Pub Date : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455546
Pei-Ming Liu, Zhizong Huang, Xianggui Guo
In this paper, an event-triggered group consensus pinning control strategy is proposed for the second-order nonlinear multi-agent systems (MASs) with directed communication graph under periodic denial-of-service (DoS) attacks, which does not require the MASs to satisfy the in-degree balance condition. On this basis, the state error systems under periodic DoS attacks are established. In addition, it should be pointed out that the control strategy includes the selection method of pinning nodes under the group consensus framework. Furthermore, the sampled-data-based event-triggered mechanism (ETM) reduces the excessive consumption of system resources. Finally, simulation examples are given to verify the effectiveness of the control strategy under periodic DoS attacks with different duration.
{"title":"Event-triggered Secure Group Consensus of Second-order Multi-agent Systems under Periodic DoS Attacks","authors":"Pei-Ming Liu, Zhizong Huang, Xianggui Guo","doi":"10.1109/DDCLS52934.2021.9455546","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455546","url":null,"abstract":"In this paper, an event-triggered group consensus pinning control strategy is proposed for the second-order nonlinear multi-agent systems (MASs) with directed communication graph under periodic denial-of-service (DoS) attacks, which does not require the MASs to satisfy the in-degree balance condition. On this basis, the state error systems under periodic DoS attacks are established. In addition, it should be pointed out that the control strategy includes the selection method of pinning nodes under the group consensus framework. Furthermore, the sampled-data-based event-triggered mechanism (ETM) reduces the excessive consumption of system resources. Finally, simulation examples are given to verify the effectiveness of the control strategy under periodic DoS attacks with different duration.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129695865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
For a cyber physical system under multiple cyber attacks, including non-periodic denial-of-service (DoS) attack and stochastic deception attack, we design a dynamic output feedback controller with dynamic event-triggered strategy. We adopts a control strategy based on dynamic trigger conditions, which reduces the number of triggers and saves network resources. Besides, we establish a switched system model to describe the presence of multiple cyber attacks with dynamic event-triggered scheme. Then, according to asymptotic stability theory, dynamic output feedback controller ensuring the switching system stable is designed by using a piecewise Lyapunov-Krasovskii function. Furthermore, the parameters of dynamc event-triggered and controller are derived in a unified framework and sufficient conditions for asymptotic stability can be obtained.
{"title":"Dynamic Event-triggered Scheme and Output Feedback Control for CPS under Multiple Cyber Attacks","authors":"Zhigang Zhang, Jinhai Liu, Shuo Zhang, Hongfei Zhu, Baojin Zhang","doi":"10.1109/DDCLS52934.2021.9455613","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455613","url":null,"abstract":"For a cyber physical system under multiple cyber attacks, including non-periodic denial-of-service (DoS) attack and stochastic deception attack, we design a dynamic output feedback controller with dynamic event-triggered strategy. We adopts a control strategy based on dynamic trigger conditions, which reduces the number of triggers and saves network resources. Besides, we establish a switched system model to describe the presence of multiple cyber attacks with dynamic event-triggered scheme. Then, according to asymptotic stability theory, dynamic output feedback controller ensuring the switching system stable is designed by using a piecewise Lyapunov-Krasovskii function. Furthermore, the parameters of dynamc event-triggered and controller are derived in a unified framework and sufficient conditions for asymptotic stability can be obtained.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131667835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455663
Chengyuan Sun, Yizhen Yin, Hongjun Ma
The data-driven methods based multivariate regression have become popular in the area of fault detection due to the development of the computer technique. However, some traditional data-driven methods only consider the statical operating environment that the dynamic relationship in the variables will be ignored to bring some false detection results. In this study, an approach called the dynamic fault detection (DFD) is proposed to solve dynamic behavior under the nonlinear case. From the view of the best KPIs, the proposed method divides the variables into two orthogonal subspaces by the improved kernel principal component regression to judge whether the happened fault is relevant to KPIs or not. Finally, in the numerical simulation, the effectiveness of the DFD approach is demonstrated by comparing it with three nonlinear methods.
