Search

Due to nonstationary operating conditions of wind turbines and surrounding harsh working environments, the impulse features induced by bearing faults are always overwhelmed by heavy noise, which brings challenges to accurately detect rolling bearing faults. Sparse representation exhibits excellent performance in nonstationary signal analysis, but it is closely bound up with the degree of similarity between the atoms in a dictionary and signals. Therefore, this paper investigates an enhanced K-SVD denoising method based on adaptive soft-threshold shrinkage to achieve high-precision extraction of impulse signals, and applies it to fault detection of generator bearing of wind turbines. An adaptive sparse coding shrinkage soft-threshold denoising is first proposed to remove noise and harmonic interference in the residual term of dictionary updating, so that the updated atoms show obvious impact characteristics. Furthermore, a soft-threshold shrinkage function with adaptive threshold is designed to further suppress clutter in atoms of the learned dictionary, so as to obtain an optimized dictionary for recovering impulse signals. Two actual engineering cases are selected for analysis, and the envelope spectrum correlation kurtosis corresponding to the results obtained by the proposed method is significantly higher than that of other comparison methods, thus verifying its superiority in detecting rolling bearing faults. • An enhanced K-SVD denoising algorithm for fault-induced periodic impulse extraction. • Adaptive sparse coding shrinkage is introduced into the dictionary updating. • A soft-threshold shrinkage function is proposed to optimize the dictionary. • Proposed method improves the extraction accuracy of rolling bearing fault features. [ABSTRACT FROM AUTHOR]

In recent years, pumps have become critical components in agriculture, industry, and the military, necessitating extensive development and implementation of the fault diagnosis method. In the majority of existing fault classification models, the connection between performance improvement and the amount of training data remains high, yet real-world samples are difficult to obtain. Combining domain migration theory and sample expansion method, this paper introduces a few-shot learning fault diagnosis method. Employing the T-SNE visualization algorithm, we examine the validity of the self-calibration attention mechanism (SCAM) and distribution edge prediction strategy (DEPS). The accomplishment demonstrated that the proposed algorithm could effectively map the expanded sample space within a separate interval, thereby avoiding the problem of feature aliasing caused by the overlap of sample features among similar categories and significantly enhancing the quality and quantity of training samples. The experimental analysis indicates that the proposed methodology can effectively increase the accuracy of few-shot tasks, especially in the 9way-15shot task, where it maintains a performance of 72 %, which leading the mean accuracy calculated from the others of about 30%. It is believed that much of the work has superior applicability to other few-shot diagnosis cases. • A combination of domain migration theory and sample expansion method. • Map the expanded sample space within a separable interval, avoid feature aliasing. • A few-shot sample augmentation algorithm for pump fault diagnosis. • Performing on 256*256 images transformed from one-dimensional acceleration signal. [ABSTRACT FROM AUTHOR]

Intelligent Fault-Tolerant Control (IFTC) refers to the applications of machine learning algorithms for fault diagnosis and design of Fault-Tolerant Control (FTC). The overall goal of the FTC is to accommodate defects in the system components while they are in use and maintain stability with little to no performance reduction. These systems are crucial for mission-critical and safety-related applications where the safety of people is at stake and service continuity is crucial. In this review paper, a systematic study has been done for the development of FTC with machine learning, deep learning, and transfer learning algorithms. The challenges and limitations faced with their possible solutions through machine learning theories for the IFTC model are lined up. This paper guides researchers on the different possible types of machine learning algorithms and their advanced forms like deep learning and transfer learning. The differences among these are highlighted by the challenges and limitations of each. The paper is significant such that most of the important literature references from the Scopus database particularly related to important electrical and mechanical industrial problems have been discussed to guide the researchers who want to apply IFTC for specific industrial problems, being the research gap. Finally, future research directions for the development of IFTC are highlighted. [ABSTRACT FROM AUTHOR]

This paper proposes a kernel function selection mechanism a support vector machine(SVM) under sparse representation and its application in bearing fault diagnosis. For a given data sample, a total of 125,150 different types of kernel functions and different parameters to classify and obtain the accuracy, root mean square error (RMSE) and mean square correlation coefficient (MSCC) of each training, these three values into an overcomplete redundant sparse dictionary. The OMP algorithm is used to solve the sparse coding, that are nonzero in the sparse coding are function types and parameters corresponding to these nonzero atoms according to the one-to-one correspondence between the sparse coding and the sparse dictionary. The nonzero atoms in the sparse coding and the kernel function types and parameters into the kernel function fitness table. According to the selection mechanism, we select the type of kernel function that is most suitable for the given data. A SVM is then composed of selected kernel function types, and PSO algorithm is used to the relevant parameters for classification of unknown data to Finally, we perform simulations and engineering experiments involving high-speed bearing fault diagnosis to verify the superiority of the selection mechanism. • This paper focuses on an intelligent diagnosis method for the kernel function selection mechanism of a support vector machine • Formulate a set of rules that make the selected kernel function type of support vector machine (SVM) is most suitable for the data. • Perform a simulation experiment and engineering experiment of high-speed bearing fault diagnosis, the experimental results show that the support vector machine model constructed by the kernel function selected by the proposed method is superior to the support vector machine model composed of other kernel functions in terms of accuracy or mean square error, which ensures the generalization ability of the model and reduces the computation time to some extent. [ABSTRACT FROM AUTHOR]

