Pub Date : 2020-07-20DOI: 10.1109/INDIN45582.2020.9442133
Chun Zheng, X. Tian, Gengsheng Nie, Yafeng Yu, Yingxue Li, Sidi Dong, Jinrui Tang, Binyu Xiong
Accurate power estimation can ensure safe and reliable operation of vanadium redox flow energy storage system (VRB-ESS) so that the battery does not violates the safe operating limits. The parameter variation of equivalent circuit model (ECM) of VRB affects the accurate estimation of state of Power (SoP), especially when considering the aging effects of the battery. In this paper, state of charge (SoC) and state of power (SoP) are estimated respectively. Firstly, the recursive least square (RLS) method is applied for online identification of the equivalent circuit parameters of VRB, then unscented Kalman filtering (UKF) is used to predict SoC of VRB, and lastly, the charged or discharged power can be predicted according to the accurate battery terminal voltage under limiting conditions. The results show that the UKF is capable for both the SoC and SoP estimation accurately.
{"title":"State of Power and State of Charge Estimation of Vanadium Redox Flow Battery Based on An Online Equivalent Circuit Model","authors":"Chun Zheng, X. Tian, Gengsheng Nie, Yafeng Yu, Yingxue Li, Sidi Dong, Jinrui Tang, Binyu Xiong","doi":"10.1109/INDIN45582.2020.9442133","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442133","url":null,"abstract":"Accurate power estimation can ensure safe and reliable operation of vanadium redox flow energy storage system (VRB-ESS) so that the battery does not violates the safe operating limits. The parameter variation of equivalent circuit model (ECM) of VRB affects the accurate estimation of state of Power (SoP), especially when considering the aging effects of the battery. In this paper, state of charge (SoC) and state of power (SoP) are estimated respectively. Firstly, the recursive least square (RLS) method is applied for online identification of the equivalent circuit parameters of VRB, then unscented Kalman filtering (UKF) is used to predict SoC of VRB, and lastly, the charged or discharged power can be predicted according to the accurate battery terminal voltage under limiting conditions. The results show that the UKF is capable for both the SoC and SoP estimation accurately.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"161 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132393714","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 : 2020-07-20DOI: 10.1109/INDIN45582.2020.9442126
Hao Qin, Jiong Jin
Shield tunnelling machine is a giant engineering equipment working deep under the ground, whose maintenance is significant in ensuring the continually operation of the machine. However, the traditional regular maintenance by engineers takes long time and plenty of people. In this case, a more intelligent maintenance method is required. To fill this gap, this paper proposes an intelligent maintenance method based on knowledge graph, which captures and reuse the knowledge generated during maintenance process in order to intelligently recommend solutions for maintenance tasks. This method includes three stages, creating knowledge representation model, building knowledge graph, developing collaborative knowledge management system for implementation. A case study on a specific shield tunnelling machine is demonstrated in this paper, with results showing the feasibility and effectiveness of this method.
{"title":"Intelligent Maintenance of Shield Tunelling Machine based on Knowledge Graph","authors":"Hao Qin, Jiong Jin","doi":"10.1109/INDIN45582.2020.9442126","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442126","url":null,"abstract":"Shield tunnelling machine is a giant engineering equipment working deep under the ground, whose maintenance is significant in ensuring the continually operation of the machine. However, the traditional regular maintenance by engineers takes long time and plenty of people. In this case, a more intelligent maintenance method is required. To fill this gap, this paper proposes an intelligent maintenance method based on knowledge graph, which captures and reuse the knowledge generated during maintenance process in order to intelligently recommend solutions for maintenance tasks. This method includes three stages, creating knowledge representation model, building knowledge graph, developing collaborative knowledge management system for implementation. A case study on a specific shield tunnelling machine is demonstrated in this paper, with results showing the feasibility and effectiveness of this method.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132609343","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 : 2020-07-20DOI: 10.1109/indin45582.2020.9442150
{"title":"Industrial Cyber-physical Systems and Industrial Agents","authors":"","doi":"10.1109/indin45582.2020.9442150","DOIUrl":"https://doi.org/10.1109/indin45582.2020.9442150","url":null,"abstract":"","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130957912","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 : 2020-07-20DOI: 10.1109/INDIN45582.2020.9442186
T. Miny, Julian Grothoff, U. Epple
OPC Unified Architecture is one of the leading technologies to realize the horizontal and vertical communication from enterprise layer down to the field layer in automation technology. It defines an address space model consisting of nodes and references without specifying how to store these. Therefore, this paper first describes the concept of a nodestore and a nodestore switch. The core contribution of the nodestore switch is the decoupling of OPC UA servers from their node storage. Based on this, four usage scenarios demonstrate how to utilize the concept to address different requirements, like performance and persistence, the integration of domain specific (proprietary) meta models, the adaptation at runtime and sharing of information models. For each usage scenario a prototypical implementation is described to show an exemplary realization and to gather a deeper understanding of the usage.
