhomogeneous support at cross-level depending on the sleeper form.The DEM simulations show that the maximal settlement intensity is up to 3.5 times lower for a wide sleeper in comparison with the conventional one.Nevertheless,the cross-level differential settlements are almost the same for both sleepers.The particle loading distribution after all loading cycles is concentrated on the smaller area,up to the half sleeper length,with fully unloaded zones under sleeper ends.Ballast flow limitation under the central part of the sleeper could improve the resilience of wide sleepers to the development of cross-level irregularities.The mechanism of initiation of the cross-level irregularity is proposed,which assumes the loss of sleeper support under sleeper ends.The further growth of inhomogeneous settlements along the sleeper is assumed as a result of the interaction of two processes:ballast flow due to dynamic impact during void closing and on the other side high pressure due to the concentration of the pressure under the middle part of the sleeper.The DEM simulation results support the assumption of the mechanism and agree with the experimental studies.展开更多
The El Niño-Southern Oscillation (ENSO) is a significant climate phenomenon with far-reaching impacts on global weather patterns, ecosystems, and economies. This study aims to enhance ENSO forecasting with the Ex...The El Niño-Southern Oscillation (ENSO) is a significant climate phenomenon with far-reaching impacts on global weather patterns, ecosystems, and economies. This study aims to enhance ENSO forecasting with the Extended Reconstruction Sea Surface Temperature v5 (ERSSTv5) climate model. The M-band discrete wavelet transforms (DWT) are utilized to capture multi-scale temporal and spatial features effectively. Long-short term memory (LSTM) autoencoders are also used to capture significant spatial and temporal patterns in sea surface temperature (SST) anomaly data. Deep learning techniques such as the convolutional neural networks (CNN) are used with non-image and image time series data. We also employ parallel computing in a various support vector regression (SVR) approximators to enhance accuracy. Preliminary results indicate that this hybrid model effectively identifies key precursors and patterns associated with El Niño events, surpassing traditional forecasting methods. Results of the hybrid model produce a correlation of 0.93 in 4-month lagged forecasting of the Oceanic Niño Index (ONI)—indicative of high success rate of the model. Future work will focus on evaluating the model’s performance using additional reanalysis datasets and other methods of deep learning to further refine its robustness and applicability. We propose wavelet-based deep learning models which have potential to shine a light on achieving United Nations’ 2030 Agenda for Sustainable Development’s goal 13: “Climate Action”, as an innovation with potential in improving time series image forecasting in all fields.展开更多
文摘This paper presents the fault diagnosis of face milling tool based on machine learning approach.While machining,spindle vibration signals in feed direction under healthy and faulty conditions of the milling tool are acquired.A set of discrete wavelet features is extracted from the vibration signals using discrete wavelet transform(DWT)technique.The decision tree technique is used to select significant features out of all extracted wavelet features.C-support vector classification(C-SVC)andν-support vector classification(ν-SVC)models with different kernel functions of support vector machine(SVM)are used to study and classify the tool condition based on selected features.From the results obtained,C-SVC is the best model thanν-SVC and it can be able to give 94.5%classification accuracy for face milling of special steel alloy 42CrMo4.
文摘This paper describes an analytical investigation into synchrophasing,a vibration control strategy on a machinery installation in which two rotational machines are attached to a beam-like raft by discrete resilient isolators.Forces and moments introduced by sources are considered,which effectively represent a practical engineering system.Adjusting the relative phase angle between the machines has been theoretically demonstrated to greatly reduce the cost function,which is defined as the sum of velocity squares of attaching points on the raft at each frequency of interest.The effect of the position of the machine is also investigated.Results show that altering the position of the secondary source may cause a slight change to the mode shape of the composite system and therefore change the optimum phase between the two machines.Although the analysis is based on a one-dimensional Euler– Bernoulli beam and each machine is considered as a rigid-body,a key principle can be derived from the results.However,the factors that can influence the synchrophasing control performance would become coupled and highly complicated.This condition has to be considered in practice.
文摘Congenital Long QT Syndrome (LQTS) is a genetic disease and associated with significant arrhythmias and sudden cardiac death. We introduce a noninva-sive procedure in which Discrete Wavelet Trans-form (DWT) is used to extract features from elec-trocardiogram (ECG) time-series data first, then the extracted features data is classified as either abnormal or unaffected using Support Vector Machines (SVM). A total of 26 genetically identified patients with LQTS and 19 healthy controls were studied. Due to the limited number of samples, model selection was done by training 44 instances and testing it on remaining one in each run. The proposed method shows reasonably high average accuracy in LQTS diagnosis when combined with best parameter selection process in the classifica-tion stage. An accuracy of 80%is achieved when Sigmoid kernel is used in v-SVM with parameters v = 0.58 and r = 0.5. The corresponding SVM model showed a classification rate of 21/26 for LQTS pa-tients and 15/19 for controls. Since the diagnosis of LQTS can be challenging, the proposed method is promising and can be a potential tool in the correct diagnosis. The method may be improved further if larger data sets can be obtained and used.
文摘Support vector machine (SVM) has become an increasingly popular tool for machine learning tasks involving classification. In this paper, we present a simple and effective method of detect and classify hard exudates. Automatic detection of hard exudates from retinal images is worth-studying problem since hard exudates are associated with diabetic retinopathy and have been found to be one of the most prevalent earliest signs of retinopathy. The algorithm is based on Discrete Cosine Transform (DCT) analysis and SVM makes use of color information to perform the classification of retinal exudates. We prospectively assessed the algorithm performance using a database containing 1200 retinal images with variable color, brightness, and quality. Results of the proposed system can achieve a diagnostic accuracy with 97.0% sensitivity and 98.7% specificity for the identification of images containing any evidence of retinopathy.
