To supplement missing logging information without increasing economic cost, a machine learning method to generate synthetic well logs from the existing log data was presented, and the experimental verification and app...To supplement missing logging information without increasing economic cost, a machine learning method to generate synthetic well logs from the existing log data was presented, and the experimental verification and application effect analysis were carried out. Since the traditional Fully Connected Neural Network(FCNN) is incapable of preserving spatial dependency, the Long Short-Term Memory(LSTM) network, which is a kind of Recurrent Neural Network(RNN), was utilized to establish a method for log reconstruction. By this method, synthetic logs can be generated from series of input log data with consideration of variation trend and context information with depth. Besides, a cascaded LSTM was proposed by combining the standard LSTM with a cascade system. Testing through real well log data shows that: the results from the LSTM are of higher accuracy than the traditional FCNN; the cascaded LSTM is more suitable for the problem with multiple series data; the machine learning method proposed provides an accurate and cost effective way for synthetic well log generation.展开更多
In this paper a novel class of neural networks called generalized congruence neural networks (GCNN) is proposed. All neurons in the neural networks are activated in the form of congruence. The architectures, learnin...In this paper a novel class of neural networks called generalized congruence neural networks (GCNN) is proposed. All neurons in the neural networks are activated in the form of congruence. The architectures, learning rules and two algorithms are presented. Simulation results indicate that such network has satisfactory generalization properties near the sample points. Since this kind of neural nets can be easily operated and implemented, it is appropriate to make further research concerning the theory and applications of GCNN.展开更多
A scheme of adaptive control based on a recurrent neural network with a neural network compensation is presented for a class of nonlinear systems with a nonlinear prefix. The recurrent neural network is used to identi...A scheme of adaptive control based on a recurrent neural network with a neural network compensation is presented for a class of nonlinear systems with a nonlinear prefix. The recurrent neural network is used to identify the unknown nonlinear part and compensate the difference between the real output and the identified model output. The identified model of the controlled object consists of a linear model and the neural network. The generalized minimum variance control method is used to identify parameters, which can deal with the problem of adaptive control of systems with unknown nonlinear part, which can not be controlled by traditional methods. Simulation results show that this algorithm has higher precision, faster convergent speed.展开更多
近年来,深度学习模型在农药发现和从头分子设计方面取得了显著进展。然而目前用于农药分子设计的深度生成模型中,基于骨架的分子生成模型较少。并且基于骨架的分子生成方法面临着生成分子质量和多样性不足的挑战。为此,该研究提出了一...近年来,深度学习模型在农药发现和从头分子设计方面取得了显著进展。然而目前用于农药分子设计的深度生成模型中,基于骨架的分子生成模型较少。并且基于骨架的分子生成方法面临着生成分子质量和多样性不足的挑战。为此,该研究提出了一种基于骨架结构的循环神经网络模型(multi head attention-recurrent neural network,MHA-RNN),首先生成简化分子线性输入规范(simplified molecular input line entry system,SMILES)格式的分子骨架,然后对骨架进行装饰以生成新的分子。试验结果表明,模型生成的分子在有效性、新颖性和唯一性方面分别达到了97.18%、99.87%和100.00%。此外,生成分子在脂水分配系数(logarithm of partition coefficient,LogP)、拓扑极性表面积(topological polar surface area,TPSA)、相对分子质量(molecular weight,MW)、类药性(quantitative estimate of drug-likeness,QED)、氢键受体(hydrogen bond acceptor,HBA)、氢键供体(hydrogen bond donor,HBD)、旋转键数(rotatable bonds,RotB)等性质上的分布与现有分子高度相似,研究结果为农药新药研发提供了技术支持与参考。展开更多
In order to forecast projectile impact points quickly and accurately,aprojectile impact point prediction method based on generalized regression neural network（GRNN）is presented.Firstly,the model of GRNN forecasting ...In order to forecast projectile impact points quickly and accurately,aprojectile impact point prediction method based on generalized regression neural network（GRNN）is presented.Firstly,the model of GRNN forecasting impact point is established;secondly,the particle swarm algorithm（PSD）is used to optimize the smooth factor in the prediction model and then the optimal GRNN impact point prediction model is obtained.Finally,the numerical simulation of this prediction model is carried out.Simulation results show that the maximum range error is no more than 40 m,and the lateral deviation error is less than0.2m.The average time of impact point prediction is 6.645 ms,which is 1 300.623 ms less than that of numerical integration method.Therefore,it is feasible and effective for the proposed method to forecast projectile impact points,and thus it can provide a theoretical reference for practical engineering applications.展开更多
