Application In Fault Diagnosis Research Articles

Digital twin-assisted dual transfer: A novel information-model adaptation method for rolling bearing fault diagnosis

Rolling bearing fault diagnosis is of great importance to the safety management of mechanical equipment. The scarcity of labelled fault data makes it difficult to adequately perform the training process of intelligent diagnosis models, and this will result in these intelligent models not being effectively and widely used in practice. Although some recent studies have verified that the addition of dynamic model response to the training process will greatly improve the ability of the model with low cost and high efficiency, it is still stuck in poor effect caused by large information distribution difference between dynamic model response and real measured data. Focusing on this issue, a digital twin-assisted dual transfer (DTa-DT) method with information and model adaptation was proposed for rolling bearing fault diagnosis. Different from the traditional digital-analogue driven transfer methods, the proposed DTa-DT aims to simultaneously synthesize data information transfer and feature model transfer together with domain transfer error minimization. In particular, it should be noted that the DTa-DT architecture consists of a dual transfer learning process, including digital twin-driven information transfer (DTd-IT) and digital-analogue-driven model transfer (DAd-MT), where the information is collaborated with the model to improve the integrated transfer diagnosis effect under sampling. On one aspect, with the employment of bearing dynamic model responses, DTd-IT is innovatively designed to establish the transfer of dynamic information and measured information. The information distribution difference between these twin data and real measured data is effetely adjusted with the introduced actual inference components, where the twin data with low information distribution difference can be well fusion generated by the information transfer digital twin (ITDT) model. On the other aspect, considering the truth that there are still small sample cases of real measured data and information distribution differences will affect the quality of the twin data, a digital-analogue driven model transfer (DAd-MT) method is further proposed, where the deep branch transfer network (DBTN) model with improved convolutional neural network (CNN) is used to achieve an accurate fault diagnosis effect with the help of digital twin data. Experiments and wear analysis verified that the proposed DTa-DT can significantly reduce the distribution difference between the dynamic model response and the real measured data, thus achieving low-cost and efficient rolling bearing transfer diagnosis compared to other ten state-of-the-art deep learning models. It can be predicted that the proposed dual transfer architecture provides more opportunities for the practical application of intelligent fault diagnosis under small sample sizes.

Adaptive DBSCAN Clustering and GASA Optimization for Underdetermined Mixing Matrix Estimation in Fault Diagnosis of Reciprocating Compressors.

Underdetermined blind source separation (UBSS) has garnered significant attention in recent years due to its ability to separate source signals without prior knowledge, even when sensors are limited. To accurately estimate the mixed matrix, various clustering algorithms are typically employed to enhance the sparsity of the mixed matrix. Traditional clustering methods require prior knowledge of the number of direct signal sources, while modern artificial intelligence optimization algorithms are sensitive to outliers, which can affect accuracy. To address these challenges, we propose a novel approach called the Genetic Simulated Annealing Optimization (GASA) method with Adaptive Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering as initialization, named the CYYM method. This approach incorporates two key components: an Adaptive DBSCAN to discard noise points and identify the number of source signals and GASA optimization for automatic cluster center determination. GASA combines the global spatial search capabilities of a genetic algorithm (GA) with the local search abilities of a simulated annealing algorithm (SA). Signal simulations and experimental analysis of compressor fault signals demonstrate that the CYYM method can accurately calculate the mixing matrix, facilitating successful source signal recovery. Subsequently, we analyze the recovered signals using the Refined Composite Multiscale Fuzzy Entropy (RCMFE), which, in turn, enables effective compressor connecting rod fault diagnosis. This research provides a promising approach for underdetermined source separation and offers practical applications in fault diagnosis and other fields.

