Fault Diagnosis Model Research Articles

Data Privacy Preserving for Centralized Robotic Fault Diagnosis With Modified Dataset Distillation

Abstract Industrial robots generate monitoring data rich in sensitive information, often making enterprises reluctant to share, which impedes the use of data in fault diagnosis modeling. Dataset distillation (DD) is an effective approach to condense large dataset into smaller, synthesized forms, focusing solely on fault-related features, which facilitates secure and efficient data transfer for diagnostic purposes. However, the challenge of achieving satisfactory fault diagnosis accuracy with distilled data stems from the computational complexity in data distillation process. To address this problem, this article proposes a modified KernelWarehouse (MKW) network-based DD method to achieve accurate fault diagnosis with the distilled dataset. In this algorithm, DD first generates distilled training and testing dataset, followed by the training of an MKW-based network based on these distilled datasets. Specifically, MKW reduces network complexity through the division of static kernels into disjoint kernel cells, which are then computed as linear mixtures from a shared warehouse. An experimental study based on the real-world robotic dataset reveals the effectiveness of the proposed approach. The experimental results indicate that the proposed method can achieve a fault diagnosis accuracy of 86.3% when only trained with distilled data.

A General and Efficient Fault Diagnosis Approach Using Hyperdimensional Computing Enhanced by Local Feature Extraction

Abstract Ensuring the safe and reliable operation of industrial equipment is of great importance, and accordingly, machine fault diagnosis has attracted considerable attention. Recently, various deep learning-based fault diagnosis models have been widely developed due to the powerful ability of feature learning and nonlinear modeling of deep learning models, and these methods heavily rely on large amounts of data and high memory and resources. However, it is difficult to obtain enough data in practical applications, thus leading to the unsatisfactory performance of deep learning-based models and high cost. In this paper, we propose a new and efficient fault diagnosis approach based on Hyperdimensional computing (HDC), which can learn high-dimensional, random, and holographic distributed representations of input features. It has the advantages of single training, low training cost, and does not require a large amount of data. Therefore, we apply HDC to the field of few-shot fault diagnosis for the first time, and propose a simple and efficient approach for few-shot fault diagnosis based on hyperdimensional computing with local feature extraction(L-HDC). Instead of using original data, the model firstly extracts the local features of original data by hand-designed features, and then carries out HDC-encoding, training, and test classification. Through the comparison of various models and the analysis of various data, the effectiveness of our proposed model is verified. In the case of few-shot learning, the recognition accuracy is as high as 90\% and the training time of ordinary HDC model is 5-10 times that of L-HDC model, which is superior to other models.

An approach for fault-related monitoring variables selection based on dual-layer correlation networks

PurposeFault-related monitoring variables selection is a process of obtaining a subset of variables from the original set, which is of great significance for reducing information redundancy and improving the performance of the fault diagnosis models. This paper aims to propose a novel variables selection approach based on complex networks.Design/methodology/approachFirstly, a dual-layer correlation networks (DlCN) which consists of mechanism-oriented correlation sub-network (MoCSN) and data-oriented correlation sub-network (DoCSN) is constructed. Secondly, an algorithm for identifying critical fault-related monitoring variables based on dual correlations is introduced. In the algorithm, the topological attributes of the MoCSN and correlation threshold of the DoCSN are used successively.FindingsIn the experiments of vertical elevator fault diagnosis, the critical fault-related monitoring variables selected by the DlCN-based approach is more effective than the traditional approaches. It indicates that fusion mechanism-oriented correlation can enhance the comprehensiveness of variable correlation analysis. Moreover, the approach has been proved to be adaptable to different fault diagnosis models.Originality/valueIn the DlCN-based variables selection approach, the mechanism-oriented correlation and data-oriented correlation are comprehensively considered. It improves the precision of variables selection. Meanwhile, it is an unsupervised and model-agnostic approach which addresses the shortcomings of some conventional approaches that require data labels and have insufficient adaptability for fault diagnosis models.

