Intelligent Diagnosis Method Research Articles

Intelligent fault diagnosis of rolling bearing based on wavelet transform and improved ResNet under noisy labels and environment

The fault diagnosis (FD) of rolling bearing (RB) has a great significance in safe operation of engineering equipment. Many intelligent diagnosis methods have been successfully developed. However, the performances of traditional fault diagnosis methods are affected by noisy labels and environment which widely exist in realistic industrial applications. This article proposed a novel FD method of RB based on wavelet transform (WT) and an improved residual neural network (IResNet), named WT-IResNet. The proposed WT-IResNet approach uses a new pooling layer for dimension reduction and a global singular value decomposition (SVD) adaptive strategy for feature extraction. Furthermore, the original softmax layer and the logistic loss for training are replaced by a new loss function containing two adjustable parameters to address fault diagnosis with label noises. Two typical bearing failure datasets are used to evaluate the feasibility and effectiveness of WT-IResNet under noisy labels and noisy environment respectively. The experimental results indicate that WT-IResNet has better robustness against noise in comparison with other methods. Whatever under noisy labels or noisy environment, the performance of WT-IResNet outperforms other methods.

Intelligent Diagnosis Method of Power Equipment Faults Based on Single‐Stage Infrared Image Target Detection

With the rapid expansion of the scale of the power grid, the efficiency of fault diagnosis has been severely challenged by the large amount of inspection image data generated by intelligent devices such as drones and inspection robots. In order to improve the efficiency of fault diagnosis for power equipment in substations, a new method for intelligently diagnosing different types of faults in power equipment is proposed. For circuit breakers and insulators, YOLOv4 is selected as the target detection model. To improve the detection performance of the YOLOv4 model, this paper improves it: the Cross Stage Partial (CSP) structure is introduced in the Spatial Pyramid Pooling (SPP) module of the neck of the YOLOv4 model. The experimental results show that after using the optimal learning rate decay strategy, the mAP and frames per second (FPS) of the improved YOLOv4 model are better than the original YOLOv4 and PP‐YOLO model. Finally, an intelligent diagnosis terminal system for power equipment faults is developed. Through the target recognition and rapid extraction of equipment temperature, the intelligent diagnosis of thermal faults of equipment is realized. This method is especially suitable for accurate fault diagnosis of more power equipment, and has potential huge applicability in the field of power equipment diagnosis. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

An Intelligent Fault Diagnosis Method of Rolling Bearings via Variational Mode Decomposition and Common Spatial Pattern-Based Feature Extraction

Monitoring and identifying the health condition of rolling bearings can reduce the risk of mechanical equipment failure. This paper proposes a novel intelligent diagnosis method of rolling bearings: First, the vibration signals are decomposed into band-limited instinct mode functions (BLIMFs) by variational mode decomposition (VMD). Then, the proposed high-dimensional common spatial pattern (hdCSP) filter is used to generate the high-dimensional eigenvectors representing the decomposed BLIMFs. Finally, the random forests classifier is used to classify the eigenvectors and obtain the diagnosis results. The performance of the proposed VMD-hdCSP method is evaluated on the Case Western Reserve University dataset. The experimental results show the proposed method can automatically classify different health states of rolling bearings and obtain precise diagnosis results.

Distribution Sub-Domain Adaptation Deep Transfer Learning Method for Bridge Structure Damage Diagnosis Using Unlabeled Data

Deep learning based bridge damage diagnosis methods can successfully use labeled data to detect bridge damage. These successful applications usually need that the training samples (source domain) and test samples (target domain) obey the same probability distribution. However, it is difficult to acquire a large amount of labeled data with damage information from actual bridges. It is also difficult to apply a model trained with bridge A to diagnose bridge B because of the distribution discrepancy of data from different bridges or environments. Therefore, transferring a well-trained damage diagnosis model to another bridge with unlabeled data remains a major challenge. Motivated by transfer learning, this paper proposes a new intelligent damage diagnosis method for bridges, namely, sub-domain adaptive deep transfer learning network (SADTLN), to solve the feature generalization problem in different bridges. In our method, a multi-kernel local maximum mean discrepancy (MK-LMMD) based sub-domain adaptation module, including a domain classifier for aligning the global distribution and a sub-domain multi-layer adaptation for aligning local distribution, is proposed for transfer learning, so that the learned features are domain-invariant. Experiments prove the effectiveness and advancement of the proposed method. This exploration will promote the practical application of intelligent bridge structural damage diagnosis.