Generalized adaptive singular spectrum decomposition and its application in fault diagnosis of rotating machinery under varying speed

Rotating machinery fault signals often consist of multiple components with time varying frequencies under variable speed conditions. Spectral overlap exists among these components, making it difficult to independently separate the features of the components. Singular spectrum decomposition (SSD), a singular spectrum analysis-based signal decomposition method, has shown its great potential in suppressing background noise and extracting fault-related components in complex background noise environments. However, SSD is a frequency domain decomposition method with equivalent filtering characteristics, and it is susceptible to the mode mixing when processing signals with spectral overlap. Moreover, the choice of a key parameter in the iteration decomposition process of SSD, the embedding dimension, is determined using an empirical formula, which might cause suboptimal decomposition outcomes. To address these issues, this paper proposes a generalized adaptive singular spectrum decomposition (GASSD) method, which combines generalized demodulation with improved embedding dimension selection for SSD. GASSD incorporates SSD into the framework of adaptive generalized demodulation to separate specific frequency domain features. Firstly, for an effective generalized demodulation analysis, a region block synchronous ridge extraction method is proposed to accurately estimate the instantaneous frequency ridges from the time-frequency plane, which helps construct proper demodulation phase functions. Secondly, to achieve optimal analysis of SSD, a Gini moderation decomposition index is designed to improve the construction of the trajectory matrix by determining an appropriate embedding dimension. Finally, the reliability of the proposed method is demonstrated by analyzing wind turbine generator bearing fault signals and rotor rubbing fault signals.

Caputo–Fabrizio fractional stochastic resonance with graphene potential enhanced by NLOF and its applications in fault diagnosis of rotating machinery

Caputo–Fabrizio fractional stochastic resonance with graphene potential enhanced by NLOF and its applications in fault diagnosis of rotating machinery

A cloud model-based interval-valued evidence fusion method and its application in fault diagnosis

In fault diagnosis methods based on evidence fusion, a piece of evidence is usually extracted from the fault feature information, which uses the single-valued belief degrees (SVB) to measure the likelihoods of the different fault modes happening. However, SVB seems rough and incomplete for modeling fault information with uncertainty. Therefore, an interval-valued evidence (IVE) fusion method is proposed via cloud model. Compared to the SVB structure, the IVE with the interval-valued belief structure contains more useful fault information. Firstly, the nominal normal cloud model (NCM) about each fault mode and the test normal cloud model (TNCM) are established through the statistical analysis of the historical and testing fault sample data, respectively. TNCMs are matched with each NCM to obtain the corresponding IVE. Then, a novel IVE reasoning rule is defined to combine all IVEs coming from different fault features. Finally, in the fault diagnosis experiments of motor rotors, the proposed method is verified to provide more accurate fault decision results compared to the traditional evidence fusion method. Furthermore, the proposed method is extended to solve general data classification problems with benchmark datasets of University of California Irvine (UCI), showing it has better classification ability compared to some classification methods.

An adaptive cepstrum feature representation method with variable frame length and variable filter banks for acoustic emission signals

Acoustic emission technology is widely employed in defect detection, structural health monitoring, fault diagnosis, and other applications due to its benefits of non-contact, real-time, sensitivity, and flexibility. To implement efficient and timely intelligent monitoring, it is crucial to promptly and precisely gather the time-varying properties in the non-stationary acoustic emission signals. The current work proposes an adaptive cepstrum feature representation method that combines variable frame length and variable filter bank. The variable frame length is implemented based on the spectral distribution correlation, and the optimal frame length and frame rate are selected by iterative operations. The variable filter bank, on the other hand, characterizes the local measure features of variable frame length signals by setting dynamic weight distributions. The proposed adaptive cepstrum algorithm can be used as an auxiliary tool to initially analyze complex non-stationary signals, and thus effectively identify the time-varying and frequency components in acoustic emission signals. The superiority of the proposed method has been confirmed on simulation data. Furthermore, the practical performance of the proposed method is evaluated and illustrated based on the burst signal from laser shock peening processing and the mixed signal from pipeline leakage. The proposed method can be extended to other broadband signals and can be used for feature pre-processing before deep learning network modeling to improve recognition accuracy due to its high time–frequency resolution.

Forecasting top oil temperature for UHV reactor using Seq2Seq model with convolutional block attention mechanism

The top oil temperature in ultra-high voltage (UHV) reactors has attracted enormous interest due to its wide applications in fault diagnosis and insulation evaluation. In this work, the precise prediction method based on the Seq2Seq module with the convolutional block attention mechanism is proposed for the UHV reactor. To reduce the influence of vibratility and improve computational efficiency, a combination of the encoding layer and decoding layer named Seq2Seq is performed to reconstruct the complex raw data. The convolutional block attention mechanism (CBAM), composed of spatial attention and channel attention, is utilized to maximize the use of information in data. The Seq2Seq-CBAM is established to forecast the variation tendency of the oil temperatures in the UHV reactor. The experimental results show that the proposed method achieves high prediction accuracy for the top oil temperature in both single-step and multi-step.