{"title":"A Dynamic Fault Detection Method for Nonlinear Process","authors":"Chengyuan Sun, Yizhen Yin, Hongjun Ma","doi":"10.1109/DDCLS52934.2021.9455663","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455663","url":null,"abstract":"The data-driven methods based multivariate regression have become popular in the area of fault detection due to the development of the computer technique. However, some traditional data-driven methods only consider the statical operating environment that the dynamic relationship in the variables will be ignored to bring some false detection results. In this study, an approach called the dynamic fault detection (DFD) is proposed to solve dynamic behavior under the nonlinear case. From the view of the best KPIs, the proposed method divides the variables into two orthogonal subspaces by the improved kernel principal component regression to judge whether the happened fault is relevant to KPIs or not. Finally, in the numerical simulation, the effectiveness of the DFD approach is demonstrated by comparing it with three nonlinear methods.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125397092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455465
Shuangshuang Xiong, Z. Hou, Lingling Fan
In this note, two kinds of distributed model free adaptive PID controllers are proposed to solve the consensus tracking problem for a class of unknown heterogenous nonaffine nonlinear discrete-time multi-agent systems based on the technique of dynamic linearization of controlled plant and ideal controller. Only the input/output data information of agent itself and its neighbours are used in the parameter estimation law of the designed adaptive PID controller. A simulation is given to illustrate the theoretical results.
{"title":"Design of Distributed Model Free Adaptive PID Controllers for Heterogenous Nonlinear Multi-agent Systems","authors":"Shuangshuang Xiong, Z. Hou, Lingling Fan","doi":"10.1109/DDCLS52934.2021.9455465","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455465","url":null,"abstract":"In this note, two kinds of distributed model free adaptive PID controllers are proposed to solve the consensus tracking problem for a class of unknown heterogenous nonaffine nonlinear discrete-time multi-agent systems based on the technique of dynamic linearization of controlled plant and ideal controller. Only the input/output data information of agent itself and its neighbours are used in the parameter estimation law of the designed adaptive PID controller. A simulation is given to illustrate the theoretical results.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123374529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455704
Haichao Chen, Zhu Wang, Zhihui Liu, Qing Chang
For the slow-switching Hammerstein system in an impulsive noise environment, multiple identifiers are used to work together to detect the switching point quickly and accurately, and at the same time obtain the parameter estimates of the sub-model. Recursive identification of multiple innovations can improve the accuracy of the identification results and increase the robustness of the identification algorithm. Recursive identification of short innovations is more sensitive to changes in the system environment. Compare the identification results of the two identification algorithms to determine whether subsystem switching occurs and can resist the interference of impulse noise. During the switching process of the subsystem, the initial identification value generated during the switching process is confirmed to improve the convergence speed and speed up the switching process. Finally, simulation experiments prove the superiority of the proposed switching scheme.
{"title":"Based on The Recursive Identifier of Different Innovation Lengths On-off Detection Strategy of Slow-switching Hammerstein System","authors":"Haichao Chen, Zhu Wang, Zhihui Liu, Qing Chang","doi":"10.1109/DDCLS52934.2021.9455704","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455704","url":null,"abstract":"For the slow-switching Hammerstein system in an impulsive noise environment, multiple identifiers are used to work together to detect the switching point quickly and accurately, and at the same time obtain the parameter estimates of the sub-model. Recursive identification of multiple innovations can improve the accuracy of the identification results and increase the robustness of the identification algorithm. Recursive identification of short innovations is more sensitive to changes in the system environment. Compare the identification results of the two identification algorithms to determine whether subsystem switching occurs and can resist the interference of impulse noise. During the switching process of the subsystem, the initial identification value generated during the switching process is confirmed to improve the convergence speed and speed up the switching process. Finally, simulation experiments prove the superiority of the proposed switching scheme.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126280857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455657
Manu Lahariya, F. Karami, Chris Develder, G. Crevecoeur
Energy storage is ubiquitous in industrial processes and comes in many forms such as material, chemical, electromechanical buffers. System identification of such energy buffers demands proper estimation/prediction of their physical quantities and unknown parameters. Once these parameters are determined, the identified model can be employed to predict the industrial process dynamics, which finally assist to build efficient control for these processes. This paper proposes physics-informed neural networks-based grey-box modeling methods for the identification of energy buffers. The underlying system dynamics are enforced on the neural network structure to ensure that the identified grey-box model follows the approximate physics. We define two novel grey-box models based on simple and recurrent neural network architectures and test these models for a generic energy buffer. Performance and training time for the proposed grey-box models are compared against a black-box baseline model. Results confirm that imposing the dynamic system's physics on the network improves the performance, and utilizing a recurrent architecture leads to a further improvement.