基金Supported by the National Natural Science Foundation of China(U1663208,51520105005)the National Science and Technology Major Project of China(2017ZX05009-005,2016ZX05037-003)
文摘To supplement missing logging information without increasing economic cost, a machine learning method to generate synthetic well logs from the existing log data was presented, and the experimental verification and application effect analysis were carried out. Since the traditional Fully Connected Neural Network(FCNN) is incapable of preserving spatial dependency, the Long Short-Term Memory(LSTM) network, which is a kind of Recurrent Neural Network(RNN), was utilized to establish a method for log reconstruction. By this method, synthetic logs can be generated from series of input log data with consideration of variation trend and context information with depth. Besides, a cascaded LSTM was proposed by combining the standard LSTM with a cascade system. Testing through real well log data shows that: the results from the LSTM are of higher accuracy than the traditional FCNN; the cascaded LSTM is more suitable for the problem with multiple series data; the machine learning method proposed provides an accurate and cost effective way for synthetic well log generation.
文摘In this paper a novel class of neural networks called generalized congruence neural networks (GCNN) is proposed. All neurons in the neural networks are activated in the form of congruence. The architectures, learning rules and two algorithms are presented. Simulation results indicate that such network has satisfactory generalization properties near the sample points. Since this kind of neural nets can be easily operated and implemented, it is appropriate to make further research concerning the theory and applications of GCNN.
文摘A scheme of adaptive control based on a recurrent neural network with a neural network compensation is presented for a class of nonlinear systems with a nonlinear prefix. The recurrent neural network is used to identify the unknown nonlinear part and compensate the difference between the real output and the identified model output. The identified model of the controlled object consists of a linear model and the neural network. The generalized minimum variance control method is used to identify parameters, which can deal with the problem of adaptive control of systems with unknown nonlinear part, which can not be controlled by traditional methods. Simulation results show that this algorithm has higher precision, faster convergent speed.
文摘近年来,深度学习模型在农药发现和从头分子设计方面取得了显著进展。然而目前用于农药分子设计的深度生成模型中,基于骨架的分子生成模型较少。并且基于骨架的分子生成方法面临着生成分子质量和多样性不足的挑战。为此,该研究提出了一种基于骨架结构的循环神经网络模型(multi head attention-recurrent neural network,MHA-RNN),首先生成简化分子线性输入规范(simplified molecular input line entry system,SMILES)格式的分子骨架,然后对骨架进行装饰以生成新的分子。试验结果表明,模型生成的分子在有效性、新颖性和唯一性方面分别达到了97.18%、99.87%和100.00%。此外,生成分子在脂水分配系数(logarithm of partition coefficient,LogP)、拓扑极性表面积(topological polar surface area,TPSA)、相对分子质量(molecular weight,MW)、类药性(quantitative estimate of drug-likeness,QED)、氢键受体(hydrogen bond acceptor,HBA)、氢键供体(hydrogen bond donor,HBD)、旋转键数(rotatable bonds,RotB)等性质上的分布与现有分子高度相似,研究结果为农药新药研发提供了技术支持与参考。
基金Project Funded by Chongqing Changjiang Electrical Appliances Industries Group Co.,Ltd
文摘In order to forecast projectile impact points quickly and accurately,aprojectile impact point prediction method based on generalized regression neural network（GRNN）is presented.Firstly,the model of GRNN forecasting impact point is established;secondly,the particle swarm algorithm（PSD）is used to optimize the smooth factor in the prediction model and then the optimal GRNN impact point prediction model is obtained.Finally,the numerical simulation of this prediction model is carried out.Simulation results show that the maximum range error is no more than 40 m,and the lateral deviation error is less than0.2m.The average time of impact point prediction is 6.645 ms,which is 1 300.623 ms less than that of numerical integration method.Therefore,it is feasible and effective for the proposed method to forecast projectile impact points,and thus it can provide a theoretical reference for practical engineering applications.