Intelligent Diagnosis Method for Mechanical Faults of High-Voltage Shunt Reactors Based on Vibration Measurements

Aiming at the difficulty of accurately identifying latent mechanical faults inside high-voltage shunt reactors (HVSRs), this paper proposes a new method for HVSR state feature extraction and intelligent diagnosis. The method integrates a modified complementary ensemble empirical mode decomposition (CEEMD)–permutation entropy–CEEMD (MCPCEEMD) method, mutual information theory (MI), multiscale fuzzy entropy (MFE), and an improved grasshopper optimization algorithm to optimize the probabilistic neural network (IGOA-PNN) model. First, we introduce MCPCEEMD for suppressing modal aliasing to decompose the HVSR raw vibration signals. Then, the correlation degree between the obtained intrinsic mode function (IMF) components and the HVSR original vibration signals is judged through MI, and the IMF with the highest correlation is selected for feature extraction. Furthermore, this study uses MFE to quantify the selected IMF. Finally, we employ piecewise inertial weights to improve GOA to select the best smoothing factor for PNN, and use the optimized IGOA-PNN model to identify feature subsets. The experimental results show that the proposed method can successfully diagnose different types and degrees of HVSR mechanical faults, and the identification accuracy rate reaches more than 98%. The high recognition accuracy of the proposed method is helpful for the state detection and field application of HVSRs.

A fused biometrics information graph convolutional neural network for effective classification of patellofemoral pain syndrome.

Patellofemoral pain syndrome (PFPS) is a common, yet misunderstood, knee pathology. Early accurate diagnosis can help avoid the deterioration of the disease. However, the existing intelligent auxiliary diagnosis methods of PFPS mainly focused on the biosignal of individuals but neglected the common biometrics of patients. In this paper, we propose a PFPS classification method based on the fused biometrics information Graph Convolution Neural Networks (FBI-GCN) which focuses on both the biosignal information of individuals and the common characteristics of patients. The method first constructs a graph which uses each subject as a node and fuses the biometrics information (demographics and gait biosignal) of different subjects as edges. Then, the graph and node information [biosignal information, including the joint kinematics and surface electromyography (sEMG)] are used as the inputs to the GCN for diagnosis and classification of PFPS. The method is tested on a public dataset which contain walking and running data from 26 PFPS patients and 15 pain-free controls. The results suggest that our method can classify PFPS and pain-free with higher accuracy (mean accuracy = 0.8531 ± 0.047) than other methods with the biosignal information of individuals as input (mean accuracy = 0.813 ± 0.048). After optimal selection of input variables, the highest classification accuracy (mean accuracy = 0.9245 ± 0.034) can be obtained, and a high accuracy can still be obtained with a 40% reduction in test variables (mean accuracy = 0.8802 ± 0.035). Accordingly, the method effectively reflects the association between subjects, provides a simple and effective aid for physicians to diagnose PFPS, and gives new ideas for studying and validating risk factors related to PFPS.

Deep subclass alignment transfer network based on time–frequency features for intelligent fault diagnosis of planetary gearboxes under time-varying speeds

Vibration signals of planetary gearboxes have complex components and time-varying characteristics. As the unstable operation of planetary gearboxes leads to unbalanced data distribution within vibration signals, it is difficult to extract gearbox fault information hidden in a large amount of data. Therefore, fault diagnosis of planetary gearboxes under nonstationary conditions is highly challenging. For the past few years, intelligent diagnosis methods have been extensively studied in the fault diagnosis field. However, inappropriate signal representations, inadequate training samples, and data differences increase the difficulty of diagnosing planetary gearbox faults. To address the above issues, this paper proposes an intelligent diagnostic framework based on time–frequency features and a deep residual joint subclass alignment transfer network (DSATN) for planetary gearbox fault diagnosis under nonstationary conditions. One-dimensional vibration signals are converted into time–frequency representation through signal processing techniques to reflect the variation of vibration frequency components within the time–frequency domain with time. During network training, the DSATN evaluates the data distributions between relevant subclasses in source and target tasks by using the local maximum mean discrepancy. Also, it utilizes a nonlinear transformation to align the global data distributions between both tasks, thus improving the generalization of the trained model for small sample sets. The proposed method is validated through planetary gearbox experiments and achieves good fault classification in the time–frequency domain of nonstationary vibration signals. Different gear and planet bearing fault categories are successfully identified.

