Pub Date : 2018-09-01DOI: 10.23919/iconac.2018.8749061
{"title":"[Copyright notice]","authors":"","doi":"10.23919/iconac.2018.8749061","DOIUrl":"https://doi.org/10.23919/iconac.2018.8749061","url":null,"abstract":"","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"520 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123076104","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 : 2018-09-01DOI: 10.23919/ICONAC.2018.8749103
Yueqi Wu, Xiandong Ma
In this paper, a multivariate statistical technique combined with a machine learning algorithm is proposed to provide a fault classification and feature extraction approach for the wind turbines. As the probability density distributions (PDDs) of the monitoring variables can illustrate the inner correlations among variables, the dominant factors causing the failure are figured out, with the comparison of PDD of the variables under the healthy and unhealthy scenarios. Then the selected variables are used for fault feature extraction by using kernel support vector machine (KSVM). The presented algorithms are implemented and assessed based on the supervisory control and data acquisition (SCADA) data acquired from an operational wind farm. The results show the features relating specifically to the faults are extracted to be able to identify and analyse different faults for the wind turbines.
{"title":"Kullback-Leibler divergence based wind turbine fault feature extraction","authors":"Yueqi Wu, Xiandong Ma","doi":"10.23919/ICONAC.2018.8749103","DOIUrl":"https://doi.org/10.23919/ICONAC.2018.8749103","url":null,"abstract":"In this paper, a multivariate statistical technique combined with a machine learning algorithm is proposed to provide a fault classification and feature extraction approach for the wind turbines. As the probability density distributions (PDDs) of the monitoring variables can illustrate the inner correlations among variables, the dominant factors causing the failure are figured out, with the comparison of PDD of the variables under the healthy and unhealthy scenarios. Then the selected variables are used for fault feature extraction by using kernel support vector machine (KSVM). The presented algorithms are implemented and assessed based on the supervisory control and data acquisition (SCADA) data acquired from an operational wind farm. The results show the features relating specifically to the faults are extracted to be able to identify and analyse different faults for the wind turbines.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115765701","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749078
Peng Zhang, Guohua Zhang, Wei Dong, Xinya Sun, Xingquan Ji
Fault diagnosis is critical to ensure the safety and reliable operation of high-speed railway. The traditional fault diagnosis methods for high-speed railway turnout rely on manual features extraction using turnout raw data, but the process is an exhausted work and greatly impacts the final result. Convolutional neural network (CNN), as a typical deep learning model, can automatically learn the representative features from the raw data. This paper investigates an intelligent fault diagnosis method for high-speed railway turnout based on CNN. The turnout current signals in time domain are converted to the 2-D grayscale images, and then the grayscale images are fed into the CNN for turnout fault classification. The proposed method is an automatic fault diagnosis system which eliminates the complex process of handcrafted features. The experimental results show a significant improvement over the state-of-the-art on the real turnout dataset for current curve and prove the effectiveness of the proposed method without manual feature extraction.
{"title":"Fault Diagnosis of High-Speed Railway Turnout Based on Convolutional Neural Network","authors":"Peng Zhang, Guohua Zhang, Wei Dong, Xinya Sun, Xingquan Ji","doi":"10.23919/IConAC.2018.8749078","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749078","url":null,"abstract":"Fault diagnosis is critical to ensure the safety and reliable operation of high-speed railway. The traditional fault diagnosis methods for high-speed railway turnout rely on manual features extraction using turnout raw data, but the process is an exhausted work and greatly impacts the final result. Convolutional neural network (CNN), as a typical deep learning model, can automatically learn the representative features from the raw data. This paper investigates an intelligent fault diagnosis method for high-speed railway turnout based on CNN. The turnout current signals in time domain are converted to the 2-D grayscale images, and then the grayscale images are fed into the CNN for turnout fault classification. The proposed method is an automatic fault diagnosis system which eliminates the complex process of handcrafted features. The experimental results show a significant improvement over the state-of-the-art on the real turnout dataset for current curve and prove the effectiveness of the proposed method without manual feature extraction.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116678130","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749040
Zhijun Li, Yanan Wang, B. Cui
Active power filter (APF) can effectively suppress harmonic current, and harmonic detection is an important part which can directly influence the effect of APF. Based on the traditional adaptive noise cancellation theory (ANCT) harmonic detection method, this paper proposes an improved variable step size adaptive harmonic detection algorithm. This algorithm uses sliding integrator to find the tracking error which can truly reflect the tracking situation, and brings it into the updated formula which is based on the L2 norm to adjust step. The L2 norm refers to the 1/2 power of the sum of squares of the vector elements. In this way, with the improvement of convergence speed and steady-state accuracy, it will have better practicability. Simulation results show that this algorithm can detect harmonic current quickly and accurately. And applying this algorithm to APF can make the effect of harmonic compensation better and enhance the power quality.
