Pub Date : 2024-04-01DOI: 10.1784/insi.2024.66.4.226
Changdong Wu, Liu Rui
With the continuous progress of science and technology, electric power equipment detection systems are developing in the direction of artificial intelligence. To achieve good automatic detection results, a high-quality and speedy algorithm is designed to intelligently detect indoor switchgear components in substations. This proposed method can detect the status of components based on image processing technology, which belongs to the field of condition monitoring. In this paper, the targets to be detected include multi-colour buttons or lights and the ammeters or voltmeters of the electrical switchgear. Two hybrid improved algorithms are used to optimise the you only look once v5s (YOLOv5s) network framework for increasing the detection speed and performance. Firstly, deeper feature map extraction is achieved using HorNet recursive gated convolution to replace the original C3 module for more efficient results. Then, a bidirectional feature pyramid network (BiFPN) algorithm is used to achieve the bidirectional propagation of feature information in the feature pyramid. This method can promote better fusion of feature information at different levels and help to convey feature and location information in the image. Finally, the improved YOLOv5s-BH model is used to detect the targets in substations. The experimental results show that the proposed method provides encouraging detection results for indoor switchgear components in substations.
{"title":"Object detection algorithm for indoor switchgear components in substations based on improved YOLOv5s","authors":"Changdong Wu, Liu Rui","doi":"10.1784/insi.2024.66.4.226","DOIUrl":"https://doi.org/10.1784/insi.2024.66.4.226","url":null,"abstract":"With the continuous progress of science and technology, electric power equipment detection systems are developing in the direction of artificial intelligence. To achieve good automatic detection results, a high-quality and speedy algorithm is designed to intelligently detect indoor\u0000 switchgear components in substations. This proposed method can detect the status of components based on image processing technology, which belongs to the field of condition monitoring. In this paper, the targets to be detected include multi-colour buttons or lights and the ammeters or voltmeters\u0000 of the electrical switchgear. Two hybrid improved algorithms are used to optimise the you only look once v5s (YOLOv5s) network framework for increasing the detection speed and performance. Firstly, deeper feature map extraction is achieved using HorNet recursive gated convolution to replace\u0000 the original C3 module for more efficient results. Then, a bidirectional feature pyramid network (BiFPN) algorithm is used to achieve the bidirectional propagation of feature information in the feature pyramid. This method can promote better fusion of feature information at different levels\u0000 and help to convey feature and location information in the image. Finally, the improved YOLOv5s-BH model is used to detect the targets in substations. The experimental results show that the proposed method provides encouraging detection results for indoor switchgear components in substations.","PeriodicalId":506650,"journal":{"name":"Insight - Non-Destructive Testing and Condition Monitoring","volume":"583 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140757778","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 : 2024-04-01DOI: 10.1784/insi.2024.66.4.215
Jing Chai, Xiaoqiang Zhao, Jie Cao
Although intelligent fault diagnosis has achieved good results, the application in practical engineering scenarios is still unsatisfactory due to the lack of sufficient fault signals to support the training of the diagnosis methods and the difficulty of extracting sensitive fault features from the original signals. To address the problem that small-sample fault data limit the diagnostic performance of traditional neural networks, a multi-scale residual parametric convolutional capsule network (MRCCCN) for small-sample bearing fault diagnosis is proposed. In the MRCCCN, the input fault information is averaged and segmented multiple times and then the initial features of the multi-segmented input are extracted by residual parameterised convolution. Then, the multi-branch features are fused and fed into an improved parametric capsule network to further extract fault features and store feature information using dynamic routing. The performance of the MRCCCN is validated using the Case Western Reserve University (CWRU) rolling bearing dataset and the Paderborn University rolling bearing dataset of vibration signals and compared with some advanced deep learning methods. The comparison results show that the proposed MRCCCN is able to accurately diagnose faults under small-sample conditions and still has significant diagnostic performance in small-sample variable noise tests.
