Pub Date : 2020-07-20DOI: 10.1109/INDIN45582.2020.9442209
Luis Piardi, P. Leitão, A. Oliveira
Modern industry demands techniques that ensure the operability of its processes, and even though the exponential technological advance in the last two decades in the manufacturing field, failures, waste, and unexpected interruptions are still present in this sector's daily routine. Within the Industry 4.0 context, fault-tolerant (FT) production systems remain a complex issue and sometimes represent a vulnerable aspect. Fault-tolerance techniques dedicated to autonomous and distributed systems, in a cyber-physical system (CPS) perspective, need to be investigated to follow the evolutionary pace of the manufacturing scenarios. This paper overviews these concepts and analyses the current situation in developing FT for CPS systems through a systematic literature review. The paper also discusses the research challenges in this new kind of FT systems due to new distributed architectures and emerging technologies, matching the several fault- tolerance phases.
{"title":"Fault-Tolerance in Cyber-Physical Systems: Literature Review and Challenges","authors":"Luis Piardi, P. Leitão, A. Oliveira","doi":"10.1109/INDIN45582.2020.9442209","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442209","url":null,"abstract":"Modern industry demands techniques that ensure the operability of its processes, and even though the exponential technological advance in the last two decades in the manufacturing field, failures, waste, and unexpected interruptions are still present in this sector's daily routine. Within the Industry 4.0 context, fault-tolerant (FT) production systems remain a complex issue and sometimes represent a vulnerable aspect. Fault-tolerance techniques dedicated to autonomous and distributed systems, in a cyber-physical system (CPS) perspective, need to be investigated to follow the evolutionary pace of the manufacturing scenarios. This paper overviews these concepts and analyses the current situation in developing FT for CPS systems through a systematic literature review. The paper also discusses the research challenges in this new kind of FT systems due to new distributed architectures and emerging technologies, matching the several fault- tolerance phases.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"20 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":"129106159","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/indin45582.2020.9442072
{"title":"Safety and Security in Industrial Applications","authors":"","doi":"10.1109/indin45582.2020.9442072","DOIUrl":"https://doi.org/10.1109/indin45582.2020.9442072","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":"132385861","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/INDIN45582.2020.9442176
T. Shimobaba, Yota Yamamoto, I. Hoshi, T. Kakue, T. Ito
This study investigates the performance of a binary neural network, which is a lightweight neural network, for classification problems in holographic applications. We performed data classification in holographic memory using XNOR-Net as one of the binary neural networks. We compared the performance of the binary neural network with convolutional neural networks.
{"title":"Data page classification in holographic memory using binary neural network","authors":"T. Shimobaba, Yota Yamamoto, I. Hoshi, T. Kakue, T. Ito","doi":"10.1109/INDIN45582.2020.9442176","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442176","url":null,"abstract":"This study investigates the performance of a binary neural network, which is a lightweight neural network, for classification problems in holographic applications. We performed data classification in holographic memory using XNOR-Net as one of the binary neural networks. We compared the performance of the binary neural network with convolutional neural networks.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"9 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":"126627227","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/indin45582.2020.9442173
{"title":"Diagnosis, Prognosis and Resilient Control for Industrial Systems","authors":"","doi":"10.1109/indin45582.2020.9442173","DOIUrl":"https://doi.org/10.1109/indin45582.2020.9442173","url":null,"abstract":"","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"158 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":"116233486","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/INDIN45582.2020.9442171
Mengmeng Xu, Hai Zhu, Juanjuan Wang, Hengzhou Xu, Chenghang Li
Data collection is an essential operation in wireless sensor networks (WSNs). Topology control and duty-cycle are two popular schemes in WSNs to improve the utilization of various network resource. The problem of low-cost topology control in duty-cycle wireless sensor networks is investigated in this paper. Due to each sensor's awake/sleep schedule, the topological graphs in duty-cycle WSNs are changed over time. A space-time graph model is presented to describe the dynamics of a series of topological graphs. The new topology control problem in a spacetime graph is defined, and then two heuristic algorithms are proposed to find the low-cost topological structures, in which the connectivity from each sensor to the sink is maintained. Simulations validate the effectiveness of the proposed algorithms.