An effective online fault diagnosis system is of great significance to improve the reliability of fuel cell vehicles. In this paper, a fault diagnosis model for proton exchange membrane fuel cells is proposed. Firstly, the tests of electrochemical impedance spectroscopy under different fault types (flooding, drying, air starvation) and fault degrees (minor, moderate, severe) are carried out, and each polarization loss of the fuel cell is denoted by an equivalent circuit model (ECM). Then, the parameters of the ECM are identified by the proposed random mutation differential evolution algorithm. Furthermore, the parameters identified under different fault conditions are used to train and test a probabilistic neural network-based fault diagnosis model. The fault diagnosis model achieves diagnosis accuracies of 100% for the fault type and 96.67% for the fault degree. By setting operating conditions with different fault degrees, the fault diagnosis model proposed in this paper can realize the fault type and fault degree diagnosis, effectively avoiding the misjudgment of fault types, and is effective for improving the reliability of the fuel cell system. [Display omitted] • A RMDE algorithm is proposed to realize the impedance parameter identification. • A fault diagnosis model based on the probabilistic neural network is developed. • The diagnosis accuracies for fault type and fault degree reach 100% and 96.67%. [ABSTRACT FROM AUTHOR]

The second-order synchrosqueezing S-transform (SSST2) is an important method for instantaneous frequency (IF) estimation of non-stationary signals. Based on the synchrosqueezing S-transform, the instantaneous frequency calculation method is modified using the second-order partial derivatives of time and frequency to achieve higher frequency resolution. However, weak multi-frequency signals with strong background noise are often drowned out during the transformation process. To achieve enhanced extraction of weak fault characteristic signals due to mechanical faults, this paper proposes an optimally weighted sliding window signal segmentation algorithm based on the SSST2. The results of simulations and experiments show that the time–frequency aggregation of the second-order synchrosqueezing S-transform based on the optimally weighted sliding window (OWSW-SSST2) is not only significantly higher than that of commonly used time–frequency transforms, but it also has better operational efficiency than the second-order synchrosqueezing S-transform. In this paper, the proposed algorithm is used to analyze fault signals from actual high-speed railway wheelset bearings. The results show that the OWSW-SSST2 algorithm greatly improves the spectral aggregation of the signal, and crucially, that high-precision IF estimates for signals can be obtained in low signal-to-noise ratio environments. This research is both of academic interest and significant for practical engineering use to ensure safe high-speed rail operations. It helps enable monitoring the status of wheelset bearings, correctly estimating the locations and causes of failures, and providing up-to-date systematic maintenance and system improvement strategies. • This paper proposes a novel method named OWSW-SSST2. • The proposed method overcomes the drawbacks of SSST. • The signal processing performance of OWSW-SSST2 is analyzed comparatively. • Simulation and application show the validity and superiority of OWSW-SSST2. [ABSTRACT FROM AUTHOR]

In the 5G smart grid, battery liquid leakage negatively affects the safe storage and transportation of electricity. Image edge detection help locate the liquid leakage phenomenon. This paper proposes a digitalization-based algorithm that converts the image to the codeword and judges the edge by the code weight. Its main steps are image sampling, quantization, coding and judging. Compared with traditional Sobel and Canny operators, the algorithm dramatically enhances detection ability with machine learning. Moreover, this paper applies the algorithm to detect the leakage of infrared battery images in the 5G smart grid; The results show that it can accurately extract the liquid leakage location, improving fault diagnosis and early risk warning. [ABSTRACT FROM AUTHOR]