{"title":"Small-sample fault diagnosis study of rolling bearings based on a residual parameterised convolutional capsule network","authors":"Jing Chai, Xiaoqiang Zhao, Jie Cao","doi":"10.1784/insi.2024.66.4.215","DOIUrl":"https://doi.org/10.1784/insi.2024.66.4.215","url":null,"abstract":"Although intelligent fault diagnosis has achieved good results, the application in practical engineering scenarios is still unsatisfactory due to the lack of sufficient fault signals to support the training of the diagnosis methods and the difficulty of extracting sensitive fault features\u0000 from the original signals. To address the problem that small-sample fault data limit the diagnostic performance of traditional neural networks, a multi-scale residual parametric convolutional capsule network (MRCCCN) for small-sample bearing fault diagnosis is proposed. In the MRCCCN, the\u0000 input fault information is averaged and segmented multiple times and then the initial features of the multi-segmented input are extracted by residual parameterised convolution. Then, the multi-branch features are fused and fed into an improved parametric capsule network to further extract\u0000 fault features and store feature information using dynamic routing. The performance of the MRCCCN is validated using the Case Western Reserve University (CWRU) rolling bearing dataset and the Paderborn University rolling bearing dataset of vibration signals and compared with some advanced\u0000 deep learning methods. The comparison results show that the proposed MRCCCN is able to accurately diagnose faults under small-sample conditions and still has significant diagnostic performance in small-sample variable noise tests.","PeriodicalId":506650,"journal":{"name":"Insight - Non-Destructive Testing and Condition Monitoring","volume":"26 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140778050","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 : 2024-04-01DOI: 10.1784/insi.2024.66.4.240
M. S. Safizadeh, R. Dardmand
A monitoring system for induction motors (IMs) is essential for most industrial plants. Bearing faults and shaft misalignment are common mechanical defects in induction motors. Since one fault could cause another fault in the system, multiple faults can occur simultaneously and change the vibration (electrical) behaviour of the induction motors from that of a single fault condition. This paper aims to identify two common faults (shaft misalignment and defective bearing) simultaneously in IMs using data fusion of vibration and current measurements. Sensor fusion of accelerometer and Hall-effect sensor signals is used to combine the vibration and current signals. The proposed method is applied via a laboratory test-rig based on data fusion to detect multiple defects simultaneously in induction motors. Then, by extracting the important features using a principal component analysis (PCA) algorithm, the K-nearest neighbours (KNN) classification algorithm is used to detect defects and make decisions. The results show that the fusion of both current and vibration signal analyses significantly improves the efficiency and reliability of multiple fault detection. Also, bispectrum analysis of the current signal is highly sensitive to misalignment and can be an effective method for detecting such faults.
感应电机（IM）监控系统对于大多数工业设备来说都是必不可少的。轴承故障和轴不对中是感应电机常见的机械故障。由于一个故障可能会导致系统中出现另一个故障，因此多个故障可能会同时发生，并改变感应电机的振动（电气）性能，使其与单个故障条件下的振动（电气）性能不同。本文旨在利用振动和电流测量数据融合技术，同时识别感应电机中的两种常见故障（轴错位和轴承缺陷）。加速度传感器和霍尔效应传感器信号的传感器融合被用来结合振动和电流信号。所提出的方法通过基于数据融合的实验室测试平台进行应用，可同时检测感应电机中的多个缺陷。然后，通过使用主成分分析 (PCA) 算法提取重要特征，使用 K 近邻 (KNN) 分类算法检测缺陷并做出决策。结果表明，融合电流和振动信号分析可显著提高多重故障检测的效率和可靠性。此外，电流信号的双谱分析对不对中高度敏感，是检测此类故障的有效方法。
{"title":"Diagnosing simultaneous bearing and misalignment faults in an induction motor using sensor fusion","authors":"M. S. Safizadeh, R. Dardmand","doi":"10.1784/insi.2024.66.4.240","DOIUrl":"https://doi.org/10.1784/insi.2024.66.4.240","url":null,"abstract":"A monitoring system for induction motors (IMs) is essential for most industrial plants. Bearing faults and shaft misalignment are common mechanical defects in induction motors. Since one fault could cause another fault in the system, multiple faults can occur simultaneously and change\u0000 the vibration (electrical) behaviour of the induction motors from that of a single fault condition. This paper aims to identify two common faults (shaft misalignment and defective bearing) simultaneously in IMs using data fusion of vibration and current measurements. Sensor fusion of accelerometer\u0000 and Hall-effect sensor signals is used to combine the vibration and current signals. The proposed method is applied via a laboratory test-rig based on data fusion to detect multiple defects simultaneously in induction motors. Then, by extracting the important features using a principal component\u0000 analysis (PCA) algorithm, the K-nearest neighbours (KNN) classification algorithm is used to detect defects and make decisions. The results show that the fusion of both current and vibration signal analyses significantly improves the efficiency and reliability of multiple fault detection.\u0000 Also, bispectrum analysis of the current signal is highly sensitive to misalignment and can be an effective method for detecting such faults.","PeriodicalId":506650,"journal":{"name":"Insight - Non-Destructive Testing and Condition Monitoring","volume":"48 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140765733","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 : 2024-04-01DOI: 10.1784/insi.2024.66.4.232
Huihui Wang, Zhe Wu, Qi Li, Yanping Cui, Suxiao Cui
