Pub Date : 2020-11-20DOI: 10.1109/ICCSNT50940.2020.9304987
Z. Liu
Traditional linear regression is the primary factor that affects measurement precision in measuring moisture content with microwave resonator. A regression is put forward based on an improved BP algorithm to modify the measurement result. First, the regression neural network is pre optimized by using the macro search ability, parallel operation and strong robustness of genetic algorithm. Then, integrating the gradient descent method of BP algorithm, the presented algorithm can effectively avoid the traditional BP algorithm of falling into local minimum, at the same time, high prediction accuracy and fast convergence speed are maintained. It has the characteristics of global superiority and accuracy for optimization, thus improving the measurement accuracy. The experimental results show that the mean square error between predicted moisture and actual moisture is 0.0109, the average absolute error is 0.0702, the average relative error is 0.1161, and the determination coefficient is 0.9989.
{"title":"Improved BP Arithmetic in Moisture Content Measurement with Microwave Resonant","authors":"Z. Liu","doi":"10.1109/ICCSNT50940.2020.9304987","DOIUrl":"https://doi.org/10.1109/ICCSNT50940.2020.9304987","url":null,"abstract":"Traditional linear regression is the primary factor that affects measurement precision in measuring moisture content with microwave resonator. A regression is put forward based on an improved BP algorithm to modify the measurement result. First, the regression neural network is pre optimized by using the macro search ability, parallel operation and strong robustness of genetic algorithm. Then, integrating the gradient descent method of BP algorithm, the presented algorithm can effectively avoid the traditional BP algorithm of falling into local minimum, at the same time, high prediction accuracy and fast convergence speed are maintained. It has the characteristics of global superiority and accuracy for optimization, thus improving the measurement accuracy. The experimental results show that the mean square error between predicted moisture and actual moisture is 0.0109, the average absolute error is 0.0702, the average relative error is 0.1161, and the determination coefficient is 0.9989.","PeriodicalId":6794,"journal":{"name":"2020 IEEE 8th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"80 1","pages":"190-193"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80034441","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}
Smart grid is willing to make full advantage of distributed clean energy to alleviate energy crisis and environmental problems. However, distributed renewable energy is usually invisible and uncontrollable for the current power system, and there are intermittent problems in its generation. Therefore, how to achieve the power balance, maintain safe operation, and ensure the reliability and quality of power supply when the distributed energy reaches a high penetration in the grid is a huge challenge. Blockchain as one of the research hotspots brings about new solution approach to the dilemma. The two fields have many commons on decentralization, autonomy, marketization and intelligence. In this paper, we discuss the feasible scheme of the integrated system and add fog computing to reduce costs. Considering the realization of system, we choose Hyper Fabric as the basic structure and add verifiable random function to the consensus aimed to improve randomness and security in the encrypted election. Meanwhile, in order to satisfy the business requirements, a flexible adjustment method based on Deep Q Learning algorithm is designed to realize the joint optimization of throughput, latency and storage cost. The proposed scheme provides the advantages including privacy, flexibility, extensibility and implantation simplicity.
{"title":"Fog Computing enabled Smart Grid Blockchain Architecture and Performance Optimization with DRL Approach","authors":"Weijun Zheng, Wenhua Wang, Guoqing Wu, Chenzi Xue, Yifei Wei","doi":"10.1109/ICCSNT50940.2020.9305000","DOIUrl":"https://doi.org/10.1109/ICCSNT50940.2020.9305000","url":null,"abstract":"Smart grid is willing to make full advantage of distributed clean energy to alleviate energy crisis and environmental problems. However, distributed renewable energy is usually invisible and uncontrollable for the current power system, and there are intermittent problems in its generation. Therefore, how to achieve the power balance, maintain safe operation, and ensure the reliability and quality of power supply when the distributed energy reaches a high penetration in the grid is a huge challenge. Blockchain as one of the research hotspots brings about new solution approach to the dilemma. The two fields have many commons on decentralization, autonomy, marketization and intelligence. In this paper, we discuss the feasible scheme of the integrated system and add fog computing to reduce costs. Considering the realization of system, we choose Hyper Fabric as the basic structure and add verifiable random function to the consensus aimed to improve randomness and security in the encrypted election. Meanwhile, in order to satisfy the business requirements, a flexible adjustment method based on Deep Q Learning algorithm is designed to realize the joint optimization of throughput, latency and storage cost. The proposed scheme provides the advantages including privacy, flexibility, extensibility and implantation simplicity.","PeriodicalId":6794,"journal":{"name":"2020 IEEE 8th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"1 1","pages":"41-45"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84930989","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 : 2020-11-20DOI: 10.1109/ICCSNT50940.2020.9305012
Can Wang, Qiang Lin, Chunming Xu, Lin Li, Xiaoyong Fan
From the perspective of formal concept analysis, the concepts of a formal context generated become larger in number with growing data. Attribute reduction based on decision formal context is to find out minimum subsets of attributes while maintaining the ability of classification, decision rules simplified as well which will make decision making much easier. This paper firstly generates decision rules, divides decision rules into strong rules and weak rules, puts forward judging theorems of non-redundant rules and rule reduction; secondly, proposes an approach of rule reduction by categories of attributes; in the end, discusses the time complexity. Comparing with other algorithms on runtime and ability of classification, experimental analysis shows that our method approves feasibility and accuracy. In the end, it draws a conclusion and discusses open issues.
