Traditional Intelligent Fault Diagnosis Methods Research Articles

FTSDC: A novel federated transfer learning strategy for bearing cross-machine fault diagnosis based on dual-correction training

In recent years, although traditional intelligent fault diagnosis methods have achieved satisfactory development in transfer learning tasks, the sample information that the single client can generally provide is extremely limited in real industrial scenarios. And the private data needs to be guaranteed not to leave the local storage during the application process, which leads to obstacles for fault diagnosis methods to solve cross-device and cross-scenario client transfer tasks. Therefore, a novel federated transfer learning strategy based on dual-correction training (FTSDC) is proposed, which enables fault diagnosis for multi-device tasks without target domain samples to participate in model training. The dual correction training of source client is proposed to enhance the local network’s generality, which involves two links: The multiple-functions correction model hyperparameters link and the transition training correction network attention area link. Multiple sets of optimization functions are introduced into local network training to reduce the covariate drift phenomenon caused by domain discrepancies. And the local model fine-tunes the parameters of the trained network through the transition dataset to correct attention areas. Furthermore, The central server evaluates each source client model according to the contribution of the local model to the transfer strategy, and the local model parameters are cumulatively optimized by referring to the diagnosic experience of the global model. It is worth noting that the trained local model can still demonstrate commendable performance even when faced with more complex scenarios. Finally, the proposed scheme was rigorously assessed against diverse federated learning methods across various task settings during the experimental session. The results confirmed the effectiveness of the proposed scheme in safeguarding the data privacy of each client while concurrently enhancing the diagnostic accuracy of the target task.

Rolling bearing fault diagnosis based on multiple wavelet coefficient dimensionality reduction and improved residual network

In response to limitations in traditional intelligent fault diagnosis methods, such as accuracy, robustness, generality, and susceptibility to noise, this article proposes Multiple Wavelet Coefficient Dimensionality Reduction and Improved Residual Network (MWCDR-IResNet). This novel approach represents the first combination of multi-wavelet transform for extracting wavelet coefficients and Principal Component Analysis (PCA) for dimensionality reduction. It incorporates a Residual Network enhanced by the Squeeze and Excitation (SE) module to focus on relevant channels and capture critical fault-related features, followed by fault classification. Validation is performed using rolling bearing datasets from Paderborn University(PBU) and Southeast University (SEU). Experimental results consistently demonstrate MWCDR-IResNet superior performance in terms of robustness, generality, and average accuracy when compared to existing methods.

Rolling Bearing Fault Monitoring for Sparse Time-Frequency Representation and Feature Detection Strategy.

Data-driven fault diagnosis methods for rotating machinery have developed rapidly with the help of deep learning methods. However, traditional intelligent fault diagnosis methods still have some limitations in fault feature extraction and the latest object detection theory has not been applied in fault diagnosis. To this end, a fault diagnosis method based on a sparse short-term Fourier transform (SSTFT) and object detection theory is developed in this paper. First, a sparse constraint is introduced in time-frequency analysis to improve the time-frequency resolution of the model without cross-term interference and proximal gradient descent (PGD) is adopted to quickly and effectively optimize the model to obtain a high-quality time-frequency representation (TFR). Second, a fault diagnosis model based on a region-based convolutional neural network (RCNN) is built; the model can extract multiple regions that can characterize fault features from the TFR. This process avoids the interference of irrelevant vibration components and improves the interpretability of the fault diagnosis model. Finally, multicategory rolling bearing fault identification is realized. The effectiveness of the proposed method is validated by simulation signals and bearing experiments. The results indicate that the proposed method is more effective than existing methods.

A New Fault Diagnosis Method for Unbalanced Data Based on 1DCNN and L2-SVM

In general, the measured health condition data from rolling bearings usually exhibit imbalanced distribution. However, traditional intelligent fault diagnosis methods usually assume that the data categories are balanced. To improve the diagnosis accuracy of unbalanced datasets, a new fault diagnosis method for unbalanced data based on 1DCNN and L2-SVM is proposed in this paper. Firstly, to prevent the minority class samples from being heavily suppressed by the rectified linear unit (ReLU) activation function in the traditional convolutional neural network (CNN), ReLU is improved by linear and scaled exponential linear units (SELUs). Secondly, to solve the problem where the cross-entropy loss treats all input samples equally, it is replaced by the L2-support vector machine (L2-SVM) loss. Furthermore, a dynamic adjustment parameter is introduced to assign less misclassification cost to the majority of class samples. Finally, we add a new modulation factor that reduces the weight of more distinguishable samples to generate more focus on training indiscernible samples. The proposed method is carried out on two kinds of bearing datasets. The experimental results illustrate a significant improvement in recognition accuracy and the higher diagnosis performance of the model when dealing with unbalanced data compared with other intelligent methods.