The vibration signal of planetary gearboxes under variable speed conditions shows non-stationary characteristics, indicating that fault diagnosis has become more complex and challenging. In order to more accurately diagnose faults in planetary gearboxes under variable speed conditions, a new method is proposed based on the angular domain Gramian angular difference field (ADGADF) and Swin Transformer. This method initially employs the chirplet path pursuit (CPP) algorithm to fit the speed curve of the original time-domain signal and then combines the speed curve with computed order tracking (COT) to achieve equal angle resampling of the time-domain signal, obtaining a stationary signal in the angular domain. On the basis of the above, the angular domain signal is creatively encoded into the two-dimensional images using the Gramian angular field (GAF), which accurately represents the fault characteristics of the original signal. Finally, the Swin Transformer network, with efficient global feature extraction capability, is used to learn advanced features from the images, achieving accurate fault recognition and classification. The proposed method is verified by experiment on the planetary gearbox and its performance is compared with several common coding methods and intelligent diagnosis algorithms. The experimental results show that the proposed method reaches an accuracy of up to 99.8%. In addition, its performance in accuracy, precision, recall, F1-score and the confusion matrix is superior to traditional diagnostic methods. It also offers the advantage of strong robustness.
{"title":"A fault diagnosis method for variable speed planetary gearbox based on ADGADF and Swin Transformer","authors":"Huihui Wang, Zhe Wu, Qi Li, Yanping Cui, Suxiao Cui","doi":"10.1784/insi.2024.66.4.232","DOIUrl":"https://doi.org/10.1784/insi.2024.66.4.232","url":null,"abstract":"The vibration signal of planetary gearboxes under variable speed conditions shows non-stationary characteristics, indicating that fault diagnosis has become more complex and challenging. In order to more accurately diagnose faults in planetary gearboxes under variable speed conditions,\u0000 a new method is proposed based on the angular domain Gramian angular difference field (ADGADF) and Swin Transformer. This method initially employs the chirplet path pursuit (CPP) algorithm to fit the speed curve of the original time-domain signal and then combines the speed curve with computed\u0000 order tracking (COT) to achieve equal angle resampling of the time-domain signal, obtaining a stationary signal in the angular domain. On the basis of the above, the angular domain signal is creatively encoded into the two-dimensional images using the Gramian angular field (GAF), which accurately\u0000 represents the fault characteristics of the original signal. Finally, the Swin Transformer network, with efficient global feature extraction capability, is used to learn advanced features from the images, achieving accurate fault recognition and classification. The proposed method is verified\u0000 by experiment on the planetary gearbox and its performance is compared with several common coding methods and intelligent diagnosis algorithms. The experimental results show that the proposed method reaches an accuracy of up to 99.8%. In addition, its performance in accuracy, precision, recall,\u0000 F1-score and the confusion matrix is superior to traditional diagnostic methods. It also offers the advantage of strong robustness.","PeriodicalId":506650,"journal":{"name":"Insight - Non-Destructive Testing and Condition Monitoring","volume":"62 23","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140784224","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 : 2024-04-01DOI: 10.1784/insi.2024.66.4.205
Yumei Ye, Cheng Chen, Jinchao Ma, Zhangyong Yu
The dynamic responses of key locations are important inputs for the life and reliability assessment of spacecraft structures. Due to the limited sensing resources, most critical responses are difficult to measure directly. A structural dynamic response reconstruction method is necessary. The responses of target locations can be reconstructed based on the empirical mode decomposition (EMD) of measured signals and the modal superposition. However, the structural modal information contained in the measured signal of a single sensor is limited, affecting the reconstruction accuracy. In this paper, a response reconstruction method based on multi-sensor data fusion is proposed. It is applied to a main load-bearing structure of a spacecraft and its typical components to verify its strain response reconstruction effect under random vibration loads. The experimental results show that multi-sensor data fusion improves the strain reconstruction accuracy. The maximum reduction in reconstruction error is from 8.7% to 1.3%. The reconstruction accuracy is further improved with the increase in the number of sensors. The optimal weighted fusion strategy for this problem is the weights defined by the Euclidean distance (EUC) or the dynamic time warping distance (DTW). The fusion results show a better performance with the increase in the power of the defined distance. The proposed multi-sensor fusion method improves the reconstruction accuracy via supplementing structural information to each other and eliminating the instability of single measured signals. More accurate dynamic responses via reconstruction reduce the large input uncertainty in life prediction and lay the foundation for building structural digital twins and managing structural health more effectively.