{"title":"Novel Attribute Reduction on Decision Rules*","authors":"Can Wang, Qiang Lin, Chunming Xu, Lin Li, Xiaoyong Fan","doi":"10.1109/ICCSNT50940.2020.9305012","DOIUrl":"https://doi.org/10.1109/ICCSNT50940.2020.9305012","url":null,"abstract":"From the perspective of formal concept analysis, the concepts of a formal context generated become larger in number with growing data. Attribute reduction based on decision formal context is to find out minimum subsets of attributes while maintaining the ability of classification, decision rules simplified as well which will make decision making much easier. This paper firstly generates decision rules, divides decision rules into strong rules and weak rules, puts forward judging theorems of non-redundant rules and rule reduction; secondly, proposes an approach of rule reduction by categories of attributes; in the end, discusses the time complexity. Comparing with other algorithms on runtime and ability of classification, experimental analysis shows that our method approves feasibility and accuracy. In the end, it draws a conclusion and discusses open issues.","PeriodicalId":6794,"journal":{"name":"2020 IEEE 8th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"48 1","pages":"69-74"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78292702","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 : 2020-11-20DOI: 10.1109/ICCSNT50940.2020.9304978
Ling Xiao, Xiang Li, Zhenyu Liao
As the the spoofing interference can result in serious consequences, the GNSS spoofing detection problem is a hot research topic now. To detect the spoofing signals, which coming from different emitting sources, an anti-spoofing method was proposed with using linear array. The method recognizes spoofing signal by comparing the carrier-phase single difference (CPSD) measurements, which is calculated between different array elements, with the expect CPSD estimations. As the attitude of the linear array is assumed to be unknown, it has to be estimated in the process of estimating expect CPSD. The spoofing decision variable was deduced based on the differences between CPSD measurements and expectations. And the statistical characterization of the variable was analyzed as well. In the last, the spoofing detection performance was evaluated by Monte-Carlo simulations. The simulation results illustrated that no matter how many emitting sources, as long as there is one spoofing signal that the angle between its incident direction and corresponding authentic one is larger than 5 degrees, it will be detected effectively by the proposed method with a 3 elements array.
{"title":"GNSS Spoofing Detection With Using Linear Array","authors":"Ling Xiao, Xiang Li, Zhenyu Liao","doi":"10.1109/ICCSNT50940.2020.9304978","DOIUrl":"https://doi.org/10.1109/ICCSNT50940.2020.9304978","url":null,"abstract":"As the the spoofing interference can result in serious consequences, the GNSS spoofing detection problem is a hot research topic now. To detect the spoofing signals, which coming from different emitting sources, an anti-spoofing method was proposed with using linear array. The method recognizes spoofing signal by comparing the carrier-phase single difference (CPSD) measurements, which is calculated between different array elements, with the expect CPSD estimations. As the attitude of the linear array is assumed to be unknown, it has to be estimated in the process of estimating expect CPSD. The spoofing decision variable was deduced based on the differences between CPSD measurements and expectations. And the statistical characterization of the variable was analyzed as well. In the last, the spoofing detection performance was evaluated by Monte-Carlo simulations. The simulation results illustrated that no matter how many emitting sources, as long as there is one spoofing signal that the angle between its incident direction and corresponding authentic one is larger than 5 degrees, it will be detected effectively by the proposed method with a 3 elements array.","PeriodicalId":6794,"journal":{"name":"2020 IEEE 8th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"1 1","pages":"181-185"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78060425","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 : 2020-11-20DOI: 10.1109/ICCSNT50940.2020.9304988
Yan-sen Zhou, Jianquan Cui, Qi Liu
The current anomaly intrusion detection system has shortcomings such as low detection rate, high false alarm rate and poor performance in processing large amounts of data. In response to the above problems, some improvement measures are put forward for the isolated forest algorithm and the FP-Growth algorithm. The improved isolated forest algorithm considers the correlation between dimensions and makes the dimension division more reasonable for abnormal analysis. The improved FP growth algorithm reduces the time of processing a large amount of data, used for correlation analysis of abnormal data. Applying the above two improved algorithms to intrusion detection can further improve the anomaly detection performance. The results show that the false alarm rate of the joint improved algorithm is relatively reduced by 25%, and the overall detection rate is 96.24%.
