Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay di...Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.展开更多
The multi-modal characteristics of mineral particles play a pivotal role in enhancing the classification accuracy,which is critical for obtaining a profound understanding of the Earth's composition and ensuring ef...The multi-modal characteristics of mineral particles play a pivotal role in enhancing the classification accuracy,which is critical for obtaining a profound understanding of the Earth's composition and ensuring effective exploitation utilization of its resources.However,the existing methods for classifying mineral particles do not fully utilize these multi-modal features,thereby limiting the classification accuracy.Furthermore,when conventional multi-modal image classification methods are applied to planepolarized and cross-polarized sequence images of mineral particles,they encounter issues such as information loss,misaligned features,and challenges in spatiotemporal feature extraction.To address these challenges,we propose a multi-modal mineral particle polarization image classification network(MMGC-Net)for precise mineral particle classification.Initially,MMGC-Net employs a two-dimensional(2D)backbone network with shared parameters to extract features from two types of polarized images to ensure feature alignment.Subsequently,a cross-polarized intra-modal feature fusion module is designed to refine the spatiotemporal features from the extracted features of the cross-polarized sequence images.Ultimately,the inter-modal feature fusion module integrates the two types of modal features to enhance the classification precision.Quantitative and qualitative experimental results indicate that when compared with the current state-of-the-art multi-modal image classification methods,MMGC-Net demonstrates marked superiority in terms of mineral particle multi-modal feature learning and four classification evaluation metrics.It also demonstrates better stability than the existing models.展开更多
Efficient assessment of battery degradation is important to effectively utilize and maintain battery management systems.This study introduces an innovative residual convolutional network(RCN)-gated recurrent unit(GRU)...Efficient assessment of battery degradation is important to effectively utilize and maintain battery management systems.This study introduces an innovative residual convolutional network(RCN)-gated recurrent unit(GRU)model to accurately assess health of lithium-ion batteries on multiple time scales.The model employs a soft parameter-sharing mechanism to identify both short-d dT and long-term degradation patterns.The continuously looped(V),T(V),dQ/dV and dT/dV are extracted to form a four-channel image,dV dV from which the RCN can automatically extract the features and the GRU can capture the temporal features.By designing a soft parameter-sharing mechanism,the model can seamlessly predict the capacity and remaining useful life(RUL)on a dual time scale.The proposed method is validated on a large MIT-Stanford dataset comprising 124 cells,showing a high accuracy in terms of mean absolute errors of 0.00477 for capacity and 83 for RUL.Furthermore,studying the partial voltage fragment reveals the promising performance of the proposed method across various voltage ranges.Specifically,in the partial voltage segment of 2.8-3.2 V,root mean square errors of 0.0107 for capacity and 140 for RUL are achieved.展开更多
Federated Learning(FL)is currently a widely used collaborative learning framework,and the distinguished feature of FL is that the clients involved in training do not need to share raw data,but only transfer the model ...Federated Learning(FL)is currently a widely used collaborative learning framework,and the distinguished feature of FL is that the clients involved in training do not need to share raw data,but only transfer the model parameters to share knowledge,and finally get a global model with improved performance.However,recent studies have found that sharing model parameters may still lead to privacy leakage.From the shared model parameters,local training data can be reconstructed and thus lead to a threat to individual privacy and security.We observed that most of the current attacks are aimed at client-specific data reconstruction,while limited attention is paid to the information leakage of the global model.In our work,we propose a novel FL attack based on shared model parameters that can deduce the data distribution of the global model.Different from other FL attacks that aim to infer individual clients’raw data,the data distribution inference attack proposed in this work shows that the attackers can have the capability to deduce the data distribution information behind the global model.We argue that such information is valuable since the training data behind a welltrained global model indicates the common knowledge of a specific task,such as social networks and e-commerce applications.To implement such an attack,our key idea is to adopt a deep reinforcement learning approach to guide the attack process,where the RL agent adjusts the pseudo-data distribution automatically until it is similar to the ground truth data distribution.By a carefully designed Markov decision proces(MDP)process,our implementation ensures our attack can have stable performance and experimental results verify the effectiveness of our proposed inference attack.展开更多
