{"title":"Gear fault classification using Vibration and Acoustic Sensor Fusion: A Case Study","authors":"Vanraj, S. S. Dhami, B. Pabla","doi":"10.1109/CMD.2018.8535974","DOIUrl":"https://doi.org/10.1109/CMD.2018.8535974","url":null,"abstract":"Condition monitoring systems are increasingly being employed in industrial applications to improve the availability of equipment and to increase the overall equipment efficiency. Condition monitoring of gears, a key element of rotating machines, ensures to continuously reduce and eliminate costs, unscheduled downtime and unexpected breakdowns. Various gear fault diagnosis techniques have been reported which primarily focus on vibration analysis using statistical measures. On the other hand, acoustic signals possess a huge potential in condition monitoring, as acoustic monitoring is more sensitive to vibrating bodies than vibration sensors and hence provides an opportunity to identify faults in early stage. Still, limited studies have been reported for condition monitoring of rotating machines using acoustic sensing as compared to vibration sensing. The advantages of vibration based and acoustic based condition monitoring approaches may be synthesized by using sensor fusion, which is combining sensory data derived from different sources such that the resulting information has less uncertainty than the information derived from these sources individually. In the present work, classification of severity of chipped tooth fault in gears has been reported using vibration and acoustic sensor fusion and its effectiveness vis-vis vibration and acoustic approaches has been evaluated.","PeriodicalId":6529,"journal":{"name":"2018 Condition Monitoring and Diagnosis (CMD)","volume":"17 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84986331","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}
Chul-ho Park, Sangsuh Park, Jeong-chae Kim, Sangbae Oh, Y. Hwang
{"title":"Development of automatic detection algorithm and system on ultrasonic diagnosis for electric facilities","authors":"Chul-ho Park, Sangsuh Park, Jeong-chae Kim, Sangbae Oh, Y. Hwang","doi":"10.1109/CMD.2018.8535754","DOIUrl":"https://doi.org/10.1109/CMD.2018.8535754","url":null,"abstract":"Nowadays the ultrasonic diagnostic equipment is used to inspect and diagnose electric facilities precisely all over the world. But the diagnosis is conducted by diagnostician manually, so that many disadvantages are occurring. To solve these problems, we have developed a high-tech system with an automatic detection algorithm and verified reliability and efficiency in the field.","PeriodicalId":6529,"journal":{"name":"2018 Condition Monitoring and Diagnosis (CMD)","volume":"69 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80360316","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}
{"title":"Analysis of Time-Frequency Characteristics of PD Electromagnetic Wave Based on Electromagnetic Simulation","authors":"Zijing Zeng, Jianwen Wang, Yue Hu, Zhi-wei Wang, Hongyi Huang","doi":"10.1109/CMD.2018.8535874","DOIUrl":"https://doi.org/10.1109/CMD.2018.8535874","url":null,"abstract":"The electromagnetic wave excited by Partial Discharge (PD) suffers severe signal fading caused by equipment, free space and the effects of multipath, when it propagates from PD source to Ultra-High Frequency (UHF) sensor. These effects make the waveform and energy of the signal received by the sensor greatly differing from the original signal. In order to accurately obtain the time-frequency characteristics of the PD pulse signal received by the sensor, analyze the factors affecting its change and searching about PD source location and pattern recognition, it is necessary to analyze the radiation mechanism and propagation process of PD electromagnetic wave deeply. This paper carried out the research on propagation characteristics of PD pulse in the space of substation based on the electromagnetic simulation. The paper firstly used the equivalent model of electric dipole to analyze the basic principle of PD electromagnetic wave radiation, and then simulated the propagation of PD electromagnetic waves in a real open-type substation 3D model based on CST microwave studio, which is an electromagnetic simulation platform. The oscillation, time delay and frequency spectrum of PD electromagnetic wave detected by probes at different distances from PD source were analyzed on E-plane and H-plane in UHF frequency band. The simulation results show that the electromagnetic simulation can obtain the changing rule of the time-frequency characteristics about PD electromagnetic wave propagation, and also explain that the different propagation distance and the complexity of channel in propagation path can greatly affect the time-frequency characteristics of PD electromagnetic wave. Meanwhile, the simulation results also provide guidance for PD sensor positioning in the substation and parameters setting. And some proposals for time delay algorithm selection in PD location are offered as well.","PeriodicalId":6529,"journal":{"name":"2018 Condition Monitoring and Diagnosis (CMD)","volume":"75 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80419893","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}
