Fault Diagnosis Problem Research Articles

Adversarial training of multi-scale channel attention network for enhanced robustness in bearing fault diagnosis

For bearing fault diagnosis problems in extremely noisy environments, this paper proposes an innovative universal adversarial training method. This method dynamically introduces noise into the training data, adaptively optimizing the model’s robustness. It applies to any neural network without incurring additional computational overhead in the reasoning process. Additionally, we introduce the multi-scale channel attention network (MSCAN). This network employs stacked convolutional kernels of varying sizes to extract features at different scales from the input signal. The incorporation of the channel attention mechanism allocates distinct weights to features of different scales, further enhancing the network’s representational capacity. Moreover, an automated machine learning-based automated tuning approach is employed to optimize the model training process, aiding in improving inference accuracy. Compared to existing designs, MSCAN exhibits exceptional accuracy. Through adversarial training, it maintains a 99.44% accuracy rate on the Case Western Reserve University dataset under strong −3 dB noise conditions. On the Paderborn University dataset at 0 dB, this adversarial training significantly improves the testing accuracy of various models by an average of 36.42%.

Reversed trend comprehensive assessment-based inverter fault diagnosis under various complex interferences in microgrid

The healthy operation of inverter is the basic issues to ensure the quality of engineering power supply. However, the various complex interferences from microgrid engineering applications are relatively a difficult problem for fault diagnosis of inverter, e.g. harmonic components and unbalanced state. It increases the difficulty of the failure analysis, model design, algorithm realization and thresholds selection, even may lead to false alarm and erroneous triggering of protection units. Hence, a new fault diagnosis algorithm is proposed. Firstly, the reversed coordinate two-dimensional processing (RCT-dP) method is proposed to obtain reversed two-dimensional data (RTD) by inserting a moving reversed coordinate, which is very convenient for data attenuation segmentation and reversed trend extraction. Secondly, the obtained RTD are used for a proposed reversed trend comprehensive assessment (RTCA) method to obtain assessment variables based on multiple reversed trends and corresponding reliability, which can effectively extract the fault component, effectively reduce the influence of harmonic components and unbalanced state. Thirdly, the relative location information of detected signals are extracted. Then, the obtained assessment variables and relative location information are processed by variable regularization processing. Finally, the diagnosis results are obtained through a fault decision. Compared with existing fault diagnosis methods, the proposed fault diagnosis method can accurately detect and locate fault for any switch of inverter under harmonic components and unbalanced state. Meanwhile, because the fault diagnosis algorithm is based on saltatory driving, it can realize very low number of start-up without affecting the accuracy of the diagnosis. The experimental results are shown to validate the proposed algorithm.

Cross-domain open-set rolling bearing fault diagnosis based on feature improvement adversarial network under noise condition

Domain adaptation (DA) technology has the ability to solve fault diagnosis (FD) problems under variable operating conditions. However, DA technology faces two issues: (1) in general, vibration signals inevitably contain noise, which makes it difficult to extract discriminant features.(2) there are unknown fault types in target domain. These issues will lead to poor diagnostic performance. To solve above issues, a new cross-domain open-set transfer FD method called feature improvement adversarial network (FIAN) is proposed in this article. Specifically, to alleviate noise interference, a feature improvement module (FIM) is proposed and embedded into the backbone convolutional neural network to form new feature extractor. FIM uses soft threshold function to enhance important information and suppresses redundant information. Furthermore,open-set DA by back-propagation (OSBP) is introduced into FIAN. OSBP can predict the probability that a target domain sample belongs to an unknown category, so that it can effectively identify unknown and known category samples. Experimental results demonstrated its effectiveness and superiority in two bearing datasets.

Vibration characterization of rolling bearings with compound fault features under multiple interference factors.

As a key component of rotating machinery power transmission system, rolling bearings in gas turbines are often required to serve in complex working conditions such as the high speed, the heavy load, the variable load, the variable rotational speed, and so on. The signals of bearing failures are easily drowned out by strong background noise and disturbances of related components. In the mechanical transmission system, the signals of bearing failures are easily submerged by the strong background noise and the disturbance of related components, especially for the composite bearing failures, which seriously hinders the effective identification of the vibration characteristics of the bearing operating state and increases the difficulty of fault diagnosis. In order to investigate the impact of interference on the bearing, through the establishment of rolling bearing composite fault vibration model, analyze the relationship between the vibration signals caused by different types of bearing failures and the corresponding vibration characteristics, to reveal the transmission system of the parts of the perturbation of the main multi-interference factors on the bearing fault signal influence law. The experimental verification shows that disturbance yp(t) caused by the sum of gear meshing frequency, and installation errors of the shaft, and coupling in the transmission system and background noise ni(t), which makes the fault frequency relatively weak and difficult to observe, and makes it difficult to accurately separate the fault information of the bearing. It provides a theoretical basis to solve the problem of damage identification and fault diagnosis of rolling bearings under multi-interference state.