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.

Time-frequency enhanced characterization method based on asymmetric image reconstruction autoencoder

The vibration signals of mechanical equipment are subject to the influence of complex and variable working conditions, often exhibiting non-smooth and non-linear characteristics. The conventional time-frequency (TF) analysis (TFA) method, which relies on energy concentration, is susceptible to noise and impact, making it challenging to accurately extract fault characteristics. To overcome these limitations, this paper proposes an innovative approach. In this paper, we introduce an asymmetric image reconstruction autoencoder model, which is based on two well-known TFA methods, namely, short-time Fourier transform (STFT) and synchroextracting transform (SET), effectively reducing noise and improving the TF energy concentration process through learning the mapping relationship between STFT and SET. To address the clarity issue in the reconstructed TF images, the paper incorporates a channel attention mechanism known as SE Block into the encoding-decoding structure. Additionally, a skip connection structure is introduced to aid in restoring the structural details of the reconstructed TF images. Moreover, an improved weighted joint loss function is proposed to adaptively enhance various types of TF distribution features. This enhancement ensures that different characteristics of TF distribution are adequately addressed during the reconstruction process. The proposed method is put to the test using both simulated signals and experimental signals from gearbox rolling bearing faults. The results demonstrate that compared to traditional TFA and post-processing methods, the proposed model exhibits superior capabilities in enhancing the TF characterization of multi-source time-varying signals. Furthermore, it demonstrates remarkable robustness to noise and can accurately extract instantaneous frequency. These findings point to the promising potential of this method for mechanical fault identification and diagnosis applications.

Expert knowledge modelling software design based on Signed Directed Graph with the application for PWR fault diagnosis

Online monitoring and Fault Diagnosis and Detection (FDD) can help the operator to enhance the situation awareness. The Signed Directed Graph (SDG) has the significant advantages that SDG-based FDD not only infers the incipient faults and reveals fault propagation paths but also comprehensively explains causes of failure. In this study, an expert knowledge modelling software is designed and developed based on SDG method. Firstly, the SDG-based process monitoring and FDD algorithms are derived by coupling the threshold method and the quality trend analysis method. Secondly, the expert knowledge modelling software is designed and developed not only considering the convenience of the engineer but also the effectiveness of the SDG-based algorithms. Finally, a Pressurized Water Reactor (PWR) is applied to demonstrate the SDG modelling and verify the SDG models. The case study demonstrates that the developed expert knowledge modelling software can effectively diagnose the incipient faults and infer variable impact as the fault propagation paths

Multivariate intrinsic wave-characteristic decomposition and its application in gear fault diagnosis

In the early stages of gear faults, the background noise in the signal is pronounced, making it challenging to fully assess the health status of equipment based on a single-channel signal. Processing multi-channel signals proves beneficial for extracting fault information comprehensively. Adaptive multivariate signal decomposition methods, such as multivariate empirical mode decomposition (MEMD) and multivariate local characteristic-scale decomposition (MLCD), employ a fixed multivariate mean curve extraction method for signal decomposition. Consequently, these methods often exhibit suboptimal performance when decomposing different multi-channel signals. This study defines nine multivariate mean curve extraction methods and introduces the multivariate intrinsic wave-characteristic decomposition (MIWD) method based on the principles of mean curve optimization and an adaptive projection method. MIWD dynamically optimizes the multivariate mean curve during the decomposition process, resulting in superior performance in terms of decomposition accuracy, capability, and orthogonality compared to MEMD and MLCD. Furthermore, we apply MIWD to gear fault diagnosis, and simulation and experimental results affirm the superiority of MIWD.

