Pub Date : 2022-10-17DOI: 10.1109/IECON49645.2022.9969049
Palla Parasuram Yadav, Nikhi Bobate, Amba Shetty, B. Raghavendra, A. Narasimhadhan
Hyperspectral images (HSIs) due to advancements in spatial-spectral resolutions and availability of multi-temporal information is in demand for many remote sensing (RS) applications including change detection (CD). The high dimensionality of HSIs and limited availability of HSI-CD data sets with ground-truth change maps make CD not so easy but a difficult task. Though there are many classical and deep learning (DL) based algorithms to detect changes, the performance of classical algorithms is not up to the satisfactory level and the final performance of DL models depend on efficiency of pre-detection techniques which provide prior knowledge on changed and unchanged areas that are required to get appropriate training samples to learn to detect changes. Classical and DL approaches consider change information at pixel level i.e. pixel to pixel change either by comparing the corresponding pixels alone or with their local neighborhood pixels. Therefore, identification of features for every pixel that relate the most significant information of the whole HSI-CD data in a simple and an efficient way to detect changes effectively is the need of the hour. In addition, there is not much comprehensive study on developing CD algorithms that not only simple to use but also as efficient as that of DL models is available. Therefore, in this paper, an endmember based feature extraction is proposed to detect changes in HSI. An automatic target generation process (ATGP) algorithm is adapted to extract endmembers present in the HSI-CD data set. Then, various spectral matching algorithms are used to measure endmember relations for all the pixels so that dimensionality of the data is reduced as well as the effective features to detect changes can be extracted. The experimental results on three benchmark HSI-CD data sets show that proposed ATGP based change vector analysis (CVA) algorithm yields remarkable results on comparing both with the classical as well as DL based CD approaches.
{"title":"ATGP based Change Detection in Hyperspectral Images","authors":"Palla Parasuram Yadav, Nikhi Bobate, Amba Shetty, B. Raghavendra, A. Narasimhadhan","doi":"10.1109/IECON49645.2022.9969049","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9969049","url":null,"abstract":"Hyperspectral images (HSIs) due to advancements in spatial-spectral resolutions and availability of multi-temporal information is in demand for many remote sensing (RS) applications including change detection (CD). The high dimensionality of HSIs and limited availability of HSI-CD data sets with ground-truth change maps make CD not so easy but a difficult task. Though there are many classical and deep learning (DL) based algorithms to detect changes, the performance of classical algorithms is not up to the satisfactory level and the final performance of DL models depend on efficiency of pre-detection techniques which provide prior knowledge on changed and unchanged areas that are required to get appropriate training samples to learn to detect changes. Classical and DL approaches consider change information at pixel level i.e. pixel to pixel change either by comparing the corresponding pixels alone or with their local neighborhood pixels. Therefore, identification of features for every pixel that relate the most significant information of the whole HSI-CD data in a simple and an efficient way to detect changes effectively is the need of the hour. In addition, there is not much comprehensive study on developing CD algorithms that not only simple to use but also as efficient as that of DL models is available. Therefore, in this paper, an endmember based feature extraction is proposed to detect changes in HSI. An automatic target generation process (ATGP) algorithm is adapted to extract endmembers present in the HSI-CD data set. Then, various spectral matching algorithms are used to measure endmember relations for all the pixels so that dimensionality of the data is reduced as well as the effective features to detect changes can be extracted. The experimental results on three benchmark HSI-CD data sets show that proposed ATGP based change vector analysis (CVA) algorithm yields remarkable results on comparing both with the classical as well as DL based CD approaches.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"51 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120816082","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 : 2022-10-17DOI: 10.1109/IECON49645.2022.9969108
F. Bento, A. Cardoso
Multilevel DC–DC power conversion solutions reveal excellent features for implementation in energy management and storage applications, such as electric vehicle (EV) charging. Conventional control approaches applied to multilevel converters show weaknesses in preserving optimal conversion performance. Despite the potential improvements in terms of control robustness, attainable through the exploitation of model-based predictive control (MBPC) approaches, parameter sensitivity of such control approaches shows potential to deteriorate the response of the converter. To overcome such challenge, this paper describes a novel Model-Free Predictive Control (MFPC) approach suitable for multilevel DC–DC power converters, convening in a single solution the benefits of predictive control and insensitivity against parameter uncertainty, which is particularly concerning in energy storage applications. A set of operation scenarios confirm the effectiveness of the proposed MFPC in both steady- and transient-states.