{"title":"OPC UA Nodestore Switch - Usage Scenarios","authors":"T. Miny, Julian Grothoff, U. Epple","doi":"10.1109/INDIN45582.2020.9442186","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442186","url":null,"abstract":"OPC Unified Architecture is one of the leading technologies to realize the horizontal and vertical communication from enterprise layer down to the field layer in automation technology. It defines an address space model consisting of nodes and references without specifying how to store these. Therefore, this paper first describes the concept of a nodestore and a nodestore switch. The core contribution of the nodestore switch is the decoupling of OPC UA servers from their node storage. Based on this, four usage scenarios demonstrate how to utilize the concept to address different requirements, like performance and persistence, the integration of domain specific (proprietary) meta models, the adaptation at runtime and sharing of information models. For each usage scenario a prototypical implementation is described to show an exemplary realization and to gather a deeper understanding of the usage.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124339383","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 : 2020-07-20DOI: 10.1109/INDIN45582.2020.9442196
Jifeng Sun, Jianwu Lin, Yi Zhou
Stock return prediction can help investors make better investment decisions and trends of country's economics. However, most of methods for stock return prediction are based on time-series models, treating the stocks as independent from each other. Inter-relations among stocks' time series are out of consideration. In this work, a Multi-Channel Temporal Graph Convolutional Neural Network (MCT-GCN) is proposed to optimize stock movement prediction. Experiments show that its performance is greater than benchmark algorithms, LSTM in the S&P 500.
{"title":"Multi-Channel Temporal Graph Convolutional Network for Stock Return Prediction","authors":"Jifeng Sun, Jianwu Lin, Yi Zhou","doi":"10.1109/INDIN45582.2020.9442196","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442196","url":null,"abstract":"Stock return prediction can help investors make better investment decisions and trends of country's economics. However, most of methods for stock return prediction are based on time-series models, treating the stocks as independent from each other. Inter-relations among stocks' time series are out of consideration. In this work, a Multi-Channel Temporal Graph Convolutional Neural Network (MCT-GCN) is proposed to optimize stock movement prediction. Experiments show that its performance is greater than benchmark algorithms, LSTM in the S&P 500.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114607638","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 : 2020-07-20DOI: 10.1109/indin45582.2020.9442111
{"title":"Human, Mechatronics and Interaction","authors":"","doi":"10.1109/indin45582.2020.9442111","DOIUrl":"https://doi.org/10.1109/indin45582.2020.9442111","url":null,"abstract":"","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128500344","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 : 2020-07-20DOI: 10.1109/INDIN45582.2020.9442090
HuanXiao Liu, Lin Huang, Hui Ye
In order to solve the problem of autonomous path planning for water-air amphibious unmanned aerial vehicle (UAV), a path planning method combining search strategy and improved A* algorithm has been proposed. In view of factors that affect the performance of amphibious vehicle, the cost function containing various heuristic information has been redefined. The classical A* algorithm has been improved and optimized by changing the corresponding cost weights to adjust the function of heuristic information in path planning. At the same time, the judgment of whether there are obstacles between adjacent nodes is added in the traversal process of the algorithm. The simulation result shows that with different cost weights, appropriate amphibious route can be generated through our improved algorithm. Under different constraints, the three-dimensional (3D) route can meet the needs of unmanned water-air amphibious vehicle.
{"title":"Autonomous path planning strategy for water-air amphibious vehicle based on improved A* algorithm","authors":"HuanXiao Liu, Lin Huang, Hui Ye","doi":"10.1109/INDIN45582.2020.9442090","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442090","url":null,"abstract":"In order to solve the problem of autonomous path planning for water-air amphibious unmanned aerial vehicle (UAV), a path planning method combining search strategy and improved A* algorithm has been proposed. In view of factors that affect the performance of amphibious vehicle, the cost function containing various heuristic information has been redefined. The classical A* algorithm has been improved and optimized by changing the corresponding cost weights to adjust the function of heuristic information in path planning. At the same time, the judgment of whether there are obstacles between adjacent nodes is added in the traversal process of the algorithm. The simulation result shows that with different cost weights, appropriate amphibious route can be generated through our improved algorithm. Under different constraints, the three-dimensional (3D) route can meet the needs of unmanned water-air amphibious vehicle.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128698384","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 : 2020-07-20DOI: 10.1109/INDIN45582.2020.9442091
Xi Wang, Weichao Zhuang, Guo-dong Yin
Vehicle active suspension systems provide possibility to bring better ride comfort, handling stability and driving safety with proper control than passive suspension. This paper utilizes deep reinforcement learning method to develop active suspension systems due to its good generalization. The controller is based on a quarter-car active suspension model, and suspension dynamic characteristics are analyzed under the condition of bump disturbance. Simulation results show that the performance of active suspension tends to be stable after proper training. Compared with the passive suspension and the Skyhook-based suspension, the deep reinforcement learning-based active suspension can reduce the vehicle body acceleration more effectively and further improve the ride comfort without sacrificing the suspension deflection and dynamic tire load. Deep reinforcement learning-based active suspension can still maintain good performance after switching bump heights or vehicle speed which verifies good generalization of the controller.