{"title":"State of the Art in GIS PD Diagnostics","authors":"G. Behrmann, W. Koltunowicz, U. Schichler","doi":"10.1109/CMD.2018.8535741","DOIUrl":"https://doi.org/10.1109/CMD.2018.8535741","url":null,"abstract":"This paper presents the state of the art in GIS PD diagnostics. The guidelines for a risk assessment procedure on defects in GIS based on PD measurements are described. The procedure starts with sensitive PD measurements to detect critical defects and follows with an identification of the type of the defect and its location inside the GIS. This information, combined with other essential data from the manufacturer's experience and a trend analysis of the PD activity, is the base for the estimation of the criticality of the defects. Finally, the risk assessment is performed based on the estimated dielectric failure probability and failure consequences. To detect and eliminate critical insulation defects, PD monitoring systems are applied. The ultra-high frequency measurement method is used worldwide by GIS manufacturers during routine testing in the factory, during on-site commissioning and by utilities for continuous in-service monitoring.","PeriodicalId":6529,"journal":{"name":"2018 Condition Monitoring and Diagnosis (CMD)","volume":"12 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81181271","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}
{"title":"Usability of fiber Bragg grating sensors for the fatigue life monitoring of overhead transmission lines","authors":"Xinbo Hang, Han Zhang, Yu Zhao","doi":"10.1109/CMD.2018.8535970","DOIUrl":"https://doi.org/10.1109/CMD.2018.8535970","url":null,"abstract":"Fretting fatigue of transmission lines, caused by Aeolian vibration, always leads to catastrophic failure of conductors. The fatigue life monitoring of overhead transmission lines is an effective method to foresee strands broken of the conductor. Fatigue severity is usually expressed by alternating bending stress which occurs in the vicinity of suspension clamps during vibration. Given that it is hard to measure the fatigue stress directly, according to IEEE, alternating bending amplitude is recommended as a substitute measured parameter for fatigue life. In this paper, an on-line monitoring system based on a fiber-optic acceleration sensor is designed to analyze the fatigue life of overhead transmission lines in Aeolian vibration surveillance. Considering its superior performance of anti-electromagnetic interference, Fiber Bragg Grating (FBG) sensor is used to measure alternating bending amplitude of overhead transmission lines. And a Cumulative Fatigue Damage (CFD) method, which is based on alternating bending amplitude for vibration and the Stress-Cycle (S-N) curves, is proposed to calculate the fatigue life of overhead transmission lines. A case study of the one-month measurement data of Aeolian vibration for 1000kV Ultra-High Voltage (UHV) transmission lines is presented. Then an on-line monitoring system based on a fiber-optic acceleration sensor is designed to analyze the fatigue life of overhead transmission lines in Aeolian vibration surveillance.","PeriodicalId":6529,"journal":{"name":"2018 Condition Monitoring and Diagnosis (CMD)","volume":"5 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82499379","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}
Yongjie Ning, Gang Wang, JiaCheng Yu, Hanhan Jiang
{"title":"A Feature Selection Algorithm Based on Variable Correlation and Time Correlation for Predicting Remaining Useful Life of Equipment Using RNN","authors":"Yongjie Ning, Gang Wang, JiaCheng Yu, Hanhan Jiang","doi":"10.1109/CMD.2018.8535843","DOIUrl":"https://doi.org/10.1109/CMD.2018.8535843","url":null,"abstract":"This In order to make full use of the influence factor of feature changes in the remaining useful life prediction problem of rolling bearings under limited state data, as well as the correlation between the feature and the time, this paper proposes a feature selection method based on variable correlation and time correlation. In this model, MIV (Mean Impact Value) algorithm is used for feature selection at first, which meets the most demands of regression network for the first selection of variables. In addition, the separability measure of residual features is calculated by the correlation coefficient identification, which implements the second feature selection based on time correlation. Then the bearing degradation curve was obtained through RNN (Recurrent Neural Networks). Finally, particle filter is used to obtain the remaining useful life. Experiments show that the feature selection algorithm based on variable correlation and time correlation selects the most informative and sensitive features and it has credibility.","PeriodicalId":6529,"journal":{"name":"2018 Condition Monitoring and Diagnosis (CMD)","volume":"113 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89467202","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}
Lianghong Cao, L. Zhong, Yinge Li, Z. Shen, Lei Jiang, Jinghui Gao, Guanghui Chen
{"title":"Effect of Blend of Polystyrene on the Temperature Dependence of DC Breakdown Characteristics of Polyethylene","authors":"Lianghong Cao, L. Zhong, Yinge Li, Z. Shen, Lei Jiang, Jinghui Gao, Guanghui Chen","doi":"10.1109/CMD.2018.8535684","DOIUrl":"https://doi.org/10.1109/CMD.2018.8535684","url":null,"abstract":"As one of environment-friendly high voltage direct current (HVDC) insulation materials show good application potential, polymer blends have aroused much attention. One of the central concerns for the application of these material systems lies in the high temperature performance of the materials, which becomes important for the insulation design considering working condition of HVDC cable. In this paper, we investigate DC breakdown strength of low density polyethylene (LDPE)-polystyrene (PS) blends at a series of temperature for 30°C, 50°C, 70°C and 90°C. The results show that at 70°C and 90°C, DC breakdown strengths of the blends are enhanced compared with pure LDPE, and they increase with the increase of PS content. Furthermore, the morphology of these blends was studied by optical microscope, and it is found that PS is dispersed into LDPE in nearly spherical shape with the dimension of several micron meter, and the improvement of high-temperature DC breakdown strength might be ascribed to such a structural modification of blending.","PeriodicalId":6529,"journal":{"name":"2018 Condition Monitoring and Diagnosis (CMD)","volume":"78 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85795811","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}
