Fault Diagnosis Task Research Articles

A Fault Diagnosis Method for Marine Engine Cross Working Conditions Based on Transfer Learning

Marine engines confront challenges of varying working conditions and intricate failures. Existing studies have primarily concentrated on fault diagnosis in a single condition, overlooking the adaptability of these methods in diverse working condition. To address the aforementioned issues, we propose a cross working condition fault diagnosis method named the Balanced Adaptation Domain Weighted Adversarial Network (BADWAN). This method combines transfer learning to tackle the challenges of cross working condition diagnosis with limited labels. Specifically tailored for scenarios with incomplete labeling in the target working conditions, we designed an Enhanced Centroid Balance scheme to balance the label space, thereby enhancing the model’s transfer capabilities. Additionally, we designed an Instance Affinity Weighting scheme on the foundation of Class-level Weighting, refining the model to the instance level for effective information interaction. Furthermore, we incorporated the Adaptive Uncertainty Suppression strategy to further boost the model’s classification prowess. Two experimental scenarios were designed to demonstrate the effectiveness of the proposed model using a Wärtsilä9L34DF dual-fuel engine as an experimental subject. The results demonstrate an over 90% diagnostic accuracy in scenarios with complete target working condition labels and 86% accuracy in scenarios with incomplete labels, outperforming other transfer learning models. The BADWAN model excels in cross-condition fault diagnosis tasks for marine engines with incomplete target working condition labels, offering a novel solution to this field.

Compound Fault Diagnosis of Planetary Gearbox Based on Improved LTSS-BoW Model and Capsule Network

The identification of compound fault components of a planetary gearbox is especially important for keeping the mechanical equipment working safely. However, the recognition performance of existing deep learning-based methods is limited by insufficient compound fault samples and single label classification principles. To solve the issue, a capsule neural network with an improved feature extractor, named LTSS-BoW-CapsNet, is proposed for the intelligent recognition of compound fault components. Firstly, a feature extractor is constructed to extract fault feature vectors from raw signals, which is based on local temporal self-similarity coupled with bag-of-words models (LTSS-BoW). Then, a multi-label classifier based on a capsule network (CapsNet) is designed, in which the dynamic routing algorithm and average threshold are adopted. The effectiveness of the proposed LTSS-BoW-CapsNet method is validated by processing three compound fault diagnosis tasks. The experimental results demonstrate that our method can via decoupling effectively identify the multi-fault components of different compound fault patterns. The testing accuracy is more than 97%, which is better than the other four traditional classification models.

Bearing fault diagnosis via fusing small samples and training multi-state Siamese neural networks

Recently, deep learning techniques have been widely applied to fault diagnosis due to their outstanding feature extraction abilities. The success of deep-learning-based fault diagnosis methods is highly dependent on the quantity and quality of the training data. In practical scenarios, it is challenging to obtain sufficient high-quality training data for fault diagnosis tasks due to complex environments, which would affect the effectiveness of the deep learning methods. In this paper, a new fault diagnosis method is proposed for motor bearing fault diagnosis under small samples. The Siamese neural networks (SNNs) are employed to extract the fault features. A multi-stage training strategy is proposed to train the SNNs with the aim to prevent the training stagnation problem and handle the small sample problem. A multi-source feature fusion network is developed to make full use of the multi-source sensor data by fusing the extracted fault features for further fault diagnosis. The proposed method is applied to motor bearing fault diagnosis on two real-world datasets. Experimental results demonstrate the effectiveness and feasibility of the introduced method for motor bearing fault diagnosis under small samples.

Fault Diagnostics Based on the Analysis of Probability Distributions Estimated Using a Particle Filter

This paper proposes a monitoring procedure based on characterizing state probability distributions estimated using particle filters. The work highlights what types of information can be obtained during state estimation and how the revealed information helps to solve fault diagnosis tasks. If a failure is present in the system, the output predicted by the model is inconsistent with the actual output, which affects the operation of the estimator. The heterogeneity of the probability distribution of states increases, and a large proportion of the particles lose their information content. The correlation structure of the posterior probability density can also be altered by failures. The proposed method uses various indicators that characterize the heterogeneity and correlation structure of the state distribution, as well as the consistency between model predictions and observed behavior, to identify the effects of failures.The applicability of the utilized measures is demonstrated through a dynamic vehicle model, where actuator and sensor failure scenarios are investigated.

