Pub Date : 2020-07-20DOI: 10.1109/INDIN45582.2020.9442130
Chen Li, Soujanya Mantravadi, Charles Møller
Manufacturing Execution Systems (MES) play an important role in production management. However, many MES are either not following the industry standard or not providing high flexibility for small and medium-sized enterprises (SMEs) that are interested in user-defined software and low-cost automation solutions. This paper presents an ISA95 based MES architecture, an open-source evolvable MES that follows an industry standard. It is specifically designed for production management (e.g., production scheduling and execution) in SMEs. We expand this work into three directions. Firstly, we follow the industry standard - ISA95 guideline to identify the key functionalities, activities, and objects of the MES. Secondly, we leverage a model-driven paradigm to show how to design the architecture and data model. To keep it open-source, a business platform Odoo is chosen as it provides various well-designed free ERP modules as a foundation for MES design. Finally, various advanced features of Aalborg University (AAU) MES are illustrated by using an example product assembly.
{"title":"AAU Open Source MES Architecture for Smart Factories – Exploiting ISA 95","authors":"Chen Li, Soujanya Mantravadi, Charles Møller","doi":"10.1109/INDIN45582.2020.9442130","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442130","url":null,"abstract":"Manufacturing Execution Systems (MES) play an important role in production management. However, many MES are either not following the industry standard or not providing high flexibility for small and medium-sized enterprises (SMEs) that are interested in user-defined software and low-cost automation solutions. This paper presents an ISA95 based MES architecture, an open-source evolvable MES that follows an industry standard. It is specifically designed for production management (e.g., production scheduling and execution) in SMEs. We expand this work into three directions. Firstly, we follow the industry standard - ISA95 guideline to identify the key functionalities, activities, and objects of the MES. Secondly, we leverage a model-driven paradigm to show how to design the architecture and data model. To keep it open-source, a business platform Odoo is chosen as it provides various well-designed free ERP modules as a foundation for MES design. Finally, various advanced features of Aalborg University (AAU) MES are illustrated by using an example product assembly.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"12 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":"129482666","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/INDIN45582.2020.9442225
Huibin Li, Xiaorong Guan, Zhong Li, Yang Li, Yi-fan Shi, Zheng Wang
This paper is written according to the wearable extra robotic legs named Extra Assistant Robotic Legs (EARL). The EARL consists of one upper base and two robotic legs. The upper base is worn through a backpack around the upper body and the robotic legs are distributed around the lower body. In this paper, the research subject is the robotic legs of the EARL. In order to ensure that the human body can have better movements matching under the state of wearing the EARL, and realize efficient, flexible and stable coordinated movements, a planning algorithm of hybrid dual-mode gait includes walking and running for movements of the robotic legs is proposed. The gait planning is an important means and a foundation of the development and design of the robotic legs. The algorithm is set up according to the dynamic model of the EARL. The dynamic model is established by using the multi-level inverted pendulum with the joint deformation when the robotic legs hit the ground. The desired joint trajectories of the EARL are planned by the piecewise function and the gait cycle is determined by an experiment. Ultimately the prototype simulation is set up to verify the tracking performance of the EARL. The proposed validity is ensured by the simulation. The simulation results show the planned trajectories are continuous curves. The angular velocity of joints minus to 0 is to call for an end or to start another cycle. It can ensure the continuity and stability of the EARL. 6 sudden changes of each figure represent 6 selected gait phases. In a word, the robotic legs of the EARL can achieve efficient and stable moving by tracking the planned trajectories. The hybrid dual-mode gait planning algorithm is not only a supplement of the gait planning theory, but the improvement of the cooperative control strategy between the robotic legs and the wearer's legs as well. (Abstract)
{"title":"Hybrid Dual-mode Gait Planning of Wearable Extra Robotic Legs based on Multi-level Inverted Pendulum Model","authors":"Huibin Li, Xiaorong Guan, Zhong Li, Yang Li, Yi-fan Shi, Zheng Wang","doi":"10.1109/INDIN45582.2020.9442225","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442225","url":null,"abstract":"This paper is written according to the wearable extra robotic legs named Extra Assistant Robotic Legs (EARL). The EARL consists of one upper base and two robotic legs. The upper base is worn through a backpack around the upper body and the robotic legs are distributed around the lower body. In this paper, the research subject is the robotic legs of the EARL. In order to ensure that the human body can have better movements matching under the state of wearing the EARL, and realize efficient, flexible and stable coordinated movements, a planning algorithm of hybrid dual-mode gait includes walking and running for movements of the robotic legs is proposed. The gait planning is an important means and a foundation of the development and design of the robotic legs. The algorithm is set up according to the dynamic model of the EARL. The dynamic model is established by using the multi-level inverted pendulum with the joint deformation when the robotic legs hit the ground. The desired joint trajectories of the EARL are planned by the piecewise function and the gait cycle is determined by an experiment. Ultimately the prototype simulation is