Enhanced symplectic Ramanujan mode pursuit and its application in mechanical composite fault diagnosis

In practical engineering applications, traditional signal decomposition methods are often affected by various factors such as strong noise, alternating periods, etc. When signal mode analysis is conducted, it is often found that the decomposition results do not meet engineering requirements. To address these issues, Enhanced Symplectic Ramanujan Mode Pursuit (ESRMP) method is proposed in this paper, which aims to improve the accuracy and reliability of signal decomposition and period estimation. First, the cyclic symplectic geometry similarity transform is used to separate the components of different modes in the signal, and the anti-noise autocorrelation function is used to estimate the period of different components. Then, the rectangular length of the intercepted signal is determined based on the estimated period, and the periodic compensation is achieved through related detection and cubic spline interpolation. Finally, the reconstructed signal is projected onto the Ramanujan subspace to extract and enhance periodical pulses. The experimental results of multimodal composite fault signals show that the ESRMP method can accurately separate components of different modes, especially periodic pulse signals.

Fuzzy regular least squares twin support vector machine and its application in fault diagnosis

Objective function ignores the generalization error in LSTSVM, and training overfitting results in poor generalization performance. All sample labels are considered deterministic, however, some samples contain outliers affected by noises, which leads to low reliability. A recognition method based on fuzzy regular LSTSVM (FRLSTSVM) is proposed. Firstly, L2 norm regular term is introduced into objective function to improve the generalization performance. Secondly, outliers of samples are detected through support vector domain description (SVDD), which improves outlier detection accuracy. Then, a membership degree S3 is constructed to give the outliers a suitable membership degree, reducing the impact of outliers on results. Finally, FRLSTSVM is extended to a multi-classification model by one versus one (OVO) and binary tree (BT) strategies, and it is combined with an improved multiscale fluctuating Rényi dispersion entropy (IMFRDE) for fault diagnosis. The results show that the method has stronger generalization, lower sensitivity to parameters and higher reliability.

The improved quantum genetic algorithm with its application in fault diagnosis

In this paper, by analyzing the characteristics of the simulated annealing algorithm (SA) and the real double-chain coding target gradient quantum genetic algorithm (DCQGA), the real double-chain coding target gradient quantum genetic simulated annealing algorithm (DCQGSAA) is proposed. Because the performance of LSSVR is extraordinarily sensitive to its key parameters, the proposed algorithm is used to optimize these parameters, then a hybrid non-parametric prediction model is put forward. This model is used in fault prediction of liquid rocket engine thrust. The simulation results show that the proposed model is effective for small samples and multi-dimensional fault prediction.

An Explicit Subcell-Based Photovoltaic Model and Its Application in Fault Diagnosis Under Partial Shading Conditions

An Explicit Subcell-Based Photovoltaic Model and Its Application in Fault Diagnosis Under Partial Shading Conditions

Refined Composite Multiscale Fuzzy Dispersion Entropy and Its Applications to Bearing Fault Diagnosis.

Rotary machines often exhibit nonlinear behavior due to factors such as nonlinear stiffness, damping, friction, coupling effects, and defects. Consequently, their vibration signals display nonlinear characteristics. Entropy techniques prove to be effective in detecting these nonlinear dynamic characteristics. Recently, an approach called fuzzy dispersion entropy (DE-FDE) was introduced to quantify the uncertainty of time series. FDE, rooted in dispersion patterns and fuzzy set theory, addresses the sensitivity of DE to its parameters. However, FDE does not adequately account for the presence of multiple time scales inherent in signals. To address this limitation, the concept of multiscale fuzzy dispersion entropy (MFDE) was developed to capture the dynamical variability of time series across various scales of complexity. Compared to multiscale DE (MDE), MFDE exhibits reduced sensitivity to noise and higher stability. In order to enhance the stability of MFDE, we propose a refined composite MFDE (RCMFDE). In comparison with MFDE, MDE, and RCMDE, RCMFDE's performance is assessed using synthetic signals and three real bearing datasets. The results consistently demonstrate the superiority of RCMFDE in detecting various patterns within synthetic and real bearing fault data. Importantly, classifiers built upon RCMFDE achieve notably high accuracy values for bearing fault diagnosis applications, outperforming classifiers based on refined composite multiscale dispersion and sample entropy methods.