{"title":"Multi-sensor data fusion reconstruction method for vibration dynamic responses of aerospace structures","authors":"Yumei Ye, Cheng Chen, Jinchao Ma, Zhangyong Yu","doi":"10.1784/insi.2024.66.4.205","DOIUrl":"https://doi.org/10.1784/insi.2024.66.4.205","url":null,"abstract":"The dynamic responses of key locations are important inputs for the life and reliability assessment of spacecraft structures. Due to the limited sensing resources, most critical responses are difficult to measure directly. A structural dynamic response reconstruction method is necessary.\u0000 The responses of target locations can be reconstructed based on the empirical mode decomposition (EMD) of measured signals and the modal superposition. However, the structural modal information contained in the measured signal of a single sensor is limited, affecting the reconstruction accuracy.\u0000 In this paper, a response reconstruction method based on multi-sensor data fusion is proposed. It is applied to a main load-bearing structure of a spacecraft and its typical components to verify its strain response reconstruction effect under random vibration loads. The experimental results\u0000 show that multi-sensor data fusion improves the strain reconstruction accuracy. The maximum reduction in reconstruction error is from 8.7% to 1.3%. The reconstruction accuracy is further improved with the increase in the number of sensors. The optimal weighted fusion strategy for this problem\u0000 is the weights defined by the Euclidean distance (EUC) or the dynamic time warping distance (DTW). The fusion results show a better performance with the increase in the power of the defined distance. The proposed multi-sensor fusion method improves the reconstruction accuracy via supplementing\u0000 structural information to each other and eliminating the instability of single measured signals. More accurate dynamic responses via reconstruction reduce the large input uncertainty in life prediction and lay the foundation for building structural digital twins and managing structural health\u0000 more effectively.","PeriodicalId":506650,"journal":{"name":"Insight - Non-Destructive Testing and Condition Monitoring","volume":"49 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140782086","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}
Steel is widely used in the aerospace, machinery and automotive industries. Surface defects not only have a negative impact on the appearance of steel but also significantly reduce its wear resistance, high temperature resistance, corrosion resistance and fatigue strength. Therefore, the detection of steel surface defects is very important to improve the quality of steel production. The limited availability of surface defect samples in the industrial sector poses significant challenges for the accurate detection of defects in high-quality materials. In addition, the existing defect detection model is highly complex and not easy to deploy. To solve this problem, a lightweight defect detection network suitable for steel defects is proposed. The cross-layer feature fusion (CFF) in the design enables effective utilisation of multi-layer semantic features, facilitating the detection of small defects in steel. Secondly, a new loss function is designed to make up for the problems of small data volume and uneven data distribution. The experimental results demonstrate that the steel surface defect detection method proposed in this paper achieves the highest detection performance on widely used public datasets such as RSDDS, NEUS and NRSD-CR(test), while maintaining the lowest model complexity.
