Fault Identification Method Research Articles

Wire bond contact defect identification in battery modules of electric vehicles using pulses and differential voltage analysis

Automotive battery packs for electromobility applications consist of a large number of interconnected battery cells. Different cell-to-busbar joining techniques are utilized, with cylindrical cells frequently being contacted using wire bonding. Failure of individual connections can occur due to strong vibrations during operation and improper stress, making detection by the battery management system a necessity. This study investigates the identification of an electrical wire bond failure in a state-of-the-art electric vehicle module of a Lucid Air with 10 series-connected and 30 parallel-connected cells (10s30p). Four individual cells were characterized extensively in order to generate a simulation model taking into account parameter scatter. The failure case under investigation was simulatively incorporated in one parallel circuit and subsequently replicated in experimental validation measurements at the module level. The results show that this defect can be detected using pulses of C/3 or higher currents at various states of charge. An even more robust detection is achieved using differential voltage analysis of constant current C/20 discharge voltage trajectories. This defect identification method does not require any additional measurement sensors beyond the voltage taps and sensors provided by the manufacturer – with one voltage sensor per parallel circuit – and can therefore be implemented during electric vehicle usage, e.g. at dedicated service checks. A discussion on the applicability and scalability as well as the limitations of the method is provided. All measurement data of the state-of-the-art Lucid battery system is available as open source alongside the article.

Surface defect identification based on broadband laser-generated Rayleigh wave with wavenumber filtering

As a non-contact, couplant-free and nondestructive technique, the laser ultrasonic technology has great potential for detecting surface defects. In this paper, we propose a surface defect identification method based on broadband laser-generated Rayleigh wave with wavenumber filtering in an area scanning mode. Firstly, a particular lowpass filter is constructed in frequency-wavenumber domain to extract the scattered wave generated by the defects, and then a surface defect image can be reconstructed based on the broadband scattered wave wavenumbers. Secondly, a threshold denoising method is employed to enhance the signal-to-noise ratio and improve the image sharpness. Thirdly, the experimental validation is carried out, in which a laser ultrasonic detection system is used to detect the surface defects of aluminum alloy specimens and identify their different parameters. The experimental results verify that the proposed method can identify the location, size and orientation of surface defects effectively, meanwhile, its imaging effect shows significantly superior to that of the conventional reflected wave energy and standing wave energy methods. Furthermore, the correlation between maximum local scattered wave energy and the depth of defects is found, which can characterize the severity of the surface defects.

Analysis and Detection of Power System Network Faults with Wavelet Transform

Fault detection technique is important for enhancing protection, stability, reliability and continuity of supply. There are many fault detection techniques implemented in power system such as Fourier transform, wavelet transform, neural networks, etc. This research presents the fault identification and analysis using wavelet transform method as well as estimation of circuit breaker rating. The discrete wavelet transform is implemented for the fault identification in five bus system. Various types of line and ground faults have been considered and studied using Daubechies wavelet function. The first level decomposition is used for the fault analysis. The maximum detailed coefficients for various faults currents are analysed for the fault identification. The wavelet transform algorithm is implemented using MATLAB programming. The five-bus system is modelled in MATLAB Simulink and various faults are simulated. The switching time of fault is taken as 0.05 to 0.1 seconds. The faults have been studied at different points in the system. The fault identification method gives accurate results for different types of faults. The load flow analysis is also done for five bus system and appropriate rating of circuit breaker is estimated.

A Multilabel Approach for Fault Detection and Classification of Transmission Lines using Binary Relevance

In Contemporary automation systems, Fault detection and classification of electrical transmission lines in grid systems are given top priority. The broad application of Machine Learning (ML) methods has enabled the substitute of conventional methods of fault identification and classification. These methods are more effective ones that can identify faults early on using a significant quantity of sensory data. So detecting simultaneous failures is difficult in the context of distracting the noise and several faults in the transmission lines. This study contributes by offering a unique way for concurrently detecting and classifying several faults using a multilabel classification approach based on binary relevance classifiers. The proposed binary relevance multilabel detection and classification models’ performances are examined. Under both ideal and problematic circumstances, faults in the dataset are collected. A variety of multilabel fault types detection and classification determines the suggested method’s effectiveness.

