Pub Date : 2019-11-01DOI: 10.1109/ICEMI46757.2019.9101568
Yang Tongzhi, Yuan Lingfeng, Xu Miner, Zeng Qi, Li Tingyu
Traditional spacecraft design focuses on function implementation and lacks the consideration of testability. Spacecraft integrated test relies on telemetry and command. The test cycle is long, the test efficiency is low and the cost is high. The traditional test mode can’t adapt well to the needs of spacecraft batch manufacture. Through Model-based BIT technology, civil automobiles and airplanes have established on-board diagnosis system and on-board maintenance system, which greatly improves the ability of rapid maintenance and functional reconfiguration. Referring to the civil rapid electrical inspection technology, the spacecraft self-test models are designed from two aspects of behavior model and structure model, so as to enhance the capability of spacecraft rapid inspection.
{"title":"Research on Spacecraft Rapid Test Technology Based on Built-in Self-test","authors":"Yang Tongzhi, Yuan Lingfeng, Xu Miner, Zeng Qi, Li Tingyu","doi":"10.1109/ICEMI46757.2019.9101568","DOIUrl":"https://doi.org/10.1109/ICEMI46757.2019.9101568","url":null,"abstract":"Traditional spacecraft design focuses on function implementation and lacks the consideration of testability. Spacecraft integrated test relies on telemetry and command. The test cycle is long, the test efficiency is low and the cost is high. The traditional test mode can’t adapt well to the needs of spacecraft batch manufacture. Through Model-based BIT technology, civil automobiles and airplanes have established on-board diagnosis system and on-board maintenance system, which greatly improves the ability of rapid maintenance and functional reconfiguration. Referring to the civil rapid electrical inspection technology, the spacecraft self-test models are designed from two aspects of behavior model and structure model, so as to enhance the capability of spacecraft rapid inspection.","PeriodicalId":419168,"journal":{"name":"2019 14th IEEE International Conference on Electronic Measurement & Instruments (ICEMI)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122731576","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 : 2019-11-01DOI: 10.1109/ICEMI46757.2019.9101478
J. Hongwei, Jiang Hongna, Liu Ming
This paper first studies the internal mechanism of strain measurement of flexible piezoelectric elements through theoretical analysis. Then, based on this, the flexible piezoelectric sensor is designed in form, and the error of the flexible piezoelectric sensor is compensated. Finally, the flexible piezoelectric sensor and the strain gauge were compared and tested, and a new test method suitable for the dynamic strain parameter test of flight test was obtained.
{"title":"Research on dynamic strain testing technology based on flexible piezoelectric element","authors":"J. Hongwei, Jiang Hongna, Liu Ming","doi":"10.1109/ICEMI46757.2019.9101478","DOIUrl":"https://doi.org/10.1109/ICEMI46757.2019.9101478","url":null,"abstract":"This paper first studies the internal mechanism of strain measurement of flexible piezoelectric elements through theoretical analysis. Then, based on this, the flexible piezoelectric sensor is designed in form, and the error of the flexible piezoelectric sensor is compensated. Finally, the flexible piezoelectric sensor and the strain gauge were compared and tested, and a new test method suitable for the dynamic strain parameter test of flight test was obtained.","PeriodicalId":419168,"journal":{"name":"2019 14th IEEE International Conference on Electronic Measurement & Instruments (ICEMI)","volume":"242 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132620971","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 : 2019-11-01DOI: 10.1109/ICEMI46757.2019.9101429
L. Xiaoyu, Guo Xiye, Liu Kai, Chen Gang
Unmanned Aerial Vehicles (UAVs) are becoming widely used in the age of intelligence, and high-precision position sensing becomes a premise for UAVs to perform various tasks. The commonly used Global Navigation Satellite System (GNSS) is vulnerable in buildings, mountains, woods, indoors, etc. due to the occlusion and interference of signals. Based on Ground-based High-precision Local Positioning System (GH-LPS), the paper proposes a tightly-coupled GH-LPS/INS integration method using carrier phase residual to solve the problem caused by GH-LPS base stations’ unsatisfactory layout. MATLAB simulation with real flight test data proves the integration method enabling the system to maintain a reliable centimeter-level precision.