Improved Conditional Domain Adversarial Networks for Intelligent Transfer Fault Diagnosis

Intelligent fault diagnosis encounters the challenges of varying working conditions and sample class imbalance individually, but very few approaches address both challenges simultaneously. This article proposes an improvement network model named ICDAN-F, which can deal with fault diagnosis scenarios with class imbalance and working condition variations in an integrated way. First, Focal Loss, which was originally designed for target detection, is introduced to alleviate the sample class imbalance problem of fault diagnosis and emphasize the key features. Second, the domain discriminator is improved by the default ReLU activation function being replaced with Tanh so that useful negative value information can help extract transferable fault features. Extensive transfer experiments dealing with varying working conditions are conducted on two bearing fault datasets with the effect of class imbalance. The results show that the fault diagnosis performance of ICDAN-F outperforms several other widely used domain adaptation methods, achieving 99.76% and 96.76% fault diagnosis accuracies in Case 1 and Case 2, respectively, which predicts that ICDAN-F can handle both challenges in a cohesive manner.

Sensor Fault Detection and Diagnosis of Linear Parabolic PDE Systems With Unknown Inputs

This paper investigates the sensor bias fault detection and diagnosis problem for linear parabolic partial differential equation (PDE) systems under the existence of unknown input signals. A variation of Wirtinger's inequality is used to design a Luenberger-type PDE observer and radial basis function (RBF) neural networks are applied to approximate the unknown inputs, guaranteeing the boundedness of the state estimation error. Taking the measurement error as the fault indication signal, a residual evaluation logic is developed to achieve fault detection. An adaptive diagnostic law is constructed to estimate the values of sensor bias faults once they are detected. <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sigma$</tex-math></inline-formula> -modification RBF neural networks are designed to compensate for the unknown inputs in the presence of sensor faults, ensuring that both state and sensor bias faults estimation errors converge to some adjustable sets. The effectiveness and applicability of the developed fault diagnosis strategy are demonstrated by simulation results on a heat diffusion process.

An open source experimental framework and public dataset for vibration-based fault diagnosis of electrical submersible pumps used on offshore oil exploration

An Electrical Submersible Pump (ESP) is an important equipment used in the industry for lifting liquids in various types of wells. An ESP is widely used in the oil industry for offshore exploration. Detecting a faulty ESP before installation is a predictive maintenance measure in order to extend its operational time. Machine learning fault diagnosis is an effective way for performing this task. Machine learning fault diagnosis algorithms are highly dependent of the availability of an appropriate problem dataset. This paper describes in detail the problem of ESP fault diagnosis and the ESPset dataset, a real-world and public dataset for vibration-based fault diagnosis of electrical submersible pumps used on offshore oil exploration. In addition, the paper also proposes an experimental framework for adequately comparing research works based on the ESPset dataset and defines benchmark classifiers and respective results as referential to the fault diagnosis research community. The framework considers the fact that some subset of samples are not drawn independently, and therefore, proposes a cross-validation sampling strategy that mitigates the similarity bias among samples. Indeed, this work shows that a conventional k-fold cross-validation may lead to a clear overestimation of the average performance. This fact is supported by results which show that the best classification model drops from a mean F-measure of 0.887 to 0.733 when removing the similarity bias from the data.

