2022 China Automation Congress (CAC)最新文献

{"title":"The Application of Simulated Annealing Algorithm in Forest Simulation Optimation System","authors":"Sizhu Ren, Chunhui Li","doi":"10.1109/cac57257.2022.10055950","DOIUrl":"https://doi.org/10.1109/cac57257.2022.10055950","url":null,"abstract":"Given that forests comprise a large portion of the global land area, forestry management plays a significant role in ecological protection. The traditional method of advocating less deforestation is no longer suitable for the sustainable development of current socio-economic. In this paper, a multi-target analysis and planning model for the forest is proposed. The main aspects of evaluating a forest, including its social value, economic value and ecological value are taken into consideration. Subsequently, the penalty function is applied to simulated annealing algorithm, transforming the problem with constraints into an unconstrained problem. Thus an algorithm base that can search for the global optimal solution to the multi-objective problem, and obtain the best forestry management strategy for each kind of forest is proposed. Experiments have demonstrated encouraging results. Drawbacks such as the demand of strict restriction of the data, the occurrence of overfitting, and easy to be trapped in a local optimal solution are conquered in the proposed algorithm, which always appear in the traditional methods like linear programming, polynomial fitting and hill-climbing algorithm. It is resulted that the temperature decay factor greatly affects the efficiency of the iteration of the algorithm, and the choice of parameters is very important for the algorithm.","PeriodicalId":287137,"journal":{"name":"2022 China Automation Congress (CAC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125313963","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}

{"title":"Short-Term Traffic Flow Prediction Based on I-SAWOA-Deep Echo State Network","authors":"Zhihui Yang, Qingyong Zhang, Changwu Li, Qiang Luo","doi":"10.1109/CAC57257.2022.10055270","DOIUrl":"https://doi.org/10.1109/CAC57257.2022.10055270","url":null,"abstract":"In recent years, the phenomenon of road congestion has occurred in all cities around the world, and this situation has become more and more severe, which has affected the travel of residents and restricted the development of cities. Short term traffic flow prediction is one of the key technologies of Intelligent Transportation System. It can predict the traffic flow in the future for a period of time through historical data, and then provide key information for traffic management personnel to make decisions. Therefore, researchers in various fields pay attention to it, and gradually propose a variety of prediction methods.In this paper, the Deep Echo State Network is selected as the basic prediction method, and the Improved-Whale Optimization Algorithm is used to optimize the super parameters of the network, which solves the problem that it is difficult to reasonably set the super parameters of the network. Finally, the experiment shows that the algorithm can follow the change trend of traffic flow data and has a good prediction effect.","PeriodicalId":287137,"journal":{"name":"2022 China Automation Congress (CAC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125321686","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}

{"title":"Fault Diagnosis of On-board Equipment in CTCS-3 Based on CNN-LSTM Model","authors":"Daqian Zhang, Yuan Cao, Miao Zhang, Ming Chai, J. Lv","doi":"10.1109/CAC57257.2022.10054856","DOIUrl":"https://doi.org/10.1109/CAC57257.2022.10054856","url":null,"abstract":"Data-driven methods based on deep learning have achieved remarkable results of fault diagnosis of train control system due to their superiority in feature extraction. However, it still faces uneven data distribution problem, which afects the detection accuracy of fault diagnosis. In this paper, by considering different failures both in system and subsystem level of train control system, we propose a novel two-stages fault diagnosis method based on a combination of Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM). Firstly, samples are obtained by segmenting and vectorizing the text form faulty data set, and fed into the proposed CNN-LSTM model. Then, in the first stage, the features of the processed data are extracted through the CNN layer, whereas the correlation between the sample data are derived through the LSTM layer. Thus, the classification of first-level faults, respect as system level, are realized with high accuracy of diagnosis. Finally, in the second stage, to solve the problem of data imbalance, we reconsider part of data from the CNN layer, and put them into the new LSTM layer for secondary faults diagnosis. We apply this method on a real CTCS-3 On-board equipment and the experimental results show that the accuracy rate of our proposed model reaches 96.7% and the accuracy of small data faults is also higher when compare with other neural network models,such as TextCNN, ANN, LSTM and RNN.","PeriodicalId":287137,"journal":{"name":"2022 China Automation Congress (CAC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125362034","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}