{"title":"Model-Free Predictive Control of Multilevel DC–DC Converters for Energy Storage Applications","authors":"F. Bento, A. Cardoso","doi":"10.1109/IECON49645.2022.9969108","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9969108","url":null,"abstract":"Multilevel DC–DC power conversion solutions reveal excellent features for implementation in energy management and storage applications, such as electric vehicle (EV) charging. Conventional control approaches applied to multilevel converters show weaknesses in preserving optimal conversion performance. Despite the potential improvements in terms of control robustness, attainable through the exploitation of model-based predictive control (MBPC) approaches, parameter sensitivity of such control approaches shows potential to deteriorate the response of the converter. To overcome such challenge, this paper describes a novel Model-Free Predictive Control (MFPC) approach suitable for multilevel DC–DC power converters, convening in a single solution the benefits of predictive control and insensitivity against parameter uncertainty, which is particularly concerning in energy storage applications. A set of operation scenarios confirm the effectiveness of the proposed MFPC in both steady- and transient-states.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"31 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120824448","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 : 2022-10-17DOI: 10.1109/IECON49645.2022.9969087
A. Paraskevopoulos, M. Schlosser, Warunee Pluemakarapunya, Dominic Schulz, Peter Hellwig, Julian Hohmann, M. Bohge, T. Menzel, H. Woesner, V. Jungnickel
Mobility is a crucial aspect when using optical wireless technology (LiFi) in an Industry 4.0 manufacturing environment. This paper presents initial results with the wireless network concept developed in the SESAM-project combining LiFi and radio frequency (RF) prototypes. In a first stage, the performance of a high-speed LiFi cell providing spatial diversity is evaluated when mobility issues are taken into account. As a second step, we demonstrate mobility in the whole manufacturing hall with a software-defined network solution. This enables a low latency vertical handover between a proprietary RF solution, denoted as EchoRing, and the LiFi cell.
{"title":"Software-defined LiFi - RF network for Industry 4.0 applications","authors":"A. Paraskevopoulos, M. Schlosser, Warunee Pluemakarapunya, Dominic Schulz, Peter Hellwig, Julian Hohmann, M. Bohge, T. Menzel, H. Woesner, V. Jungnickel","doi":"10.1109/IECON49645.2022.9969087","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9969087","url":null,"abstract":"Mobility is a crucial aspect when using optical wireless technology (LiFi) in an Industry 4.0 manufacturing environment. This paper presents initial results with the wireless network concept developed in the SESAM-project combining LiFi and radio frequency (RF) prototypes. In a first stage, the performance of a high-speed LiFi cell providing spatial diversity is evaluated when mobility issues are taken into account. As a second step, we demonstrate mobility in the whole manufacturing hall with a software-defined network solution. This enables a low latency vertical handover between a proprietary RF solution, denoted as EchoRing, and the LiFi cell.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123939262","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 : 2022-10-17DOI: 10.1109/IECON49645.2022.9969096
H. Kunisada, K. Fujitani, F. Ito, M. Okui, Taro Nakamura
In this paper, we describe the development of short-fiber oriented rubber and its application to elongation-type actuators. Short-fiber oriented rubber, i.e., rubber containing oriented short fibers with lengths of 3 mm, has anisotropy in the direction of fiber orientation. In a previous study, it was shown that short fiber-reinforced artificial muscles made of short-fiber oriented rubber can achieve up to 17% shrinkage. However, in that study, characteristics other than the amount of shrinkage were not measured, the basic characteristics of the developed artificial muscle were unclear, and the shrinkage ratio was smaller than that for existing straight-fiber-type artificial muscle. In the present study, we developed a new method for fabricating short-fiber oriented rubber and measured the tensile characteristics in the direction of fiber orientation and vertical to the orientation direction. Moreover, we developed an elongation-type artificial muscle from the rubber sheet and measured its elongation characteristics. Test results indicated that the fabricated rubber sheet had anisotropy. They also indicated that the anisotropy increased with the fiber concentration and that the fiber restraint acted not only in the orientation direction but also in the vertical direction. Furthermore, the developed elongation-type artificial muscle was three times more anisotropic in the ratio of axial changes to diametral changes. On the basis of these results, we expect to develop an automated production method for soft actuators.
