Fault Identification Problem Research Articles

LTFM-net framework: Advanced intelligent diagnostics and interpretability of insulated bearing faults in offshore wind turbines under complex operational conditions

The rapid advancement of intelligent theories and models, exemplified by deep learning, has achieved remarkable success across numerous fields. However, given that the complexity and variability of offshore wind turbine systems, particularly in the context of high-power variable-frequency control of insulated bearings in offshore wind turbines, the problem of fault identification has become a recognized technical challenge. Additionally, fully exploiting the temporal characteristics of insulated bearing fault data poses a key problem that demands urgent resolution. To address these gaps, this paper pioneers a novel Lightweight Temporal Feature-focused framework, named LTFM-Net, aimed at solving the difficult problem of identifying insulated bearing faults in offshore wind turbines in practical engineering applications. Specifically, this framework enables the intelligent identification of insulated bearing faults under harsh operating conditions such as alternating voltage and variable loads, marking a first in this field. Furthermore, an innovative strategy named Weighted Diminish Recurrent Unit (WDRU) was developed, along with the derivation of its backpropagation formula, which is innovatively applied to the feature extraction module of the LTFM-Net framework for the first time. Thus, an efficient method for acquiring fault data from insulated bearings in offshore wind turbines was proposed. Based on a unified dataset, the diagnostic performance of the LTFM-Net framework was evaluated and compared with seven advanced methods. The results demonstrate that the LTFM-Net achieves precise identification of insulated bearing faults, confirming its excellent generalization, robustness, and superiority. The introduction of t-SNE for visualizing the fault characteristics of insulated bearings uncovered by the LTFM-Net framework further enhances its reliability, accuracy, and credibility.

Experimental study on classification and identification method for fault signals of mining steel wire ropes

Abstract In the coal mining production process, wire ropes play a crucial role as the main tool for transporting personnel and materials in the entire coal mine hoisting system, and their fault identification is particularly critical. To address the problem of fault identification of mining wire ropes, a recognition model design combining K Singular Value Decomposition (SVD) with Genetic Algorithm (GA) optimized Support Vector Machine (SVM) is proposed. Firstly, K Singular Value Decomposition is used to denoise the collected wire rope damage signals. Feature vectors are extracted from the denoised and reconstructed signals to form the feature set of wire rope damage. Genetic Algorithm is utilized to select the optimal parameters of the Support Vector Machine and train it to obtain the optimal identification model for wire rope damage. Simulation and experimental results show that compared with wavelet thresholding and Empirical Mode Decomposition (EMD) denoising algorithms, the method using K Singular Value Decomposition for denoising achieves a signal-to-noise ratio of 25.166dB and a root mean square error of 0.805. Compared with Particle Swarm Optimization (PSO) optimized Support Vector Machine identification model, the identification rate of the Support Vector Machine identification model optimized by Genetic Algorithm is higher, reaching 96.67%. This method realizes accurate identification of different damage signals of wire ropes, which is conducive to ensuring the safe and efficient production of coal mines.

Monitoring of Perception Systems: Deterministic, Probabilistic, and Learning-Based Fault Detection and Identification (Abstract Reprint)

This paper investigates runtime monitoring of perception systems. Perception is a critical component of high-integrity applications of robotics and autonomous systems, such as self-driving cars. In these applications, failure of perception systems may put human life at risk, and a broad adoption of these technologies requires the development of methodologies to guarantee and monitor safe operation. Despite the paramount importance of perception, currently there is no formal approach for system-level perception monitoring. In this paper, we formalize the problem of runtime fault detection and identification in perception systems and present a framework to model diagnostic information using a diagnostic graph. We then provide a set of deterministic, probabilistic, and learning-based algorithms that use diagnostic graphs to perform fault detection and identification. Moreover, we investigate fundamental limits and provide deterministic and probabilistic guarantees on the fault detection and identification results. We conclude the paper with an extensive experimental evaluation, which recreates several realistic failure modes in the LGSVL open-source autonomous driving simulator, and applies the proposed system monitors to a state-of-the-art autonomous driving software stack (Baidu's Apollo Auto). The results show that the proposed system monitors outperform baselines, have the potential of preventing accidents in realistic autonomous driving scenarios, and incur a negligible computational overhead.