{"title":"A lightweight image-level segmentation method for steel surface defects based on cross-layer feature fusion","authors":"Peng Wang, Liangliang Li, Baolin Sha, Xiaoyan Li, Zhigang Lü","doi":"10.1784/insi.2024.66.3.167","DOIUrl":"https://doi.org/10.1784/insi.2024.66.3.167","url":null,"abstract":"Steel is widely used in the aerospace, machinery and automotive industries. Surface defects not only have a negative impact on the appearance of steel but also significantly reduce its wear resistance, high temperature resistance, corrosion resistance and fatigue strength. Therefore,\u0000 the detection of steel surface defects is very important to improve the quality of steel production. The limited availability of surface defect samples in the industrial sector poses significant challenges for the accurate detection of defects in high-quality materials. In addition, the existing\u0000 defect detection model is highly complex and not easy to deploy. To solve this problem, a lightweight defect detection network suitable for steel defects is proposed. The cross-layer feature fusion (CFF) in the design enables effective utilisation of multi-layer semantic features, facilitating\u0000 the detection of small defects in steel. Secondly, a new loss function is designed to make up for the problems of small data volume and uneven data distribution. The experimental results demonstrate that the steel surface defect detection method proposed in this paper achieves the highest\u0000 detection performance on widely used public datasets such as RSDDS, NEUS and NRSD-CR(test), while maintaining the lowest model complexity.","PeriodicalId":506650,"journal":{"name":"Insight - Non-Destructive Testing and Condition Monitoring","volume":"3 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140268078","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 : 2024-03-01DOI: 10.1784/insi.2024.66.3.141
R. A. Smith, R. B. Tayong, L. J. Nelson, M. Mienczakowski, P. D. Wilcox
Due to their high strength-to-weight ratio, composite materials are now in use in many high-stress applications, particularly where light weight is also a requirement. In these situations, the detrimental knock-down in mechanical strength due to an out-of-plane wrinkle defect can have serious consequences and is the reason for a requirement to rapidly detect any such wrinkles at manufacture. Unfortunately, current ultrasonic inspection techniques used for quality control at manufacture are not sensitive enough to detect these wrinkles above coherent structural noise variations. This paper exploits the ply resonance that is a characteristic of multi-layer structures to generate two new metrics for both detection and classification of out-of-plane wrinkles, due to their perturbations of the ply spacing. These can be measured at every location on a structure using the instantaneous frequency, which is the rate of change of phase in the pulse-echo ultrasonic response. The proposed two new metrics for detection and classification of wrinkles are mean spacing and spacing difference and they can be applied to each waveform in real time, as it is acquired. Use of an analytical model to predict the ultrasonic response of the structure has allowed an understanding of how these metrics will be affected by various wrinkle types and how they can not only detect wrinkles but also classify the type of wrinkle and provide an approximate indication of severity. Three main types of wrinkle are considered: classic wrinkles near the mid-plane of a structure, back-surface wrinkles formed from a resin bulge near the back of a structure and folded wrinkles where several plies can be folded over completely in the bulk of the structure. Both simulations and experimental results demonstrate the effectiveness of these metrics on various types of structure, including carbon-fibre and hybrid carbon/glass-fibre composites with a range of ply thicknesses and wrinkle types.
{"title":"Ultrasonic metrics for large-area rapid wrinkle detection and classification in composites","authors":"R. A. Smith, R. B. Tayong, L. J. Nelson, M. Mienczakowski, P. D. Wilcox","doi":"10.1784/insi.2024.66.3.141","DOIUrl":"https://doi.org/10.1784/insi.2024.66.3.141","url":null,"abstract":"Due to their high strength-to-weight ratio, composite materials are now in use in many high-stress applications, particularly where light weight is also a requirement. In these situations, the detrimental knock-down in mechanical strength due to an out-of-plane wrinkle defect can have\u0000 serious consequences and is the reason for a requirement to rapidly detect any such wrinkles at manufacture. Unfortunately, current ultrasonic inspection techniques used for quality control at manufacture are not sensitive enough to detect these wrinkles above coherent structural noise variations.