A Novel 1D-CNN-Based Diagnosis Method for a Rolling Bearing with Dual-Sensor Vibration Data Fusion

Due to variation of working conditions and influence of noise in vibration data, rolling bearing intelligent diagnosis based on deep learning faces challenges in efficient utilization of monitoring data and scientific extraction of fault features. This study proposes a one-dimensional convolution neural network (1D-CNN)-based intelligent diagnosis method for a rolling bearing, which fuses the horizontal and the vertical vibration signals, makes full use of spectral order features by full-spectrum analysis, and achieves accurate classification of fault pattern by 1D-CNN model. The experimental datasets of constant and variable working conditions of rolling bearing are constructed. The test results of the proposed method show that spectral order features are extracted effectively by full-spectrum analysis and high diagnostic accuracy is obtained by the constructed 1D-CNN model on both datasets. The comparison with the other four similar methods indicates that the diagnostic accuracy of the proposed method outperforms the comparative methods significantly in the case of variable operating conditions.

Research on Fault Diagnosis Technology of Industrial Robot Operation Based on Deep Belief Network

Fault diagnosis technology is the science of identifying the operating state of a machine or unit, and it studies the response of the change in the operating state of the machine or unit in the diagnostic information. It can give an early warning to the failure state of the machine and stop the machine before a major failure occurs so as to protect the life safety of the on-site staff and avoid huge economic losses to the enterprise. For mechanical equipment, fault diagnosis consists of three main links: fault detection; fault identification; and fault classification. Aiming at the problems that need to be solved in the fault diagnosis of industrial robots, this paper adopts a data-driven intelligent diagnosis method to establish a fault diagnosis model of industrial robots based on Deep Belief Network (DBN) and DSmT theory. Firstly, based on wavelet transform and information energy entropy correlation theory, the vibration signal of industrial robot is extracted, and the energy entropy normalized eigenvector is established. Then, the energy entropy normalized feature vector is divided into training set and test set to complete the creation of DBN network model. Finally, using DSmT theory to carry out decision-making fusion, a fault diagnosis model for industrial robots is established, and experiments are carried out on the K-R-R540 robot to verify the applicability of the established fault diagnosis model. It is proved by experiments that the industrial robot fault diagnosis model based on the deep belief network can meet the requirements of the recognition accuracy of robot faults, and the model will perform poorly when the faults coexist with multiple faults.

Improved Variational Mode Decomposition and CNN for Intelligent Rotating Machinery Fault Diagnosis.

This paper proposes an intelligent diagnosis method for rotating machinery faults based on improved variational mode decomposition (IVMD) and CNN to process the rotating machinery non-stationary signal. Firstly, to solve the problem of time-domain feature extraction for fault diagnosis, this paper proposes an improved variational mode decomposition method with automatic optimization of the number of modes. This method overcomes the problems of the traditional VMD method, in that each parameter is set by experience and is greatly influenced by subjective experience. Secondly, the decomposed signal components are analyzed by correlation, and then high correlated components with the original signal are selected to reconstruct the original signal. The continuous wavelet transform (CWT) is employed to extract the two-dimensional time–frequency domain feature map of the fault signal. Finally, the deep learning method is used to construct a convolutional neural network. After feature extraction, the two-dimensional time-frequency image is applied to the neural network to identify fault features. Experiments verify that the proposed method can adapt to rotating machinery faults in complex environments and has a high recognition rate.

An Improved MobileNet Network with Wavelet Energy and Global Average Pooling for Rotating Machinery Fault Diagnosis.