A bearing fault diagnosis method with improved symplectic geometry mode decomposition and feature selection

A rolling bearing fault diagnosis method based on improved symplectic geometry mode decomposition (SGMD) and feature selection was proposed to solve the problem of low fault identification due to the influence of noise on early bearing fault features. First, the SGMD SGMD is improved to enhance its robustness in decomposing signals with noise, then the time domain, frequency domain, and time-frequency features of each symplectic geometric component are extracted as feature vectors. Second, a comprehensive feature selection strategy is proposed to select the optimal subset of features that are conducive to fault classification. Finally, considering the problem of low classification accuracy of a single machine learning model, the AdaBoost-WSO-SVM model is constructed for fault classification using the AdaBoost algorithm of integrated learning. Experimental decomposition of complex signals with noise indicates that the improved SGMD is more effective compared to traditional SGMD. Subsequently, multiple experiments were conducted using the bearing datasets from Case Western Reserve University (CWRU) and Jiangnan University (JNU). The experimental results reveal that, after comprehensive feature selection and ensemble learning pattern recognition experiments on the CWRU dataset, the average accuracy of fault diagnosis can reach 99.67%. On the JNU dataset, the proposed fault diagnosis method achieves an average accuracy of 95.03%. This suggests that, compared to other feature selection methods and classification models, the proposed approach in this paper exhibits higher accuracy and generalization capabilities.

A Fault Identification Method for Metal Oxide Arresters Combining Suppression of Environmental Temperature and Humidity Interference with a Stacked Autoencoder

Most existing methods aiming to solve the fault identification problem of metal oxide arresters (MOAs) are limited by strong subjectivity in judgment, the significant impact of environmental temperature and humidity on the online monitoring of the resistance current, and poor generalization ability. Therefore, in this article, we propose an MOA fault identification method that combines suppressing environmental temperature and humidity interference with a stacked autoencoder (SAE). Firstly, a functional relationship model between resistance current and environmental temperature and humidity is established. Then, a temperature and humidity interference suppression method based on weighted nonlinear surface modeling is proposed to normalize the resistance current to the same reference temperature and humidity conditions. Finally, an MOA fault identification method combining the suppression of environmental temperature and humidity interference with an SAE is proposed. Furthermore, a comprehensive comparison is conducted on the recall, accuracy, F1-score, and average accuracy of support vector machine, random forest, logistic regression, and SAE classification algorithms in three different scenarios to demonstrate the effectiveness of the proposed method. The results indicate that environmental temperature and humidity interference suppression for resistive current prior to MOA fault classification significantly reduce the number of false alarms. Compared with other methods, the MOA fault identification method, which combines environmental temperature and humidity interference suppression with an SAE, has the highest average accuracy of 99.7%.

Multi-view feature fusion fault diagnosis method based on an improved temporal convolutional network

This paper addresses the problem of fault identification in rotating machinery by analysing vibration data using a neural network approach. Temporal convolutional networks (TCNs) have attracted a lot of focus in the domain of fault identification; however, TCN convolution kernels are small and susceptible to high-frequency noise interference. Furthermore, the default weight coefficient of the internal residual connection is 1. When there are few residual blocks, the residual block characteristic extraction ability is suppressed and only the vibration signal collected at a single location is utilised for fault diagnosis as it contains incomprehensive fault information. To tackle the above issues, this paper proposes a multi-view feature fusion fault diagnosis algorithm with an adaptive residual coefficient assignment TCN with wide first-layer kernels (WD-ARCATCN). Firstly, a WD-ARCATCN feature extraction network is designed to extract deep state features from different views and the first layer of the TCN is set as a wide-kernel (WD) convolutional layer to suppress high-frequency noise. An adaptive residual coefficient assignment (ARCA) unit is designed in the residual connection to increase the characteristic learning capability of the residual blocks and the residual blocks with ARCA units are stacked to further extract multi-view deep fault features. In this paper, acceleration signals collected at different positions are used as the multi-view feature source for the first time and the fault information contained is more comprehensive. Then, based on a self-attention mechanism, the multi-view feature fusion method is improved and the view weights are adaptively assigned to effectively fuse different view characteristics and enhance the identification of the fault characteristics. Finally, the mapping between the multi-view fusion features and the labels is achieved using a softmax classifier. The algorithm has been tested using experimental data from the bearing vibration database at Case Western Reserve University (CWRU) and it performed much better compared to other diagnostic algorithms.