Study on blade fault diagnosis of free flying UAV based on multiparameter and deep learning method

With the widespread application of UAV (UAV) in various fields, more and more attention has been paid to the operation status monitoring and fault diagnosis of UAV. During the use of UAV, the motors, blades, connectors and other components may inevitably experience wear, fatigue, and breakage, which are difficult to directly monitor through sensors. Therefore, a fault identification method based on one-dimensional convolutional neural network (1D-CNN) is proposed to provide ideas for the research on the mechanical fault diagnosis of UAV. A Bluetooth wireless acceleration-attitude sensor is used to collect the acceleration, angular velocity and angle of the free flying UAV in X, Y, and Z directions. With these characteristic parameters as sample data, fault identification can be implemented using deep learning model. Besides, to deal with over-fitting, a data reconstruction method of partition sampling is proposed. By comparing different input parameters and optimization functions, we found that when using multi-parameter + RMSProp optimization, the recognition accuracy reaches 98%. In addition, a comparative analysis is carried out using shallow neural network PNN and SVM methods, and the results show that the proposed 1D-CNN model outperforms both shallow neural networks and traditional machine learning methods.

Attention-Guided Multitask Learning for Surface Defect Identification

Surface defect identification is an essential task in the industrial quality control process, in which visual checks are conducted on a manufactured product to ensure that it meets quality standards. Convolutional Neural Network (CNN) based surface defect identification method has proven to outperform traditional image processing techniques. However, the real-world surface defect datasets are limited in size due to the expensive data generation process and the rare occurrence of defects. To address this issue, this paper presents a method for exploiting auxiliary information beyond the primary labels to improve the generalization ability of surface defect identification tasks. Considering the correlation between pixel level segmentation masks, object level bounding boxes and global image level classification labels, we argue that jointly learning features of the related tasks can improve the performance of surface defect identification tasks. This paper proposes a framework named Defect-Aux-Net, based on multi-task learning with attention mechanisms that exploit the rich additional information from related tasks with the goal of simultaneously improving robustness and accuracy of the CNN based surface defect identification. We conducted a series of experiments with the proposed framework. The experimental results showed that the proposed method can significantly improve the performance of state-of-the-art models while achieving an overall accuracy of 97.1%, Dice score of 0.926 and mAP of 0.762 on defect classification, segmentation and detection tasks.

A new method for fault identification of T-connection transmission line based on multi-scale traveling wave reactive power and random forest.

Though the traditional fault diagnosis method of T-connected transmission lines can identify the faults inside and outside the area, it can not identify the specific branches. To improve the accuracy and reliability of fault diagnosis of T-connection transmission lines, a new method is proposed to identify specific faulty branches of T-connection transmission lines based on multi-scale traveling wave reactive power and random forest. Based on the S-transform, the mean and sum ratios of the corresponding short-time series traveling wave reactive powers of each two traveling wave protection units at multiple frequencies are calculated respectively to form the fault feature vector sample set of the T-connection transmission line. A random forest fault branch identification model is established, and it is trained and tested by the fault feature sample set of T-connection transmission line to identify the fault branch. The simulation results show that the proposed algorithm can identify the branch where the fault is located inside and outside the protection zone of T-connection transmission line quickly and accurately under various working conditions. This method also shows good performance to identify faults even under the situation of CT saturation, noise influence and data loss.

Hybrid Method with Parallel-Factor Theory, a Support Vector Machine, and Particle Filter Optimization for Intelligent Machinery Failure Identification

Here, a novel hybrid method of intelligent fault identification within complex mechanical systems was proposed using parallel-factor (PARAFAC) theory and adaptive particle swarm optimization (APSO) for a support vector machine (SVM). The parallel-factor multi-scale analysis theory was studied to reconstruct tensor feature information based on a three-dimensional matrix for time, frequency, and spatial vectors. A multi-scale wavelet analysis was used to transform the original multi-channel experimental data acquired from a gearbox into a three-dimensional feature matrix of the multi-level structure. The optimal correspondence among the two-dimensional feature signals in the frequency and time domains for the different fault modes was established by the PARAFAC theory. An intelligent APSO algorithm was developed to obtain the optimal parameter structures of an SVM classifier. A comparison with the existing time–frequency analysis method showed that the proposed hybrid PARAFAC-PSO-SVM diagnosis model effectively eliminated the redundant information in the multi-dimensional tensor features but retained the important components. The PARAFAC-APSO-SVM hybrid diagnostic model achieved fast, accurate, and simple fault-classification and identification results, and could provide theoretical support for the application of the PARAFAC theory to complex mechanical fault diagnosis.