{"title":"Research and Improvement of Intrusion Detection Based on Isolated Forest and FP-Growth","authors":"Yan-sen Zhou, Jianquan Cui, Qi Liu","doi":"10.1109/ICCSNT50940.2020.9304988","DOIUrl":"https://doi.org/10.1109/ICCSNT50940.2020.9304988","url":null,"abstract":"The current anomaly intrusion detection system has shortcomings such as low detection rate, high false alarm rate and poor performance in processing large amounts of data. In response to the above problems, some improvement measures are put forward for the isolated forest algorithm and the FP-Growth algorithm. The improved isolated forest algorithm considers the correlation between dimensions and makes the dimension division more reasonable for abnormal analysis. The improved FP growth algorithm reduces the time of processing a large amount of data, used for correlation analysis of abnormal data. Applying the above two improved algorithms to intrusion detection can further improve the anomaly detection performance. The results show that the false alarm rate of the joint improved algorithm is relatively reduced by 25%, and the overall detection rate is 96.24%.","PeriodicalId":6794,"journal":{"name":"2020 IEEE 8th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"38 1","pages":"160-164"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91273128","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 : 2020-11-20DOI: 10.1109/ICCSNT50940.2020.9305008
Ming Huang, Shasha Shi, Xu Liang, Xuan Jiao, Yijie Fu
For flow shop scheduling problem, an improved biogeography-based optimization algorithm (IBBO) is proposed. Firstly, the mathematical model of the problem is established with the objective function of minimizing the maximum completion time. Secondly, the NEH algorithm is used to initialize the population. The cosine migration model is introduced to perform the migration operation. Besides the elite retention strategy is added in the iteration process. And the simulated annealing algorithm is combined to improve the optimization ability of biogeography-based optimization algorithm. Finally, on the basis of Taillard example, the performance of the proposed method is analyzed by using ARPD through experimental simulation. The results show the advantages of the improved biogeography-based optimization.
{"title":"An Improved Biogeography-Based Optimization Algorithm for Flow Shop Scheduling Problem","authors":"Ming Huang, Shasha Shi, Xu Liang, Xuan Jiao, Yijie Fu","doi":"10.1109/ICCSNT50940.2020.9305008","DOIUrl":"https://doi.org/10.1109/ICCSNT50940.2020.9305008","url":null,"abstract":"For flow shop scheduling problem, an improved biogeography-based optimization algorithm (IBBO) is proposed. Firstly, the mathematical model of the problem is established with the objective function of minimizing the maximum completion time. Secondly, the NEH algorithm is used to initialize the population. The cosine migration model is introduced to perform the migration operation. Besides the elite retention strategy is added in the iteration process. And the simulated annealing algorithm is combined to improve the optimization ability of biogeography-based optimization algorithm. Finally, on the basis of Taillard example, the performance of the proposed method is analyzed by using ARPD through experimental simulation. The results show the advantages of the improved biogeography-based optimization.","PeriodicalId":6794,"journal":{"name":"2020 IEEE 8th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"7 1","pages":"59-63"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84446802","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 : 2020-11-20DOI: 10.1109/ICCSNT50940.2020.9304991
Xiaoquan Chu, Yue Li, Luyao Wang, Jianying Feng, Weisong Mu
Applications of data science for agriculture has been widely discussed, this study attempts to construct a novel machine learning-based strategy for products price analyzing and forecasting. To do this, we follow the framework of "divide and conquer" to strategically integrate the Ensemble Empirical Mode Decomposition (EEMD), reconstruction algorithms, evolutionary Least Squares Support Vector Machine (LSSVM) and Extreme Learning Machine (ELM) to realize numerical forecasting and qualitative analysis. In the price prediction scenario of table grape, which is a typical perishable fruit in China's fruit market, the performance of the proposed method is verified. This paper is committed to provide a reference for the univariate time series price analysis of perishable agricultural products when the conditions are not enough to analyze the influencing factors, free it from the tedious process of data collection, and realize the accurate prediction and qualitative analysis of the target series.