A cross-domain intelligent fault diagnosis method based on multi-source domain feature adaptation and selection

Although fault diagnosis methods integrating transfer learning are research hotspots, their ability to handle industrial fault diagnosis problems with large domain differences still needs to be improved. A multi-source domain feature adaptation and selection method is presented to address the issues of domain mismatch and domain negative transfer. The method integrates the top-level network parameter transfer strategy with the 2D convolutional neural network backbone network to acquire the target domain feature extractor quickly. Multiple feature adaptive extractors (FAEs) are constructed using a multi-branch structure to align the source and target domain’s feature distributions, respectively. The inter-domain distance computed by multi-kernel maximum mean discrepancy is embedded in the FAEs loss function to improve the inter-domain matching degree. Based on the information gain of the adaptively integrated features, the ensemble adaptive selection is performed on the extracted feature matrices to exclude the negative transfer feature. Finally, the effective feature matrix is input into the diagnosis classifier for classification. Cross-domain fault diagnosis experiments are developed based on the data set gathered from several types of rotating machinery operated under varied working conditions. The experimental results show that the proposed method outperforms the existing intelligent fault diagnosis methods in terms of fault detection accuracy, generalization, and stability.

Attention-enhanced conditional-diffusion-based data synthesis for data augmentation in machine fault diagnosis

Data scarcity and class imbalance are pervasive challenges in machine fault diagnosis, impeding the development and broad adaptation of accurate and reliable deep-learning-based fault detection systems. To address these issues, we propose a novel attention-enhanced conditioning-guided diffusion-based approach for synthesizing additional training data. By generating noisy motor-current signals and employing a diffusion process to reduce noise levels, we obtain synthetic data that closely resembles the statistical properties and patterns of real-world data. The quality of the synthesized samples is assessed using a four-layer, pre-trained convolutional neural network, achieving an impressive classification rate of 96.39%. This demonstrates the effectiveness of our attention-enhanced conditioned diffusion-based model in synthesizing critical features for fault detection, making it well-suited for the introduced fault detection task. To further investigate the quality of the synthesized data samples, we implement a specific training strategy that uses the generated samples as training data. The trained diffusion model generates samples per class, which are then used to train a simple four-layer convolutional neural network for fault classification. Remarkably, the model achieves an accuracy of 98.96% when evaluated with real inverter signals, indicating that the generated samples effectively capture the distribution of real data. For further evaluation, multiple scenarios are created confirming the value of the additionally synthesized samples for real-world bearing fault detection. Our approach presents a well-suited solution to the data scarcity and class imbalance problem in machine fault diagnosis. The proposed method enhances the accuracy and reliability of fault diagnosis systems, offering valuable insights for various real-world condition monitoring applications.

A multi-feature-based fault diagnosis method based on the weighted timeliness broad learning system

Accurate and timely fault diagnosis is a vital task to ensure process safety of modern industrial facilities. Motivated by the complex variations of process signals and mutual coupling of faults, this paper presents a multi-feature-based fault diagnosis method based on the weighted timeliness Broad Learning System (BLS). The proposed method fuses multiple features extracted from the original process data to improve the fault diagnosis performance, and makes the diagnosis model suitable for dynamic fault diagnosis problems by incorporating the BLS. The major contributions of this study are twofolds: 1) A systematic multi-feature extraction method is proposed to extract long-term trend features, short-term trend features, and binary alarm signals, which reflect the direction and amplitude changes of process signals under faulty conditions; 2) a weighted timeliness BLS structure with multiple fault-sensitive features as the input is proposed to ensure the dynamic characteristics of the fault diagnosis model. The designed fault diagnosis model can be updated in an incremental manner, and thus can improve the model updating efficiency while ensuring accuracy. The effectiveness and superiority of the proposed method is demonstrated by a case study based on the Tennessee Eastman benchmark process.

Interval Observer Design for Fault Diagnosis

The problem of interval observer design for systems described by linear models under the external disturbances is considered. The problem is solved based on the reduced-order model of the original system of minimal dimension. The relations allowing designing interval observer insensitive or having minimal sensitivity to the disturbance are obtained. The designed interval observers are used to solve the problem of fault diagnosis. Theoretical results are illustrated by example.

Intelligent Machinery Fault Diagnosis With Event-Based Camera

Event-based cameras are the emerging bio-inspired technology in vision sensing. Different from the traditional standard cameras, the event-based cameras asynchronously record the brightness change per pixel, and have the great merits of high temporal resolution, low energy consumption, high dynamic range, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">etc</i> . While the event-based cameras have been initially exploited in several common vision-based tasks in the recent years, the investigation on machine condition monitoring problem is quite limited. This paper offers the first attempt in the current literature on exploring the contactless event vision data for machine fault diagnosis. A vibration event representation is proposed to transform the event records into typical data samples, and a deep convolutional neural network model is used for processing the event information. To enhance the model robustness against environmental noisy vision events, an event data augmentation method is proposed to introduce variations of the event patterns. A deep representation clustering method is further proposed to improve the pattern recognition performance with respect to different machine health conditions. Experiments on the event vision-based rotating machine fault diagnosis problem are carried out. It is extensively validated that high fault diagnosis accuracies can be obtained using the vision data from the event-based cameras, which are competitive with the popular accelerometer data. Considering the properties of flexibility, portability and data recognizability, the event-based cameras thus provide a promising new tool for contactless machine health condition monitoring and fault 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.