Intelligent Fault Diagnosis Methods for Hydraulic Piston Pumps: A Review

As the modern industry rapidly advances toward digitalization, networking, and intelligence, intelligent fault diagnosis technology has become a necessary measure to ensure the safe and stable operation of mechanical equipment and effectively avoid major disaster accidents and huge economic losses caused by mechanical equipment failure. As the “power heart” of hydraulic transmission systems, hydraulic piston pumps (HPPs) occupy an important position in aerospace, navigation, national defense, industry, and many other high-tech fields due to their high-rated pressure, compact structure, high efficiency, convenient flow regulation, and other advantages. Faults in HPPs can create serious hazards. In this paper, the research on fault recognition technology for HPPs is reviewed. Firstly, the existing fault diagnosis methods are described, and the typical fault types and mechanisms of HPPs are introduced. Then, the current research achievements regarding fault diagnosis in HPPs are summarized based on three aspects: the traditional intelligent fault diagnosis method, the modern intelligent fault diagnosis method, and the combined intelligent fault diagnosis method. Finally, the future development trend of fault identification methods for HPPs is discussed and summarized. This work provides a reference for developing intelligent, efficient, and accurate fault recognition methods for HPPs. Moreover, this review will help to increase the safety, stability, and reliability of HPPs and promote the implementation of hydraulic transmission technology in the era of intelligent operation and maintenance.

Compound faults identification of rolling bearing based on one-dimensional mixed binary pattern

To address the difficulty in extracting the characteristics of combined failure of rolling bearings, a novel fault identification method, one-dimensional mixed binary pattern (1D-MBP), is proposed. Firstly, regarding that variance can better highlight the partial weak failure information of sequence than median, the binarization of vibration signals based on one-dimensional local binary pattern (1D-LBP) is carried out with variance as criterion. Meanwhile, binarization sequence is converted to decimal sequence as the local conversion signal (LCS). Secondly, considering that failure information of rolling bearings is reflected in partial and global texture, the paper proposed the method of gaining global weighted mean value by weighting partial mean value with partial energy. Binarize vibration signals based on one-dimensional global binary pattern (1D-GBP) with obtained global weighted mean value as criterion and convert the obtained binarized sequence into decimal as the global conversion signal (GCS). Thirdly, signals are reconstructed by obtained LCS and GCS to get 1D-MBP signal. Finally, combined failure types of bearing can be identified from 1D-MBP signals based on TEAGER energy spectrum (TES). The result indicates that the 1D-MBP not only can effectively control noise components in vibration signal but also can precisely identify the combined failure types of rolling bearings.

A Mechanical Defect Localization and Identification Method for High-Voltage Circuit Breakers Based on the Segmentation of Vibration Signals and Extraction of Chaotic Features.

To address the problem of mechanical defect identification in a high-voltage circuit breaker (HVCB), this paper studies the circuit breaker vibration signal and proposes a method of feature extraction based on phase-space reconstruction of the vibration substages. To locate mechanical defects in circuit breakers, vibration signals are divided into different substages according to the time sequence of the parts of the circuit breakers. The largest Lyapunov exponent (LLE) of the vibration signals' substages is calculated, and then the substages are reconstructed in high-dimensional phase space. The geometric features of the phase trajectory mean center distance (MCD) and vector diameter offset (VDO) are calculated, and the LLE, MCD, and VDO are selected as the three fault identification features of the vibration substages. The eigenvalue anomaly rate of each substage of the vibration signal under defect state are calculated and analyzed to locate the vibration substage of the mechanical defect. Finally, a fault diagnosis model is constructed by a support vector machine (SVM), and the common mechanical defects of circuit breakers simulated in the laboratory are effectively identified.

Fault identification method based on generative adversarial network in distributed acoustic sensing

With the rapid development of machine learning and deep learning, neural-network-based pattern recognition techniques have become a trend for distributed acoustic sensing (DAS) systems. However, in some cases, certain types of data are difficult to obtain, which leads to imbalanced sample sets. To solve this problem, a data augmentation method based on a generative adversarial network is proposed in this study. First, normal operation samples, including the normal operation training and testing sets are collected using the DAS system. The cyclegan algorithm is then used to generate fault operation samples, a part of which can be selected as the fault operation training set, whereas the others can be viewed as the fault operation testing set. Furthermore, an effective method of data augmentation, called k-means clustering-synthetic minority oversampling technique deep convolutional generative adversarial network, is proposed to enhance the fault operation training set. Finally, the proposed method is applied to the on-load tap-changer, and the experimental results show that the average accuracy of the validation set for the classification task can reach 97%.

Computer Vision Aided Pantograph Fault Identification Method for Multiple Units

<p>In order to solve the technical requirements for automatic recognition and judgment of pantograph wear degree of Multiple Units, this paper designs a network structure based on Mask R-CNN structure. At the same time, in order to improve the ability of image feature extraction in the network, the original backbone network is replaced with ResNet-50, a residual network with more prominent feature extraction ability. Secondly, in order to improve the ability to search for targets in the image, the detection head is reconstructed, to improve the recognition ability of targets. Finally, the effectiveness of the algorithm and its ability to identify pantograph faults were verified through simulation experiments.</p> <p> </p>

Series arc fault identification method based on wavelet transform and feature values decomposition fusion DNN