{"title":"Low-Cost Topology Control for Data Collecting in Duty-Cycle Wireless Sensor Networks","authors":"Mengmeng Xu, Hai Zhu, Juanjuan Wang, Hengzhou Xu, Chenghang Li","doi":"10.1109/INDIN45582.2020.9442171","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442171","url":null,"abstract":"Data collection is an essential operation in wireless sensor networks (WSNs). Topology control and duty-cycle are two popular schemes in WSNs to improve the utilization of various network resource. The problem of low-cost topology control in duty-cycle wireless sensor networks is investigated in this paper. Due to each sensor's awake/sleep schedule, the topological graphs in duty-cycle WSNs are changed over time. A space-time graph model is presented to describe the dynamics of a series of topological graphs. The new topology control problem in a spacetime graph is defined, and then two heuristic algorithms are proposed to find the low-cost topological structures, in which the connectivity from each sensor to the sink is maintained. Simulations validate the effectiveness of the proposed algorithms.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"358 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":"122742152","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/INDIN45582.2020.9442149
Fanbiao Bao, B. Huang, Xinfeng Zou, C. Lai
According to the requirements of the vehicle parameters and vehicle performance parameters in the early stage of vehicle design, this paper analyzes and matches the performance of pure electric vehicle motors, power batteries, and vehicle transmission ratio parameters, and uses AVL-Cruise software to analyze the vehicle motors and energy batteries Model the entire vehicle with the drive train, select the powertrain parameters initially, and use AVL-Cruise software for calculation and verification. Combined with the analysis and verification of partial performance of the electric vehicle on the road, compare the simulation data with the road of the actual vehicle. The results obtained from the test data basically agree with each other to verify the rationality of the matching of vehicle dynamics and economic parameters based on AVL-Cruise and the accuracy of the modeling analysis.
{"title":"Analysis and Matching of Electric Vehicle Dynamic Performance Based on CRUISE","authors":"Fanbiao Bao, B. Huang, Xinfeng Zou, C. Lai","doi":"10.1109/INDIN45582.2020.9442149","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442149","url":null,"abstract":"According to the requirements of the vehicle parameters and vehicle performance parameters in the early stage of vehicle design, this paper analyzes and matches the performance of pure electric vehicle motors, power batteries, and vehicle transmission ratio parameters, and uses AVL-Cruise software to analyze the vehicle motors and energy batteries Model the entire vehicle with the drive train, select the powertrain parameters initially, and use AVL-Cruise software for calculation and verification. Combined with the analysis and verification of partial performance of the electric vehicle on the road, compare the simulation data with the road of the actual vehicle. The results obtained from the test data basically agree with each other to verify the rationality of the matching of vehicle dynamics and economic parameters based on AVL-Cruise and the accuracy of the modeling analysis.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"36 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":"131378125","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/INDIN45582.2020.9442221
Mengtian Hu, Yu Tian, Tao Liu, Meimei Han
This paper presents the mechanism design and coordination control strategy of a lower limb rehabilitation robot in the bed, which may be helpful for improving the rehabilitation quality of patients with limb injuries when staying on the bad. It not only has a variety of rehabilitation training mode, but also has an adjustable structure and simple operation. It is more adaptable and friendly to patients in different circumstances. We conducted in-depth research on the configuration design, human kinematics analysis and man-machine coordination control of the horizontal lower limb rehabilitation robot. A prototype experimental platform developed to validate the effectiveness of the proposed control method. The result shows that the rehabilitation robot can meet the training needs of patients with different posture and injury degree in various stage of rehabilitation.
{"title":"Development of a Novel Lower Limb Rehabilitation robot in the Bed","authors":"Mengtian Hu, Yu Tian, Tao Liu, Meimei Han","doi":"10.1109/INDIN45582.2020.9442221","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442221","url":null,"abstract":"This paper presents the mechanism design and coordination control strategy of a lower limb rehabilitation robot in the bed, which may be helpful for improving the rehabilitation quality of patients with limb injuries when staying on the bad. It not only has a variety of rehabilitation training mode, but also has an adjustable structure and simple operation. It is more adaptable and friendly to patients in different circumstances. We conducted in-depth research on the configuration design, human kinematics analysis and man-machine coordination control of the horizontal lower limb rehabilitation robot. A prototype experimental platform developed to validate the effectiveness of the proposed control method. The result shows that the rehabilitation robot can meet the training needs of patients with different posture and injury degree in various stage of rehabilitation.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"8 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":"132529291","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/INDIN45582.2020.9442210
Lina Zhou, Xudong Chen, Wen Chen
We present deep learning method that can be used to reconstruct high-quality objects through turbulent media mixed with water and milk. The objects are placed behind turbulent media, and a series of speckle patterns are correspondingly recorded. By using many pairs of the recorded speckle patterns and input object images, a designed convolutional neural network (CNN) is fully trained, and then enables the recorded speckle patterns to be processed in real time. The proposed method is promising for imaging through turbulent media, and it is also believed that the proposed method can be applicable in many areas, e.g., imaging and information optics (such as optical encoding).