set up to verify the tracking performance of the EARL. The proposed validity is ensured by the simulation. The simulation results show the planned trajectories are continuous curves. The angular velocity of joints minus to 0 is to call for an end or to start another cycle. It can ensure the continuity and stability of the EARL. 6 sudden changes of each figure represent 6 selected gait phases. In a word, the robotic legs of the EARL can achieve efficient and stable moving by tracking the planned trajectories. The hybrid dual-mode gait planning algorithm is not only a supplement of the gait planning theory, but the improvement of the cooperative control strategy between the robotic legs and the wearer's legs as well. (Abstract)","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"13 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":"128051136","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/INDIN45582.2020.9442232
Bing Zhou, Yu-meng Li, Zhong-Guo Zhou
This paper explored the impact of corporate social responsibility (CSR) and product market competition (PMC) on the financial performance of listed companies in China, using the panel data of 1,100 Chinese A-share companies listed on the Shanghai and Shenzhen Stock Exchanges over the period from 2009 to 2014. The results show that for listed companies in china: (1) CSR can significantly and positively impact the short-term and long-term financial performance of listed companies in China. (2) PMC can only enhance corporate short-term financial performance, but has a significantly negative impact on corporate long-term financial performance. (3) The synergy between CSR and PMC can significantly and negatively affect both corporate short-term and long-term financial performance.
{"title":"Corporate Social Responsibility, Product Market Competition and Financial performance: Evidence from Listed Companies in China","authors":"Bing Zhou, Yu-meng Li, Zhong-Guo Zhou","doi":"10.1109/INDIN45582.2020.9442232","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442232","url":null,"abstract":"This paper explored the impact of corporate social responsibility (CSR) and product market competition (PMC) on the financial performance of listed companies in China, using the panel data of 1,100 Chinese A-share companies listed on the Shanghai and Shenzhen Stock Exchanges over the period from 2009 to 2014. The results show that for listed companies in china: (1) CSR can significantly and positively impact the short-term and long-term financial performance of listed companies in China. (2) PMC can only enhance corporate short-term financial performance, but has a significantly negative impact on corporate long-term financial performance. (3) The synergy between CSR and PMC can significantly and negatively affect both corporate short-term and long-term financial performance.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"115 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":"124523959","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/INDIN45582.2020.9442106
Tao Xu, H. Hou, Qingyong Zhang, Jianjian Wang, Peng Liu, A. Tang
The rapid development of renewable energy and adjustable load has brought challenges to the safety and economic operation of power system. In this paper, we propose a generation and load integrated optimal scheduling strategy. The power generation side considers the wind-photovoltaic hybrid power system with battery energy storage system. The user side considers electric vehicles and the adjustable load such as transferable load and interruptible load to participate in scheduling. A scheduling strategy model is established to optimize both the benefits of power generation side and the user side. The multi-objective particle swarm optimization algorithm is used to solve the model. Simulation results based on historical data of a particular region (105.0° E, 35.40° N) show the feasibility of the proposed optimal scheduling strategy.
{"title":"Generation and Load Integrated Optimal Scheduling Incorporating Distributed Energy Storage and Adjustable Load","authors":"Tao Xu, H. Hou, Qingyong Zhang, Jianjian Wang, Peng Liu, A. Tang","doi":"10.1109/INDIN45582.2020.9442106","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442106","url":null,"abstract":"The rapid development of renewable energy and adjustable load has brought challenges to the safety and economic operation of power system. In this paper, we propose a generation and load integrated optimal scheduling strategy. The power generation side considers the wind-photovoltaic hybrid power system with battery energy storage system. The user side considers electric vehicles and the adjustable load such as transferable load and interruptible load to participate in scheduling. A scheduling strategy model is established to optimize both the benefits of power generation side and the user side. The multi-objective particle swarm optimization algorithm is used to solve the model. Simulation results based on historical data of a particular region (105.0° E, 35.40° N) show the feasibility of the proposed optimal scheduling strategy.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"79 3 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":"126080497","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/INDIN45582.2020.9442101
Heping Pan
This paper presents a specific form of the Intelligent Portfolio Theory for trading in commodity futures markets. The theory is based on the recognition of the reality that any single trading strategy is bounded in rationality, so it is unable to remain profitable consistently over time; thus an intelligent portfolio consists of a multi-market portfolio of which capital allocation on each market is managed by a multi-strategy portfolio. In Chinese commodity futures markets, 3 futures are selected; and 2 trading strategies are developed and applied on each of the selected futures. This specific intelligent portfolio trading system is tested on historical intraday data, and the result exhibits superior performance with the least maximum drawdown and the biggest reward-to-risk ratio.