In recent years, neural networks have shown good performance in terms of accuracy and efficiency. However, along with the continuous improvement in diagnostic accuracy, the number of parameters in the network is increasing and the models can often only be run in servers with high computing power. Embedded devices are widely used in on-site monitoring and fault diagnosis. However, due to the limitation of hardware resources, it is difficult to effectively deploy complex models trained by deep learning, which limits the application of deep learning methods in engineering practice. To address this problem, this article carries out research on network lightweight and performance optimization based on the MobileNet network. The network structure is modified to make it directly suitable for one-dimensional signal processing. The wavelet convolution is introduced into the convolution structure to enhance the feature extraction ability and robustness of the model. The excessive number of network parameters is a challenge for the deployment of networks and also for the running performance problems. This article analyzes the influence of the full connection layer size on the total network. A network parameter reduction method is proposed based on GAP to reduce the network parameters. Experiments on gears and bearings show that the proposed method can achieve more than 97% classification accuracy under the strong noise interference of −6 dB, showing good anti-noise performance. In terms of performance, the network proposed in this article has only one-tenth of the number of parameters and one-third of the running time of standard networks. The method proposed in this article provides a good reference for the deployment of deep learning intelligent diagnosis methods in embedded node systems.

A Novel Fault Diagnosis Method for Marine Blower with Vibration Signals

Abstract The vibration signals on marine blowers are non-linear and non-stationary. In addition, the equipment in marine engine room is numerous and affects each other, which makes it difficult to extract fault features of vibration signals in the time domain. This paper proposes a fault diagnosis method based on the combination of Ensemble Empirical Mode Decomposition (EEMD), an Autoregressive model (AR model) and the correlation coefficient method. Firstly, a series of Intrinsic Mode Function (IMF) components were obtained after the vibration signal was decomposed by EEMD. Secondly, effective IMF components were selected by the correlation coefficient method. AR models were established and the power spectrum was analysed. It was verified that blower failure can be accurately diagnosed. In addition, an intelligent diagnosis method was proposed based on the combination of EEMD energy and a Back Propagation Neural Network (BPNN), with a correlation coefficient method to get effective IMF components, and the energy components were calculated, normalised as a feature vector. Finally, the feature vector was sent to the BPNN for training and state recognition. The results indicated that the EEMD-BPNN intelligent fault diagnosis method is suitable for higly accurate fault diagnosis of marine blowers.

Task-Sequencing Meta Learning for Intelligent Few-Shot Fault Diagnosis With Limited Data

Recently, deep learning-based intelligent fault diagnosis methods have been developed rapidly, which rely on massive data to train the diagnosis model. However, it is usually difficult to collect sufficient failure data in practical industrial production, thus limits the application of intelligent diagnosis methods. To address the few-shot fault diagnosis problem, a task-sequencing meta-learning method is proposed in this article. First, the meta-learning model is trained over a series of learning tasks to obtain knowledge about how to diagnosis. Thus, the learned knowledge can help adapt and generalize with a few examples when dealing with new tasks that have never been encountered. Then, considering the difference and connection between different failures and diagnosis tasks, a task-sequencing algorithm is proposed to sort meta training tasks from easy to difficult, which followed the way human acquire knowledge. After evaluating the difficulty of each task, the proposed method learns simple tasks first and generalizes the learned knowledge to complex tasks. Better knowledge adaptability is obtained by gradually increasing the task difficulty. Finally, utilizing gradient-based meta learning, the initialization parameters are trained by a small number of gradient steps. The effectiveness of the proposed method is validated by a practice rolling bearing dataset and a power system dataset. The experiment results illustrate that the proposed method can identify new categories with only several samples. In addition, it also shows advantages in fault diagnosis when the categories are fine-grained according to the working conditions. Therefore, the proposed method is suitable for solving the few-shot problem in practice and complicated fault diagnosis.