A receptive field transfer strategy via layer-aligned distillation learning for fault signal denoising

To improve fault diagnosis performance in complex noise environments, effective signal denoising techniques are necessary. However, traditional denoising methods have proven inadequate for multivariate fault signal denoising, neglecting the correlation among these signals. To this end, we propose a novel denoising module, inspired by traditional signal decomposition and reconstruction methods. Furthermore, to enhance the performance of proposed denoising module, we consider the influence of the receptive field and develop a receptive field transfer strategy using layer-aligned distillation learning. The experiments demonstrate that our approach effectively balances the denoising performance and computational load, offering a novel strategy for developing high-performance denoising networks. What’s more, our strategy reduces the difficulty for fault diagnosis tasks under complex noise environments.

OWFD-UCPM: An open-world fault diagnosis scheme based on uncertainty calibration and prototype management

In real-world fault diagnosis tasks, it is never possible to enumerate all fault types beforehand since there are always unseen situations that may arise unexpectedly. Therefore, fault diagnosis is essentially an open-world recognition task. A desirable open-world fault diagnosis model must be able to perform open-set recognition (OSR) and incremental learning (IL). Classifier calibration and prototype replay are popular in two subtasks. However, existing calibration and replay strategies suffer from tampering with raw data and ignoring resource allocation, respectively. In this work, we formulate an open-world fault diagnosis scheme to address both issues. Firstly, we calibrate the uncertainty of the classifier’s prediction by assigning soft labels to the samples based on their distance from the class center. Then, Shannon entropy is employed to quantify the uncertainty as an estimate of the probability that the sample belongs to the unknown. Secondly, we adaptively manage the memory of old and new known classes according to the training accuracy. Then, based on this memory budget, a dissimilarity-based sparse subset selection algorithm is utilized to pick more diverse exemplars as prototypes for replay. Furthermore, we extend the open-set F-Measure (OSFM) to the weighted OSFM to make it applicable even when the classes are imbalanced. Experimental results on multiphase flow facility and wastewater treatment plant demonstrate the feasibility and superiority of the proposed method.

A Fault Diagnosis Method for 5G Cellular Networks Based on Knowledge and Data Fusion.

As 5G networks become more complex and heterogeneous, the difficulty of network operation and maintenance forces mobile operators to find new strategies to stay competitive. However, most existing network fault diagnosis methods rely on manual testing and time stacking, which suffer from long optimization cycles and high resource consumption. Therefore, we herein propose a knowledge- and data-fusion-based fault diagnosis algorithm for 5G cellular networks from the perspective of big data and artificial intelligence. The algorithm uses a generative adversarial network (GAN) to expand the data set collected from real network scenarios to balance the number of samples under different network fault categories. In the process of fault diagnosis, a naive Bayesian model (NBM) combined with domain expert knowledge is firstly used to pre-diagnose the expanded data set and generate a topological association graph between the data with solid engineering significance and interpretability. Then, as the pre-diagnostic prior knowledge, the topological association graph is fed into the graph convolutional neural network (GCN) model simultaneously with the training data set for model training. We use a data set collected by Minimization of Drive Tests under real network scenarios in Lu'an City, Anhui Province, in August 2019. The simulation results demonstrate that the algorithm outperforms other traditional models in fault detection and diagnosis tasks, achieving an accuracy of 90.56% and a macro F1 score of 88.41%.

High imbalance fault diagnosis of aviation hydraulic pump based on data augmentation via local wavelet similarity fusion