\u0000 This paper exploits the ply resonance that is a characteristic of multi-layer structures to generate two new metrics for both detection and classification of out-of-plane wrinkles, due to their perturbations of the ply spacing. These can be measured at every location on a structure using the\u0000 instantaneous frequency, which is the rate of change of phase in the pulse-echo ultrasonic response. The proposed two new metrics for detection and classification of wrinkles are mean spacing and spacing difference and they can be applied to each waveform in real time, as it is acquired. Use\u0000 of an analytical model to predict the ultrasonic response of the structure has allowed an understanding of how these metrics will be affected by various wrinkle types and how they can not only detect wrinkles but also classify the type of wrinkle and provide an approximate indication of severity.\u0000 Three main types of wrinkle are considered: classic wrinkles near the mid-plane of a structure, back-surface wrinkles formed from a resin bulge near the back of a structure and folded wrinkles where several plies can be folded over completely in the bulk of the structure. Both simulations\u0000 and experimental results demonstrate the effectiveness of these metrics on various types of structure, including carbon-fibre and hybrid carbon/glass-fibre composites with a range of ply thicknesses and wrinkle types.","PeriodicalId":506650,"journal":{"name":"Insight - Non-Destructive Testing and Condition Monitoring","volume":"471 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140281566","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 : 2024-03-01DOI: 10.1784/insi.2024.66.3.159
Hai Gong, Jia Liu, Tao Zhang, Xuan Cao, Long Zhang
The accuracy of defect localisation and its size quantification is poor in the detection of internal defects of cylindrical components using the ultrasonic Amplituden und Laufzeit Orts-Kurven (ALOK) method. The influence of acoustic beam spread is not taken into consideration in the ultrasonic ALOK method, resulting in difficulties with the precise characterisation of the defect state. To address this, the relationship between the acoustic distance, amplitude, ultrasonic frequency, size and depth of hole defects was studied. The acoustic distance curve and the amplitude curve were fitted and then the localisation model of the defect was obtained. The acoustic beam spreading angle and echo sound pressure were introduced and then the size quantification model for defects was acquired based on principal component analysis (PCA). Both the simulated and experimental results show that the modified ALOK algorithm improved the detection accuracy of the defect location and its size and the relative error of defect sizing decreased by more than 35% compared with the original algorithm.
{"title":"Accuracy improvement of inner defects of cylindrical components using ultrasonic detection with modified ALOK method","authors":"Hai Gong, Jia Liu, Tao Zhang, Xuan Cao, Long Zhang","doi":"10.1784/insi.2024.66.3.159","DOIUrl":"https://doi.org/10.1784/insi.2024.66.3.159","url":null,"abstract":"The accuracy of defect localisation and its size quantification is poor in the detection of internal defects of cylindrical components using the ultrasonic Amplituden und Laufzeit Orts-Kurven (ALOK) method. The influence of acoustic beam spread is not taken into consideration in the\u0000 ultrasonic ALOK method, resulting in difficulties with the precise characterisation of the defect state. To address this, the relationship between the acoustic distance, amplitude, ultrasonic frequency, size and depth of hole defects was studied. The acoustic distance curve and the amplitude\u0000 curve were fitted and then the localisation model of the defect was obtained. The acoustic beam spreading angle and echo sound pressure were introduced and then the size quantification model for defects was acquired based on principal component analysis (PCA). Both the simulated and experimental\u0000 results show that the modified ALOK algorithm improved the detection accuracy of the defect location and its size and the relative error of defect sizing decreased by more than 35% compared with the original algorithm.","PeriodicalId":506650,"journal":{"name":"Insight - Non-Destructive Testing and Condition Monitoring","volume":"23 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140268488","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}
In this study, a WC-Fe-based coating is prepared on a 45 steel substrate utilising laser cladding technology. To optimise the composition of the Fe-based alloy powder, a thorough analysis of the cracks observed during the formation of the cladding layer is conducted. Elemental control of the WC-Fe-based alloy powder is employed to mitigate issues such as porosity and slagging, consequently reducing the susceptibility to cracking. The optimised WC-Fe-based alloy coating exhibits enhanced wear and abrasion resistance when compared to the widely used Ni45 coating. Microstructural investigations reveal that both coatings feature dendrites, cellular crystals and equiaxial crystals; however, the WC-Fe coating displays a finer and denser microstructure, highlighting its superior characteristics. Hardness and abrasion resistance tests demonstrate the exceptional performance of the WC-Fe-based coatings, having approximately three times the hardness of the substrate and a wear rate approximately seven times lower than that of the substrate. The friction coefficient remains consistently stable for the WC-Fe-based coatings at approximately 0.4, indicative of remarkable friction reduction and abrasion resistance.