{"title":"Deveropmrnt of Anisotropic Short-Fiber Oriented Rubber and its Application To Elongation Actuators","authors":"H. Kunisada, K. Fujitani, F. Ito, M. Okui, Taro Nakamura","doi":"10.1109/IECON49645.2022.9969096","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9969096","url":null,"abstract":"In this paper, we describe the development of short-fiber oriented rubber and its application to elongation-type actuators. Short-fiber oriented rubber, i.e., rubber containing oriented short fibers with lengths of 3 mm, has anisotropy in the direction of fiber orientation. In a previous study, it was shown that short fiber-reinforced artificial muscles made of short-fiber oriented rubber can achieve up to 17% shrinkage. However, in that study, characteristics other than the amount of shrinkage were not measured, the basic characteristics of the developed artificial muscle were unclear, and the shrinkage ratio was smaller than that for existing straight-fiber-type artificial muscle. In the present study, we developed a new method for fabricating short-fiber oriented rubber and measured the tensile characteristics in the direction of fiber orientation and vertical to the orientation direction. Moreover, we developed an elongation-type artificial muscle from the rubber sheet and measured its elongation characteristics. Test results indicated that the fabricated rubber sheet had anisotropy. They also indicated that the anisotropy increased with the fiber concentration and that the fiber restraint acted not only in the orientation direction but also in the vertical direction. Furthermore, the developed elongation-type artificial muscle was three times more anisotropic in the ratio of axial changes to diametral changes. On the basis of these results, we expect to develop an automated production method for soft actuators.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124464122","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 : 2022-10-17DOI: 10.1109/IECON49645.2022.9968434
Mateja Car, M. Vašak, Mojtaba Hajihosseini, V. Lešić
This paper presents a microgrid energy flow optimization algorithm with variable battery storage efficiency in order to achieve energy savings and expand the lifespan of the components. The converter efficiency curve is deduced from converter’s datasheets and approximated with mathematical functions. The power loss on the battery internal resistance is also included in order to achieve a more accurate model of the complete storage system. The obtained nonlinear model is used in model predictive control formulation and solved by using a sequential linear program (SLP) algorithm. The SLP algorithm iteratively linearizes the model around the current solution and uses corresponding efficiencies over the prediction horizon. Simulations in MATLAB are performed for a 7-day period and compared with a conventional, constant-efficiency battery system model. The results show an improved performance regarding the charging and discharging battery power and the overall savings of 7% in comparison with the conventional model used in model predictive control.
{"title":"Nonlinear model predictive control of a microgrid with a variable efficiency battery storage system","authors":"Mateja Car, M. Vašak, Mojtaba Hajihosseini, V. Lešić","doi":"10.1109/IECON49645.2022.9968434","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9968434","url":null,"abstract":"This paper presents a microgrid energy flow optimization algorithm with variable battery storage efficiency in order to achieve energy savings and expand the lifespan of the components. The converter efficiency curve is deduced from converter’s datasheets and approximated with mathematical functions. The power loss on the battery internal resistance is also included in order to achieve a more accurate model of the complete storage system. The obtained nonlinear model is used in model predictive control formulation and solved by using a sequential linear program (SLP) algorithm. The SLP algorithm iteratively linearizes the model around the current solution and uses corresponding efficiencies over the prediction horizon. Simulations in MATLAB are performed for a 7-day period and compared with a conventional, constant-efficiency battery system model. The results show an improved performance regarding the charging and discharging battery power and the overall savings of 7% in comparison with the conventional model used in model predictive control.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129860551","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 : 2022-10-17DOI: 10.1109/IECON49645.2022.9968783
A. Tisan, E. Monmasson, C. C. Took
In this paper, it is explored the use of the high-level synthesis (HLS) tool to design field-programmable gate array (FPGA)-based Quaternion Least Mean Square (QLMS) filters. The QLMS behaviour is modelled in system level C-code, and performance criteria, such as parallelism level and timing closure requirements, set through specific directives. The design outcome is a synthesizable hardware description model of the QLMS filter, and its implementation performance is evaluated for different data type representations. The results demonstrate that HLS is a framework that allows rapid design development and efficient FPGA implementation and opens the hyper complex filters hardware design to a larger design community.
