Pub Date : 2020-07-20DOI: 10.1109/INDIN45582.2020.9442157
Shengkai Wang, J. Zhang
With industrial production processes becoming more and more sophisticated, traditional fault diagnosis systems may be insufficient to meet current industrial diagnostic performance requirements. In order to improve fault diagnosis performance, this paper proposes an enhanced neural network based fault diagnosis system by integrating Andrews plot and Autoencoder. Features are first extracted from on-line measurements by Andrews plot and the high-dimensional features are compressed by autoencoder to an appropriate dimension, which are then fed to a neural network for fault classification. Application to a simulated CSTR process demonstrates that the proposed method can give more reliable and earlier diagnosis than the traditional neural network based fault diagnosis method.
{"title":"Improved Process Fault Diagnosis by Using Neural Networks with Andrews Plot and Autoencoder","authors":"Shengkai Wang, J. Zhang","doi":"10.1109/INDIN45582.2020.9442157","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442157","url":null,"abstract":"With industrial production processes becoming more and more sophisticated, traditional fault diagnosis systems may be insufficient to meet current industrial diagnostic performance requirements. In order to improve fault diagnosis performance, this paper proposes an enhanced neural network based fault diagnosis system by integrating Andrews plot and Autoencoder. Features are first extracted from on-line measurements by Andrews plot and the high-dimensional features are compressed by autoencoder to an appropriate dimension, which are then fed to a neural network for fault classification. Application to a simulated CSTR process demonstrates that the proposed method can give more reliable and earlier diagnosis than the traditional neural network based fault diagnosis method.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"75 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":"114850223","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/INDIN45582.2020.9442116
Jianwu Lin, Yishen Xu, Dayu Qin
Algorithmic trading has become the major trading mechanism and one of the core technologies of electronic transactions globally. In USA, above 90% of electronic trading volumes has been done by algorithmic trading systems. However, algorithmic trading is still new in China capital market, only less than 10% of the volume has been done by algorithmic trading systems. With the rapid development of Chinese capital market and QFII capacity expansion, it will be the major trading mechanism in China. While being introduced into Chinese markets, it has to adapt to some special local trading rules, such as: Price limits (limit up and limit down). Because of the particular preferences by the Chinese investors, the market has a unique morphology forms in price limits. How to improve the model of price limits in China's algorithmic trading is the main focus of this research, especially under recent increasing volatility of global stock market in early 2020. This paper proposes a novel volume ratio prediction model, which can obtain a more accurate value of the price limit trading volume distribution. And an improved algorithmic trading logic based this model is proposed and proves its effectiveness.
{"title":"Volume ratio prediction model during Price Limits Periods in China stock markets","authors":"Jianwu Lin, Yishen Xu, Dayu Qin","doi":"10.1109/INDIN45582.2020.9442116","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442116","url":null,"abstract":"Algorithmic trading has become the major trading mechanism and one of the core technologies of electronic transactions globally. In USA, above 90% of electronic trading volumes has been done by algorithmic trading systems. However, algorithmic trading is still new in China capital market, only less than 10% of the volume has been done by algorithmic trading systems. With the rapid development of Chinese capital market and QFII capacity expansion, it will be the major trading mechanism in China. While being introduced into Chinese markets, it has to adapt to some special local trading rules, such as: Price limits (limit up and limit down). Because of the particular preferences by the Chinese investors, the market has a unique morphology forms in price limits. How to improve the model of price limits in China's algorithmic trading is the main focus of this research, especially under recent increasing volatility of global stock market in early 2020. This paper proposes a novel volume ratio prediction model, which can obtain a more accurate value of the price limit trading volume distribution. And an improved algorithmic trading logic based this model is proposed and proves its effectiveness.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"21 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":"114890889","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/indin45582.2020.9442074
{"title":"Sustainable and Intelligent Precision Agriculture","authors":"","doi":"10.1109/indin45582.2020.9442074","DOIUrl":"https://doi.org/10.1109/indin45582.2020.9442074","url":null,"abstract":"","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"40 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":"124194503","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/indin45582.2020.9442122
{"title":"Real-time and Networked Embedded Computing and IoT","authors":"","doi":"10.1109/indin45582.2020.9442122","DOIUrl":"https://doi.org/10.1109/indin45582.2020.9442122","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":"116928613","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/INDIN45582.2020.9442240
Hard disk (HDD) failure is the most important reliability issue in the data center. Therefore, the prediction of hard disk failure has become the focus of attention of major data centers. However, most current research work does not notice the fact that the data on the hard disk is mostly unlabeled data. Since the degradation period in HDD is very short, the mixture of health data and erroneous data can cause serious data imbalance. This makes fault prediction a difficult task. In response to the above problems, a multi-instance long-term sequence classification method based on long-short-term memory (LSTM) network is proposed. By dividing the longterm sequence data packet into multiple instances, the relationship between the instance and the sample label is studied to predict HDD failure. Through the analysis of the hard disk data of a communication company and the Backblaze data center, this method can obtain better results than other methods.