{"title":"Imaging Through Turbulent Media Using Deep Learning Method","authors":"Lina Zhou, Xudong Chen, Wen Chen","doi":"10.1109/INDIN45582.2020.9442210","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442210","url":null,"abstract":"We present deep learning method that can be used to reconstruct high-quality objects through turbulent media mixed with water and milk. The objects are placed behind turbulent media, and a series of speckle patterns are correspondingly recorded. By using many pairs of the recorded speckle patterns and input object images, a designed convolutional neural network (CNN) is fully trained, and then enables the recorded speckle patterns to be processed in real time. The proposed method is promising for imaging through turbulent media, and it is also believed that the proposed method can be applicable in many areas, e.g., imaging and information optics (such as optical encoding).","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"20 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":"114660489","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/INDIN45582.2020.9442085
Weiqi Sun, W. Dai
Industrial Cyber-Physical Systems require more flexibility and resilience to meet the requirement of flexible manufacturing. Model-driven engineering methods are often linked with the development and deployment of distributed automation systems. However, most legacy systems currently do not have a system-level model or even source code, which hinders the maintenance of future-proof systems. With a huge amount of operation data collected by acquisition processes in the existing industrial systems, the system behavior model can be recovered but in an effective way. This paper proposes an automatic software behavior model recovery method based on data mining from industrial controllers. This method can recover and optimize the system models based on the state machines and largely reduce the computing power required for generating a system behavior state machine model. Finally, the proposed method was verified by the FSM model inferring and code generation using a color sorter example.
{"title":"An Automatic Software Behavior Model Generation Method for Industrial Cyber-Physical System","authors":"Weiqi Sun, W. Dai","doi":"10.1109/INDIN45582.2020.9442085","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442085","url":null,"abstract":"Industrial Cyber-Physical Systems require more flexibility and resilience to meet the requirement of flexible manufacturing. Model-driven engineering methods are often linked with the development and deployment of distributed automation systems. However, most legacy systems currently do not have a system-level model or even source code, which hinders the maintenance of future-proof systems. With a huge amount of operation data collected by acquisition processes in the existing industrial systems, the system behavior model can be recovered but in an effective way. This paper proposes an automatic software behavior model recovery method based on data mining from industrial controllers. This method can recover and optimize the system models based on the state machines and largely reduce the computing power required for generating a system behavior state machine model. Finally, the proposed method was verified by the FSM model inferring and code generation using a color sorter example.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"117 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":"124942025","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/INDIN45582.2020.9442151
Chuanlei Zhang, Dashuo Wu, Jia Chen, Jucheng Yang
Efficient and accurate recognition of plant diseases based on leaf images is a hot research topic. The plant diseased leaf images are complex and diverse. It is generally difficult to extract reliable features. In this paper, a new plant disease recognition method is proposed, based on a Modified Residual Neural Network (MRNN) and transfer learning. Compared with the classical residual neural network ResNet-50, the residual block structure in MRNN is modified. The experiment results on the AI Challenger dataset show MRNN can achieve 91.4% recognition accuracy which is higher than other classic CNN models. Combined with the Kaggle Cassava dataset, the MRNN is trained with transfer learning, which improves the accuracy, robustness and generalization ability. The experiments results show that the proposed method not only has an advantage in accuracy, but also has a significant improvement in training speed, which validates the efficiency and effectiveness of the proposed approach.
{"title":"Efficient Plant Diseases Recognition based on Modified Residual Neural Network and Transfer Learning","authors":"Chuanlei Zhang, Dashuo Wu, Jia Chen, Jucheng Yang","doi":"10.1109/INDIN45582.2020.9442151","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442151","url":null,"abstract":"Efficient and accurate recognition of plant diseases based on leaf images is a hot research topic. The plant diseased leaf images are complex and diverse. It is generally difficult to extract reliable features. In this paper, a new plant disease recognition method is proposed, based on a Modified Residual Neural Network (MRNN) and transfer learning. Compared with the classical residual neural network ResNet-50, the residual block structure in MRNN is modified. The experiment results on the AI Challenger dataset show MRNN can achieve 91.4% recognition accuracy which is higher than other classic CNN models. Combined with the Kaggle Cassava dataset, the MRNN is trained with transfer learning, which improves the accuracy, robustness and generalization ability. The experiments results show that the proposed method not only has an advantage in accuracy, but also has a significant improvement in training speed, which validates the efficiency and effectiveness of the proposed approach.","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":"129374002","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：