Monitoring of perception systems: Deterministic, probabilistic, and learning-based fault detection and identification

This paper investigates runtime monitoring of perception systems. Perception is a critical component of high-integrity applications of robotics and autonomous systems, such as self-driving cars. In these applications, failure of perception systems may put human life at risk, and a broad adoption of these technologies requires the development of methodologies to guarantee and monitor safe operation. Despite the paramount importance of perception, currently there is no formal approach for system-level perception monitoring. In this paper, we formalize the problem of runtime fault detection and identification in perception systems and present a framework to model diagnostic information using a diagnostic graph. We then provide a set of deterministic, probabilistic, and learning-based algorithms that use diagnostic graphs to perform fault detection and identification. Moreover, we investigate fundamental limits and provide deterministic and probabilistic guarantees on the fault detection and identification results. We conclude the paper with an extensive experimental evaluation, which recreates several realistic failure modes in the LGSVL open-source autonomous driving simulator, and applies the proposed system monitors to a state-of-the-art autonomous driving software stack (Baidu's Apollo Auto). The results show that the proposed system monitors outperform baselines, have the potential of preventing accidents in realistic autonomous driving scenarios, and incur a negligible computational overhead.

Analysis of Statistical Data Heterogeneity in Federated Fault Identification

Federated Learning (FL) is a setting where different clients collaboratively train a Machine Learning model in a privacy-preserving manner, i.e., without the requirement to share data. Given the importance of security and privacy in real-world applications, FL is gaining popularity in many areas, including predictive maintenance. For example, it allows independent companies to construct a model collaboratively. However, since different companies operate in different environments, their working conditions may differ, resulting in heterogeneity among their data distributions. This paper considers the fault identification problem and simulates different scenarios of data heterogeneity. Such a setting remains challenging for popular FL algorithms, and thus we demonstrate the considerations to be taken into account when designing federated predictive maintenance solutions.

Output‐feedback fault‐tolerant tracking control for coupled 2 × 2 hyperbolic PDE systems with multiplicative sensor faults

AbstractThis paper proposes an output‐feedback fault‐tolerant tracking control scheme for coupled hyperbolic PDE systems with multiplicative sensor faults. In order to estimate the system states, an observer is designed by constructing four filters, which impose time delays to their input signals. For sensor fault identification problem, the gradient descent method is utilized based on a parametric model to estimate the fault parameter. With the filter‐based observer and the estimated fault parameters, a novel control strategy is proposed via backstepping design technique to achieve the tracking objective. Finally, the simulation studies are given to verify the tracking performance of the proposed fault‐tolerant tracking control scheme.

Intelligent diagnosis of rolling bearings with imbalanced data based on the ConVAE-CNN model

Data-driven intelligent diagnosis method has been widely used in mechanical equipment fault identification. However, the data set imbalance is still one of the critical problems affecting the effect of intelligent diagnosis in the practical work of rotating machinery. To solve the problem of fault identification of rolling bearings with imbalanced data sets, a rolling bearing intelligent diagnosis method based on the ConVAE-CNN model was proposed in this paper. In this method, a convolutional variational autoencoder network (ConVAE) model is constructed. In the coding stage, the convolutional layer is used to extract the features of minority samples. In the decoding stage, full connection layers are used to expand the dataset of minority samples. Bearing fault features were extracted by convolution and pooling operations of the convolutional neural network model, and the performance of the proposed method was tested using rolling bearing experimental data. The results show that the proposed method effectively solves the bearing fault classification problem with imbalanced data sets. Compared with the other diagnosis methods, the performance of the proposed method is better, and it has a broad application prospect in the diagnosis of imbalanced data.

Domain-Adaptive Prototype-Recalibrated Network with Transductive Learning Paradigm for Intelligent Fault Diagnosis under Various Limited Data Conditions.

In real industrial scenarios, intelligent fault diagnosis based on data-driven methods has been widely researched in the past decade. However, data scarcity is widespread in fault diagnosis tasks owning to the difficulties in collecting adequate data. As a result, there is an increasing demand for both researchers and engineers for fault identification with scarce data. To address this issue, an innovative domain-adaptive prototype-recalibrated network (DAPRN) based on a transductive learning paradigm and prototype recalibration strategy (PRS) is proposed, which has the potential to promote the generalization ability from the source domain to target domain in a few-shot fault diagnosis. Within this scheme, the DAPRN is composed of a feature extractor, a domain discriminator, and a label predictor. Concretely, the feature extractor is jointly optimized by the minimization of few-shot classification loss and the maximization of domain-discriminative loss. The cosine similarity-based label predictor, which is promoted by the PRS, is exploited to avoid the bias of naïve prototypes in the metric space and recognize the health conditions of machinery in the meta-testing process. The efficacy and advantage of DAPRN are validated by extensive experiments on bearing and gearbox datasets compared with seven popular and well-established few-shot fault diagnosis methods. In practical application, the proposed DAPRN is expected to solve more challenging few-shot fault diagnosis scenarios and facilitate practical fault identification problems in modern manufacturing.