{"title":"A Novel Machine Learning-based Strategy for Agricultural Time Series Analyzing and Forecasting: a Case Study in China's Table Grape Price","authors":"Xiaoquan Chu, Yue Li, Luyao Wang, Jianying Feng, Weisong Mu","doi":"10.1109/ICCSNT50940.2020.9304991","DOIUrl":"https://doi.org/10.1109/ICCSNT50940.2020.9304991","url":null,"abstract":"Applications of data science for agriculture has been widely discussed, this study attempts to construct a novel machine learning-based strategy for products price analyzing and forecasting. To do this, we follow the framework of \"divide and conquer\" to strategically integrate the Ensemble Empirical Mode Decomposition (EEMD), reconstruction algorithms, evolutionary Least Squares Support Vector Machine (LSSVM) and Extreme Learning Machine (ELM) to realize numerical forecasting and qualitative analysis. In the price prediction scenario of table grape, which is a typical perishable fruit in China's fruit market, the performance of the proposed method is verified. This paper is committed to provide a reference for the univariate time series price analysis of perishable agricultural products when the conditions are not enough to analyze the influencing factors, free it from the tedious process of data collection, and realize the accurate prediction and qualitative analysis of the target series.","PeriodicalId":6794,"journal":{"name":"2020 IEEE 8th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"1 1","pages":"75-80"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85495121","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 : 2020-11-20DOI: 10.1109/ICCSNT50940.2020.9305005
Ming Huang, Dongsheng Guo, Xu Liang, Xiuyan Liang
This paper takes minimizing the maximum completion time as the optimization goal, establishes a disjunctive graph model of the Job-shop scheduling problem, and proposes an improved ant colony algorithm to solve it. The new algorithm improves the ant colony algorithm from two aspects: pheromone update rules and state transition rules, aiming at the problem that ant colony algorithm is easy fall into local optimal solution and slow convergence speed. The feasibility and effectiveness of the proposed algorithm are verified by the experimental simulation of classical examples and the comparison with other relevant literature in recent years.
{"title":"An Improved Ant Colony Algorithm is Proposed to Solve the Single Objective Flexible Job-shop Scheduling Problem","authors":"Ming Huang, Dongsheng Guo, Xu Liang, Xiuyan Liang","doi":"10.1109/ICCSNT50940.2020.9305005","DOIUrl":"https://doi.org/10.1109/ICCSNT50940.2020.9305005","url":null,"abstract":"This paper takes minimizing the maximum completion time as the optimization goal, establishes a disjunctive graph model of the Job-shop scheduling problem, and proposes an improved ant colony algorithm to solve it. The new algorithm improves the ant colony algorithm from two aspects: pheromone update rules and state transition rules, aiming at the problem that ant colony algorithm is easy fall into local optimal solution and slow convergence speed. The feasibility and effectiveness of the proposed algorithm are verified by the experimental simulation of classical examples and the comparison with other relevant literature in recent years.","PeriodicalId":6794,"journal":{"name":"2020 IEEE 8th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"145 1","pages":"16-21"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73548924","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 : 2020-11-20DOI: 10.1109/ICCSNT50940.2020.9304995
Guanghua Tong, Wang Jing, Gao Shan, Sun Yang, Wang Jinxiu, Zuo Jing
Layered water injection is a simple and effective way of secondary exploitation in oil fields. It can maintain the pressure of the oil layer and improve the effect of oilfield development, considered the basis for achieving stable and high production of crude oil. The traditional layered water injection method is inefficient and cannot meet the needs of mining. Therefore, this paper analyzes the current development of layered water injection technology and designs an automatic layered water injection system based on the Internet of Things. It is divided into perception recognition layer, network construction layer, and comprehensive application layer. Considering that the daily injection volume of water injection wells does not meet the standard caused by the actual water injection process, an automatic injection strategy of layered water injection is designed based on the K-means algorithm. Experiments demonstrate that the actual flow value of each layer after the automatic injection adjustment is completed is within the allowable error range of 10%, which meets the requirements of the qualified rate of layered water injection.