{"title":"An Improved Adaptive Harmonic Detection Algorithm","authors":"Zhijun Li, Yanan Wang, B. Cui","doi":"10.23919/IConAC.2018.8749040","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749040","url":null,"abstract":"Active power filter (APF) can effectively suppress harmonic current, and harmonic detection is an important part which can directly influence the effect of APF. Based on the traditional adaptive noise cancellation theory (ANCT) harmonic detection method, this paper proposes an improved variable step size adaptive harmonic detection algorithm. This algorithm uses sliding integrator to find the tracking error which can truly reflect the tracking situation, and brings it into the updated formula which is based on the L2 norm to adjust step. The L2 norm refers to the 1/2 power of the sum of squares of the vector elements. In this way, with the improvement of convergence speed and steady-state accuracy, it will have better practicability. Simulation results show that this algorithm can detect harmonic current quickly and accurately. And applying this algorithm to APF can make the effect of harmonic compensation better and enhance the power quality.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121336700","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749091
Shaista Bibi, M. A. Shah, B. Abbasi, Shahid Hussain
Traffic congestion is one of the most significant problems around the world. Literature shows various analyses of real time traffic incidents detection and crowd sensing. However, few researchers quantified the traffic congestion impacts on public health. To the best of our knowledge, there is no study, which determines the correlation between traffic congestion and public health issues via social media. In this paper, we propose a methodology to compute the correlation between traffic congestion and public health issues through social media analysis. To purse this task, we have used topic modeling and sentimental analysis. We mined a collection of 97 million tweets extracted from Twitter. Subsequently, different filters are applied to get the most traffic-congested locations around the world and the top health issues in the corresponding areas. Additionally, we have performed sentimental analysis to get the public perception about the initiatives taken to improve the health issues in those regions. We have found 36 most traffic congested cities around the world, such as Mexico, Bangkok, Jakarta and Chongqing etc. Apart from that, heart diseases, respiratory and psychological problems are identified as the common problems in traffic congested cities. Almost 71% public comments shows the negative sentiments. Which reflects their level of frustration about the steps taken to reduce the traffic by the higher authorities.
{"title":"A methodology to characterize and compute correlation between traffic congestion and health issues via social media","authors":"Shaista Bibi, M. A. Shah, B. Abbasi, Shahid Hussain","doi":"10.23919/IConAC.2018.8749091","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749091","url":null,"abstract":"Traffic congestion is one of the most significant problems around the world. Literature shows various analyses of real time traffic incidents detection and crowd sensing. However, few researchers quantified the traffic congestion impacts on public health. To the best of our knowledge, there is no study, which determines the correlation between traffic congestion and public health issues via social media. In this paper, we propose a methodology to compute the correlation between traffic congestion and public health issues through social media analysis. To purse this task, we have used topic modeling and sentimental analysis. We mined a collection of 97 million tweets extracted from Twitter. Subsequently, different filters are applied to get the most traffic-congested locations around the world and the top health issues in the corresponding areas. Additionally, we have performed sentimental analysis to get the public perception about the initiatives taken to improve the health issues in those regions. We have found 36 most traffic congested cities around the world, such as Mexico, Bangkok, Jakarta and Chongqing etc. Apart from that, heart diseases, respiratory and psychological problems are identified as the common problems in traffic congested cities. Almost 71% public comments shows the negative sentiments. Which reflects their level of frustration about the steps taken to reduce the traffic by the higher authorities.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"421 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116244226","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8748962
O. A. Khan, M. A. Shah, Muhammad Salman, Abdul Hannan, M. Haris, T. Khan, N. Ejaz
The fragmented networks are formed due to the disaster such as fire, earthquake and flood etc. which can occur in the metropolitan area network. The communication among the nodes in the fragmented networks is very important to research question. Different solutions have been proposed to establish the communication between the nodes in a fermented network which makes use of the named-based network (NDN). The NDN with the help of a content store (CS), pending interest table (PIT), and forward interest-based (FIB), establishes the communication with the other nodes. However, these solutions are inefficient in the case of fragmented networks. In this research, we proposed an NDN-based technique which uses satisfaction interest table (SIT) along with push-based Special Alert Message (SAM) to communicate with the other nodes. We also enable Nonce phenomena. The use of SIT helps the node to find the relative information quickly in fermented networks. Using this technique along with the SAM, we achieved better efficiency and response time