Stack performance classification and fault diagnosis optimization of solid oxide fuel cell system based on bayesian artificial neural network and feature selection

Solid oxide fuel cell (SOFC) has attracted much attention because of its high efficiency and silent power generation, and can be applied to the field of fuel cell-powered unmanned boats. However, a fuel deficit failure in the system can lead to reduced stack performance, reducing the reliability of SOFC applications in the field of unmanned boats. Therefore, this paper proposes an efficient breakdown diagnosis model for SOFC system fault diagnosis. Firstly, Bayesian artificial neural network is constructed by using the best feature data subset after Relief-F combined with minimum Redundancy Maximum Relevance algorithm feature selecting. Secondly, the correct diagnosis rate under different number of optimal features is calculated, and the best feature combinations are combined to verify. Finally, the particle swarm algorithm selects the optimal hidden neuron count to optimization model. Experimental findings suggest that for correct diagnosis rate, the breakdown diagnosis model based on the optimal number of 3 features can reduce the training time and maintain high accuracy compared with the use of all 34 features. This research result provides a feasible way for the fault diagnosis application of SOFC system power generation in the field of unmanned boats.

Adaptive fault diagnosis for high-purity carbonate process based on unsupervised and transfer learning

Reactive distillation integrates reaction and distillation to achieve process intensification. And the increasing process complexity urgently requires fault diagnosis system to ensure its safe and efficient operation. However, establishing fault diagnosis model is facing intractable challenges, e.g. scarce labeled data, operating mode changeover due to product proportion variation. To tackle absent labeled data problem, pseudo-labeled database is established by integrating data mining, density-based spatial clustering of applications with noise algorithm and process knowledge, based on which unsupervised deep learning is developed. Besides, to make intelligent fault diagnosis system adaptive for multimode operation changeover, transfer learning with domain adaptation strategy is adopted, which could mitigate different data distributions in various operating states and transfer knowledge learned from source domain to target domain. Taking carbonate ester process with reactive distillation as benchmark, the performance and superiority of unsupervised learning and transfer learning is verified and demonstrated in solving the corresponding puzzle.

Fault diagnosis of complex industrial equipment based on chunked statistical global-local feature fusion

Abstract Industrial process equipment is bulky and complex in structure, which is easy to produce faults during operation and affect production efficiency, cause huge economic losses, and even threaten the safety of workers. To achieve sustainable operation of large-scale industrial processes, timely and accurate monitoring and handling of abnormal situations are essential. However, fault monitoring of large equipment requires the collection of abundant data, which includes many complex related variables, resulting in excessive redundant data generated during the fault monitoring process. Moreover, the existing principal component analysis (PCA) method can only retain the global characteristic of variance information, and cannot obtain the local characteristic that can characterize the topological relationship between the data points, which affects its monitoring reliability and intelligence level. In response to these issues, a fault diagnosis model for complex industrial processes based on chunked statistical global-local feature fusion (CSGLFF) is proposed in this paper. First, considering the correlation characteristics between industrial process variables, a correlation variable chunking method mutual information-based is designed to merge the variables with small correlation to obtain the optimal chunking of variables. Second, PCA and locality preserving projections (LPP) are combined to construct a global-local feature fusion (GLFF) model that can extract global and local features simultaneously. The chunked data are imported into the GLFF for the extraction of its features respectively, and the corresponding CSGLFF is established. In addition, Bayesian inference is used to fuse the statistics of each sub-chunk to establish an overall fault monitoring statistical indicators, and the reason for failure is found through the variable contribution graph. Finally, two cases of Tennessee Eastman process (TEP) and laboratory emulsion pump were used to conduct experimental research on the performance of CSGLFF. The results show that compared with the chunked statistical PCA, chunked statistical LPP, and GLFF algorithms, The accuracy of fault monitoring for TEP mean, flow pulsation impact, and pressure anomaly of this method reached 92.91%, 97%, and 90.30%, respectively. It has good monitoring effect in processing data with large variables, reducing the generation of redundant data, improving the accuracy of industrial monitoring, and accurately identifying the relevant variables of fault occurrence. This provides a theoretical basis for determining the fault location and points out the direction for maintenance by staff.