Federated contrastive prototype learning: An efficient collaborative fault diagnosis method with data privacy

Data-driven fault diagnosis approaches have attracted considerable attention in the past few years, and promising diagnostic performance has been achieved with sufficient monitoring data. However, in real industrial scenarios, individual users often struggle to collect enough labeled data. Meanwhile, direct data aggregation from multiple users is not always feasible due to data privacy concerns and conflicts of interest. To solve this issue, a novel federated contrastive prototype learning scheme is proposed for collaborative fault diagnosis of rotating machinery. The collaborative modeling between the central server and multiple clients is implemented to establish a global fault diagnostic model with data privacy. A contrastive prototype learning module is designed to align the prototypes of the same classes across different clients while separating them away from other class prototypes, thus effectively eliminating distribution discrepancies across clients and learning domain-invariant discriminative features. To remove the bias of the global model during federated communication, an unbiased prototype learning module is constructed, which aligns the class prototypes of different clients to the global prototype center and enhances the generalization ability of the proposed approach under unseen conditions. Experimental results on two self-built testbeds and a laboratory dataset demonstrate that the proposed approach is a potential solution for real-world fault diagnosis applications.

Caputo-Fabrizio fractional order derivative stochastic resonance enhanced by ADOF and its application in fault diagnosis of wind turbine drivetrain

Fault diagnosis of wind turbine drivetrains is vital to maintain the reliability of wind turbines and stochastic resonance (SR) is regarded as a powerful method to amplify the fault-induced weak characteristics of vibration signals. However, without considering the high dependence between current and previous values of vibration signals, integer-order SR may not be effective enough to amplify the weak characteristics. Moreover, non-Gaussian noise originating from severe working condition generally reduce the efficiency of amplification. To address these issues, a Caputo-Fabrizio fractional order derivative (CF) SR improved by ascending density outlier factor (ADOF) for fault diagnosis of wind turbine drivetrains is proposed in this paper. First, ADOF is constructed to remove the large impulsive noise of vibration signals. Second, CF is discretized into the second-order SR model, then the weak characteristics of vibration signal are amplified by the established CF second-order SR model (CF-SR). The effectiveness is validated by a simulation and two experimentations based on two real vibration signals collected from the key components of wind turbines. Compared with traditional diagnosis methods such as deconvolution and Kurtogram, the proposed method is superior for fault diagnosis of wind turbines working in severe environments.

Retracted: Semigroup of Finite-State Deterministic Intuitionistic Fuzzy Automata with Application in Fault Diagnosis of an Aircraft Twin-Spool Turbofan Engine

Retracted: Semigroup of Finite-State Deterministic Intuitionistic Fuzzy Automata with Application in Fault Diagnosis of an Aircraft Twin-Spool Turbofan Engine

Attribute fusion transfer for zero-shot fault diagnosis

In most industrial processes, it is impossible to collect samples of all fault modes, which greatly limits fault diagnosis applications in industrial fields. The fault diagnosis for the inaccessible fault modes having no labeled samples, termed zero-shot fault diagnosis, is quite challenging. This paper proposed an Attribute Fusion Transfer (AFT) for zero-shot fault diagnosis. First, we proposed a multi-Gaussian assumption for the posterior probability calculation in fault attribute transfer process and theoretically and experimentally proved its feasibility and effectiveness. Then, considering the ability difference of various attribute transfer methods to predict the same attribute, we proposed an attribute fusion network, which fuses the Bayesian fault attribute transfer and the attribute transfer under the multi-Gaussian assumption to attain better attribute transfer ability. Finally, AFT transfers fault attribute knowledge from accessible fault modes to inaccessible fault modes, thereby getting the ability to identify inaccessible fault modes. A series of ablation experiments and comparative experiments on the Tennessee–Eastman process were conducted to demonstrate the rationality and effectiveness of AFT fusion structure and the superiority of AFT. Furthermore, we conducted attribute-level and data-level interpretability analyses to reveal why our proposed AFT can obtain excellent zero-shot fault diagnosis ability. Codes are available at https://github.com/foryichuanqi/ADVEI-Paper-2023.11-Zero-shot-fault-diagnosis-by-attribute-fusion-transferGithub.