{"title":"Learning-Based Vibration Control of Vehicle Active Suspension","authors":"Xi Wang, Weichao Zhuang, Guo-dong Yin","doi":"10.1109/INDIN45582.2020.9442091","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442091","url":null,"abstract":"Vehicle active suspension systems provide possibility to bring better ride comfort, handling stability and driving safety with proper control than passive suspension. This paper utilizes deep reinforcement learning method to develop active suspension systems due to its good generalization. The controller is based on a quarter-car active suspension model, and suspension dynamic characteristics are analyzed under the condition of bump disturbance. Simulation results show that the performance of active suspension tends to be stable after proper training. Compared with the passive suspension and the Skyhook-based suspension, the deep reinforcement learning-based active suspension can reduce the vehicle body acceleration more effectively and further improve the ride comfort without sacrificing the suspension deflection and dynamic tire load. Deep reinforcement learning-based active suspension can still maintain good performance after switching bump heights or vehicle speed which verifies good generalization of the controller.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129531770","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 : 2020-07-20DOI: 10.1109/INDIN45582.2020.9442099
Yimin Yang, Min Wu
Money laundering is the process of making large amounts of fund obtained from criminal activities appear to originate from a legitimate source. Fraud occurs when a person or business intentionally deceives another with promises of services or financial benefits that do not exist or were misrepresented. Fraud and Money laundering detections require to analyze abnormal behavioral patterns. To develop a detection model, we present a machine learning-based model which incorporates risk scoring and statistical clustering approaches. Given a customer represented by its values in a set of attributes, we define its Customer Behavior Score based on its percentile rank in each attribute, which measures the behavior of the customer against the median or “normal” customers in the group. The Customer Behavior Score induces a distance, called Behavior Measuring Distance, between any two customers. The k-medoids clustering technique based on the Behavior Measuring Distance is then applied iteratively to classify customers. The key features of the model are that the abnormality of customers' behaviors are measured based on their percentile ranks in their respective classes and that such measurement is dynamically updated based on the reclassification after each iteration during the training. Finally, the model is tested using the country risk data collected from public and internal sources, and the model outcomes are compared against a benchmark model. The experimental results show convergence and effectiveness of the model.
{"title":"Supervised and Unsupervised Learning for Fraud and Money Laundering Detection using Behavior Measuring Distance","authors":"Yimin Yang, Min Wu","doi":"10.1109/INDIN45582.2020.9442099","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442099","url":null,"abstract":"Money laundering is the process of making large amounts of fund obtained from criminal activities appear to originate from a legitimate source. Fraud occurs when a person or business intentionally deceives another with promises of services or financial benefits that do not exist or were misrepresented. Fraud and Money laundering detections require to analyze abnormal behavioral patterns. To develop a detection model, we present a machine learning-based model which incorporates risk scoring and statistical clustering approaches. Given a customer represented by its values in a set of attributes, we define its Customer Behavior Score based on its percentile rank in each attribute, which measures the behavior of the customer against the median or “normal” customers in the group. The Customer Behavior Score induces a distance, called Behavior Measuring Distance, between any two customers. The k-medoids clustering technique based on the Behavior Measuring Distance is then applied iteratively to classify customers. The key features of the model are that the abnormality of customers' behaviors are measured based on their percentile ranks in their respective classes and that such measurement is dynamically updated based on the reclassification after each iteration during the training. Finally, the model is tested using the country risk data collected from public and internal sources, and the model outcomes are compared against a benchmark model. The experimental results show convergence and effectiveness of the model.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127037317","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 : 2020-07-20DOI: 10.1109/INDIN45582.2020.9442223
A. Wendt, Stefan Kollmann, A. Bratukhin, A. Estaji, T. Sauter, A. Jantsch
In smart manufacturing, the demand increases to be able to monitor and adjust process execution during production. It has led to a shift towards distributed, modular automation. A solution seems to be to use a cognitive architecture. It turns out that their generality often makes them unsuitable for specific industrial problems. In this paper, we propose a cognition-inspired architecture design for health monitoring tasks. The problem class is represented by a conveyor belt use case. We then discuss to what extent this architecture matches common implementations of cognitive theories by following a generalized cognitive process.
{"title":"Cognitive Architectures for Process Monitoring - an Analysis","authors":"A. Wendt, Stefan Kollmann, A. Bratukhin, A. Estaji, T. Sauter, A. Jantsch","doi":"10.1109/INDIN45582.2020.9442223","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442223","url":null,"abstract":"In smart manufacturing, the demand increases to be able to monitor and adjust process execution during production. It has led to a shift towards distributed, modular automation. A solution seems to be to use a cognitive architecture. It turns out that their generality often makes them unsuitable for specific industrial problems. In this paper, we propose a cognition-inspired architecture design for health monitoring tasks. The problem class is represented by a conveyor belt use case. We then discuss to what extent this architecture matches common implementations of cognitive theories by following a generalized cognitive process.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129998255","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：