{"title":"FPGA accelerators HLS-based design of hyper complex LMS filters","authors":"A. Tisan, E. Monmasson, C. C. Took","doi":"10.1109/IECON49645.2022.9968783","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9968783","url":null,"abstract":"In this paper, it is explored the use of the high-level synthesis (HLS) tool to design field-programmable gate array (FPGA)-based Quaternion Least Mean Square (QLMS) filters. The QLMS behaviour is modelled in system level C-code, and performance criteria, such as parallelism level and timing closure requirements, set through specific directives. The design outcome is a synthesizable hardware description model of the QLMS filter, and its implementation performance is evaluated for different data type representations. The results demonstrate that HLS is a framework that allows rapid design development and efficient FPGA implementation and opens the hyper complex filters hardware design to a larger design community.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129596819","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 : 2022-10-17DOI: 10.1109/IECON49645.2022.9968850
Mohammad Salah Abdullatif, Salam Hajjar, A. Khanna
The development of instrument grade mmWave transceivers comes with many challenges. A general rule of thumb requires that the performance of any instrument must be higher than the performance of the unit under test. The performance is measured in terms of accuracy and stability. The calibration and characterization of mmWave transceivers are important pillars for commercial products. One famous method for calibrating a mmWave test equipment transceiver is using the Vector Network Analyzer (VNA) with a mixer option. This method has proven a high performance in mmWave transceivers’ calibration. However, this approach comes with a high cost. It costs a million dollars for some configuration. In this work, a reduced-cost method to calibrate mmWave instrument grade transceivers is proposed. The method is based on employing a Magic Tee whereas, the VNA technology relies on internal couplers to signal source and receiver to perform the S-parameters. A comparison between the proposed method and the VNA technology is provided. A demonstration of significant challenges is discussed, and an approach to meet the requirements is proposed.
{"title":"Cost-effective, Accuracy Preserving Scalar Characterization for mmWave Transceivers","authors":"Mohammad Salah Abdullatif, Salam Hajjar, A. Khanna","doi":"10.1109/IECON49645.2022.9968850","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9968850","url":null,"abstract":"The development of instrument grade mmWave transceivers comes with many challenges. A general rule of thumb requires that the performance of any instrument must be higher than the performance of the unit under test. The performance is measured in terms of accuracy and stability. The calibration and characterization of mmWave transceivers are important pillars for commercial products. One famous method for calibrating a mmWave test equipment transceiver is using the Vector Network Analyzer (VNA) with a mixer option. This method has proven a high performance in mmWave transceivers’ calibration. However, this approach comes with a high cost. It costs a million dollars for some configuration. In this work, a reduced-cost method to calibrate mmWave instrument grade transceivers is proposed. The method is based on employing a Magic Tee whereas, the VNA technology relies on internal couplers to signal source and receiver to perform the S-parameters. A comparison between the proposed method and the VNA technology is provided. A demonstration of significant challenges is discussed, and an approach to meet the requirements is proposed.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129606214","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 : 2022-10-17DOI: 10.1109/IECON49645.2022.9968501
Thomas Frühwirth, Thomas Preindl, W. Kastner
An important field of application for the Internet of Things (IoT) is the area of monitoring and control, which imposes requirements on dependability. As devices in the IoT become increasingly capable, they can make use of concepts and technologies provided by the area of knowledge engineering to cope with these requirements. Existing work in this area mainly covers dependability threats and means, but dependability attributes are less well investigated.This paper presents a dependability rating ontology that enables the quantification of dependability attributes and, thus, makes them comparable. This is achieved by combining a dependability tree ontology with an ontology covering metrics and scales. IoT devices can use the dependability rating ontology, e.g., to improve their control algorithms, which is demonstrated on the switching optimization problem, a Smart Grid use-case.