{"title":"Intelligent Portfolio Theory and Trading in Commodity Futures","authors":"Heping Pan","doi":"10.1109/INDIN45582.2020.9442101","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442101","url":null,"abstract":"This paper presents a specific form of the Intelligent Portfolio Theory for trading in commodity futures markets. The theory is based on the recognition of the reality that any single trading strategy is bounded in rationality, so it is unable to remain profitable consistently over time; thus an intelligent portfolio consists of a multi-market portfolio of which capital allocation on each market is managed by a multi-strategy portfolio. In Chinese commodity futures markets, 3 futures are selected; and 2 trading strategies are developed and applied on each of the selected futures. This specific intelligent portfolio trading system is tested on historical intraday data, and the result exhibits superior performance with the least maximum drawdown and the biggest reward-to-risk ratio.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"23 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":"124053878","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/INDIN45582.2020.9442183
Kostas Blekos, Stavros Nousias, A. Lalos
Delineation approaches provide significant benefits to various domains, including agriculture, environmental and natural disasters monitoring. Most of the work in the literature utilize traditional segmentation methods that require a large amount of computational and storage resources. Deep learning has transformed computer vision and dramatically improved machine translation, though it requires massive dataset for training and significant resources for inference. More importantly, energy-efficient embedded vision hardware delivering real-time and robust performance is crucial in the aforementioned application. In this work, we propose a U-Net based tree delineation method, which is effectively trained using multi-spectral imagery but can then delineate single-spectrum images. The deep architecture that also performs localization, i.e., a class label corresponds to each pixel, has been successfully used to allow training with a small set of segmented images. The ground truth data were generated using traditional image denoising and segmentation approaches. To be able to execute the proposed DNN efficiently in embedded platforms designed for deep learning approaches, we employ traditional model compression and acceleration methods. Extensive evaluation studies using data collected from UAV s equipped with multi-spectral cameras demonstrate the effectiveness of the proposed methods in terms of delineation accuracy and execution efficiency.
{"title":"Efficient automated U - Net based tree crown delineation using UAV multi-spectral imagery on embedded devices","authors":"Kostas Blekos, Stavros Nousias, A. Lalos","doi":"10.1109/INDIN45582.2020.9442183","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442183","url":null,"abstract":"Delineation approaches provide significant benefits to various domains, including agriculture, environmental and natural disasters monitoring. Most of the work in the literature utilize traditional segmentation methods that require a large amount of computational and storage resources. Deep learning has transformed computer vision and dramatically improved machine translation, though it requires massive dataset for training and significant resources for inference. More importantly, energy-efficient embedded vision hardware delivering real-time and robust performance is crucial in the aforementioned application. In this work, we propose a U-Net based tree delineation method, which is effectively trained using multi-spectral imagery but can then delineate single-spectrum images. The deep architecture that also performs localization, i.e., a class label corresponds to each pixel, has been successfully used to allow training with a small set of segmented images. The ground truth data were generated using traditional image denoising and segmentation approaches. To be able to execute the proposed DNN efficiently in embedded platforms designed for deep learning approaches, we employ traditional model compression and acceleration methods. Extensive evaluation studies using data collected from UAV s equipped with multi-spectral cameras demonstrate the effectiveness of the proposed methods in terms of delineation accuracy and execution efficiency.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"19 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":"130340997","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/INDIN45582.2020.9442192
Ryan Lankin, Kyungki Kim, Pei-Chi Huang
Utilizing autonomous robots to perform repetitive and labor-intensive tasks in the construction industry is one of the most promising directions to explore in order to enhance productivity, safety/health, and quality of construction projects. Such robots must have construction-related knowledge and skills in order to generate task plans capable of dealing with the unique and highly dynamic work environment of typical construction sites. However, autonomous and flexible behavior is currently impossible due to the lack of a robotics-compatible construction knowledge base. To overcome this bottleneck, this study proposes the establishment and utilization of such a construction knowledge base for use in generating autonomous behavior in robots. Specifically, this study provides an implementation of a small, mobile, autonomous robotics platform capable of performing fine-grained construction tasks in dynamic environments. Such tasks include painting, drilling screws, and transporting material and equipment. The platform is tested with a simulated robot based on the KUKA youBot tasked with painting walls in a room containing obstacles. In the simulation results, the proposed approach shows promise in being able to achieve autonomous operation of construction robots. Further development of this study will include implementing a more diverse set of skills, expanding the construction knowledge base, and tailoring localization, navigation planning, and task planning algorithms for the characteristics of the construction sites and the hardware tools used.