Fuzzy Clustering of Infrared Image Features Based on Lazy Snapping Algorithm

Substation equipment is an important part of the power grid, which undertakes the function of power transmission and conversion and directly affects the operation status of the whole substation and power system. When the substation equipment is in an abnormal working state, the temperature will change. Therefore, the temperature information of the substation equipment is used as the judgment basis to complete the judgment of the working state of the equipment, which can realize the fault diagnosis of the substation equipment and ensure that the power system works in a safe and reliable environment. In this paper, according to the characteristics of the transformer equipment shape stability, the invariant moment is used to extract the infrared image feature of the transformer equipment. The support vector machine is used to complete the classification and recognition of the image. Hu invariant moments and Zernike invariant moments are used to extracting features respectively, and the results of feature extraction are used as training samples to train support vector machines for recognition. Using the Lazy Snapping algorithm to complete the infrared image segmentation processing of substation equipment, the target region is extracted from the background completely, and the segmentation image information is completed. In the experimental test, through the test of the recognition model constructed by invariant moments, it is proved that the recognition accuracy of Zernike invariant moments combined with support vector machine in this paper is higher, and the Lazy Snapping algorithm has obvious advantages in segmentation quality compared with other methods. Therefore, the method of intelligent identification and diagnosis of the thermal fault of substation equipment studied in this paper has important practical significance for the establishment of an online diagnosis system.

A key-factor denoising strategy for quasi periodic non-stationary incipient faults diagnosis

Currently, the analysis method based on monitoring data has become an effective means of machinery fault diagnosis, and the fault diagnosis with obvious data features has achieved fruitful results. However, the incipient fault signals of equipment not only show the characteristics of weak intensity, quasi periodic and non-stationary, but also are submerged in strong background noise, which often makes it difficult to extract effective information directly from the original signals. Therefore, in order to effectively solve the problem of incipient fault diagnosis, and considering the capability of sparse autoencoder (SAE) to extract features automatically, this paper proposes a key-factor denoising strategy and an improved SAE network, and then an improved SAE network with key-factor denoising strategy (KF-ISAE) based intelligent diagnosis method for quasi periodic non-stationary incipient faults is proposed. The main contributions of the proposed method are as follows. On the one hand, signal denoising that cannot be ignored in fault diagnosis is achieved by the developed incipient faults sensitivity based key-factor denoising strategy, and on the other hand, for SAE, the blindness of feature learning is handled by the formed weights constraints. In addition, the health condition identification and the fault severity level determination of machinery are completed by the improved SAE network designed in this paper. Finally, verification and comparative experiments show the effectiveness and practicability of the proposed method.

An intelligent diagnosis method of rolling bearing based on multi-scale residual shrinkage convolutional neural network

The vibration signals of rolling bearings are affected by changing operating conditions and environmental noise, so they are characterized by multi-scale complexity. Deep residual shrinkage network can achieve bearing fault diagnosis in strong noise environment, but ignore the multi-scale complexity feature. To address this problem, we propose a multi-scale residual shrinkage convolutional neural network for fault diagnosis of rolling bearing. In this method, a multi-scale residual shrinkage layer based on multi-scale learning and a residual shrinkage block is constructed. By stacking multiple multi-scale residual shrinkage layers, the features of vibration signals are automatically learned from the input data. In addition, to establish the connection of different vibration signals and to reduce the number of parameters in the network, we design a separable convolution block using residual connections and separable convolution. By verifying the effectiveness of the proposed method in Case Western Reserve University and Mechanical Failure Prevention Technology datasets, the results show that the proposed method not only has good noise resistance in strong noise environments, but also has high diagnostic accuracy and good generalization performance in different load condition domains. The proposed method is compared with three other deep learning methods under the same experimental conditions, and the results show that it is superior in rolling bearing fault diagnosis.

Intelligent Mechanical Fault Diagnosis Using Multisensor Fusion and Convolution Neural Network

Diagnosis of mechanical faults in manufacturing systems is critical for ensuring safety and saving costs. With the development of data transmission and sensor technologies, measuring systems can acquire massive amounts of multisensor data. Although deep learning (DL) provides an end-to-end way to address the drawbacks of traditional methods, it is necessary to do deep research on an intelligent fault diagnosis method based on multisensor data. In this article, a novel intelligent diagnosis method based on multisensor fusion (MSF) and convolutional neural network (CNN) is explored. First, a multisignals-to-RGB-image conversion method based on principal component analysis is applied to fuse multisignal data into three-channel red−green−blue (RGB) images. Then, an improved CNN with residual networks is proposed, which can balance the relationship between computational cost and accuracy. Two datasets are used to verify the effectiveness of the proposed method. The results show that the proposed method outperforms other DL-based methods in terms of accuracy.