Data augmentation methods, such as SMOTE and deep generative networks, have the potential to solve class-imbalance issue in aviation hydraulic pump fault diagnosis. Nevertheless, the scarcity of faulty samples often leads augmented samples generated using such methods suffer from blurred category boundaries, limited diversity, and mode collapse. To avoid these issues, a new data augmentation method namely Local Wavelet Similarity Fusion (LWSF) is proposed, which augments faulty samples by preserving and distorting the wavelet packet coefficients (WPCs) of the original faulty samples. An important property is that LWSF can generate high-quality synthesis samples without complex model training. First, faulty samples are decomposed into a series of frequency bands using wavelet packet decomposition. Second, the amplitudes of WPCs at a few randomly selected frequency bands are distorted, which is accomplished through a similarity-weighted fusion of the target WPCs with the closest related WPCs matched from reference samples, with the goal of keeping distortion within an appropriate range. Third, these WPCs are used to reconstruct the samples, which serve as the augmented samples. Besides, to enhance diversity, normal samples are also employed to assist in the distortion. Finally, the effectiveness of LWSF is validated by a series of experimental comparisons. In an imbalanced fault diagnosis task, the accuracy and F1-score obtained by LWSF are 97.16 % and 97.35 %, respectively, which are 3.59 % and 7.30 % higher than the best one among the five compared methods.

A novel mechanical fault diagnosis for high-voltage circuit breakers with zero-shot learning

In recent years, data-driven methods have been widely used in the field of high-voltage circuit breakers (HVCBs) fault diagnosis. However, due to the complex mechanical structure of HVCBs and the special operating environment, it is difficult to obtain a large amount of fault samples and exhaust all fault types. The lack of fault samples and fault types typically results in significant degradation of diagnostic performance. To address this problem, we design a novel method named R-MLL for zero-shot HVCB fault diagnosis. R-MLL tries to identify unseen fault types only by training seen fault types. First, to focus on all the details of the HVCB mechanical vibration signal, the wavelet transform is used to multi-scale refine the fault data. Second, a new network (RDSCNN) is designed to extract multidimensional features based on convolutional neural network incorporating residual block and depthwise separable convolution. Third, a multi-label attribute learning network is designed, enabling the fusion of fault features and attributes and allowing attribute labels to assist fault diagnosis tasks. Extensive experiments show that R-MLL gets average accuracy of 86.2% for compound fault diagnosis without the need of using target fault samples for building the diagnostic model. Comparisons with a number of state-of-the-art techniques show the superiority of the proposed method for zero-shot HVCB diagnosis.

Fault Diagnosis of Complex Industrial Systems Based on Multi-Granularity Dictionary Learning and Its Application

Nowadays, the intelligent fault diagnosis problem of modern industrial systems has received increasing attention. However, with the increasing scale of industrial systems, the same category of faulty data often contains multiple working conditions, which leads to the multi-granularity of faulty data and the increasing complexity of data distribution. The possible existence of fine-granularity inter-class similarities in multi-granularity data can interfere with coarse-granularity recognition tasks, which brings challenges to data-driven fault diagnosis tasks. To solve the above issue, a fault diagnosis method based on multi-granularity dictionary learning is proposed in this paper. Specifically, the proposed method integrates prior knowledge into the dictionary learning framework by introducing the concept of “centroid atom”, which embeds the multi-granularity structure in the dictionary and improves the discrimination of dictionary atoms. In order to validate the proposed approach, experiments are conducted on a numerical simulation case and a zinc smelting roasting process. Compared with some state-of-the-art methods, the proposed approach performs better in the classification accuracy which shows that it can make full use of the knowledge provided by the multi-granularity structure while it is difficult to be modeled by the other methods. Therefore, it can be applied to fault diagnosis tasks more precisely and efficiently. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Motivated by the fact that industrial faults often occur in different modes, and different faults may occur in the same mode, the fault data often has multi-granularity characteristics, this paper proposes a multi-granularity dictionary learning method for complex industrial fault diagnosis. The proposed method can learn the multi-granularity structure in the data, and the obtained model contains both coarse-grained and fine-grained information, which effectively improves the fault diagnosis accuracy. Intensive experimental results show that the proposed method performs better than some state-of-the-art methods, it can make full use of the knowledge provided by the multi-granularity structure, while it is difficult to be modeled by others. Above all, it is verified as suitable for fault diagnosis of real industrial systems.