{"title":"NDN Based Communication for Fragmented Network: The Case of Smart Metropolitan (MAN)","authors":"O. A. Khan, M. A. Shah, Muhammad Salman, Abdul Hannan, M. Haris, T. Khan, N. Ejaz","doi":"10.23919/IConAC.2018.8748962","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8748962","url":null,"abstract":"The fragmented networks are formed due to the disaster such as fire, earthquake and flood etc. which can occur in the metropolitan area network. The communication among the nodes in the fragmented networks is very important to research question. Different solutions have been proposed to establish the communication between the nodes in a fermented network which makes use of the named-based network (NDN). The NDN with the help of a content store (CS), pending interest table (PIT), and forward interest-based (FIB), establishes the communication with the other nodes. However, these solutions are inefficient in the case of fragmented networks. In this research, we proposed an NDN-based technique which uses satisfaction interest table (SIT) along with push-based Special Alert Message (SAM) to communicate with the other nodes. We also enable Nonce phenomena. The use of SIT helps the node to find the relative information quickly in fermented networks. Using this technique along with the SAM, we achieved better efficiency and response time","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124666697","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8748963
I. Alqatawneh, Kuosheng Jiang, Zainab Mones, Q. Zeng, F. Gu, A. Ball
Planetary gearbox (PG) exhibits unique dynamic behaviour that imposes great challenges in gear fault diagnosis. In particular, multiple and time-varying vibration transmission paths from the gear meshing point to the sensor, usually mounted on the PG housing, cause not only additional spectral components in the signal but also strong noise. Thus, the influence of the transmission paths and multiple vibration sources make fault indications hard to distinguish. This paper presents a new approach for fault diagnosis of PG based on Multipoint Optimal Minimum Entropy Deconvolution Adjusted (MOMEDA). MOMEDA has been demonstrated effective to suppress the path dissertation for linear time-invariant (LTI) system. However, its performance has not been examined with the case of a time-variant system such as PG vibration system. Therefore, an experimental evaluation is carried out to evaluate and optimise MOMEDA analysis for minimising the path influnces and enhancing periodic fault impulses generated by the faulty gear. A set of experimental data acquired from the PG with seeded with common faults on the planet gear and sun gear. The results obtained by the optimised filter length show that the MOMEDA has the expected capability and allows the seeded faults to be diagnostic successfully under different loads, confirming the generality of the approach.
{"title":"Condition Monitoring and Fault Diagnosis Based on Multipoint Optimal Minimum Entropy Deconvolution Adjusted Technique","authors":"I. Alqatawneh, Kuosheng Jiang, Zainab Mones, Q. Zeng, F. Gu, A. Ball","doi":"10.23919/IConAC.2018.8748963","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8748963","url":null,"abstract":"Planetary gearbox (PG) exhibits unique dynamic behaviour that imposes great challenges in gear fault diagnosis. In particular, multiple and time-varying vibration transmission paths from the gear meshing point to the sensor, usually mounted on the PG housing, cause not only additional spectral components in the signal but also strong noise. Thus, the influence of the transmission paths and multiple vibration sources make fault indications hard to distinguish. This paper presents a new approach for fault diagnosis of PG based on Multipoint Optimal Minimum Entropy Deconvolution Adjusted (MOMEDA). MOMEDA has been demonstrated effective to suppress the path dissertation for linear time-invariant (LTI) system. However, its performance has not been examined with the case of a time-variant system such as PG vibration system. Therefore, an experimental evaluation is carried out to evaluate and optimise MOMEDA analysis for minimising the path influnces and enhancing periodic fault impulses generated by the faulty gear. A set of experimental data acquired from the PG with seeded with common faults on the planet gear and sun gear. The results obtained by the optimised filter length show that the MOMEDA has the expected capability and allows the seeded faults to be diagnostic successfully under different loads, confirming the generality of the approach.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114536647","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749128
Huniya Shahid, M. A. Shah, Bilal Khalid Dar, Fizzah Fizzah
Smartphones are becoming more popular among the visually impaired people due to its inbuilt screen readers (e.g. TalkBack, VoiceOver). These screen readers enable visually impaired people to access some of the smartphone's features. There are other functions which can be inaccessible, time-consuming, and mental-workload inducing. Among these aforementioned functions is text entry. The text entry on smartphones using a virtual keyboard is inherently an ocular task as it requires target hitting accuracy. There has been a significant amount of research regarding text entry on smartphones for visually impaired. The purpose of this study is to conduct a new research from HCI perspective about the various types of text entry methods in smartphones for visually impaired. The systematic search is carried out in 6 databases to find the relevant papers, during the time frame of 2010–2017, to study the recent developments in smartphone text entry methods for visually impaired. This search resulted in 16 research papers, which helped in answering the research questions adapted from Siqueira et al. [1], because this paper not only serves as a guideline for SLRs related to braille-based text entry, but it is also a significant contribution in this field, and the main author of this study has more than 21000 citations. Our study not only presents a concise description of various text entry methods, but it also lists 22 research and design consideration for text entry solutions.