{"title":"ROS-Based Robot Simulation for Repetitive Labor-Intensive Construction Tasks","authors":"Ryan Lankin, Kyungki Kim, Pei-Chi Huang","doi":"10.1109/INDIN45582.2020.9442192","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442192","url":null,"abstract":"Utilizing autonomous robots to perform repetitive and labor-intensive tasks in the construction industry is one of the most promising directions to explore in order to enhance productivity, safety/health, and quality of construction projects. Such robots must have construction-related knowledge and skills in order to generate task plans capable of dealing with the unique and highly dynamic work environment of typical construction sites. However, autonomous and flexible behavior is currently impossible due to the lack of a robotics-compatible construction knowledge base. To overcome this bottleneck, this study proposes the establishment and utilization of such a construction knowledge base for use in generating autonomous behavior in robots. Specifically, this study provides an implementation of a small, mobile, autonomous robotics platform capable of performing fine-grained construction tasks in dynamic environments. Such tasks include painting, drilling screws, and transporting material and equipment. The platform is tested with a simulated robot based on the KUKA youBot tasked with painting walls in a room containing obstacles. In the simulation results, the proposed approach shows promise in being able to achieve autonomous operation of construction robots. Further development of this study will include implementing a more diverse set of skills, expanding the construction knowledge base, and tailoring localization, navigation planning, and task planning algorithms for the characteristics of the construction sites and the hardware tools used.","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":"130348077","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/INDIN45582.2020.9442123
Michael Gundall, Daniel Reti, H. Schotten
Industry 4.0 describes an adaptive and changeable production, where its factory cells have to be reconfigured at very short intervals, e.g. after each workpiece. Furthermore, this scenario cannot be realized with traditional devices, such as programmable logic controllers. Here the use of well-proven technologies of the information technology are conquering the production hall (IT-OT convergence). Therefore, both virtualization and novel communication technologies are being introduced in the field of industrial automation. In addition, these technologies are seen as the key for facilitating various emerging use cases. However, it is not yet clear whether each of the dedicated hardware and software components, which have been developed for specific control tasks and have performed well over decades, can be upgraded without major adjustments. In this paper, we examine the opportunities and challenges of hardware and operating system-level virtualization based on the stringent requirements imposed by industrial applications. For that purpose, benchmarks for different virtualization technologies are set by determining their computational and networking overhead, configuration effort, accessibility, scalability, and security.
{"title":"Application of Virtualization Technologies in Novel Industrial Automation: Catalyst or Show-Stopper?","authors":"Michael Gundall, Daniel Reti, H. Schotten","doi":"10.1109/INDIN45582.2020.9442123","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442123","url":null,"abstract":"Industry 4.0 describes an adaptive and changeable production, where its factory cells have to be reconfigured at very short intervals, e.g. after each workpiece. Furthermore, this scenario cannot be realized with traditional devices, such as programmable logic controllers. Here the use of well-proven technologies of the information technology are conquering the production hall (IT-OT convergence). Therefore, both virtualization and novel communication technologies are being introduced in the field of industrial automation. In addition, these technologies are seen as the key for facilitating various emerging use cases. However, it is not yet clear whether each of the dedicated hardware and software components, which have been developed for specific control tasks and have performed well over decades, can be upgraded without major adjustments. In this paper, we examine the opportunities and challenges of hardware and operating system-level virtualization based on the stringent requirements imposed by industrial applications. For that purpose, benchmarks for different virtualization technologies are set by determining their computational and networking overhead, configuration effort, accessibility, scalability, and security.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"7 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":"116674814","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/INDIN45582.2020.9442160
Haixin Lv, Jinglong Chen, Tongyang Pan
Data-driven intelligent method has shown superior performance in remaining useful life (RUL) prediction. However, the model training is difficult due to the limited degradation data. To address the challenges of small data set, a Sequence Adaptation Adversarial Network (SAAN) is proposed in this paper. SAAN could expand training data with auxiliary set by sequence domain adaption. We verify the proposed method with C-MAPSS dataset. By comparing with the literature methods, results show SAAN could significantly improve the accuracy of RUL prediction under small data set, and also keeps a competitive performance on sequence life prediction.
{"title":"Sequence Adaptation Adversarial Network for Remaining Useful Life Prediction Using Small Data Set","authors":"Haixin Lv, Jinglong Chen, Tongyang Pan","doi":"10.1109/INDIN45582.2020.9442160","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442160","url":null,"abstract":"Data-driven intelligent method has shown superior performance in remaining useful life (RUL) prediction. However, the model training is difficult due to the limited degradation data. To address the challenges of small data set, a Sequence Adaptation Adversarial Network (SAAN) is proposed in this paper. SAAN could expand training data with auxiliary set by sequence domain adaption. We verify the proposed method with C-MAPSS dataset. By comparing with the literature methods, results show SAAN could significantly improve the accuracy of RUL prediction under small data set, and also keeps a competitive performance on sequence life prediction.","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":"131024019","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：