Wave front rising time based traveling wave protection for multi-terminal VSC-HVDC grids

To deal with the problem of high-resistance fault identification in multi-terminal VSC-HVDC grids, a novel wave front rising time based traveling wave protection is proposed in this paper. For such purpose, the traveling wave is firstly analyzed from its generation, propagation to refraction for the sake of discovering its influence factors. The wave front rising time is revealed to be approximately proportional to the fault distance while insensitive to the fault resistance and operation condition during line propagation. Moreover, it significantly increases when refraction occurs at the line terminal. Secondly, based on these characteristics, the novel wave front rising time based traveling wave protection as well as its analytical setting calculation is proposed. The proposed protection can work with higher-fault-resistance identification capability and faster-operating speed, compared with other protections. Besides, the efficiency of the proposed protection setting calculation is greatly improved since tedious electromagnetic transient simulations are avoided. Finally, the feasibility and robustness of the proposed protection are validated by a four-terminal VSC-HVDC grid on PSCAD/EMTDC platform.

ИДЕНТИФИКАЦИЯ ДЕФЕКТОВ В ПРИВОДАХ НА ОСНОВЕ МЕТОДОВ ОПТИМАЛЬНОГО УПРАВЛЕНИЯ

The paper exams the problem of identifying faults in the drives of robotic systems, the dynamicsmodel of which is described by linear differential equations. It is proposed to search for asolution to the fault identification problem based on the solution of an auxiliary optimal controlproblem for a dynamical system in which the role of an unknown vector function describingemerging faults is performed by some auxiliary control, which should provide a minimum for theresidual functional. Based on the solution of the auxiliary optimal control problem, a fault diagnosticobserver is proposed. In this case, the fault itself is found through the solution of the correspondingalgebraic Riccati equation and the differential equation for the auxiliary variable. Unlikepopular approaches to solving the problem of fault identification based on observers operatingin a sliding mode, the proposed method allows us to expand the class of systems for which theidentification problem can be solved. It is known that the methods of sliding mode observers designimpose certain restrictions on the systems under consideration. The proposed approach basedon optimal control can also give results for systems with nonlinear dynamics. In this case, methodsof approximate solution of optimal control problems based on the representation of the system inlinear form with state-dependent coefficients (the so-called State-dependent Riccati Equation,SDRE) are likely to be effective. The improvement of the proposed method in this direction will bethe subject of further research. The stated theory is shown on the example of fault identification ina DC drive. Different cases are considered for a system with complete observations (the entirestate vector is known) and with incomplete observations. It was shown during the simulation thatthe quality of faults identification can be improved by selecting the appropriate values of the penaltymatrices in the residual functional, while it is possible to achieve good diagnostics separatelythrough various channels of faults occurrence. The paper presents recommendations on the choiceof penalty matrices. The simulation results confirmed the operability of the diagnostic observerssynthesized using the proposed method.

Improved DCNN Based on Multi-Source Signals for Motor Compound Fault Diagnosis

Induction motors, the key equipment for rotating machinery, are prone to compound faults, such as a broken rotor bars and bearing defects. It is difficult to extract fault features and identify faults from a single signal because multiple fault features overlap and interfere with each other in a compound fault. Since current signals and vibration signals have different sensitivities to broken rotor and bearing faults, a multi-channel deep convolutional neural network (MC-DCNN) fault diagnosis model based on multi-source signals is proposed in this paper, which integrates the original signals of vibration and current of the motor. Dynamic attenuation learning rate and SELU activation function were used to improve the network hyperparameters of MC-DCNN. The dynamic attenuated learning rate can improve the stability of model training and avoid model collapse effectively. The SELU activation function can avoid the problems of gradient disappearance and gradient explosion during model iteration due to its function configuration, thereby avoiding the model falling into local optima. Experiments showed that the proposed model can effectively solve the problem of motor compound fault identification, and three comparative experiments verified that the improved method can improve the stability of model training and the accuracy of fault identification.