Cross-Condition Fault Diagnosis of an Aircraft Environmental Control System (ECS) by Transfer Learning

Fault diagnosis models based on machine learning are often subjected to degradation in performance when dealing with data that are differently distributed than the training data. Such an occasion is common in reality because machines usually operate under various conditions. Transfer learning is a solution for the performance degradation of cross-condition fault diagnosis problems. This paper studies how transfer learning algorithms transfer component analysis (TCA) and joint distribution alignment (JDA) improve the cross-condition fault diagnosis accuracy of an aircraft environmental control system (ECS). Both methods work by transforming the source and target domain data into a feature space where their distributions are aligned to allow a uniform classifier to act accurately in both domains. This paper discovered that both TCA and JDA produce significantly more accurate results than traditional methods on target domains with unlabelled ECS data taken at different operating conditions than the source domain. Additionally, when dealing with unlabelled data from unknown conditions bearing a different composition of classes in the target domain, TCA is found to be more robust and accurate, generating an average predictive accuracy of 95.22%, which demonstrates the ability of transfer learning in solving similar problems in the real-world application of fault diagnosis.

Multidimensional clustering based fault diagnosis method for wind turbine transmission chain

Abstract With the rapid development of wind power generation, ensuring the reliability and fault diagnosis of wind turbine transmission chains has become a focal point. Traditional clustering methods that address the fault diagnosis problem in wind turbine transmission chains suffer from low fault discrimination and accuracy, as they rely on a single indicator. This paper proposes a two-dimensional clustering model that utilizes multiple indicators to address the issue of distinguishing similar faults within the wind turbine transmission chain from various perspectives and dimensions. The proposed approach involves collecting vibration signals from the transmission chain of wind turbines using sensors and using the root mean square and kurtosis of the fault signal as clustering features. A multidimensional polar coordinate clustering model is established, with the signal kurtosis representing the polar angle and the root mean square representing the polar radius. The clustering of fault signals within wind turbine transmission chains is achieved by optimizing the clustering boundaries by establishing a clustering boundary optimization equation. The results of the developed clustering model are evaluated using external and internal evaluation methods. Experimental results demonstrate that this method exhibits high accuracy and low computational complexity in diagnosing faults within wind turbine transmission chains. In comparison with other clustering methods, the proposed method outperforms them according to the experimental results. Hence, this study presents a novel approach for health monitoring and fault diagnosis of the transmission chain of wind turbines, which has significant implications for improving the reliability of wind turbine operation and reducing maintenance costs.

Fault diagnosis of analogue circuits based on artificial intelligence algorithms

Abstract The fault diagnosis problem of analog circuits has been paid more and more attention, and the realization of circuit fault feature extraction and pattern classification are two of the key problems. This paper first combines wavelet packet and energy entropy to design a fault feature extraction method based on wavelet packet entropy to solve the problem of analog circuit fault feature extraction. Secondly, the principle of SVM and particle swarm optimization algorithm are combined to design the fault diagnosis process of analog circuits based on an artificial intelligence algorithm. Finally, take the sallen-key circuit as an example to analyze the effectiveness of the wavelet packet entropy algorithm for fault feature extraction and analyze the effectiveness of this paper’s method based on the analog circuit of Wen’s bridge oscillation circuit. The results show that after wavelet packet entropy extraction of the feature vector values is less than 0.001, and the accuracy of the extraction is more than 0.98, the best parameters of the optimization is (182.4, 0.05), the false alarm rate of the fault diagnostic method is 0, the misdiagnosis rate is 0.08, the omission rate is 0, and the correctness rate of the diagnosis of the fault is 0.92. Based on this research is able to carry out the fault diagnosis of the analog circuit.