Series arc fault identification method based on wavelet transform and feature values decomposition fusion DNN

An adaptive weighting multimodal fusion classification system for steel plate surface defect

In steel surface inspection, an accurate steel surface defect identification method is needed to evaluate the impact of defects on structural performance and system maintenance. Traditionally, the recognition accuracy of methods based on handcrafted features is limited, but the system performance can be improved by feature fusion extracted by different methods. Therefore, this research uses the pre-trained convolutional neural network (CNN) combined with transfer learning to extract effective abstract features, and carries out adaptive weighting multimodal fusion of three the abstract features and handcrafted feature sets at the decision-making level, that is, proposes an adaptive weighting multimodal fusion classification system. The system uses handcrafted features as a supplement to abstract features, and accurately classifies steel surface defects in completely different feature representation spaces. Based on the NEU steel plate surface defect benchmark database, the classification results of feature sets before and after fusion are compared and analyzed. The experimental results show that the classification accuracy of the fusion system is improved by at least 3.4% compared with that before fusion, and the final accuracy rate is 99.0%, which proves the effectiveness of the proposed system.

Adaptive feature mode decomposition: a fault-oriented vibration signal decomposition method for identification of multiple localized faults in rotating machinery

Adaptive feature mode decomposition: a fault-oriented vibration signal decomposition method for identification of multiple localized faults in rotating machinery

Improved stack imaging of spectral amplitude based on the impact echo method for identification of defects in grout-filled lap connection

In this paper, we designed defects considering different sizes, burial depths and arrangement modes in the grout-filled lap connection specimens to carry out impact echo test. Different signal processing methods, including Fast Fourier Transform (FFT), Wavelet Transform (WT), and improved Stack Imaging of spectral amplitude based on the Impact Echo (SIBIE), were used to analyze the data. The results show that the improved SIBIE method can efficiently increase the accuracy of multi-media interface defect imaging by filtering the original echo signal and smoothing the spectrum. The superposition of multiple sets of data can eliminate the adverse effects of abnormal samples.

Deep learning assisted non-contact defect identification method using diffraction phase microscopy.

Reliable detection of defects from optical fringe patterns is a crucial problem in non-destructive optical interferometric metrology. In this work, we propose a deep-learning-based method for fringe pattern defect identification. By attributing the defect information to the fringe pattern's phase gradient, we compute the spatial phase derivatives using the deep learning model and apply the gradient map to localize the defect. The robustness of the proposed method is illustrated on multiple numerically synthesized fringe pattern defects at various noise levels. Further, the practical utility of the proposed method is substantiated for experimental defect identification in diffraction phase microscopy.

Composite Insulator Defect Identification Method Based on Acoustic–Electric Feature Fusion and MMSAE Network

Aiming to solve the partial discharge problem caused by defects in composite insulators, most existing live detection methods are limited by the subjectivity of human judgment, the difficulty of effective quantification, and the use of a single detection method. Therefore, a composite insulator defect diagnosis model based on acoustic–electric feature fusion and a multi-scale perception multi-input of stacked auto-encoder (MMSAE) network is proposed in this paper. Initially, during the withstanding voltage experiment, the electromagnetic wave spectrometer and ultrasonic detector were used to collect and process the data of six types of composite insulator samples with artificial defects. The electromagnetic wave spectrum, ultrasonic power spectral density, and n-S map were then obtained. Then, the network architecture of MMSAE was built by integrating a stacked auto-encoder and multi-scale perception module; the feature extraction and fusion methods of the electromagnetic wave spectrum and ultrasonic signal were investigated. The proposed method was used to diagnose test samples, and the diagnostic results were compared to those obtained using a single input source and the artificial neural network (ANN) method. The results demonstrate that the detection accuracy of acoustic–electric feature fusion is greater than that of a single feature; the accuracy of the proposed method is 99.17%, which is significantly higher than the accuracy of the conventional ANN method. Finally, composite insulator defect diagnosis software based on PYQT5 and Keras was developed. Ten 500 kV aging composite insulators were used to validate the effectiveness of the proposed method and design software.

Research on Defect Identification Method of Engine Lining

The engine lining can prevent fuel from debonding with the insulating layer, isolate heat, prevent combustion and buffer stress. Although its proportion is small, the bonding performance of the lining is directly related to whether the engine can maintain a complete structure, and also determines the stability of fuel combustion. How to identify the defects of the formed lining and complete the comprehensive detection of the lining is of great significance to maintain the stability of the engine structure. In this study, an image acquisition system composed of industrial cameras, line-array lenses and line-light sources is used to achieve the integrity acquisition of the lining surface image. Then, through self-made small-scale data sets for the lining image, the backbone network design, and the improvement of existing detectors and network components, the high-precision identification of image defects is achieved.