Unsupervised Deep Transfer Learning Method for Rolling Bearing Fault Diagnosis Based on Improved Convolutional Neural Network

As a critical component widely used in mechanical equipment, the implementation of intelligent fault diagnosis for rolling bearings can improve the reliability of equipment. In this paper, a method named JMMD-CKDSCNet is proposed to address the task of fault diagnosis under unsupervised domain discrepancy scenarios. First, the convolutional kernel dropout (CKD) mechanism is introduced in the convolutional layer, and partial convolutional kernel weights are set to be inactive during the training process using the random mask. Second, skip connection (SC) fuses the features of multiple shallow layers to preserve and transfer the original features. Finally, domain alignment is achieved using joint maximum mean discrepancy (JMMD), which measures the joint distribution between different domains with feature discrepancies under the condition that the target domain lacks labeled data. The experimental results demonstrate that CKDSCNet exhibits superior generalization performance and outperforms other models in terms of diagnostic accuracy and model performance. Compared with other domain adaptation methods, JMMD has significant superiority, proving the application value of JMMD-CKDSCNet.

Research on Fault Detection and Localization Techniques for Distribution Networks Based on Edge Clustering

Abstract With the intelligent transformation of the power grid, the number and type of various terminals, sensors, and new types of loads in the distribution network increase, and the huge amount of information and noise information accessing the power grid brings great challenges for fault detection and localization. In this paper, we propose to combine wavelet transform and LSTM unit to form a novel neural network basic unit TFM and examine the fault detection and localization capability of TFM by combining them with a typical example system, IEEE33. Spectral clustering and the K-Means algorithm are utilized to cluster the edge nodes, and the number of nodes in the three partitions after partition correction is 11, 10, and 12 nodes in order. The data shows that the TFM system performs the fault diagnosis task with better test accuracy than LSTM in every dimension, and its accuracy improvement for fault localization is the largest, at 5.39%. Introducing two reconfiguration scenarios for three edge node partitioning models and retrograde fault localization detection, compared with the no reconfiguration scenario, their localization accuracies all produce different degrees of decline, but always not less than 80%. The localization accuracy of the MⅡ model is still not less than 98% in the fault resistance range of 500~1000Ω, which proves that the TFM system can effectively extract high-resistance fault features.

Mechanical Fault Diagnosis With Noisy Multisource Signals via Unified Pinball Loss Intuitionistic Fuzzy Support Tensor Machine

In this paper, a challenging and significant intelligent fault diagnosis task is investigated, in which multisource sensor signals with intense noise and outlier disturbances are jointly analyzed. Such a scenario has hardly been considered in industrial research. To this end, we develop a novel tensor-based nonlinear classifier called unified pinball loss intuitionistic fuzzy support tensor machine (UPIFSTM), which can successfully solve the above tasks and improve the performance of fault diagnosis in practical applications. First, the noisy multisource signals are converted into time-frequency images and reconstructed into tensor samples to mine the time domain, frequency domain features and coupled structure information in the spatial domain. Next, we design two nonlinear forms of nonmembership functions in the tensor space, and obtain an intuitionistic fuzzy score for each training sample to enhance the robustness of the model. Subsequently, pinball loss function is introduced to better handle noise sensitivity and resampling instability problems. Note that, we employ the tensor robust principal component analysis method to accurately recover the low-rank tensors corrupted by sparse noise from the original tensors. Finally, two numerical examples are presented to verify the feasibility and validity of the proposed method.

Data-Driven Joint Fault Diagnosis Based on RMK-ASSA and DBSKNet for Blast Furnace Iron-Making Process

Blast furnace iron-making process (BFIP) is one of the most critical procedures in the iron and steel industry where timely detection and accurate classification of faults have always been of core focus. However, the coupling effects of system’s nonlinear and nonstationary characteristics often cause process consistent underlying information to be buried, allowing accurate extraction to be a significant challenge. This also complicates the development of BFIP fault diagnosis model. Therefore, we propose a novel data-driven joint fault diagnosis strategy that employs regularized mutual kernel analytic stationary subspace analysis (RMK-ASSA) and deep broad stationary kernel network (DBSKNet) to eliminate this interference. To develop this method, we first construct an RMK-ASSA approach to address the poor modeling accuracy caused by standard analytic stationary subspace analysis (ASSA)’s inability to handle complex process nonlinearity. Global and local kernels are utilized to account for multiple nonlinearities in BFIP data. The weight of different nonlinear data is calculated by regularized principal component analysis, and the main information is imported into ASSA to obtain more robust and accurate modeling results by eliminating the interference of redundant noise. Subsequently, we design a DBSKNet-based classifier to implement the fault diagnosis task. This network further considers the nonlinearity by boosting kernel structure in depth and width while distinguishing the respective contributions of different kernels to fault diagnosis results. Finally, a double-layer loop parameter optimization algorithm is used for optimizing. Simulated cases and practical BFIP tests validate that RMK-ASSA eliminates the negative impact caused by nonstationary data and that the proposed joint fault diagnosis strategy outperforms other methods. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —BFIP’s nonlinear and nonstationary coupling properties pose unique challenges in eliminating distractions, constructing fault classifiers and accurately detecting process anomalies. To tackle these challenges, this paper proposes a joint fault diagnosis strategy based on RMK-ASSA and DBSKNet. RMK-ASSA effectively estimates nonlinear consistent features, while DBSKNet mines rich deep nonlinear information, accurately distinguishing variations in BFIP data under different working conditions. Experimental results demonstrate that this data-driven strategy can perform high-quality fault diagnosis, enabling field engineers to execute operations efficiently.