The increasing integration of intermittent renewable energy sources(RESs)poses great challenges to active distribution networks(ADNs),such as frequent voltage fluctuations.This paper proposes a novel ADN strategy base...The increasing integration of intermittent renewable energy sources(RESs)poses great challenges to active distribution networks(ADNs),such as frequent voltage fluctuations.This paper proposes a novel ADN strategy based on multiagent deep reinforcement learning(MADRL),which harnesses the regulating function of switch state transitions for the realtime voltage regulation and loss minimization.After deploying the calculated optimal switch topologies,the distribution network operator will dynamically adjust the distributed energy resources(DERs)to enhance the operation performance of ADNs based on the policies trained by the MADRL algorithm.Owing to the model-free characteristics and the generalization of deep reinforcement learning,the proposed strategy can still achieve optimization objectives even when applied to similar but unseen environments.Additionally,integrating parameter sharing(PS)and prioritized experience replay(PER)mechanisms substantially improves the strategic performance and scalability.This framework has been tested on modified IEEE 33-bus,IEEE 118-bus,and three-phase unbalanced 123-bus systems.The results demonstrate the significant real-time regulation capabilities of the proposed strategy.展开更多
Inventory management(e.g.lost sales)is a central problem in supply chain management.Lost sales inventory systems with lead times and complex cost function are notoriously hard to optimize.Deep reinforcement learning(D...Inventory management(e.g.lost sales)is a central problem in supply chain management.Lost sales inventory systems with lead times and complex cost function are notoriously hard to optimize.Deep reinforcement learning(DRL)methods can learn optimal decisions based on trails and errors from the environment due to its powerful complex function representation capability and has recently shown remarkable successes in solving challenging sequential decision-making problems.This paper studies typical lost sales and multi-echelon inventory systems.We first formulate inventory management problem as a Markov Decision Process by taking into account ordering cost,holding cost,fixed cost and lost-sales cost and then develop a solution framework DDLS based on Double deep Q-networks(DQN).In the lost-sales scenario,numerical experiments demonstrate that increasing fixed ordering cost distorts the ordering behavior,while our DQN solutions with improved state space are flexible in the face of different cost parameter settings,which traditional heuristics find challenging to handle.We then study the effectiveness of our approach in multi-echelon scenarios.Empirical results demonstrate that parameter sharing can significantly improve the performance of DRL.As a form of information sharing,parameter sharing among multi-echelon suppliers promotes the collaboration of agents and improves the decisionmaking efficiency.Our research further demonstrates the potential of DRL in solving complex inventory management problems.展开更多
文摘Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.
基金supported by the National Natural Science Foundation of China(Grant Nos.62071315 and 62271336).
文摘The multi-modal characteristics of mineral particles play a pivotal role in enhancing the classification accuracy,which is critical for obtaining a profound understanding of the Earth's composition and ensuring effective exploitation utilization of its resources.However,the existing methods for classifying mineral particles do not fully utilize these multi-modal features,thereby limiting the classification accuracy.Furthermore,when conventional multi-modal image classification methods are applied to planepolarized and cross-polarized sequence images of mineral particles,they encounter issues such as information loss,misaligned features,and challenges in spatiotemporal feature extraction.To address these challenges,we propose a multi-modal mineral particle polarization image classification network(MMGC-Net)for precise mineral particle classification.Initially,MMGC-Net employs a two-dimensional(2D)backbone network with shared parameters to extract features from two types of polarized images to ensure feature alignment.Subsequently,a cross-polarized intra-modal feature fusion module is designed to refine the spatiotemporal features from the extracted features of the cross-polarized sequence images.Ultimately,the inter-modal feature fusion module integrates the two types of modal features to enhance the classification precision.Quantitative and qualitative experimental results indicate that when compared with the current state-of-the-art multi-modal image classification methods,MMGC-Net demonstrates marked superiority in terms of mineral particle multi-modal feature learning and four classification evaluation metrics.It also demonstrates better stability than the existing models.
基金Supported by the Science and Technology Project of Datang North China InstituteunderGrant2023HBY-GL001.