{"title":"A multi-instance LSTM network for failure detection of hard disk drives","authors":"","doi":"10.1109/INDIN45582.2020.9442240","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442240","url":null,"abstract":"Hard disk (HDD) failure is the most important reliability issue in the data center. Therefore, the prediction of hard disk failure has become the focus of attention of major data centers. However, most current research work does not notice the fact that the data on the hard disk is mostly unlabeled data. Since the degradation period in HDD is very short, the mixture of health data and erroneous data can cause serious data imbalance. This makes fault prediction a difficult task. In response to the above problems, a multi-instance long-term sequence classification method based on long-short-term memory (LSTM) network is proposed. By dividing the longterm sequence data packet into multiple instances, the relationship between the instance and the sample label is studied to predict HDD failure. Through the analysis of the hard disk data of a communication company and the Backblaze data center, this method can obtain better results than other methods.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"49 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":"116944831","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/indin45582.2020.9442154
{"title":"Artificial Intelligence Based Distributed Fault Diagnosis and Prognosis in Industrial Applications","authors":"","doi":"10.1109/indin45582.2020.9442154","DOIUrl":"https://doi.org/10.1109/indin45582.2020.9442154","url":null,"abstract":"","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"253 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":"115006923","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/INDIN45582.2020.9442129
Binbin Chen, Wenjun Xu, Jiayi Liu, Zhenrui Ji, Zude Zhou
Remanufacturing has enormous economic and environmental benefits in terms of resource conservation and environmental protection. Disassembly, as an essential step in remanufacturing, is always manually executed, it has the disadvantages of high labor intensive, time consuming and low efficiency while robotic disassembly can cover the shortages of manual disassembly. During the robotic disassembly process, considering the structure and movement characteristics of the industrial robot, the industrial robot need to perform collision avoidance movements considering the obstacle caused by the End-of-Life (EoL) product. The moving time considering the robotic collision avoidance trajectory is a non-negligible part of total disassembly time. In this paper, robotic disassembly sequence planning (RDSP) considering robotic collision avoidance trajectory is proposed. This method is used to obtain the collision avoidance trajectory and the moving time between different disassembly points by the robotic collision avoidance model established in this paper. Afterwards, an optimized discrete bee algorithm (ODBA) is used to generate the optimal disassembly sequence to minimize the total disassembly time. Finally, case studies based on a gear pump verify the effectiveness of proposed methods.
{"title":"Robotic Disassembly Sequence Planning Considering Robotic Collision Avoidance Trajectory in Remanufacturing","authors":"Binbin Chen, Wenjun Xu, Jiayi Liu, Zhenrui Ji, Zude Zhou","doi":"10.1109/INDIN45582.2020.9442129","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442129","url":null,"abstract":"Remanufacturing has enormous economic and environmental benefits in terms of resource conservation and environmental protection. Disassembly, as an essential step in remanufacturing, is always manually executed, it has the disadvantages of high labor intensive, time consuming and low efficiency while robotic disassembly can cover the shortages of manual disassembly. During the robotic disassembly process, considering the structure and movement characteristics of the industrial robot, the industrial robot need to perform collision avoidance movements considering the obstacle caused by the End-of-Life (EoL) product. The moving time considering the robotic collision avoidance trajectory is a non-negligible part of total disassembly time. In this paper, robotic disassembly sequence planning (RDSP) considering robotic collision avoidance trajectory is proposed. This method is used to obtain the collision avoidance trajectory and the moving time between different disassembly points by the robotic collision avoidance model established in this paper. Afterwards, an optimized discrete bee algorithm (ODBA) is used to generate the optimal disassembly sequence to minimize the total disassembly time. Finally, case studies based on a gear pump verify the effectiveness of proposed methods.","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":"128982165","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/INDIN45582.2020.9442172
Qingnan Li, Yun Yang, Po Yang
Human activity recognition (HAR) has been widely used in some areas such as smart home, health care and so on. However, there are still some low recognition accuracy cases in actual scenarios. In order to improve the accuracy of recognition, we propose a multi-feature weighted ensemble classification method on triaxial accelerometer sensor data. We perform weighted integration on five base classifiers to obtain the final prediction classification label. Among these five base classifiers, three are K-nearest neighbor (KNN) classifiers with different features respectively using three traditional feature extraction methods from original data. Another two are currently popular deep learning models—Attention Mechanisms on Long Short-Term Memory Network (Attention-LSTM) and Convolutional Neural Network (CNN), which can automatically extract features and classify. We demonstrated the feasibility of this ensemble method on a dataset containing eight human daily activities. Comparing experimental results, our method achieved the best recognition effect, with an accuracy of 95.58%.