{"title":"GH-LPS/INS integration for precise UAV application","authors":"L. Xiaoyu, Guo Xiye, Liu Kai, Chen Gang","doi":"10.1109/ICEMI46757.2019.9101429","DOIUrl":"https://doi.org/10.1109/ICEMI46757.2019.9101429","url":null,"abstract":"Unmanned Aerial Vehicles (UAVs) are becoming widely used in the age of intelligence, and high-precision position sensing becomes a premise for UAVs to perform various tasks. The commonly used Global Navigation Satellite System (GNSS) is vulnerable in buildings, mountains, woods, indoors, etc. due to the occlusion and interference of signals. Based on Ground-based High-precision Local Positioning System (GH-LPS), the paper proposes a tightly-coupled GH-LPS/INS integration method using carrier phase residual to solve the problem caused by GH-LPS base stations’ unsatisfactory layout. MATLAB simulation with real flight test data proves the integration method enabling the system to maintain a reliable centimeter-level precision.","PeriodicalId":419168,"journal":{"name":"2019 14th IEEE International Conference on Electronic Measurement & Instruments (ICEMI)","volume":"54 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133899818","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 : 2019-11-01DOI: 10.1109/ICEMI46757.2019.9101474
Ren Guoyue, Wu Jinjie, Zhai Yudan, Bai Zhanguo
The main purpose of this paper is to calibrate the detection efficiency and energy linearity of a hard X-ray imager (HXI), one of the payloads on the ASO-S satellite. In this experiment, HPGe calibrated by radioactive source was used as the standard detector, and the experimental device used was a double crystal calibration device. The experimental method is to first measure the single energy peak of the corresponding energy point with a standard detector, and then use the HXI LaBr3 crystal detector probe to obtain the same single energy peak. It should be noted here that in order to eliminate the statistical fluctuations and other factors, we set the detection time of both detectors to 1000 seconds. Then, the dobule crystal parallelism is detuned (ie, non-parallel) to measure the unfiltered background and the electronic noise. Finally, the open source software Root is used to perform relatively clean single-energy X-ray beam data obtained after subtracting the background data of the beam.
{"title":"Preliminary calibration of the hard X-ray imager LaBr3 probe","authors":"Ren Guoyue, Wu Jinjie, Zhai Yudan, Bai Zhanguo","doi":"10.1109/ICEMI46757.2019.9101474","DOIUrl":"https://doi.org/10.1109/ICEMI46757.2019.9101474","url":null,"abstract":"The main purpose of this paper is to calibrate the detection efficiency and energy linearity of a hard X-ray imager (HXI), one of the payloads on the ASO-S satellite. In this experiment, HPGe calibrated by radioactive source was used as the standard detector, and the experimental device used was a double crystal calibration device. The experimental method is to first measure the single energy peak of the corresponding energy point with a standard detector, and then use the HXI LaBr3 crystal detector probe to obtain the same single energy peak. It should be noted here that in order to eliminate the statistical fluctuations and other factors, we set the detection time of both detectors to 1000 seconds. Then, the dobule crystal parallelism is detuned (ie, non-parallel) to measure the unfiltered background and the electronic noise. Finally, the open source software Root is used to perform relatively clean single-energy X-ray beam data obtained after subtracting the background data of the beam.","PeriodicalId":419168,"journal":{"name":"2019 14th IEEE International Conference on Electronic Measurement & Instruments (ICEMI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134331341","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 : 2019-11-01DOI: 10.1109/ICEMI46757.2019.9101442
Luo Qinghua, Liu Sicheng, Yang Yipeng, Ju Chunyu, Yan Xiaozhen
Ultra Wideband (UWB)-based platform is a system which is suitable for high precision distance estimation and localization. A localization algorithm based on UWB platform can gain high accuracy of distance estimation and localization. Among localization methods, the maximum likelihood (MLL) is a simple and accurate location algorithm, which can meet the requirements of location algorithm based on UWB platform. In this paper, a method of maximum likelihood estimation based on outlier detection and UWB platform is studied. Firstly, we analyzed the principle of the UWB-based distance estimation and MLL localization algorithm. Then, the algorithm was verified by simulation analysis of localization accuracy and efficiency. Finally, indoor and outdoor localization experiments were carried out to compare and analyze the localization accuracy of the three localization algorithms in different environments, and the conclusions were drawn. The experimental results demonstrated that MLL has the highest accuracy in indoor and outdoor environments compared with LS and trilateration methods, and it is suitable localization algorithm for UWB localization.