{"title":"Adaptive neural network output-feedback tracking control for switched nonlinear ship maneuvering systems with time delays under arbitrary switching","authors":"Zhenhua Li, Xiangxuan Ren, Botao Dong, Hong Chen, W. Zhang","doi":"10.1109/CAC57257.2022.10056105","DOIUrl":"https://doi.org/10.1109/CAC57257.2022.10056105","url":null,"abstract":"This paper focuses on the tracking control problem for switched nonlinear ship maneuvering time-delay systems with only a heading angle available by adaptive neural network (NN) output feedback. Using the backstepping method, an adaptive NN control mechanism is designed to solve the problem cooperated with the state observer. The uncertain terms of the system are approximated by NNs, and the state observer is designed to estimate the yaw rate and rudder angle. The unknown time delays are overcome by exploiting the common Lyapunov-Krasovskii functionals (CLKFs). Combined with error transformation, the proposed control method guarantees that i) all of the signals for the system are semi-global uniformly ultimately boundedness (SGUUB) under arbitrary switching; and, ii) the tracking error of system output keeps within a small neighborhood around the origin. The results of simulation results are shown to demonstrate the feasibility of the control strategy.","PeriodicalId":287137,"journal":{"name":"2022 China Automation Congress (CAC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125376688","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}

{"title":"Research on improving requirement of renewable energy forecasting for system anti-disturbance","authors":"Qingming Xiao, Dahai Yu, Y. Li, Xutao Li, Chao Wang, D. Ai, Zhenyu Ding, Ming Nian","doi":"10.1109/CAC57257.2022.10055339","DOIUrl":"https://doi.org/10.1109/CAC57257.2022.10055339","url":null,"abstract":"Due to the integration of renewable energy, the maximum output of conventional power plants is reduced, and the change of peak valley difference is no longer periodic. In order to cope with the fluctuation of renewable energy, the system needs to increase the rotating reserve capacity. At present, power supply is mainly thermal power in China. The inflexibility of thermal power switch and the existence of minimum technical output increase the volatility of start-up response to renewable energy, and limit the output of renewable energy in the period of low load and renewable energy. Predicting the output power of renewable energy and reducing the uncertainty of renewable energy fluctuation is one of the effective means to reduce the redundant standby capacity of the system. The increase of reserve capacity is related to the prediction accuracy of output power of renewable energy stations. Therefore, renewable energy power prediction is of great significance to the safe and economic operation of power system. According to the requirements of relevant documents and regulations of the national energy administration, all grid connected renewable energy stations need to establish a renewable energy power prediction system. In this paper, hundreds of renewable energy power forecasting service providers has emerged. However, the performance and prediction accuracy of renewable energy power prediction results are uneven, there is a lack of unified test standards and test platform, and an effective integration mechanism and identification method have not been established. Therefore, it is necessary to establish relevant evaluation mechanisms and provide third-party evaluation services, so as to provide a fair reference for selecting strong renewable energy production scheduling support services. However, different from conventional power supply, renewable energy has random volatility, and large-scale renewable energy grid connection brings challenges to the security, stability and economic operation of power grid.","PeriodicalId":287137,"journal":{"name":"2022 China Automation Congress (CAC)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126826131","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}

{"title":"of Fractional-order Complex Dynamical Networks with Actuator Failure by Dynamical Event-triggered Pinning Control","authors":"Liang Meng, Haibo Bao","doi":"10.1109/CAC57257.2022.10055734","DOIUrl":"https://doi.org/10.1109/CAC57257.2022.10055734","url":null,"abstract":"This article investigates a new dynamical event-triggered pinning control (ETPC) to handle the synchronization problem of fractional-order complex dynamical networks (FOCDNs) with actuator faults. Firstly, in order to improve the stability of the control system, a fault-tolerant control system (FTCS) based on ETPC is established. The dynamical event-triggered control (ETC) effectively reduces the number of triggering of the system and saves communication resources by constructing an internal dynamical variable. Then, the sufficient conditions for realizing synchronization of FOCDNs are obtained by using the fractional-order Lyapunov theory. It is further proved that the minimum time interval of the system is less than a positive constant, thus avoiding the Zeno phenomenon. Finally, the reliability of the results is verified by simulation.","PeriodicalId":287137,"journal":{"name":"2022 China Automation Congress (CAC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126865759","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}

{"title":"Non-Fragile H∞ Controller Design for Networked Systems Under False Data Injection Attacks and Consecutive Packet Dropouts","authors":"Kai Chen, Zhipei Hu","doi":"10.1109/CAC57257.2022.10056100","DOIUrl":"https://doi.org/10.1109/CAC57257.2022.10056100","url":null,"abstract":"In this paper, the non-fragile H∞ controller design problems for the networked control systems with false data injection attacks and packet losses are investigated. A non-fragile H∞ controller is utilized to render system tolerant or insensitive to external disturbances or random factors. First, the controlled system is converted into a discrete-time system by discrete-time approach. Subsequently, with the stochastic analysis technology and the law of total expectation, the stability condition of the networked control system is derived. Then, the desired non-fragile H∞ controller is obtained, with which the controlled system is exponentially mean-square stable with a desired H∞ performance. Finally, a numerical simulation and an aircraft flight control system are exploited to confirm the validity and practicability of the designed approach.","PeriodicalId":287137,"journal":{"name":"2022 China Automation Congress (CAC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115197369","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}