文摘为解决传统数字滤波器在有限精度实现时因有限字长(Finite Word Length,FWL)效应导致滤波器性能下降的问题,提出一种L_(2)灵敏度最小化的数字滤波器状态空间实现稀疏化方法.推导前向差分算子数字滤波器结构传输函数及其等效状态空间实现,根据可控及可观格莱姆矩阵得到基于相似变换矩阵的L_(2)灵敏度表达式,并进行稀疏化校准,将L_(2)灵敏度最小化问题转换为凸函数求最值问题,求导得到L_(2)灵敏度最小化表达式,代回即得前向差分算子数字滤波器的稀疏化状态空间实现.仿真结果表明,所提方法设计的数字滤波器具有更好的抗FWL效应.
文摘针对如何充分利用空间特征来达到较高的高光谱图像分类精度的问题,提出了一种基于三维离散小波变换(3D-DWT)与随机补丁网络(RPNet)结合的高光谱图像的地物属性分类算法。在分类过程中,综合3D-DWT提取的特征和RPNet深度学习框架提取的特征,利用支持向量机(SVM)对特征向量进行分类。所提出的方法在Indian Pines和University of Pavia两个数据集上进行测试,结果表明该方法比现有方法有显著的分类性能的提高。
基金supported by the Natural Sciences and Engineering Research Council of Canada(Grant No.RGPIN-2019-06707).
文摘Ground control in underground mines employs rock reinforcement and surface support to maintain the integrity of excavations for their anticipated working life.The performance of a ground support system,however,is more complex and relies on effective load distribution between reinforcement and surface support elements.Typically,failure of the ground support system is along its weakest link,often the surface support.Consequently,the degradation of any ground support element over time will compromise the structural integrity of the ground support system.Degradation of ground support can be due to multiple factors.This paper focuses on the role of corrosion in the long-term performance of mesh.It presents a comprehensive methodology for quantifying the impact of degradation on bolted welded wire mesh over time.This is an important aspect,as the mesh is often the first element that fails in a ground support system.This paper combines information from extensive field and laboratory studies on mesh corrosion with calibrated numerical models to capture the long-term performance of different bolting patterns under a range of corrosion environments.A series of three-dimensional(3D)distinct element models(DEM)were constructed to quantify the impact of different corrosion rate scenarios on the loading capacity,displacement,and failure mechanisms of bolted welded wire mesh in diamond and square bolting patterns.This work can contribute to the management of long-term hazards associated with corrosion of mesh in corrosive environments under non-seismic mining conditions.
文摘The cross-level and twist irregularities are the most dangerous irregularity types that could cause wheel unloading with the risk of derailments and additional maintenance expenses.However,the mechanism of the irregularities initiation and development is unclear.The motivation of the present study was the previous experimental studies on the application of wide sleepers in the ballasted track.The long-term track geometry measurements with wide sleepers show an enormous reduction of the vertical longitudinal irregularities compared to the conventional track.However,wide sleepers had higher twist and cross-section level irregularities.The present paper aims to explain the phenomenon by discrete element method(DEM)modeling the development process of sleeper inhomogeneous support at cross-level depending on the sleeper form.The DEM simulations show that the maximal settlement intensity is up to 3.5 times lower for a wide sleeper in comparison with the conventional one.Nevertheless,the cross-level differential settlements are almost the same for both sleepers.The particle loading distribution after all loading cycles is concentrated on the smaller area,up to the half sleeper length,with fully unloaded zones under sleeper ends.Ballast flow limitation under the central part of the sleeper could improve the resilience of wide sleepers to the development of cross-level irregularities.The mechanism of initiation of the cross-level irregularity is proposed,which assumes the loss of sleeper support under sleeper ends.The further growth of inhomogeneous settlements along the sleeper is assumed as a result of the interaction of two processes:ballast flow due to dynamic impact during void closing and on the other side high pressure due to the concentration of the pressure under the middle part of the sleeper.The DEM simulation results support the assumption of the mechanism and agree with the experimental studies.
文摘The El Niño-Southern Oscillation (ENSO) is a significant climate phenomenon with far-reaching impacts on global weather patterns, ecosystems, and economies. This study aims to enhance ENSO forecasting with the Extended Reconstruction Sea Surface Temperature v5 (ERSSTv5) climate model. The M-band discrete wavelet transforms (DWT) are utilized to capture multi-scale temporal and spatial features effectively. Long-short term memory (LSTM) autoencoders are also used to capture significant spatial and temporal patterns in sea surface temperature (SST) anomaly data. Deep learning techniques such as the convolutional neural networks (CNN) are used with non-image and image time series data. We also employ parallel computing in a various support vector regression (SVR) approximators to enhance accuracy. Preliminary results indicate that this hybrid model effectively identifies key precursors and patterns associated with El Niño events, surpassing traditional forecasting methods. Results of the hybrid model produce a correlation of 0.93 in 4-month lagged forecasting of the Oceanic Niño Index (ONI)—indicative of high success rate of the model. Future work will focus on evaluating the model’s performance using additional reanalysis datasets and other methods of deep learning to further refine its robustness and applicability. We propose wavelet-based deep learning models which have potential to shine a light on achieving United Nations’ 2030 Agenda for Sustainable Development’s goal 13: “Climate Action”, as an innovation with potential in improving time series image forecasting in all fields.