{"title":"An accurate maximum likelihood location method based on UWB platform","authors":"Luo Qinghua, Liu Sicheng, Yang Yipeng, Ju Chunyu, Yan Xiaozhen","doi":"10.1109/ICEMI46757.2019.9101442","DOIUrl":"https://doi.org/10.1109/ICEMI46757.2019.9101442","url":null,"abstract":"Ultra Wideband (UWB)-based platform is a system which is suitable for high precision distance estimation and localization. A localization algorithm based on UWB platform can gain high accuracy of distance estimation and localization. Among localization methods, the maximum likelihood (MLL) is a simple and accurate location algorithm, which can meet the requirements of location algorithm based on UWB platform. In this paper, a method of maximum likelihood estimation based on outlier detection and UWB platform is studied. Firstly, we analyzed the principle of the UWB-based distance estimation and MLL localization algorithm. Then, the algorithm was verified by simulation analysis of localization accuracy and efficiency. Finally, indoor and outdoor localization experiments were carried out to compare and analyze the localization accuracy of the three localization algorithms in different environments, and the conclusions were drawn. The experimental results demonstrated that MLL has the highest accuracy in indoor and outdoor environments compared with LS and trilateration methods, and it is suitable localization algorithm for UWB localization.","PeriodicalId":419168,"journal":{"name":"2019 14th IEEE International Conference on Electronic Measurement & Instruments (ICEMI)","volume":"435 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134317575","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 : 2019-11-01DOI: 10.1109/ICEMI46757.2019.9101554
Sun Jiang, Xing Hongyan, Wu Jiajia
In order to improve the detection accuracy of sea clutter wavelet prediction model further, a sea clutter hybrid denosing algorithm based on variational modal decomposition (VMD) is proposed. The VMD is adopted to decompose the sea clutter signal into a finite number of intrinsic modal functions (IMF) with limited bandwidths of different center frequencies. Then, we analyze the auto-correlation property of the decomposed signal and perform wavelet hard threshold filtering on the modal component with noise characteristics. Reconstructing the filtered component and the residual component to obtain a denosied signal. The sea clutter prediction model based on LSSVM is adopted to verify the denosing result, and the denosing result is evaluated by comparing the predicted root mean square error (RMSE) before and after denosing. Comparing the prediction results of the two groups of experiments, it is not difficult to find that the predicted RMSE after denosing is 0.00055, which is two orders of magnitude lower than the predicted RMS error before denosing (0.0125).