First-order differential filtering spectrum division method and information fusion multi-scale network for fault diagnosis of bearings under different loads

In recent years, data-driven intelligent diagnosis methods have been widely applied in the field of bearing fault diagnosis. However, these methods involve some expert experience and knowledge, and cannot accurately mine bearing fault characteristics under different loads. To solve this problem, this paper proposes a first-order differential filtering spectrum division (FDFSD) method and an information fusion multi-scale network (IFMSNet) to realize bearing fault diagnosis under different working conditions. First of all, the proposed spectrum division method based on the first-order differential filtering, the first-order differential processing of time domain signals, and the introduction of triangular filter, reclassify the spectrum features, highlight feature information, can accurately extract bearing fault features. Secondly, a new multi-scale network model of information fusion is constructed in this paper. Convolution kernels of different sizes are used to extract fault features of bearings of different scales, and information fusion is carried out to identify bearing working conditions and realize intelligent diagnosis of bearings under different loads. Finally, in order to verify the effectiveness and accuracy of the proposed method, it is verified on a variety of bearing experimental data sets. The results show that the average prediction accuracy of the proposed method is 99.11% and 97.74%, respectively. Compared with the proposed three single-scale network, K-nearest neighbor, Naive Bayes, support vector machine and random forest methods, the proposed method has more advantages in bearing intelligent diagnosis under different loads.

Partial Transfer Ensemble Learning Framework: A Method for Intelligent Diagnosis of Rotating Machinery Based on an Incomplete Source Domain.

Most cross-domain intelligent diagnosis approaches presume that the health states in training datasets are consistent with those in testing. However, it is usually difficult and expensive to collect samples under all failure states during the training stage in actual engineering; this causes the training dataset to be incomplete. These existing methods may not be favorably implemented with an incomplete training dataset. To address this problem, a novel deep-learning-based model called partial transfer ensemble learning framework (PT-ELF) is proposed in this paper. The major procedures of this study consist of three steps. First, the missing health states in the training dataset are supplemented by another dataset. Second, since the training dataset is drawn from two different distributions, a partial transfer mechanism is explored to train a weak global classifier and two partial domain adaptation classifiers. Third, a particular ensemble strategy combines these classifiers with different classification ranges and capabilities to obtain the final diagnosis result. Two case studies are used to validate our method. Results indicate that our method can provide robust diagnosis results based on an incomplete source domain under variable working conditions.

Analyzing the Treatment of Patients with Acute Exacerbation of COPD with the Aid of Intelligent Diagnosis Method.

To observe the clinical efficacy of heat clearing phlegm mixture combined with vibration sputum excretion instrument in the treatment of patients with acute exacerbation of COPD with phlegm-heat obstructing lung, 90 patients with acute exacerbation of COPD are selected and divided into three groups, namely, control group, traditional medicine group, and combined group: the control group (conventional western medicine treatment), traditional medicine group (heat clearing and phlegm mixture), and combined group (heat clearing and phlegm mixture + vibratory sputum excretion instrument) with 30 cases each. All the patients in the three groups were given conventional western medicine treatment. On this basis, the traditional medicine group was given the oral administration of the heat-clearing and phlegm-clearing mixture, and the combined group was given the oral administration of the heat-clearing and phlegm-clearing mixture and the vibratory sputum discharge apparatus. Machine learning is used to classify the patients into three groups based on the characteristics of their biomarkers, physical attributes, and medical history. The TCM syndrome score, blood gas analysis, lung function, and inflammatory indexes of the three groups were compared. TCM syndrome scores of the three groups were all lower than before; both the combined group and the TCM group were better than the control group (P < 0.05). Although the improvement degree of the combined group was better than that of the TCM group, the difference was not statistically significant (P > 0.05). TCM syndrome effect is seen to be 96.55% in the combined group, 89.29% in the TCM group, and 63.33% in the control group. Blood gas analysis is also performed; PO2 and PCO2 of the three groups were significantly improved after treatment. The combination group was superior to the traditional medicine group and the control group (P < 0.05), and the traditional medicine group was superior to the control group (P < 0.05). It is concluded that the combination of heat clearing phlegm mixture and vibration sputum excretion instrument can improve TCM syndrome score, CAT score, blood gas analysis, lung function, and inflammatory indicators in patients with acute exacerbation of COPD with phlegm-heat obstructing lung.