{"title":"Physics-informed Recurrent Neural Networks for The Identification of a Generic Energy Buffer System","authors":"Manu Lahariya, F. Karami, Chris Develder, G. Crevecoeur","doi":"10.1109/DDCLS52934.2021.9455657","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455657","url":null,"abstract":"Energy storage is ubiquitous in industrial processes and comes in many forms such as material, chemical, electromechanical buffers. System identification of such energy buffers demands proper estimation/prediction of their physical quantities and unknown parameters. Once these parameters are determined, the identified model can be employed to predict the industrial process dynamics, which finally assist to build efficient control for these processes. This paper proposes physics-informed neural networks-based grey-box modeling methods for the identification of energy buffers. The underlying system dynamics are enforced on the neural network structure to ensure that the identified grey-box model follows the approximate physics. We define two novel grey-box models based on simple and recurrent neural network architectures and test these models for a generic energy buffer. Performance and training time for the proposed grey-box models are compared against a black-box baseline model. Results confirm that imposing the dynamic system's physics on the network improves the performance, and utilizing a recurrent architecture leads to a further improvement.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126687190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455509
Zhifen Guo, Lezhou Wu, Yun Li, Beilin Li
Schizophrenia(SZ) is a disease of unknown etiology and pathogenesis and is ranked by the World Health Organization as one of the top ten diseases contributing to the global burden of disease. Studying the internal physiological differences between EEG of schizophrenia patients and normal individuals is important for diagnosing and treating schizophrenia in order to determine objective physiological diagnostic criteria. The EEG data of patients with schizophrenia were preprocessed and markers were extracted. The convolutional neural network was used to characterize the difference of distributed structure of data for classification and the classification results were given. The accuracy of the classification was 92%, and the disease classification was effectively performed using deep learning networks.
{"title":"Deep neural network classification of EEG data in schizophrenia","authors":"Zhifen Guo, Lezhou Wu, Yun Li, Beilin Li","doi":"10.1109/DDCLS52934.2021.9455509","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455509","url":null,"abstract":"Schizophrenia(SZ) is a disease of unknown etiology and pathogenesis and is ranked by the World Health Organization as one of the top ten diseases contributing to the global burden of disease. Studying the internal physiological differences between EEG of schizophrenia patients and normal individuals is important for diagnosing and treating schizophrenia in order to determine objective physiological diagnostic criteria. The EEG data of patients with schizophrenia were preprocessed and markers were extracted. The convolutional neural network was used to characterize the difference of distributed structure of data for classification and the classification results were given. The accuracy of the classification was 92%, and the disease classification was effectively performed using deep learning networks.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116273228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455476
Dazi Li, Jianghai Du
This study proposes a preprocessing framework for expert examples based on behavior cloning (BC) to solve the problem that inverse reinforcement learning (IRL) is inaccurate due to the noises of expert examples. In order to remove the noises in the expert examples, we first use supervised learning to learn the approximate expert policy, and then use this approximate expert policy to clone new expert examples from the old expert examples, the idea of this preprocessing framework is BC, IRL can obtain higher quality expert examples after preprocessing. The IRL framework adopts the form of maximum entropy, and specific experiments demonstrate the effectiveness of the proposed approach, in the case of expert examples with noises, the reward functions that after BC preprocessing is better than that without preprocessing, especially with the increase of noise level, the effect is particularly obvious.