{"title":"Sea clutter hybrid denoising algorithm based on VMD","authors":"Sun Jiang, Xing Hongyan, Wu Jiajia","doi":"10.1109/ICEMI46757.2019.9101554","DOIUrl":"https://doi.org/10.1109/ICEMI46757.2019.9101554","url":null,"abstract":"In order to improve the detection accuracy of sea clutter wavelet prediction model further, a sea clutter hybrid denosing algorithm based on variational modal decomposition (VMD) is proposed. The VMD is adopted to decompose the sea clutter signal into a finite number of intrinsic modal functions (IMF) with limited bandwidths of different center frequencies. Then, we analyze the auto-correlation property of the decomposed signal and perform wavelet hard threshold filtering on the modal component with noise characteristics. Reconstructing the filtered component and the residual component to obtain a denosied signal. The sea clutter prediction model based on LSSVM is adopted to verify the denosing result, and the denosing result is evaluated by comparing the predicted root mean square error (RMSE) before and after denosing. Comparing the prediction results of the two groups of experiments, it is not difficult to find that the predicted RMSE after denosing is 0.00055, which is two orders of magnitude lower than the predicted RMS error before denosing (0.0125).","PeriodicalId":419168,"journal":{"name":"2019 14th IEEE International Conference on Electronic Measurement & Instruments (ICEMI)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134361134","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 : 2019-11-01DOI: 10.1109/ICEMI46757.2019.9101590
Zhang Haifeng, C. Kai, Wang Jian, Wang Xin, Liu Changying
During the operation of the EMU, the traction motor generates a lot of heat. The traction motor fan was added to the bottom of the EMU to solve the heat dissipation problem of the traction motor. The bearing is one of the important parts of the traction motor fan, which is of great significance for the bearing life prediction. In this paper, the multi-body dynamics simulation analysis method was proposed. According to the actual working condition of the traction motor fan of the EMU, the mechanical model of the traction motor fan was established. The rigid-flexible multi-body dynamics simulation analysis of the traction motor fan bearing was completed by RecurDyn software. According to the results of dynamic simulation analysis, the fatigue life analysis module was used to predict the life of the finite element. The life prediction result was basically the same as the basic rated life of the bearing, indicating that the life prediction method was reasonable.
{"title":"Life prediction of fan bearings for traction motors of EMU based on RecurDyn","authors":"Zhang Haifeng, C. Kai, Wang Jian, Wang Xin, Liu Changying","doi":"10.1109/ICEMI46757.2019.9101590","DOIUrl":"https://doi.org/10.1109/ICEMI46757.2019.9101590","url":null,"abstract":"During the operation of the EMU, the traction motor generates a lot of heat. The traction motor fan was added to the bottom of the EMU to solve the heat dissipation problem of the traction motor. The bearing is one of the important parts of the traction motor fan, which is of great significance for the bearing life prediction. In this paper, the multi-body dynamics simulation analysis method was proposed. According to the actual working condition of the traction motor fan of the EMU, the mechanical model of the traction motor fan was established. The rigid-flexible multi-body dynamics simulation analysis of the traction motor fan bearing was completed by RecurDyn software. According to the results of dynamic simulation analysis, the fatigue life analysis module was used to predict the life of the finite element. The life prediction result was basically the same as the basic rated life of the bearing, indicating that the life prediction method was reasonable.","PeriodicalId":419168,"journal":{"name":"2019 14th IEEE International Conference on Electronic Measurement & Instruments (ICEMI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129097137","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 : 2019-11-01DOI: 10.1109/ICEMI46757.2019.9101482
Zhao Ke, Liu Yujie, T. Ming, Yang Jinggang, Wang Jian
The switching coil of circuit breaker operating mechanism has many current characteristics and it can reflect the potential failure state. By analyzing these characteristics, the state of circuit breaker can be evaluated reasonably. However, unbalanced class data, large data volume, and poor classification efficacy are the problems that conventional classification methods must face to. This paper presents a distributed ensemble back propagation neural network (DE-BPNN) method to evaluate circuit breaker state based on coil current characteristics. Firstly, the coil current data are de-noised by wavelet packet with db5 and 9 characteristic parameters are extracted. In order to deal with imbalanced class data, the SMOTE method is adopted to ensure that training samples are the same volume. And it also provides a differential sample extraction method to segment training samples. Then, by building multiple differentiated subset BPNN, the voting strategy is used to generate the final results. Finally, DE-BPNN algorithm is deployed on the distributed large data computing platform Spark to reduce the computation time. Two classification algorithms such as K-means and standalone BPNN are used to compare classification accuracy and efficiency with DE-BPNN. The experimental results show that DE-BPNN has high classification accuracy with the unbalanced training data volume. In addition, the computation time of DE-BPNN keeps stable with the increase of data quantity.