{"title":"Combining Deep Reinforcement Learning with Rule-based Constraints for Safe Highway Driving","authors":"Tingting Liu, Qianqian Liu, Hanxiao Liu, Xiaoqiang Ren","doi":"10.1109/CAC57257.2022.10055747","DOIUrl":"https://doi.org/10.1109/CAC57257.2022.10055747","url":null,"abstract":"Deep reinforcement learning (DRL) has been employed in solving challenging decision-making problems in autonomous driving. Safe decision-making in autonomous highway driving is among the foremost open problems due to the highly evolving driving environments and the influence of surrounding road users. In this paper, we present a powerful safe framework, which leverages the merits of both rule-based constraints and DRL for safety assurance. We model the highway scenario as a Markov Decision Process (MDP) and apply the deep Q-network (DQN) algorithm to optimize the driving performance. Moreover, a multi-head attention mechanism is introduced as a way to observe that vehicles with strong interactions make a difference in the decision-making of the ego vehicle, which can enhance the safety of the ego vehicle under complex highway driving environments. We also implement a safety module based on common traffic practices to ensure a minimum relative distance between two vehicles. This safety module will serve as feedback on the action of the DRL agent. If the action leads to risk, it will be replaced by a safer one and a negative reward will be assigned. The test and evaluation for our approach in a three-lane highway driving scenario have been done. The experiment results indicate that the proposed framework is capable of reducing the collision rate and accelerating the learning process.","PeriodicalId":287137,"journal":{"name":"2022 China Automation Congress (CAC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116409239","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}

{"title":"Application of Kurtosis Based Dynamic Window to Enhance SSVEP Recognition","authors":"Haojun Yin, Zhou Ji, Zequan Lian, Yuliang Yang, Nankun Liu, Hongtao Wang","doi":"10.1109/CAC57257.2022.10055430","DOIUrl":"https://doi.org/10.1109/CAC57257.2022.10055430","url":null,"abstract":"Steady-state visual evoked potential (SSVEP) is one of the main paradigms in the field of brain-computer interface (BCI). However, the challengeable issues for SSVEP are still how to make decisions from electroencephalogram to get a higher accuracy with a shorter time on recognition. In recent years, calibrated-free SSVEP algorithms have been constantly innovated and improved. As an effective approach, the dynamic window has been used to intercept EEG signals for recognition, and improving the information transfer rate (ITR) has become a hot research point. In this paper, the properties of the kurtosis feature were applied to select an appropriate kurtosis value as the threshold of SSVEP calibrated-free algorithm. To improve the accuracy of target recognition in the shortest possible time to achieve improvement of ITR, the length of the time window can be adjusted according to the threshold. For evaluation, the Benchmark dataset and four algorithms (Multivariate Synchro-nization Index (MSI), Canonical Correlation Analysis (CCA), Temporally Local Canonical Correlation Analysis (TCCA), and Filter Bank Canonical Correlation Analysis (FBCCA)) were applied to evaluate the recognition effect of dynamic window based on kurtosis. Experimental results showed that when the kurtosis is between 3.5 and 4, the performance of average ITR could achieve the best effect, and the highest ITR could reach up to 352.90 bits/min. In addition, this method was used in the 2021 BCI Robot Contest in World Robot Conference Contest. Using the strategy of CCA combining kurtosis value for dynamic window, the average ITR of five subjects was achieved 114.94 bits/min, and our team ranked fifth in the final contest.","PeriodicalId":287137,"journal":{"name":"2022 China Automation Congress (CAC)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116457135","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}

{"title":"Unsupervised Optimal Anomaly Detection Model Selection in Power Data","authors":"Guangrong Yu, Qinsheng Yang, Yongjin Zhu, Shiwei Zhang, Baotai Wu, Shangdong Liu, Yimu Ji","doi":"10.1109/CAC57257.2022.10054730","DOIUrl":"https://doi.org/10.1109/CAC57257.2022.10054730","url":null,"abstract":"Power data is complex and diverse. Different data types correspond to different power anomaly monitoring models. How to use a variety of feature combinations to automatically screen the optimal power anomaly detection model in the scenario of unsupervised power data anomaly detection is an urgent problem to be solved. First, extract the complex power data features into seven types of eigenvalues. Then, using the selection algorithm for unsupervised anomaly detection models based on the METAOD method, the optimal selection results of anomaly detection models under various power data sets are used to generate a selection database. Finally, divide the seven types of features into different combinations and use the reward principle and the corresponding abnormal detection results to combine and screen the optimal feature combination and the optimal power abnormality monitoring model for the existing data.","PeriodicalId":287137,"journal":{"name":"2022 China Automation Congress (CAC)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116561441","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}