Semi-supervised multi-sensor information fusion tailored graph embedded low-rank tensor learning machine under extremely low labeled rate

This paper investigates a demanding and meaningful task of intelligent fault diagnosis, in which multi-sensors signals are fused for semi-supervised analysis with few labeled fault data. Exploring effective strategies to solve this task from an industrial or academic perspective remains a challenging and resource-consuming task. To this issue, this study develops a new low-rank tensor-based semi-supervised classifier, called graph embedded low-rank tensor learning machine (GE-LRTLM), which can effectively alleviate the foregoing difficulties and increase the diagnosis precision in engineering applications. First, multi-sensor and multi-channel vibration signals are converted into the pixel matrices that are stacked as the multi-sensor information fusion feature tensors, making the coupling relationship between multi-sensor signals remained and achieving a reasonable fusion of multi-source features. Additionally, an advanced tensor decomposition method, tensor nuclear norm (TNN), is introduced in GE-LRTLM model to obtain the low-rank structure information of each feature tensor, implementing the extraction of the most important feature and patterns from the tensor data while ensuring that the tensor data structure remains unchanged. Ultimately, the manifold regularization and tensor-based graph construction method are introduced to obtain potential label information from unlabeled samples, achieving better description of the geometry similarity and distribution of tensor data. Numerous semi-supervised experiments are conducted across multiple datasets, and the results demonstrate that the proposed method can achieve a classification accuracy of 97% even when the number of labeled samples is extremely limited. Simultaneously, it also verifies that the combination of the constructed labeled and unlabeled multi-sensor information fusion tensor samples can promote the improvement of model accuracy.

Gaussian-Linearized Transformer with Tranquilized Time-Series Decomposition Methods for Fault Diagnosis and Forecasting of Methane Gas Sensor Arrays

Methane is considered as a clean energy that is widely used in places with high environmental requirements. The increasing demand for methane exploration in polar and deep sea extreme environments has a positive role in carbon neutrality policies. As a result, there will be a gradual increase in exploration activities for deep sea methane resources. Methane sensors require high reliability but are prone to faults, so fault diagnosis and forecasting of gas sensors are of vital practical significance. In this work, a Gaussian-linearized transformer model with a tranquilized time-series decomposition method is proposed for fault diagnosis and forecasting tasks. Since the traditional transformer model requires more computational expense with time complexity of O (N2) and is not applicable to continuous-sequence prediction tasks, two blocks of the transformer are improved. First, a Gaussian-linearized attention block is modified for fault-diagnosis tasks so that its time complexity can be changed to O (N), which can reduce computational resources. Second, a model with proposed attention for fault forecasting replaces the traditional embedding block with a decomposed block, which can input the continuous sequence data to the model completely and preserve the continuity of the methane data. Results show that the Gaussian-linearized transformer improves the accuracy of fault diagnosis to 99% and forecasting with low computational cost, which is superior to that of traditional methods. Moreover, the least mean-square-error loss of fault forecasting is 0.04, which is lower compared with the traditional time series prediction models and other deep learning models, highlighting the great potential of the proposed transformer for fault diagnosis and fault forecasting of gas sensor arrays.