Multichannel intelligent fault diagnosis of hoisting system using differential search algorithm‐variational mode decomposition and improved deep convolutional neural network

Nowadays, the feature extraction method of multichannel acoustic emission (AE) signal provides a solid research foundation for digital and intelligent fault diagnosis of the hoisting system. More specifically, AE signal collected from the hoisting system is generally characterized by nonlinear and non-stationary, thus making the traditional intelligent fault diagnosis methods cannot accurately extract the inherent fault features. To alleviate this problem and improve the accuracy of multichannel fault diagnosis, a new fault diagnosis method for hoisting system based on differential search algorithm-variational mode decomposition (DSA-VMD) and improved deep convolutional neural network (IDCNN) is proposed in this paper. Specifically, the proposed DSA-VMD and IDCNN method is divided into two main components: (i) the inside parameters (K, a) of VMD is optimized to effectively extract the multichannel AE fault feature via DSA-VMD and (ii) the extracted multichannel fault components are fed into the designed IDCNN algorithm to accomplish fault identification automatically. Experimental results from the hoisting system demonstrate the effectiveness of the proposed approach. Additionally, the superiority of the proposed approach has also been verified in extracting fault information and fault identification compared to the other multichannel fault diagnosis methods.

Unsupervised Joint Subdomain Adaptation Network for Fault Diagnosis

Domain shift is the main reason that the recognition accuracy of traditional intelligent fault diagnosis methods greatly decreases. However, previous methods mainly focus on global domain matching, without considering the finer internal structure and making full use of source domain data, resulting in unsatisfactory adaptive effects. In this paper, we present an unsupervised joint subdomain adaptation network (JSAN), which reduces the discrepancy between the two domains by joint local maximum mean discrepancy (JLMMD). JLMMD divides the features of the specific activation layer into different subdomains according to the labels and matches the subdomains which have the same labels. At the same time, the joint distribution of the feature space and the prediction space of the target domain is matched utilizing the joint distribution of the source domain feature and the label. The experimental results show that the proposed method has achieved remarkable results in the domain adaptation task.

Multi-Domain Weighted Transfer Adversarial Network for the Cross-Domain Intelligent Fault Diagnosis of Bearings

Transfer learning is a topic that has attracted attention for the intelligent fault diagnosis of bearings since it addresses bearing datasets that have different distributions. However, the traditional intelligent fault diagnosis methods based on transfer learning have the following two shortcomings. (1) The multi-mode structure characteristics of bearing datasets are neglected. (2) Some local regions of the bearing signals may not be suitable for transfer due to signal fluctuation. Therefore, a multi-domain weighted adversarial transfer network is proposed for the cross-domain intelligent fault diagnosis of bearings. In the proposed method, multi-domain adversarial and attention weighting modules are designed to consider bearing multi-mode structure characteristics and solve the influence of local non-transferability regions of signals, respectively. Two diagnosis cases are used to verify the proposed method. The results show that the proposed method is able to extract domain invariant features for different cross-domain diagnosis cases, and thus improves the accuracy of fault identification.

Scale adaptive subdomain matching network for bearing fault diagnosis

The wide application of transfer learning technology can effectively solve the problem of the difference between data collection and actual application equipment of traditional intelligent fault diagnosis methods in the practical application process. However, the difference in subdomain space and the serious imbalance of data samples in the process of simultaneous transfer restricts the deep transfer learning technology to the engineering application of high-precision diagnosis. In order to solve the problem of subdomain matching with different subspaces and unbalanced data samples, in this paper we study the subdomain adaptive method and propose a scale adaptive subdomain matching (SASM) method. The SASM method divides the global feature space according to the sample labels, and features with the same label will be divided into the same sub-feature space. Using the edge distribution of the sample and the category weight of the label, the SASM method can effectively optimize the feature distribution of the same subdomain and the weight distribution of different subdomains. Based on the establishment of a clearer internal structure of features, the field adaptation effect is improved, and the matching ability is enhanced when the sample is unevenly distributed. At the same time, the SASM network (SASMN) method for unsupervised bearing fault diagnosis is constructed and validated by experiments. The results indicate that SASMN can effectively optimize the subdomain adaptive effect, and the diagnostic accuracy of the target domain data set is significantly higher than the other three currently popular domain adaptive fault diagnosis methods.