{"title":"A distributed ensemble bpnn used for status assessment of circuit breakers based on coil current characteristics","authors":"Zhao Ke, Liu Yujie, T. Ming, Yang Jinggang, Wang Jian","doi":"10.1109/ICEMI46757.2019.9101482","DOIUrl":"https://doi.org/10.1109/ICEMI46757.2019.9101482","url":null,"abstract":"The switching coil of circuit breaker operating mechanism has many current characteristics and it can reflect the potential failure state. By analyzing these characteristics, the state of circuit breaker can be evaluated reasonably. However, unbalanced class data, large data volume, and poor classification efficacy are the problems that conventional classification methods must face to. This paper presents a distributed ensemble back propagation neural network (DE-BPNN) method to evaluate circuit breaker state based on coil current characteristics. Firstly, the coil current data are de-noised by wavelet packet with db5 and 9 characteristic parameters are extracted. In order to deal with imbalanced class data, the SMOTE method is adopted to ensure that training samples are the same volume. And it also provides a differential sample extraction method to segment training samples. Then, by building multiple differentiated subset BPNN, the voting strategy is used to generate the final results. Finally, DE-BPNN algorithm is deployed on the distributed large data computing platform Spark to reduce the computation time. Two classification algorithms such as K-means and standalone BPNN are used to compare classification accuracy and efficiency with DE-BPNN. The experimental results show that DE-BPNN has high classification accuracy with the unbalanced training data volume. In addition, the computation time of DE-BPNN keeps stable with the increase of data quantity.","PeriodicalId":419168,"journal":{"name":"2019 14th IEEE International Conference on Electronic Measurement & Instruments (ICEMI)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131551056","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 : 2019-11-01DOI: 10.1109/ICEMI46757.2019.9101411
Ren Guoyue, Wu Jinjie, Wang Bo, Bai Zhanguo
In this paper, we mainly study the measurement problem of the half-value layer of the narrow-spectrum (250-600) kV X-ray re-filtering narrow-band, and use the experimental and simulation methods to obtain the half-value layer of the high-energy segment re-filtering narrow spectrum. The half-value layer is one of the important parameter characteristics describing the radiation quality. Therefore, measuring the half-value layer plays an important role in the establishment of the radiation quality. The corresponding specification is not given in the additional filter ISO with a tube voltage greater than 300 kV. The method for determining the additional filter thickness used for the tube voltage greater than 300 kV is to linearly fit the relationship between the tube voltage and the additional filter in ISO, and then calculate the thickness value of the additional filter after 300 kV according to the fitted formula. After determining the thickness value, the corresponding energy spectrum is simulated by Monte Carlo simulation. The energy spectrum simulated by Monte Carlo is compared with the theoretical energy spectrum given in ISO-4037. The results show that the average energy and simulation of N250ISO are obtained. The average energy relative deviation is 0.38%, and the N300 average energy relative deviation is 0.35%. The average energy is within 5% in accordance with ISO specifications. The half-value layer of the narrow spectrum can be re-filtered by the experimental (250-600) kV X-ray by the corresponding method given in ISO.