Rolling bearing fault diagnosis method based on multi-scale pooling residual convolutional neural network under noisy environment

To address the issues of unstable performance and poor generalization ability of bearing fault diagnosis model caused by strong noise and variable operating conditions in actual production，this paper proposes a rolling bearing fault diagnosis method based on MSPRCNN model. By converting vibration signals to frequency domain with FTand utilizing wide convolution kernels for feature extraction, the approach aims to enhance fault detection. A MSPFE module captures information at different scales to simplify complexity, while an UPA module establishes correlations between frequency domain positions. To reduce the impact of noise and address the vanishing gradient problem, the MSPRCNN model employs GC instead of standard convolution, and utilizes the IReLU activation function to improve model feature representation. Experimental results on two datasets show that the fault recognition accuracy is 98.71% under variable loads and 98.2% under variable speeds. The MSPRCNN model outperforms other methods in fault recognition and generalization in noisy environments.

Rolling Bearing Fault Diagnosis in Agricultural Machinery Based on Multi-Source Locally Adaptive Graph Convolution

Maintaining agricultural machinery is crucial for efficient mechanized farming. Specifically, diagnosing faults in rolling bearings, which are essential rotating components, is of significant importance. Domain-adaptive technology often addresses the challenge of limited labeled data from a single source domain. However, information transfer can sometimes fall short in providing adequate relevant details for supporting target diagnosis tasks, leading to poor recognition performance. This paper introduces a novel fault diagnosis model based on a multi-source locally adaptive graph convolution network to diagnose rolling bearing faults in agricultural machinery. The model initially employs an overlapping sampling method to enhance sample data. Recognizing that two-dimensional time–frequency signals possess richer spatial characteristics in neural networks, wavelet transform is used to convert time series samples into time–frequency graph samples before feeding them into the feature network. This approach constructs a sample data pair from both source and target domains. Furthermore, a feature extraction network is developed by integrating the strengths of deep residual networks and graph convolutional networks, enabling the model to better learn invariant features across domains. The locally adaptive method aids the model in more effectively aligning features from the source and target domains. The model incorporates a Softmax layer as the bearing state classifier, which is set up after the graph convolutional network layer, and outputs bearing state recognition results upon reaching a set number of iterations. The proposed method’s effectiveness was validated using a bearing dataset from Jiangnan University. For three different groups of bearing fault diagnosis tasks under varying working conditions, the proposed method achieved recognition accuracies above 99%, with an improvement of 0.30%-4.33% compared to single-source domain diagnosis models. Comparative results indicate that the proposed method can effectively identify bearing states even without target domain labels, showcasing its practical engineering application value.

Machine Fault Diagnosis: Experiments with Different Attention Mechanisms Using a Lightweight SqueezeNet Architecture

As artificial intelligence technology progresses, deep learning models are increasingly utilized for machine fault classification. However, a significant drawback of current state-of-the-art models is their high computational complexity, rendering them unsuitable for deployment in portable devices. This paper presents a compact fault diagnosis model that integrates a self-attention SqueezeNet architecture with a hybrid texture representation technique utilizing empirical mode decomposition (EMD) and a gammatone spectrogram (GS) filter. In the model, the dominant signal is first isolated from the audio fault signals by discarding lower intrinsic mode functions (IMFs) from EMD, and subsequently, the dominant signals are transformed into 2D texture maps using the GS filter. These generated texture maps feed as input into the modified self-attention SqueezeNet classifier, featuring reduced model width and depth, for training and validation. Different attention modules were tested in the paper, including the self-attention, channel attention, spatial attention, and convolutional block attention module (CBAM). The models were tested on the MIMII and ToyADMOS datasets. The experimental results demonstrated that the self-attention mechanism with SqueezeNet achieved an accuracy of 97% on the previously unseen MIMII and ToyADMOS datasets. Furthermore, the proposed model outperformed the SqueezeNet attention model with other attention mechanisms and state-of-the-art deep architectures, exhibiting a higher precision, recall, and F1-score. Lastly, t-SNE is applied to visualize the features of the self-attention SqueezeNet for different fault classes of both MIMII and ToyADMOS.