{"title":"Optimisation and wear performance analysis of laser-cladded WC-Fe-based coating","authors":"Youhong Cao, Ziqiang Yin, Y. Zhan, Shouren Wang, Daosheng Wen, Gaoqi Wang, Dianxiu Xia, Yitong Li, Dongxu Hou","doi":"10.1784/insi.2024.66.3.153","DOIUrl":"https://doi.org/10.1784/insi.2024.66.3.153","url":null,"abstract":"In this study, a WC-Fe-based coating is prepared on a 45 steel substrate utilising laser cladding technology. To optimise the composition of the Fe-based alloy powder, a thorough analysis of the cracks observed during the formation of the cladding layer is conducted. Elemental control\u0000 of the WC-Fe-based alloy powder is employed to mitigate issues such as porosity and slagging, consequently reducing the susceptibility to cracking. The optimised WC-Fe-based alloy coating exhibits enhanced wear and abrasion resistance when compared to the widely used Ni45 coating. Microstructural\u0000 investigations reveal that both coatings feature dendrites, cellular crystals and equiaxial crystals; however, the WC-Fe coating displays a finer and denser microstructure, highlighting its superior characteristics. Hardness and abrasion resistance tests demonstrate the exceptional performance\u0000 of the WC-Fe-based coatings, having approximately three times the hardness of the substrate and a wear rate approximately seven times lower than that of the substrate. The friction coefficient remains consistently stable for the WC-Fe-based coatings at approximately 0.4, indicative of remarkable\u0000 friction reduction and abrasion resistance.","PeriodicalId":506650,"journal":{"name":"Insight - Non-Destructive Testing and Condition Monitoring","volume":"252 18","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140275339","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 : 2024-03-01DOI: 10.1784/insi.2024.66.3.174
Chen Qian, Jun Gao, Xing Shao, Cui-Xiang Wang, Jianhua Yuan
Aiming to address the problem that faults in rolling bearings make effective fault diagnosis difficult under small-sample and varying working conditions, this paper proposes a new fault diagnosis method for rolling bearings that monitors their vibration signals and is based on an improved deep residual Siamese neural network, called a WDRCNN. Firstly, the Siamese neural network is applied to extract features with shared weights to achieve an expansion in the number of fault samples. Then, multiple residual blocks are used to extract deeper feature information and effectively alleviate the problem of overfitting. In addition, the attention mechanism is employed to assign weights to the feature information to reduce the interference of redundant features. Finally, the Euclidean distance between the sample pairs is calculated to determine the similarity of the sample pairs and to classify bearing faults for end-to-end bearing fault diagnosis. The experimental results demonstrate that the WDRCNN achieves an average accuracy of 96.31% under different operating conditions. Even when only 90 training samples are available, the WDRCNN achieves an accuracy of over 93%.
{"title":"Bearing fault diagnosis method based on improved deep residual Siamese neural network","authors":"Chen Qian, Jun Gao, Xing Shao, Cui-Xiang Wang, Jianhua Yuan","doi":"10.1784/insi.2024.66.3.174","DOIUrl":"https://doi.org/10.1784/insi.2024.66.3.174","url":null,"abstract":"Aiming to address the problem that faults in rolling bearings make effective fault diagnosis difficult under small-sample and varying working conditions, this paper proposes a new fault diagnosis method for rolling bearings that monitors their vibration signals and is based on an improved\u0000 deep residual Siamese neural network, called a WDRCNN. Firstly, the Siamese neural network is applied to extract features with shared weights to achieve an expansion in the number of fault samples. Then, multiple residual blocks are used to extract deeper feature information and effectively\u0000 alleviate the problem of overfitting. In addition, the attention mechanism is employed to assign weights to the feature information to reduce the interference of redundant features. Finally, the Euclidean distance between the sample pairs is calculated to determine the similarity of the sample\u0000 pairs and to classify bearing faults for end-to-end bearing fault diagnosis. The experimental results demonstrate that the WDRCNN achieves an average accuracy of 96.31% under different operating conditions. Even when only 90 training samples are available, the WDRCNN achieves an accuracy\u0000 of over 93%.","PeriodicalId":506650,"journal":{"name":"Insight - Non-Destructive Testing and Condition Monitoring","volume":"716 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140281439","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：