Research on Rotating Machinery Fault Diagnosis Method Based on Energy Spectrum Matrix and Adaptive Convolutional Neural Network

Traditional intelligent fault diagnosis methods focus on distinguishing different fault modes, but ignore the deterioration of fault severity. This paper proposes a new two-stage hierarchical convolutional neural network for fault diagnosis of rotating machinery bearings. The failure mode and failure severity are modeled as a hierarchical structure. First, the original vibration signal is transformed into an energy spectrum matrix containing fault-related information through wavelet packet decomposition. Secondly, in the model training method, an adaptive learning rate dynamic adjustment strategy is further proposed, which adaptively extracts robust features from the spectrum matrix for fault mode and severity diagnosis. To verify the effectiveness of the method, the bearing fault data was collected using a rotating machine test bench. On this basis, the diagnostic accuracy, convergence performance and robustness of the model under different signal-to-noise ratios and variable load environments are evaluated, and the feature learning ability of the method is verified by visual analysis. Experimental results show that this method has achieved satisfactory results in both fault pattern recognition and fault severity evaluation, and is superior to other machine learning and deep learning methods.

An Intelligent Fault Diagnosis Method Based on Domain Adaptation and Its Application for Bearings Under Polytropic Working Conditions

In engineering practice, mechanical equipment is usually in polytropic working conditions, where the data distribution of training set and test set is inconsistent, resulting in insufficient generalization ability of the intelligent diagnosis model. Simultaneously, different tasks often need to be modeled separately. Domain adaptation, as one of the research contents of transfer learning, has certain advantages in solving the problem of inconsistent feature distribution. This article designs and establishes a domain adaptation framework based on multiscale mixed domain feature (DA-MMDF) for cross-domain intelligent fault diagnosis of rolling bearings under polytropic working conditions. The proposed method first uses the MMDF extractor to obtain features from the collected data, which constructs a complete feature space through variational mode decomposition (VMD) and mixed domain feature extraction to fully mine the state information and intrinsic attributes of the vibration signal. Second, the dimensionality reduction and optimization of features are achieved through extreme gradient promotion, and meaningful and sensitive features are selected according to the importance of features to eliminate redundant information. The optimized important features are combined with the manifold embedded distribution alignment method to realize the distribution alignment of data in different fields and cross-domain diagnosis. In order to verify the effectiveness of the proposed approach, the rolling bearing data sets gathered from the laboratories are employed and analyzed. The analysis result confirms that DA-MMDF is able to achieve effective transfer diagnosis between polytropic working conditions. Compared with traditional intelligent fault diagnosis methods and DA methods, the method proposed in this article achieved the state-of-the-art performances.

Semisupervised Graph Convolution Deep Belief Network for Fault Diagnosis of Electormechanical System With Limited Labeled Data

The labeled monitoring data collected from the electromechanical system is limited in the real industries; traditional intelligent fault diagnosis methods cannot achieve satisfactory accurate diagnosis results. To deal with this problem, an intelligent fault diagnosis method for electromechanical system based on a new semisupervised graph convolution deep belief network algorithm is proposed in this article. Specifically, the labeled and unlabeled samples are first employed to design a new adaptive local graph learning method for constructing the graph neighbor relationship. Meanwhile, the labeled samples are applied to describe the discriminative structure information of data via the latest circle loss. Finally, the local and discriminative objective functions are reconstructed under the semisupervised learning framework. The experimental results from the motor-bearing system demonstrate that the method can achieve 98.66 % accuracy with only 10 % of training labeled data, which indicates that it is a promising semisupervised intelligent fault diagnosis method.

A Novel Intelligent Fault Diagnosis Method for Rolling Bearing Based on Integrated Weight Strategy Features Learning.