{"title":"Ontology for Rating Dependability Attributes","authors":"Thomas Frühwirth, Thomas Preindl, W. Kastner","doi":"10.1109/IECON49645.2022.9968501","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9968501","url":null,"abstract":"An important field of application for the Internet of Things (IoT) is the area of monitoring and control, which imposes requirements on dependability. As devices in the IoT become increasingly capable, they can make use of concepts and technologies provided by the area of knowledge engineering to cope with these requirements. Existing work in this area mainly covers dependability threats and means, but dependability attributes are less well investigated.This paper presents a dependability rating ontology that enables the quantification of dependability attributes and, thus, makes them comparable. This is achieved by combining a dependability tree ontology with an ontology covering metrics and scales. IoT devices can use the dependability rating ontology, e.g., to improve their control algorithms, which is demonstrated on the switching optimization problem, a Smart Grid use-case.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129663054","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 : 2022-10-17DOI: 10.1109/IECON49645.2022.9968765
Hanul Jung, Taejune Kong, Jae-gu Kang, Sehoon Oh
In this paper, the parametric identification is addressed by a kernel-based model with covariance and a novel model order selection algorithm. The kernel-based model is uti-lized for training the sampled frequency response characteristics, which is insufficient for parametric identification because of noisy and discrete data. The kernel-based frequency response model improves the parametric identification by using the high covariance data. In addition, prior knowledge of the model order is essential for parametric identification. This paper proposes a novel model order selection based on the robust stability criterion of disturbance observer (DOB). The effectiveness of the proposed algorithm is verified through numerical simulations under several conditions.
{"title":"Parametric Identification using Kernel-based Frequency Response Model with Model Order Selection based on Robust Stability","authors":"Hanul Jung, Taejune Kong, Jae-gu Kang, Sehoon Oh","doi":"10.1109/IECON49645.2022.9968765","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9968765","url":null,"abstract":"In this paper, the parametric identification is addressed by a kernel-based model with covariance and a novel model order selection algorithm. The kernel-based model is uti-lized for training the sampled frequency response characteristics, which is insufficient for parametric identification because of noisy and discrete data. The kernel-based frequency response model improves the parametric identification by using the high covariance data. In addition, prior knowledge of the model order is essential for parametric identification. This paper proposes a novel model order selection based on the robust stability criterion of disturbance observer (DOB). The effectiveness of the proposed algorithm is verified through numerical simulations under several conditions.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127117538","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 : 2022-10-17DOI: 10.1109/IECON49645.2022.9968491
Hongbin Zhu, Weichao Xu, C. Delpha, Yanguang Wang
This work proposes a diagnosis method based on mutual dimensionless indices (MDIs) and receiver operating characteristic (ROC) analysis for the detection of rolling bearing faults, which is of great importance to maintain the functionality of rotating machines. The proposed method consists of five steps. Firstly, the mutual dimensionless technique is used to extract five MDIs from the raw vibration signal. Secondly, the principal components analysis (PCA) is employed to reduce the five MDIs to a one-dimensional feature. Thirdly, we obtain the areas under the ROC curve (AUC) and associated variances using two sliding windows along the one-dimensional feature sequence. Fourthly, the potential fault occurring time is estimated via comparing the AUC and the associated variances with the corresponding detection thresholds. Finally, a parameter K is introduced to delete the false alarms, and then the predicting fault occurring time is chosen from the local extrema of the potential fault occurring times. Experimental results demonstrate that our proposed approach is capable to detect fault occurring time with high accuracy and a low false-positive rate.
{"title":"Mutual Dimensionless Indices and ROC Analysis in Bearing Fault Occurrence Detection","authors":"Hongbin Zhu, Weichao Xu, C. Delpha, Yanguang Wang","doi":"10.1109/IECON49645.2022.9968491","DOIUrl":"https://doi.org/10.1109/IECON49645.2022.9968491","url":null,"abstract":"This work proposes a diagnosis method based on mutual dimensionless indices (MDIs) and receiver operating characteristic (ROC) analysis for the detection of rolling bearing faults, which is of great importance to maintain the functionality of rotating machines. The proposed method consists of five steps. Firstly, the mutual dimensionless technique is used to extract five MDIs from the raw vibration signal. Secondly, the principal components analysis (PCA) is employed to reduce the five MDIs to a one-dimensional feature. Thirdly, we obtain the areas under the ROC curve (AUC) and associated variances using two sliding windows along the one-dimensional feature sequence. Fourthly, the potential fault occurring time is estimated via comparing the AUC and the associated variances with the corresponding detection thresholds. Finally, a parameter K is introduced to delete the false alarms, and then the predicting fault occurring time is chosen from the local extrema of the potential fault occurring times. Experimental results demonstrate that our proposed approach is capable to detect fault occurring time with high accuracy and a low false-positive rate.","PeriodicalId":125740,"journal":{"name":"IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127537967","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：