Transfer learning based cross-process fault diagnosis of industrial robots

In the actual industrial application of robots, the characteristics of robot malfunctions change accordingly as the working environment becomes increasingly diverse and complex. Utilizing the original fault diagnosis models in new working environments correspondingly leads to a decline in the performance and the generalization capability of the model. Moreover, the monitoring data collected in new working processes often has limited or no labels, making the diagnosis models trained with this data unable to identify faults accurately. In this paper, we propose a Domain adaptive Cross-process Fault Diagnosis method (DCFD) to leverage knowledge from existing working processes for diagnosing faults in new working processes. DCFD uses Multi-Kernel Maximum Mean Discrepancy (MK-MMD) to measure the difference between the current working processes and the previous working processes, enhancing the fault diagnosis capability of the robotic system in cross-process scenarios. DCFD achieves an average fault classification accuracy of 98% on 12 types of migration tasks, which demonstrates the effectiveness of DCFD on cross-process fault diagnosis classification tasks in real-time industrial application scenarios.

Transformer fault diagnosis based on DBO-BiLSTM algorithm and LIF technology

Abstract In response to the deficiencies of traditional power transformer fault detection techniques, such as low sensitivity and the inability for online monitoring, a novel transformer fault diagnosis model combining Laser-Induced Fluorescence (LIF) technology with deep learning is proposed. Initially, the spectral data of transformer insulation oil is acquired using LIF technology, yielding spectral data for various fault types. Subsequently, MinMaxScaler (MMS) and Standard Normalized Variate (SNV) methods are employed for denoising and preprocessing the spectral data. The preprocessed data is then subjected to dimensionality reduction using Linear Discriminant Analysis (LDA) and T-distributed Stochastic Neighbor Embedding (T-SNE) to ensure that the spectral data retains maximal feature information while minimizing its dimensionality. Following this, Long Short-Term Memory (LSTM), Bi-directional Long Short-Term Memory (BiLSTM), Dung Beetle Optimizer-Bi-directional Long Short Term Memory (DBO-BiLSTM), Convolutional Neural Network (CNN), and Support Vector Machine (SVM) models are constructed. The reduced-dimensional data is fed into each of the five models for training to facilitate transformer fault diagnosis. Through comparative analysis among the five models, the optimal model is selected. Experimental results indicate that the DBO-BiLSTM model is the most suitable for transformer fault diagnosis in this experiment, underscoring its significant implications for ensuring the safety of power systems.

Fault diagnosis method for continuous casting machine’s sector segment based on SG-PCA-LSTM

Abstract To address challenges such as the high variability of variables and difficulties in feature extraction during the casting process of the continuous casting machine’s sector segment, a fault diagnosis method based on SG-PCA-LSTM is proposed. This method aims to overcome the issue of fault features obscured by noise in the total tension time series by employing the SG smoothing algorithm for filtering and denoising. By leveraging the inter-segment data correlation and the advantage of PCA in extracting fault feature information, combined with the powerful learning capability of LSTM in modeling, a Principal Component Analysis - Long Short-Term Memory (PCA-LSTM) fault diagnosis model is established. Through comparative analysis against different diagnostic methods in terms of recognition rate, false positive rate, etc., the results obtained by this method are compared against those obtained by using other algorithms. Experimental results demonstrate that the proposed method exhibits good overall performance in terms of accuracy and training time.

Bushing fault diagnosis based on SVM and the improved sparrow search algorithm

Abstract In order to address the issue of low precision in traditional bushing fault diagnosis, a bushing fault diagnosis method based on an improved sparrow search algorithm (ISSA) and support vector machine (SVM) is proposed in this paper. Firstly, the bushing vibration signals are extracted by wavelet packet, and the feature vectors are used as inputs for the SVM. In view of the impact of support vector machine parameters on the model, a sparrow search algorithm is proposed for intelligent optimization. To prevent reaching a local optimum, adaptive inertia weight is added based on the original approach. The final bushing fault diagnosis model is established by training. Comparison experiments with three fault diagnosis models, SSA-SVM, PSO-SVM, and SVM, found that the proposed method achieves complete diagnosis in a shorter time, and the diagnostic accuracy rate is 96.5%, which verifies the feasibility and effectiveness of the model.