Intelligent methods have long been researched in fault diagnosis. Traditionally, feature extraction and fault classification are separated, and this process is not completely intelligent. In addition, most traditional intelligent methods use an individual model, which cannot extract the discriminate features when the machines work in a complex condition. To overcome the shortcomings of traditional intelligent fault diagnosis methods, in this paper, an intelligent bearing fault diagnosis method based on ensemble sparse auto-encoders was proposed. Three different sparse auto-encoders were used as the main architecture. To improve the robustness and stability, a novel weight strategy based on distance metric and standard deviation metric was employed to assign the weights of three sparse auto-encodes. Softmax classifier is used to classify the fault types of integrated features. The effectiveness of the proposed method is validated with extensive experiments, and comparisons with the related methods and researches on the widely-used motor bearing dataset verify the superiority of the proposed method. The results show that the testing accuracy and the standard deviation are 99.71% and 0.05%.

A Method of Rolling Bearing Fault Diagnose Based on Double Sparse Dictionary and Deep Belief Network

Feature extraction is the key technology in the data-driven intelligent fault diagnosis methods of rolling bearing. However, the acquired features by the traditional methods, which mainly based on time-frequency domain, sometimes cannot well represent the characteristics of the signal and are difficult to accurately identify because of their complexity and subjectivity. Aiming at this problem, the sparse representation theory is used to the field of fault diagnosis because the different types of rolling bearing fault signals only has the highest matching degree with the dictionary atoms trained by the same type of fault signals. A novel method based on the double sparse dictionary model joint with Deep Belief Network (DBN) is proposed for the fault diagnosis of rolling bearing. Firstly, each type of fault signal is trained according to the double sparse dictionary learning algorithm and the corresponding double sparse subdictionaries is obtained. In order to reduce the feature dimension of sparse representation coefficients, the low contribution atoms of all subdictionaries are removed and the rest are recombined into a comprehensive double sparse dictionary. Then, the Orthogonal Matching Pursuit (OMP) algorithm is adopted to obtain the corresponding sparse feature coefficients of each fault signal on the comprehensive double sparse dictionary. Finally, the coefficient is used as the input of DBN to train and judge the faults of the rolling bearing. The experimental results show that the proposed method has higher diagnosis accuracy and stability compared with the traditional intelligent fault diagnosis methods, and the training and testing time of DBN is greatly reduced.

Intelligent fault diagnosis of rotating machinery using a new ensemble deep auto-encoder method

In traditional intelligent fault diagnosis methods of rotating machinery, features are designed manually by experts, which makes these methods less automatic. Deep auto-encoder (DA) provides an effective way to learn discriminative features. However, individual DA is of low generalization and not robust. This work develops an ensemble DA(EDA) method for intelligent fault diagnosis. EDA is constructed by combining sparse DA, denoising DA and contractive DA. Thus, EDA can effectively handle redundant information, noisy corruption and signal perturbation. To ensure the feature learning performance of each DA model, a self-adaptive fine-tuning is designed to obtain stable convergence. To enhance the discriminative features, a dynamic weighted average method is designed to aggregate these learned features. EDA is verified on three public datasets, and achieves the testing accuracies of 100%, 99.69% and 99.92%. Comparisons with other methods, including both traditional methods and individual DA methods, demonstrate that EDA obtains higher diagnosis accuracy.

Combining translation-invariant wavelet frames and convolutional neural network for intelligent tool wear state identification

On-machine monitoring of tool wear in machining processes has found its importance to reduce equipment downtime and reduce tooling costs. As the tool wears out gradually, the contact state of the cutting edge and the workpiece changes, which has a significant influence on the vibration state of the spindle. The performance of traditional intelligent fault diagnosis methods depend on feature extraction of dynamic signals, which requires expert knowledge and human labor. Recently, deep learning algorithms have been applied widely in machine health monitoring. In this paper, we present a novel intelligent technique for tool wear state recognition using machine spindle vibration signals. The proposed technique combines derived wavelet frames (DWFs) and convolutional neural network (CNN). Constructed based on dual tree wavelets, DWF are equipped with merits of centralized multiresolution and nearly translation-invariance. In this method, DWFs are employed to decompose the original signal into frequency bands of different bandwidths and different center frequencies, which are more pronounced as the tool wears. Further, the reconstructed sub-signals are stacked into a 2-D signal matrix to match the structure of 2-D CNN while retaining more dynamic information. The 2-D convolutional neural network is utilized to automatically recognize features from the multiscale 2-D signal matrix. End-milling experiments were performed on a S45C steel workpiece at different machining parameters. The experiment results of the recognition for tool wear state show the feasibility and effectiveness of the proposed method.