Huan Niu, Wenfeng Liu, X. Chi, Yin Huang, Shusai Zheng, D. Min, Shengtao Li, Yu Xia, Wen Wang
{"title":"Effects of Hygrothermal Ageing on Breakdown Performance of Polyesterimide Nanocomposites","authors":"Huan Niu, Wenfeng Liu, X. Chi, Yin Huang, Shusai Zheng, D. Min, Shengtao Li, Yu Xia, Wen Wang","doi":"10.1109/CMD.2018.8535812","DOIUrl":"https://doi.org/10.1109/CMD.2018.8535812","url":null,"abstract":"Polyesterimide and its nanocomposites are widely applied in motors and generators. However, the electrical properties of them deteriorated under the hygrothermal environment, which is a critical problem for safe operation of motors and generators in power systems. Therefore, it is urgent to study the mechanism of electrical properties during hygrothermal ageing. In this paper, neat polyesterimide and polyesterimide nanocomposites were prepared. The specimens were exposed in an oven with 100% relative humidity and 80°C for two weeks. The changes of specimen mass were measured to acquire moisture absorption. The breakdown experiment and the thermally stimulated current experiment were conducted. It is found that the trap level decreases after hygrothermal ageing process, which leads to the promoted carrier migration and the deceased breakdown strength. In addition, as the ageing time increases, the reduction proportion of breakdown strength of polyesterimide nanocomposites is smaller than that of neat polyesterimide. It is inferred that the interaction zone induced by nanoparticles, on one hand, increases the deep trap level. On the other hand, the bonding between nanoparticles and the matrix is enhanced by the surface treatment on nanoparticles, resulting in improved property stability of nanocomposites in the hygrothermal ageing.","PeriodicalId":6529,"journal":{"name":"2018 Condition Monitoring and Diagnosis (CMD)","volume":"17 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80082598","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}
Yue Tong, B. Liu, A. Abu‐Siada, Zhenhua Li, Chunyan Li, Binxin Zhu
{"title":"Research on calibration technology for electronic current transformers","authors":"Yue Tong, B. Liu, A. Abu‐Siada, Zhenhua Li, Chunyan Li, Binxin Zhu","doi":"10.1109/CMD.2018.8535787","DOIUrl":"https://doi.org/10.1109/CMD.2018.8535787","url":null,"abstract":"In order to improve the stability and reliability of the electronic current transformer, it needs to be tested regularly. The current research status of electronic current transformer testing technology is analyzed in this paper, and the test project of electronic current transformer is introduced. On the basis of analyzing the existing shortages of off-line calibration, an on-line calibration technology of electronic current transformer is proposed in this paper. Test results show that the technology can effectively simplify the calibration process and reduce the cost of the calibration.","PeriodicalId":6529,"journal":{"name":"2018 Condition Monitoring and Diagnosis (CMD)","volume":"60 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79024418","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}
{"title":"Pattern Recognition of Partial Discharge Image Based on One-dimensional Convolutional Neural Network","authors":"Xiaoqi Wan, Hui Song, Lingen Luo, Zhe Li, G. Sheng, Xiuchen Jiang","doi":"10.1109/CMD.2018.8535761","DOIUrl":"https://doi.org/10.1109/CMD.2018.8535761","url":null,"abstract":"Big data platforms and centers are ubiquitous today where a large amount of unstructured data on site such as images is accumulated. For structured data, partial discharge pattern recognition method has been extensively studied, whereas traditional methods can not be directly applied to unstructured data. To this end, a time-domain waveform pattern recognition method based on one-dimensional convolutional neural network (CNN) is proposed. Image processing techniques are applied to obtain one-dimensional characteristics of the waveform. Based on deep learning, the network is constructed for pattern recognition straight forwardly. Through on site detection and simulation experiments, image data sets of five partial discharge defects are established and comparative experiments are conducted. Experimental results show that the proposed method can successfully perform pattern recognition with applications in work of data mining and data utilization. Under the same complexity, it is also with higher accuracy comparing to two-dimensional CNN. Furthermore, the method autonomously extrapolates features without manual extraction, which achieves low experimental complexity and robustness simultaneously.","PeriodicalId":6529,"journal":{"name":"2018 Condition Monitoring and Diagnosis (CMD)","volume":"206 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77608048","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}