{"title":"A Review of Smartphone's Text Entry for Visually Impaired","authors":"Huniya Shahid, M. A. Shah, Bilal Khalid Dar, Fizzah Fizzah","doi":"10.23919/IConAC.2018.8749128","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749128","url":null,"abstract":"Smartphones are becoming more popular among the visually impaired people due to its inbuilt screen readers (e.g. TalkBack, VoiceOver). These screen readers enable visually impaired people to access some of the smartphone's features. There are other functions which can be inaccessible, time-consuming, and mental-workload inducing. Among these aforementioned functions is text entry. The text entry on smartphones using a virtual keyboard is inherently an ocular task as it requires target hitting accuracy. There has been a significant amount of research regarding text entry on smartphones for visually impaired. The purpose of this study is to conduct a new research from HCI perspective about the various types of text entry methods in smartphones for visually impaired. The systematic search is carried out in 6 databases to find the relevant papers, during the time frame of 2010–2017, to study the recent developments in smartphone text entry methods for visually impaired. This search resulted in 16 research papers, which helped in answering the research questions adapted from Siqueira et al. [1], because this paper not only serves as a guideline for SLRs related to braille-based text entry, but it is also a significant contribution in this field, and the main author of this study has more than 21000 citations. Our study not only presents a concise description of various text entry methods, but it also lists 22 research and design consideration for text entry solutions.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124057194","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 : 2018-09-01DOI: 10.23919/ICONAC.2018.8749043
Chenhua Ni, Xiandong Ma, Yang Bai
The prediction of power generation from a marine wave energy converter (WEC) has been increasingly recognized, which needs to be efficient and cost-effective. This paper introduces a four-inputs model based approach that uses convolutional neural network (CNN) to predict the electricity generated from a oscillating buoy WEC device. The CNN works essentially by converting values of the multiple variables into images. The study shows that the proposed model based CNN outperforms both multivariate linear regression and conventional artificial neural network-based approaches. This model-based approach can furthermore detects changes that could be due to the presence of anomalies of the WEC device by comparing output data obtained from operational device with those predicted by the model. The precise prediction can also be used to control the electricity balance among energy conversion, electrical power production and storage.
{"title":"Convolutional Neural Network based power generation prediction of wave energy converter","authors":"Chenhua Ni, Xiandong Ma, Yang Bai","doi":"10.23919/ICONAC.2018.8749043","DOIUrl":"https://doi.org/10.23919/ICONAC.2018.8749043","url":null,"abstract":"The prediction of power generation from a marine wave energy converter (WEC) has been increasingly recognized, which needs to be efficient and cost-effective. This paper introduces a four-inputs model based approach that uses convolutional neural network (CNN) to predict the electricity generated from a oscillating buoy WEC device. The CNN works essentially by converting values of the multiple variables into images. The study shows that the proposed model based CNN outperforms both multivariate linear regression and conventional artificial neural network-based approaches. This model-based approach can furthermore detects changes that could be due to the presence of anomalies of the WEC device by comparing output data obtained from operational device with those predicted by the model. The precise prediction can also be used to control the electricity balance among energy conversion, electrical power production and storage.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126441643","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749084
Haiying Qi, A. Ertiame, Kingsley Madubuike, Dingli Yu, J. Gomm
Early failure detection for an exothermic semi-batch polymerization reactor is investigated in this paper. The extended Kalman filter (EKF) is used to estimate the system state from reactor nonlinear dynamics via input/output data. Then, a statistical method is employed to detect early system fault. The decision-making is made by a hypothesis testing through a generated innovation sequence. The reactor is a multivariable nonlinear dynamic process and is subjected to several major disturbances. A mathematical model is developed for the reactor with some model parameters identified from the input/output data, and then the developed continuous model is discretized into a discrete model. Being detected in this work are three faults on three sensors and one on the actuator. These fault are simulated on the reactor and are detected using the developed method. Simulation results are given.
{"title":"Failure Prediction for an Exothermic Semi-batch Reactor via A combined EKF with Statistical Method","authors":"Haiying Qi, A. Ertiame, Kingsley Madubuike, Dingli Yu, J. Gomm","doi":"10.23919/IConAC.2018.8749084","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749084","url":null,"abstract":"Early failure detection for an exothermic semi-batch polymerization reactor is investigated in this paper. The extended Kalman filter (EKF) is used to estimate the system state from reactor nonlinear dynamics via input/output data. Then, a statistical method is employed to detect early system fault. The decision-making is made by a hypothesis testing through a generated innovation sequence. The reactor is a multivariable nonlinear dynamic process and is subjected to several major disturbances. A mathematical model is developed for the reactor with some model parameters identified from the input/output data, and then the developed continuous model is discretized into a discrete model. Being detected in this work are three faults on three sensors and one on the actuator. These fault are simulated on the reactor and are detected using the developed method. Simulation results are given.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128074425","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：