{"title":"(250-600) kv re-filtering narrow-spectrum x-ray half-value layer measurement method","authors":"Ren Guoyue, Wu Jinjie, Wang Bo, Bai Zhanguo","doi":"10.1109/ICEMI46757.2019.9101411","DOIUrl":"https://doi.org/10.1109/ICEMI46757.2019.9101411","url":null,"abstract":"In this paper, we mainly study the measurement problem of the half-value layer of the narrow-spectrum (250-600) kV X-ray re-filtering narrow-band, and use the experimental and simulation methods to obtain the half-value layer of the high-energy segment re-filtering narrow spectrum. The half-value layer is one of the important parameter characteristics describing the radiation quality. Therefore, measuring the half-value layer plays an important role in the establishment of the radiation quality. The corresponding specification is not given in the additional filter ISO with a tube voltage greater than 300 kV. The method for determining the additional filter thickness used for the tube voltage greater than 300 kV is to linearly fit the relationship between the tube voltage and the additional filter in ISO, and then calculate the thickness value of the additional filter after 300 kV according to the fitted formula. After determining the thickness value, the corresponding energy spectrum is simulated by Monte Carlo simulation. The energy spectrum simulated by Monte Carlo is compared with the theoretical energy spectrum given in ISO-4037. The results show that the average energy and simulation of N250ISO are obtained. The average energy relative deviation is 0.38%, and the N300 average energy relative deviation is 0.35%. The average energy is within 5% in accordance with ISO specifications. The half-value layer of the narrow spectrum can be re-filtered by the experimental (250-600) kV X-ray by the corresponding method given in ISO.","PeriodicalId":419168,"journal":{"name":"2019 14th IEEE International Conference on Electronic Measurement & Instruments (ICEMI)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131530119","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 : 2019-11-01DOI: 10.1109/ICEMI46757.2019.9101840
Z. Guangquan, Wu Kankan, Gao Yong-cheng, L. Yongmei, Hu Cong
In recent years, machine learning technology is widely used in the field of fault diagnosis for bearings. Although these methods usually work well, the following defects still exist when they are dealing with large amount of fault data: (1) feature extraction methods need to rely on expertise or signal processing technologies. Therefore, there is a lack of a feature extraction method that is common to different diagnostic problems; (2) shallow models can't learn more complex mapping relationships well; (3) traditional intelligent diagnostic methods are usually computationally intensive and slow in convergence. Inspired by the Auto-encoder’s (AE) feature extraction capability and fast training speed of the Extreme Learning Machine (ELM), a new fault diagnosis method for bearings based on Extreme Learning Machine-Autoencoder (ELM-AE) is proposed in this paper. With its automatic feature extraction capability and very efficient learning strategy, the raw vibration signals of bearings are directly sent to the model without any manual feature extraction for fault diagnosis, which overcomes the above drawbacks. The experimental results on CWRU bearing dataset show that the proposed method takes into account both diagnostic accuracy and time efficiency. Compared with existing literatures, our proposed method obtains superior accuracy.
{"title":"Bearing fault diagnosis from raw vibration signals using multi-layer extreme learning machine","authors":"Z. Guangquan, Wu Kankan, Gao Yong-cheng, L. Yongmei, Hu Cong","doi":"10.1109/ICEMI46757.2019.9101840","DOIUrl":"https://doi.org/10.1109/ICEMI46757.2019.9101840","url":null,"abstract":"In recent years, machine learning technology is widely used in the field of fault diagnosis for bearings. Although these methods usually work well, the following defects still exist when they are dealing with large amount of fault data: (1) feature extraction methods need to rely on expertise or signal processing technologies. Therefore, there is a lack of a feature extraction method that is common to different diagnostic problems; (2) shallow models can't learn more complex mapping relationships well; (3) traditional intelligent diagnostic methods are usually computationally intensive and slow in convergence. Inspired by the Auto-encoder’s (AE) feature extraction capability and fast training speed of the Extreme Learning Machine (ELM), a new fault diagnosis method for bearings based on Extreme Learning Machine-Autoencoder (ELM-AE) is proposed in this paper. With its automatic feature extraction capability and very efficient learning strategy, the raw vibration signals of bearings are directly sent to the model without any manual feature extraction for fault diagnosis, which overcomes the above drawbacks. The experimental results on CWRU bearing dataset show that the proposed method takes into account both diagnostic accuracy and time efficiency. Compared with existing literatures, our proposed method obtains superior accuracy.","PeriodicalId":419168,"journal":{"name":"2019 14th IEEE International Conference on Electronic Measurement & Instruments (ICEMI)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131602800","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：