Fault diagnosis method for distribution network based on improved deep learning

Abstract Due to the complexity of the grid structure, limited fault samples, and difficulty in obtaining them, there is a need to improve the accuracy of fault diagnosis in distribution networks. To address the issue of insufficient training samples in the target domain leading to poor training results, a fault diagnosis method for distribution networks based on improved deep learning is proposed. Firstly, finite element simulation is employed to generate fault data under different operating conditions, obtaining a sufficient number of samples for feature extraction and enhancement. Secondly, a deep convolutional neural network (DCNN) model is constructed, and the model is trained using the sample data. Finally, the model is used for fault diagnosis in distribution networks under different operating conditions. Experimental results demonstrate that the fault diagnosis model achieves high testing accuracy and is capable of detecting fault locations and types with high precision.

A novel deep learning framework for rolling bearing fault diagnosis enhancement using VAE-augmented CNN model

In the context of burgeoning industrial advancement, there is an increasing trend towards the integration of intelligence and precision in mechanical equipment. Central to the functionality of such equipment is the rolling bearing, whose operational integrity significantly impacts the overall performance of the machinery. This underscores the imperative for reliable fault diagnosis mechanisms in the continuous monitoring of rolling bearing conditions within industrial production environments. Vibration signals are primarily used for fault diagnosis in mechanical equipment because they provide comprehensive information about the equipment's condition. However, fault data often contain high noise levels, high-frequency variations, and irregularities, along with a significant amount of redundant information, like duplication, overlap, and unnecessary information during signal transmission. These characteristics present considerable challenges for effective fault feature extraction and diagnosis, reducing the accuracy and reliability of traditional fault detection methods. This research introduces an innovative fault diagnosis methodology for rolling bearings using deep convolutional neural networks (CNNs) enhanced with variational autoencoders (VAEs). This deep learning approach aims to precisely identify and classify faults by extracting detailed vibration signal features. The VAE enhances noise robustness, while the CNN improves signal data expressiveness, addressing issues like gradient vanishing and explosion. The model employs the reparameterization trick for unsupervised learning of latent features and further trains with the CNN. The system incorporates adaptive threshold methods, the "3/5" strategy, and Dropout methods. The diagnosis accuracy of the VAE-CNN model for different fault types at different rotational speeds typically reaches more than 90 %, and it achieves a generally acceptable diagnosis result. Meanwhile, the VAE-CNN augmented fault diagnosis model, after experimental validation in various dimensions, can achieve more satisfactory diagnosis results for various fault types compared to several representative deep neural network models without VAE augmentation, significantly improving the accuracy and robustness of rolling bearing fault diagnosis.

Toward compound fault diagnosis via EMAGAN and large kernel augmented few-shot learning

Bearings are essential in machinery. Damage to them can cause financial losses and safety risks at industrial sites. Therefore, it is necessary to design an accurate diagnostic model. Although many bearing fault diagnosis methods have been proposed recently, they still cannot meet the requirements of high-accurate prediction of bearing faults. There are several challenges in this: 1) In practical settings, gathering sufficient and balanced sample data for training diagnostic network models proves challenging. 2) The damage to bearings in real industrial production sites is not singular, and compound faults are also a huge challenge for diagnostic networks. To address these issues, this study introduces a novel fault diagnosis model called EMALKNet that integrates DCGAN with Efficient Multi-Scale Attention (EMAGAN) and RepLKNet-XL, enhancing the detection and analysis of bearing faults in industrial machinery. This model employs EMAGAN to explore the underlying distribution of raw data, thereby enlarging the fault sample pool and enhancing the model’s diagnostic capabilities; The large kernel structure of RepLKNet-XL is different from the current mainstream small kernel and has stronger representation extraction ability. The proposed method has been validated on the Paderborn University dataset and the Huazhong University of Science and Technology dataset.

Research on transformer fault diagnosis method based on ACGAN and CGWO-LSSVM

This paper proposes a transformer fault diagnosis method based on ACGAN and CGWO-LSSVM to address the problem of misjudgment and low diagnostic accuracy caused by the small number and uneven distribution of some fault samples in transformer fault diagnosis. Firstly, generate adversarial networks through auxiliary classification conditions, The ACGAN method expands a small and imbalanced number of samples to obtain balanced and expanded data; Secondly, the non coding ratio method is used to construct the characteristics of dissolved gases in oil, and kernel principal component analysis is used, KPCA method for feature fusion; Finally, using the improved cubic gray wolf optimization algorithm, CGWO for least square support vector machines, optimize the parameters of the LSSVM model and construct a transformer fault diagnosis model. The results show that the proposed method has a low false alarm rate and a diagnostic accuracy of 97.66%, compared to IGOA-LSSVM the IChOA-LSSVM and PSO-LSSVM methods improved accuracy by 0.12, 1.76, and 2.58%, respectively. This method has been proven to solve the problems of misjudgment and low diagnostic accuracy caused by small sample sizes and uneven distribution. It is suitable for multi classification fault diagnosis of transformer imbalanced datasets and is superior to other methods.