{"title":"Human activity recognition based on triaxial accelerometer using multi-feature weighted ensemble","authors":"Qingnan Li, Yun Yang, Po Yang","doi":"10.1109/INDIN45582.2020.9442172","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442172","url":null,"abstract":"Human activity recognition (HAR) has been widely used in some areas such as smart home, health care and so on. However, there are still some low recognition accuracy cases in actual scenarios. In order to improve the accuracy of recognition, we propose a multi-feature weighted ensemble classification method on triaxial accelerometer sensor data. We perform weighted integration on five base classifiers to obtain the final prediction classification label. Among these five base classifiers, three are K-nearest neighbor (KNN) classifiers with different features respectively using three traditional feature extraction methods from original data. Another two are currently popular deep learning models—Attention Mechanisms on Long Short-Term Memory Network (Attention-LSTM) and Convolutional Neural Network (CNN), which can automatically extract features and classify. We demonstrated the feasibility of this ensemble method on a dataset containing eight human daily activities. Comparing experimental results, our method achieved the best recognition effect, with an accuracy of 95.58%.","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":"125288775","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}
A photovoltaic (PV) generator exhibits nonlinear current-voltage characteristics and its maximum power point varies with incident atmospheric conditions. Therefore, maximum power point tracking (MPPT) control is required to maximize the output power of the PV generator. In this paper, deep Q-network based reinforcement learning strategy is proposed to optimize MPPT process for the photovoltaic system. The proposed system uses a novel control method which introduces agent to interface with the environment and finally gets the strategy of maximum reward accordingly. Simulations and experiments show the feasibility and effectiveness of the proposed system. Compared with the traditional perturb and observe (P&O) and incremental conductance (InC) methods, this method prominently saves tracking steps.
{"title":"Maximum Power Point Tracking of Photovoltaic Systems Using Deep Q-networks","authors":"Kangshi Wang, Dou Hong, Jieming Ma, K. Man, Kaizhu Huang, Xiaowei Huang","doi":"10.1109/INDIN45582.2020.9442100","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442100","url":null,"abstract":"A photovoltaic (PV) generator exhibits nonlinear current-voltage characteristics and its maximum power point varies with incident atmospheric conditions. Therefore, maximum power point tracking (MPPT) control is required to maximize the output power of the PV generator. In this paper, deep Q-network based reinforcement learning strategy is proposed to optimize MPPT process for the photovoltaic system. The proposed system uses a novel control method which introduces agent to interface with the environment and finally gets the strategy of maximum reward accordingly. Simulations and experiments show the feasibility and effectiveness of the proposed system. Compared with the traditional perturb and observe (P&O) and incremental conductance (InC) methods, this method prominently saves tracking steps.","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":"127938223","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/INDIN45582.2020.9442147
Xiliu Man, Jianwu Lin, Yujiu Yang
Financial news plays an important role in investors' decisions and then influences stock markets. Previous studies mainly focus on establishing sentiment index from financial text and then making stock return prediction and trading strategy based on the index. This procedure demands costly manual label and may not directly correspond to actual stock market reaction. This paper solves this problem by using labels of stocks' residual return as sentiment labels for BERT model training. Distinct from ordinary task, buying or selling action will be taken after judgement of the stock news' sentiment. Hence, weighted cross-entropy loss and cost-sensitive accuracy are used to reveal influence and cost of judgement. Different settings of weighted cross-entropy loss are applied to learn self-adaptively and a selection method is designed to seek capable base classifiers for ensemble learning. This paper then develops a stock trading strategy based on the ensemble BERT model. Experiments and ablation study show the robust effectiveness of our strategy.
{"title":"Stock-UniBERT: A News-based Cost-sensitive Ensemble BERT Model for Stock Trading","authors":"Xiliu Man, Jianwu Lin, Yujiu Yang","doi":"10.1109/INDIN45582.2020.9442147","DOIUrl":"https://doi.org/10.1109/INDIN45582.2020.9442147","url":null,"abstract":"Financial news plays an important role in investors' decisions and then influences stock markets. Previous studies mainly focus on establishing sentiment index from financial text and then making stock return prediction and trading strategy based on the index. This procedure demands costly manual label and may not directly correspond to actual stock market reaction. This paper solves this problem by using labels of stocks' residual return as sentiment labels for BERT model training. Distinct from ordinary task, buying or selling action will be taken after judgement of the stock news' sentiment. Hence, weighted cross-entropy loss and cost-sensitive accuracy are used to reveal influence and cost of judgement. Different settings of weighted cross-entropy loss are applied to learn self-adaptively and a selection method is designed to seek capable base classifiers for ensemble learning. This paper then develops a stock trading strategy based on the ensemble BERT model. Experiments and ablation study show the robust effectiveness of our strategy.","PeriodicalId":185948,"journal":{"name":"2020 IEEE 18th International Conference on Industrial Informatics (INDIN)","volume":"21 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":"129954177","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：