A fault diagnosis method based on feature-level fusion of multi-sensor information for rotating machinery

Traditionally, most fault diagnosis work on rotating machinery is carried out on single sensor datasets. However, the single feature source may suffer from missing or inaccurate features, which is especially sluggish for fault diagnosis tasks under noise interference. Feature-level fusion of multi-sensor information can obtain more comprehensive and abundant feature information, while improving the feature discrimination. Therefore, through feature-level fusion of multi-sensor information, a parallel multi-scale attentional convolutional neural network (PMSACNN) is proposed in this paper to achieve rotating machinery fault diagnosis. A dilated wide convolutional layer is designed to extract the short-time features of signals with noise by performing sparse sampling on them. The multi-scale structure is constructed to capture the diversity feature information of signals, and the feature-level stitching of multi-sensor information is realized by the parallel input mechanism. Feature fusion is achieved by adaptively correcting the importance of different channel features by using channel attention. The global averaging pooling operation is introduced to reduce the number of parameters and improve the efficiency of the model operation. The effectiveness of PMSACNN is verified by using the bearing dataset acquired from the mechanical comprehensive diagnosis simulation platform. The experimental results indicate that the proposed method outperforms the existing methods of this field in terms of fault diagnosis accuracy and noise immunity, which can improve the reliability and safety of rotating machinery.

Open set recognition fault diagnosis framework based on convolutional prototype learning network for nuclear power plants

As an Open Set Recognition (OSR) problem, nuclear power plant fault diagnosis requires not only the correct classification of known faults, but also the effective identification of unknown faults, which cannot be satisfied by most previously developed models. In this study, a novel nuclear power plant OSR fault diagnosis framework based on Convolutional Prototype Learning (CPL) is proposed, in which CPL is used to extract discriminative fault features from raw nuclear power plant data. Besides, two classification methods, One-Class Support Vector Machine (OCSVM) method and Prototype Matching by Distance (PMD) method, are developed to complete the fault diagnosis of open space for the framework. To verify the feasibility and effectiveness of the proposed OSR framework, numerical experiments on 24 OSR tasks with high-dimensional and strong-nonlinear complex nuclear power plant simulation data are conducted, and the OSR performance evaluate by normalized accuracy and Youden's index, feature visualization and convergence rates are analyzed. Results show that compared with adopting traditional Convolutional Neural Network (CNN), the proposed CPL-based framework can significantly boost the OSR diagnostic performance on nuclear power plant fault diagnosis tasks, which benefits from the excellent ability of CPL to extract intra-class compact and inter-class separable feature representation.

A novel generalized source-free domain adaptation approach for cross-domain industrial fault diagnosis

Domain adaptation has been widely applied in data-driven fault diagnosis tasks to address the domain shift problem between source and target data. However, conventional domain adaptation methods require both domains to be known, which is not always feasible due to privacy concerns and big data transmission. To overcome this limitation, a dedicated method called source-free domain adaptation (SFDA) has been developed to ensure reliable performance without relying on source data during target model adaptation. SFDA can achieve accurate classification tasks under domain shift problems and source data-free scenarios. We propose a generalized source model with manifold Mixup data augmentation and label smoothing techniques to avoid overfitting during the source model training. Based on this model, a novel self-training framework is proposed to implement the domain adaptation task and achieve accurate prediction performance. The experimental results from three real-world datasets demonstrate the effectiveness of the proposed approach.

A two-step image segmentation based on clone selection multi-object emperor penguin optimizer for fault diagnosis of power transformer

Power transformer is one of the critical and valuableness apparatus in the secure operation of the power system. The infrared image fault diagnosis can reflect the status of the power transformer. However, how to detect the fault point of the diverse infrared images is a difficult problem. We present a two-stage multilevel threshold image segmentation method to finish the task of power transformers fault diagnosis. The multi-objective emperor penguin optimizer based on the clone selection strategy optimizes the multi-level image segmentation method for discovering the optimal threshold. The 3DOtsu and determination of optimal target number function as the fitness function and we convert them into multi-objective optimization problems. The proposed method is compared with the multi-objective optimization algorithms and novel fault diagnosis methods under the classic images and infrared images of the power transformer. The experiment results show that MOEPO/C has a good performance than others compared algorithms in Feature Similarity Index, Uniformity measure, Peak Signal‑to‑Noise Ratio, and CPU time. Especially, the proposed method obtains high accuracy in power transformer fault diagnosis.