A novel acceleration criterion for remote-end grounding-fault in MMC-MTDC under communication anomalies

The multi-terminal HVDC system based on the modular multilevel converter (MMC-MTDC) has very high technical merits for long-distance, flexible power transmission. In recent years, there has been a significant improvement in developing its fast-speed primary protection, especially for local-measurement-based ones immune to communication anomalies. However, in many cases, the problem of remote-end fault identification for the local-measurement-based protection elements needs further studies, mainly because such protection elements should balance between sensitivity and security. This paper proposes a novel acceleration criterion to identify remote-end faults for the MMC-MTDC. Based on the difference of the traveling wave propagation characteristics between the scenario of internal faults and that of the external fault, the local-end protection element will detect a highly-oscillating signal due to the opening of the remote-end DC circuit breaker. In contrast, no such signal will be observed in the external fault scenario. The wavelet time entropy is utilized to quantify the feature of oscillation. The performance of the proposed criterion is assessed based on the established four-terminal MMC-MTDC on the PSCAD/EMTDC platform. Results indicate that by using the proposed criterion, the sensitivity of the local-measurement-based protection element against remote-end faults is greatly enhanced.

Fault Identification in Electric Servo Actuators of Robot Manipulators Described by Nonstationary Nonlinear Dynamic Models Using Sliding Mode Observers.

The problem of fault identification in electric servo actuators of robot manipulators described by nonstationary nonlinear dynamic models under disturbances is considered. To solve the problem, sliding mode observers are used. The suggested approach is based on the reduced order model of the original system having different sensitivity to faults and disturbances. This model is realized in canonical form that enables relaxing the limitation imposed on the original system. Theoretical results are illustrated by practical example.

Fault Identification in Mechatronic Systems

The paper studies the problem of fault identification in mechatronic systems described by nonlinear models under the disturbances. To address the problem, sliding mode observers are used. The suggested approach for constructing sliding mode observer is based on the reduced order model of the initial system. This allows reducing complexity of sliding mode observer and relaxing the restrictions imposed on the initial system. The obtained results are illustrated by the example of general electric servoactuator.

Fault Diagnosis of Energy Networks: A Graph Embedding Learning Approach

For industrial parks containing energy systems, fault diagnosis technology is of great significance for their safe operation. In recent years, the topology of energy systems has become more complex due to the use of technologies such as cogeneration, leading to multi-energy coupling. Critical equipment and user nodes in these complex energy networks are vulnerable to a lack of sensor data or non-idealities in the measurement environment. There is an urgent need for a unified and robust fault-diagnosis framework for the overall system to identify faults even under non-ideal data conditions. In this paper, to address the problem of fault identification and state prediction, a novel deep learning model is constructed based on graph-embedded recurrent neural networks (RNNs) with self-attentional layers. Unstructured data are put into the graph neural network to extract common spatial features. An additive attention mechanism is implemented in the graph attention network (GAT) to integrate multi-scale node information. The graph operator is computed within a gated recurrent unit (GRU) that captures the full range of temporal features. In addition, loss functions are introduced for fault identification and state prediction. Data from an industrial park experiment platform is used for fault identification experiments. The advantages of the proposed approach are illustrated by comparative experiments with different levels of missing data.

Fault Identification in Non-Stationary Systems Based on Sliding Mode Observers

The paper is devoted to the problem of fault identification in technical systems described by non-stationary nonlinear dynamic equations under unmatched disturbances. To solve the problem, sliding mode observers are used. The suggested ap- proach is based on the model of the original system of minimal dimension having different sensitivity to the faults and distur- bances in contrast to the traditional approaches to sliding observer design which are based on the original system. Additionally it is assumed that matrices describing such a model have the canonical form and are constant. The main purpose of using such a model is possibility to take into account the non-stationary feature of the systems. As a result, the model has stationary dynamic and non-stationary additional term that allows to promote sliding mode design. Besides, the new approach to design sliding mode observers is suggested. The peculiarity of this approach is that it does not require that original systems should be minimum phase and detectable. According to the traditional approaches stability of the observer is provided by minimum phase and detectability properties. In our approach, stability of the observer is achieved due to the canonical form of the matrices describing the model. In addition, the matching condition is not necessary. This allows to extend a class of systems for which sliding mode observers can be designed. Theoretical results are illustrated by practical example of electric servoactuator.

Fault identification in nonlinear dynamic systems not satisfying matching, minimum phase, and detectability conditions

The paper studies the fault identification problem for nonlinear control systems under unmatched disturbances. A novel approach to construct a sliding mode observer is proposed for systems that do not satisfy common conditions required for fault estimation, in particular matching condition, minimum phase condition, and detectability conditions. The suggested approach is based on the reduced order model of the original system and on the canonical form of matrices describing such a model. This allows to reduce the complexity of sliding mode observers and relax the limitations imposed on the original system. Three different cases for disturbances are considered and the appropriate solutions are suggested.