Complete Ensemble Empirical Mode Decomposition with Adaptive Noise to Extract Deep Information of Bearing Fault in Steam Turbines via Deep Belief Network

Extracting to enhance the accuracy of diagnosing bearing faults in steam turbines, a novel approach focused on extracting key fault features from vibration signals is introduced. Recognizing the complex, non-linear, and non-stationary nature of bearing vibration signals, our strategy involves a sensitivity analysis utilizing a multivariate diagnostic algorithm. The process begins with collecting vibration data from defective bearings via the TMI system. This data is then subjected to Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), enabling the integration of adaptive noise for the extraction of in-depth information. Following this, an analysis in both time and frequency domains — post Fast Fourier Transform (FFT) — is conducted on the decomposed signals, forming the basis of a diagnostic features database. To streamline data analysis and boost the model’s computational efficiency, a combination of eXtreme Gradient Boosting (XGBoost) and Mutual Information Criterion (MIC) is applied for dimensionality reduction. Furthermore, a deep belief network (DBN) is implemented to develop a precise fault diagnosis model for the bearings in rotating machinery. By incorporating sensitivity analysis, a diagnostic matrix is crafted, facilitating highly accurate fault identification. The superiority of this diagnostic algorithm is corroborated by testing with real on-site data and a benchmark database, demonstrating its enhanced diagnostic capabilities relative to other feature selection techniques.

Uncertainty-aware deep learning for monitoring and fault diagnosis from synthetic data

Deep neural networks (DNNs) are often coupled with physics-based and data-driven models to perform fault detection and health monitoring. The system models serve as digital surrogates that generate large quantities of data for training DNNs which would otherwise be difficult to obtain from the real-life system. In such a scenario, the uncertainty in the system model and in the DNN parameters will influence the predictions of the DNN. Here, we quantify the impact of this uncertainty on the performance of DNNs. The uncertainty from the system model is captured with two methods, namely assumed density filtering and heteroskedastic modelling. In addition to quantification, these methods allow training DNNs in an uncertainty-aware manner. The uncertainty in the DNN parameters is captured with Monte Carlo dropout. The proposed approach is demonstrated for fault diagnosis of electric power lines. Data generated from a physics-based model calibrated with real-life measurements is used to train three neural network architectures for fault diagnosis. The results reveal that uncertainty-aware models can provide 1% to 19% improvement in classification accuracy than their deterministic counterparts. The uncertainty-aware models also exhibit better robustness to uncertainty and, thus, offer more reliable models for deployment. Remarkably, the article provides a system-agnostic framework for uncertainty-aware training of DNN models for fault diagnosis and monitoring that explicitly accounts for the synthetic nature of training data.

Empirical study on fine-tuning pre-trained large language models for fault diagnosis of complex systems

With increasing complexity and interconnectivity of the modern industrial systems, effectively diagnosing faults is a core step to Prognostic and Health Management (PHM). Language models, particularly Large Language Models (LLMs) that pre-trained on massive corpora, have demonstrated remarkable capabilities in Natural Language Processing (NLP) and its related downstream tasks. However, how to leverage these models for facilitating system fault diagnosis and verify its effectiveness is rarely explored. This paper incorporates the potential comprehension ability of pre-trained LLMs, and investigates the efficacy of fine-tuning LLMs for realizing efficient system fault diagnosis. The experiments conducted in this study involve both open-source and closed-source models, and utilize a simulation and a real fault diagnosis dataset. We find that these models consistently achieve high performance across various metrics compared to the baselines. Additionally, qualitative and quantitative analysis is performed to investigate several aspects of the approach, such as the impact of dataset size, data normalization, missing values and explainability of the diagnosis, further showcasing the potential as well as limitations of the approach.