{"title":"Design of Automatic Layered Water Injection System Based on Internet of Things","authors":"Guanghua Tong, Wang Jing, Gao Shan, Sun Yang, Wang Jinxiu, Zuo Jing","doi":"10.1109/ICCSNT50940.2020.9304995","DOIUrl":"https://doi.org/10.1109/ICCSNT50940.2020.9304995","url":null,"abstract":"Layered water injection is a simple and effective way of secondary exploitation in oil fields. It can maintain the pressure of the oil layer and improve the effect of oilfield development, considered the basis for achieving stable and high production of crude oil. The traditional layered water injection method is inefficient and cannot meet the needs of mining. Therefore, this paper analyzes the current development of layered water injection technology and designs an automatic layered water injection system based on the Internet of Things. It is divided into perception recognition layer, network construction layer, and comprehensive application layer. Considering that the daily injection volume of water injection wells does not meet the standard caused by the actual water injection process, an automatic injection strategy of layered water injection is designed based on the K-means algorithm. Experiments demonstrate that the actual flow value of each layer after the automatic injection adjustment is completed is within the allowable error range of 10%, which meets the requirements of the qualified rate of layered water injection.","PeriodicalId":6794,"journal":{"name":"2020 IEEE 8th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"6 1","pages":"194-197"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86697753","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 : 2020-11-20DOI: 10.1109/ICCSNT50940.2020.9304993
Jianfeng Wang, Zhaozhen Zhang
Accurate estimation of the lithium-ion battery SOC is critical to the battery management system (BMS). In order to accurately estimate the lithium-ion battery SOC, a second-order equivalent model of the lithium-ion battery is firstly established in this paper, and the lithium-ion battery's nonlinear relationship of SOC-OCV is obtained through the experiment. Then the online parameter identification method based on the least square method is used to estimate the parameters of the lithium-ion battery's online model, and the accurate estimation of lithium-ion battery SOC is achieved by combining weighted adaptive recursive least square method with extended Kalman filter. This paper compares estimation accuracy of the battery SOC based on the extended Kalman filter algorithm (EKF), the recursive least square method based on the forgetting factor (FRLS), and the weighted adaptive recursive extended Kalman filter joint algorithm (WAREKF) in the experiment. The experiment result shows that the estimation accuracy of the battery SOC based on WAREKF which is proposed in this paper is higher than that of EKF and FRLS, and its root mean square error (RMSE) is less than 1%.
{"title":"Lithium-ion Battery SOC Estimation Based on Weighted Adaptive Recursive Extended Kalman Filter Joint Algorithm","authors":"Jianfeng Wang, Zhaozhen Zhang","doi":"10.1109/ICCSNT50940.2020.9304993","DOIUrl":"https://doi.org/10.1109/ICCSNT50940.2020.9304993","url":null,"abstract":"Accurate estimation of the lithium-ion battery SOC is critical to the battery management system (BMS). In order to accurately estimate the lithium-ion battery SOC, a second-order equivalent model of the lithium-ion battery is firstly established in this paper, and the lithium-ion battery's nonlinear relationship of SOC-OCV is obtained through the experiment. Then the online parameter identification method based on the least square method is used to estimate the parameters of the lithium-ion battery's online model, and the accurate estimation of lithium-ion battery SOC is achieved by combining weighted adaptive recursive least square method with extended Kalman filter. This paper compares estimation accuracy of the battery SOC based on the extended Kalman filter algorithm (EKF), the recursive least square method based on the forgetting factor (FRLS), and the weighted adaptive recursive extended Kalman filter joint algorithm (WAREKF) in the experiment. The experiment result shows that the estimation accuracy of the battery SOC based on WAREKF which is proposed in this paper is higher than that of EKF and FRLS, and its root mean square error (RMSE) is less than 1%.","PeriodicalId":6794,"journal":{"name":"2020 IEEE 8th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"1 1","pages":"11-15"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90110297","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：