Design of a remote assistance model for truck maintenance in the mining industry

PurposeIt is well known in the mining industry that the increase in failures and breakdowns is due mainly to a poor maintenance policy for the equipment, in addition to the difficult access that specialized personnel have to combat the breakdown, which translates into more machine downtime. For this reason, this study aims to propose a remote assistance model for diagnosing and repairing critical breakdowns in mining industry trucks using augmented reality techniques and data analytics with a quality approach that considerably reduces response times, thus optimizing human resources.Design/methodology/approachIn this work, the six-phase CRIPS-DM methodology is used. Initially, the problem of fault diagnosis in trucks used in the extraction of material in the mining industry is addressed. The authors then propose a model under study that seeks a real-time connection between a service technician attending the truck at the mine site and a specialist located at a remote location, considering the data transmission requirements and the machine's characterization.FindingsIt is considered that the theoretical results obtained in the development of this study are satisfactory from the business point of view since, in the first instance, it fulfills specific objectives related to the telecare process. On the other hand, from the data mining point of view, the results manage to comply with the theoretical aspects of the establishment of failure prediction models through the application of the CRISP-DM methodology. All of the above opens the possibility of developing prediction models through machine learning and establishing the best model for the objective of failure prediction.Originality/valueThe original contribution of this work is the proposal of the design of a remote assistance model for diagnosing and repairing critical failures in the mining industry, considering augmented reality and data analytics. Furthermore, the integration of remote assistance, the characterization of the CAEX, their maintenance information and the failure prediction models allow the establishment of a quality-based model since the database with which the learning machine will work is constantly updated.

Few-Shot Fault Diagnosis Method of Rotating Machinery Using Novel MCGM Based CNN

The existing fault diagnosis methods can achieve good results when various status fault data are available. However, the construction of the diagnosis model is often unachievable in the actual application because only normal data are available, which is actually a few-shot fault diagnosis problem. Therefore, a novel intelligent few-shot fault diagnosis method of rotating machinery based on the convolutional neural network (CNN) using virtual samples generated by the mechanism character generative model (MCGM) integrating the generative adversarial network (GAN) is proposed. The distribution pattern of common parameters that reflect the fault category is learned using the GAN and source domain fault data. Then, the normal state data of the target domain is combined with the distribution common parameters to generate virtual samples in target domain based on the MCGM. Moreover, the fault diagnosis model is trained by virtual samples based on the CNN. Finally, the proposed fault diagnosis method is validated using the laboratory bearing data, the industrial data and the public data of the rotating machinery, respectively. The results show that the proposed method achieves an average accuracy of 93.38% in the diagnostic task, exhibiting at least 4.56% better performance than other comparison methods.

A novel asymmetrical autoencoder with a sparsifying discrete cosine Stockwell transform layer for gearbox sensor data compression

The lack of an efficient compression model remains a challenge for the wireless transmission of gearbox data in non-contact gear fault diagnosis problems. In this paper, we present a signal-adaptive asymmetrical autoencoder with a transform domain layer to compress sensor signals. First, a new discrete cosine Stockwell transform (DCST) layer is introduced to replace linear layers in a multi-layer autoencoder. A trainable filter is implemented in the DCST domain by utilizing the multiplication property of the convolution. A trainable hard-thresholding layer is applied to reduce redundant data in the DCST layer to make the feature map sparse. In comparison to the linear layer, the DCST layer reduces the number of trainable parameters and improves the accuracy of data reconstruction. Second, training the autoencoder with a sparsifying DCST layer only requires a small number of datasets. The proposed method is superior to other autoencoder-based methods on the University of Connecticut (UoC) and Southeast University (SEU) gearbox datasets, as the average quality score is improved by 2.00% at the lowest and 32.35% at the highest with a limited number of training samples.

Research on a novel fault diagnosis method for gearbox based on matrix distance feature

Aiming at the problem of fault diagnosis and classification of rolling bearing and gear of gearboxes, a novel method based on matrix distance features of Gramian angular field (GAF) image is proposed based on sliding window compressible GAF transformation. The method converts the one-dimensional fault signal into a two-dimensional feature matrix and constructs the discrimination matrix of each fault category by establishing the mean value of the feature matrix of a priori samples. For the new sampled signal, after converting it into a two-dimensional feature matrix, the feature matrix is obtained. The fault classification is carried out by using the matrix distance between feature matrix and the discrimination matrix of each category. The method is validated by the test data of Case Western Reserve University and the acoustic emission data from a gearbox test bench. The classification accuracy is 99.17% and 95.71%, which presented the feasibility and effectiveness of the novel method proposed in this paper.