文摘Efficient assessment of battery degradation is important to effectively utilize and maintain battery management systems.This study introduces an innovative residual convolutional network(RCN)-gated recurrent unit(GRU)model to accurately assess health of lithium-ion batteries on multiple time scales.The model employs a soft parameter-sharing mechanism to identify both short-d dT and long-term degradation patterns.The continuously looped(V),T(V),dQ/dV and dT/dV are extracted to form a four-channel image,dV dV from which the RCN can automatically extract the features and the GRU can capture the temporal features.By designing a soft parameter-sharing mechanism,the model can seamlessly predict the capacity and remaining useful life(RUL)on a dual time scale.The proposed method is validated on a large MIT-Stanford dataset comprising 124 cells,showing a high accuracy in terms of mean absolute errors of 0.00477 for capacity and 83 for RUL.Furthermore,studying the partial voltage fragment reveals the promising performance of the proposed method across various voltage ranges.Specifically,in the partial voltage segment of 2.8-3.2 V,root mean square errors of 0.0107 for capacity and 140 for RUL are achieved.
文摘Federated Learning(FL)is currently a widely used collaborative learning framework,and the distinguished feature of FL is that the clients involved in training do not need to share raw data,but only transfer the model parameters to share knowledge,and finally get a global model with improved performance.However,recent studies have found that sharing model parameters may still lead to privacy leakage.From the shared model parameters,local training data can be reconstructed and thus lead to a threat to individual privacy and security.We observed that most of the current attacks are aimed at client-specific data reconstruction,while limited attention is paid to the information leakage of the global model.In our work,we propose a novel FL attack based on shared model parameters that can deduce the data distribution of the global model.Different from other FL attacks that aim to infer individual clients’raw data,the data distribution inference attack proposed in this work shows that the attackers can have the capability to deduce the data distribution information behind the global model.We argue that such information is valuable since the training data behind a welltrained global model indicates the common knowledge of a specific task,such as social networks and e-commerce applications.To implement such an attack,our key idea is to adopt a deep reinforcement learning approach to guide the attack process,where the RL agent adjusts the pseudo-data distribution automatically until it is similar to the ground truth data distribution.By a carefully designed Markov decision proces(MDP)process,our implementation ensures our attack can have stable performance and experimental results verify the effectiveness of our proposed inference attack.
基金supported by the National Natural Science Foundation of China(No.52077146)Sichuan Science and Technology Program(No.2023NSFSC1945)。
文摘The increasing integration of intermittent renewable energy sources(RESs)poses great challenges to active distribution networks(ADNs),such as frequent voltage fluctuations.This paper proposes a novel ADN strategy based on multiagent deep reinforcement learning(MADRL),which harnesses the regulating function of switch state transitions for the realtime voltage regulation and loss minimization.After deploying the calculated optimal switch topologies,the distribution network operator will dynamically adjust the distributed energy resources(DERs)to enhance the operation performance of ADNs based on the policies trained by the MADRL algorithm.Owing to the model-free characteristics and the generalization of deep reinforcement learning,the proposed strategy can still achieve optimization objectives even when applied to similar but unseen environments.Additionally,integrating parameter sharing(PS)and prioritized experience replay(PER)mechanisms substantially improves the strategic performance and scalability.This framework has been tested on modified IEEE 33-bus,IEEE 118-bus,and three-phase unbalanced 123-bus systems.The results demonstrate the significant real-time regulation capabilities of the proposed strategy.
基金supported in part by the National Natural Science Foundation of China,under grant Nos.72022001,92146003,,71901003CAAI-Huawei MindSpore,CCF-Tencent Open Research Fund。
文摘Inventory management(e.g.lost sales)is a central problem in supply chain management.Lost sales inventory systems with lead times and complex cost function are notoriously hard to optimize.Deep reinforcement learning(DRL)methods can learn optimal decisions based on trails and errors from the environment due to its powerful complex function representation capability and has recently shown remarkable successes in solving challenging sequential decision-making problems.This paper studies typical lost sales and multi-echelon inventory systems.We first formulate inventory management problem as a Markov Decision Process by taking into account ordering cost,holding cost,fixed cost and lost-sales cost and then develop a solution framework DDLS based on Double deep Q-networks(DQN).In the lost-sales scenario,numerical experiments demonstrate that increasing fixed ordering cost distorts the ordering behavior,while our DQN solutions with improved state space are flexible in the face of different cost parameter settings,which traditional heuristics find challenging to handle.We then study the effectiveness of our approach in multi-echelon scenarios.Empirical results demonstrate that parameter sharing can significantly improve the performance of DRL.As a form of information sharing,parameter sharing among multi-echelon suppliers promotes the collaboration of agents and improves the decisionmaking efficiency.Our research further demonstrates the potential of DRL in solving complex inventory management problems.