An intelligent fault diagnosis method of rotating machinery using L1-regularized sparse filtering

Traditional intelligent fault diagnosis methods take advantage of diagnostic expertise but are labor-intensive and time-consuming. Among various unsupervised feature extraction methods, sparse filtering computes fast and has less hyperparameters. However, the standard sparse filtering has poor generalization ability and the extracted features are not so discriminative by only constraining the sparsity of the feature matrix. Therefore, an improved sparse filtering with L1 regularization (L1SF) is proposed to improve the generalization ability by improving the sparsity of the weight matrix, which can extract more discriminative features. Based on Fourier transformation (FFT), L1SF, softmax regression, a new three-stage intelligent fault diagnosis method of rotating machinery is developed. It first transforms time-domain samples into frequency-domain samples by FFT, then extracts features in L1-regularized sparse filtering and finally identifies the health condition in softmax regression. Meanwhile, we propose employing different activation functions in the optimization of L1SF and feedforward for considering their different requirements of the non-saturating and anti-noise properties. Furthermore, the effectiveness of the proposed method is verified by a bearing dataset and a gearbox dataset respectively. Through comparisons with the standard sparse filtering and L2-regularized sparse filtering, the superiority of the proposed method is verified. Finally, an interpretation of the weight matrix is given and two useful sparse properties of weight matrix are defined, which explain the effectiveness of L1SF.

Intelligent fault diagnosis of rolling bearings using an improved deep recurrent neural network

Traditional intelligent fault diagnosis methods for rolling bearings heavily depend on manual feature extraction and feature selection. For this purpose, an intelligent deep learning method, named the improved deep recurrent neural network (DRNN), is proposed in this paper. Firstly, frequency spectrum sequences are used as inputs to reduce the input size and ensure good robustness. Secondly, DRNN is constructed by the stacks of the recurrent hidden layer to automatically extract the features from the input spectrum sequences. Thirdly, an adaptive learning rate is adopted to improve the training performance of the constructed DRNN. The proposed method is verified with experimental rolling bearing data, and the results confirm that the proposed method is more effective than traditional intelligent fault diagnosis methods.

Rolling element bearing fault diagnosis using convolutional neural network and vibration image

Detecting in prior bearing faults is an essential task of machine health monitoring because bearings are the vital components of rotary machines. The performance of traditional intelligent fault diagnosis methods depend on feature extraction of fault signals, which requires signal processing techniques, expert knowledge, and human labor. Recently, deep learning algorithms have been applied widely in machine health monitoring. With the capacity of automatically learning complex features of input data, deep learning architectures have great potential to overcome drawbacks of traditional intelligent fault diagnosis. This paper proposes a method for diagnosing bearing faults based on a deep structure of convolutional neural network. Using vibration signals directly as input data, the proposed method is an automatic fault diagnosis system which does not require any feature extraction techniques and achieves very high accuracy and robustness under noisy environments.

A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines

In traditional intelligent fault diagnosis methods of machines, plenty of actual effort is taken for the manual design of fault features, which makes these methods less automatic. Among deep learning techniques, autoencoders may be a potential tool for automatic feature extraction of mechanical signals. However, traditional autoencoders have two following shortcomings. (1) They may learn similar features in mechanical feature extraction. (2) The learned features have shift variant properties, which leads to the misclassification of mechanical health conditions. To overcome the aforementioned shortcomings, a local connection network (LCN) constructed by normalized sparse autoencoder (NSAE), namely NSAE-LCN, is proposed for intelligent fault diagnosis. We construct LCN by input layer, local layer, feature layer and output layer. When raw vibration signals are fed to the input layer, LCN first uses NSAE to locally learn various meaningful features from input signals in the local layer, then obtains shift-invariant features in the feature layer and finally recognizes mechanical health conditions in the output layer. Thus, NSAE-LCN incorporates feature extraction and fault recognition into a general-purpose learning procedure. A gearbox dataset and a bearing dataset are used to validate the performance of the proposed NSAE-LCN. The results indicate that the learned features of NSAE are meaningful and dissimilar, and LCN helps to produce shift-invariant features and recognizes mechanical health conditions effectively. Through comparing with commonly used diagnosis methods, the superiority of the proposed NSAE-LCN is verified.