{"title":"Maximum Entropy Inverse Reinforcement Learning Based on Behavior Cloning of Expert Examples","authors":"Dazi Li, Jianghai Du","doi":"10.1109/DDCLS52934.2021.9455476","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455476","url":null,"abstract":"This study proposes a preprocessing framework for expert examples based on behavior cloning (BC) to solve the problem that inverse reinforcement learning (IRL) is inaccurate due to the noises of expert examples. In order to remove the noises in the expert examples, we first use supervised learning to learn the approximate expert policy, and then use this approximate expert policy to clone new expert examples from the old expert examples, the idea of this preprocessing framework is BC, IRL can obtain higher quality expert examples after preprocessing. The IRL framework adopts the form of maximum entropy, and specific experiments demonstrate the effectiveness of the proposed approach, in the case of expert examples with noises, the reward functions that after BC preprocessing is better than that without preprocessing, especially with the increase of noise level, the effect is particularly obvious.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128032209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455563
Jiafeng Wang, Dong Ding, Jiancheng Zhang, Ze Tang
This paper studies the consensus problem for a kind of multi-agent systems with nonlinear and discontinuous dynamics through distributed adaptive control. By applying saturation strategy, the control signal is limited into a reasonable range in order to simulate the practical applications. Then utilize the Gaussian error function and the differential mean value theorem to simulate the saturation effect. By designing the adaptive updating law, appropriate control gain is finally obtained. According to Filippov differential inclusion and measure selection theorem as well as Lyapunov stability theorem, sufficient conditions for achieving the consensus of multi-agent systems are derived. Ultimately, the validity of our conclusion is verified by establishing a numerical simulation.
{"title":"Saturated Adaptive Pinning Control and Consensus of Discontinuous Multi-Agent Systems","authors":"Jiafeng Wang, Dong Ding, Jiancheng Zhang, Ze Tang","doi":"10.1109/DDCLS52934.2021.9455563","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455563","url":null,"abstract":"This paper studies the consensus problem for a kind of multi-agent systems with nonlinear and discontinuous dynamics through distributed adaptive control. By applying saturation strategy, the control signal is limited into a reasonable range in order to simulate the practical applications. Then utilize the Gaussian error function and the differential mean value theorem to simulate the saturation effect. By designing the adaptive updating law, appropriate control gain is finally obtained. According to Filippov differential inclusion and measure selection theorem as well as Lyapunov stability theorem, sufficient conditions for achieving the consensus of multi-agent systems are derived. Ultimately, the validity of our conclusion is verified by establishing a numerical simulation.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122476845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-14DOI: 10.1109/ddcls52934.2021.9455564
Lin Sui, B. Du, Mengyan Zhang, Kai Sun
This paper proposes an accurate and reliable input variable selection algorithm by embedding a nonnegative garrote (NNG) algorithm into long short term memory (LSTM) neural network to perform data-driven modeling on a highly nonlinear and dynamic time-delay dataset. Firstly, an LSTM deep neural network is trained, and a well-trained LSTM network is obtained by optimizing the parameters of LSTM through a grid search algorithm. Secondly, the initial input weights of LSTM are compressed accurately by the NNG algorithm, and block cross-validation is applied to the optimization calculation process to achieve input variable selection. Finally, the performance of the algorithm is verified by the improved Friedman time-delay artificial datasets. Simulation results show that the algorithm could construct a more simplified and better predictive model than other traditional algorithms.
{"title":"A new variable selection algorithm for LSTM neural network","authors":"Lin Sui, B. Du, Mengyan Zhang, Kai Sun","doi":"10.1109/ddcls52934.2021.9455564","DOIUrl":"https://doi.org/10.1109/ddcls52934.2021.9455564","url":null,"abstract":"This paper proposes an accurate and reliable input variable selection algorithm by embedding a nonnegative garrote (NNG) algorithm into long short term memory (LSTM) neural network to perform data-driven modeling on a highly nonlinear and dynamic time-delay dataset. Firstly, an LSTM deep neural network is trained, and a well-trained LSTM network is obtained by optimizing the parameters of LSTM through a grid search algorithm. Secondly, the initial input weights of LSTM are compressed accurately by the NNG algorithm, and block cross-validation is applied to the optimization calculation process to achieve input variable selection. Finally, the performance of the algorithm is verified by the improved Friedman time-delay artificial datasets. Simulation results show that the algorithm could construct a more simplified and better predictive model than other traditional algorithms.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122759521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：