As a critically supporting and rotational component for wind turbines, blade bearings need special health monitoring for safe operation in actual industrial conditions. One of the main difficulties of the wind turbine blade bearing condition monitoring is noisy signals generated under fluctuating slow speed with heavy loads. This is because blade bearing rotation speed is influenced by blade flipping and external disturbances, and this influence is time-varying. This paper proposes a new method, Bayesian and Adapted Kalman Augmented Lagrangian (BAKAL), to filter the signal under this time-varying condition. The new method uses a two-step search (coarse and fine search) to deal with the filtering process based on Bayesian Augmented Lagrangian (BAL) framework. In addition, both linear and nonlinear effects and their sparsity are considered for model construction. Finally, the smearing problem in the frequency spectrum is dealt with through signal resample in the order domain for superior performance of fault diagnosis. The proposed BAKAL algorithm is strictly validated in several experiments under approximately fixed speed and variable speed within the condition of heavy loadings. The experiments use an industrial and rotational wind turbine blade bearing with natural defects, which has been served in an actual wind power plant for over 15 years. The experimental results demonstrate the effectiveness of the proposed method. • Fault diagnosis for the wind turbine blade bearing with fluctuating slow speed. • Course-and-fine search method for improving fault signal filtering performance. • The filtered signal is transformed into order domain for fluctuating slow speed. • Validated extensively on an industrial-scale and naturally damaged wind turbine. [ABSTRACT FROM AUTHOR]

Fault diagnosis plays an important role in maintaining the reliability of interconnection networks. Let v be a given node in an interconnection network G. v is conditionally locally t -diagnosable in G if the fault or fault-free status of node v can be identified correctly when the number of faults presented does not exceed t and every node has at least one healthy neighboring node. The conditional local diagnosis can be regarded as a local strategy toward the conditional diagnosis of networks, which puts more emphasis on identifying the status of a particular processor. In this paper, we first show a sufficient condition for a regular network to be conditionally locally t -diagnosable at a given node under the MM* model. As its applications, we derive the conditional diagnosability of hierarchical star network H S n etc. We also design an algorithm under the MM* model to identify the fault or fault-free status of a given processor in a regular network. According to our result, an α -regular network with a balanced three-tiered tree T (v ; α , α − 1 , β) rooted at v is conditionally locally (2 α + β − 3) -diagnosable at node v and the time complexity of our algorithm to diagnose v is o (α 2 β 2). As an application, we show our algorithm can identify the status of each node of star graph S n if the fault node number does not exceed 3 n − 9. Compared with existing algorithms, our algorithm allows more faults to arise in a network. [ABSTRACT FROM AUTHOR]

• A novel iteratively reweighted accurate sparse low-rank (IRASLR) matrix estimation algorithm is proposed. • An equivalent variant of minimax concave penalty (MCP) is constructed. • The equivalent weighted MCP and equivalent weighted matrix γ - n o r m are defined with their proximal operators provided. • The simulation and experiment signal proved that the proposed IRASLR method shows better reconstruction accuracy. Bearing fault diagnosis is significant to ensure the safe functioning of mechanical systems. One of the key issues in bearing fault diagnosis is the accurate and effective extraction of fault characteristic features. In order to further explore the construction of penalty function, further alleviate the problem of bias estimation and enhance the capabilities of the sparse low-rank (SLR) method in effectively diagnosing bearing faults, in this paper, an iteratively reweighted accurate sparse low-rank (IRASLR) matrix estimation algorithm is proposed. Taking the sparse and low-rank properties of fault transient signals in time–frequency domain into account, an optimization problem is formulated. Two penalty functions, derived from a core minimax-concave penalty (MCP), induce sparse and low-rank properties, respectively. Specifically, to facilitate the design of weighting schemes, we construct an equivalent variant of MCP (EVMCP). By separately extending EVMCP to matrix elements and singular values, we obtain equivalent weighted MCP and equivalent weighted matrix γ - n o r m. Finally, based on the proximal operators of the two penalty functions, we deduce an IRASLR algorithm under the alternating direction method of the multipliers (ADMM) framework. The performance of IRASLR is verified by processing simulated and experimental signals, while the superiority of the algorithm is confirmed through comparative experiments. [ABSTRACT FROM AUTHOR]

With the rapid expansion of the scale of multiprocessor systems, the importance of fault tolerance and fault diagnosis is increasingly concerned. For an interconnection network G , the h -component connectivity is an important indicator for evaluating the fault tolerance of G , which is defined as the minimum number of vertices whose deletion will disconnect G such that the remaining has at least h components. The h -component diagnosability, a newly precise diagnosis strategy to analyze the reliability of G , is the diagnosability under the condition that the number of components is at least h in the resulting graph after removing the faulty processor set. The t / k -diagnosability is a classic imprecise diagnosis strategy, which can identify up to t faulty processors by sacrificing accuracy to a certain extent, namely misdiagnosing at most k fault-free processors. In this paper, we investigate some combinatorial properties and the fault tolerance ability of the n -dimensional Bicube network, denoted by B Q n. Then we first prove that the (h + 1) -component connectivity of B Q n is h (n − 1) − h (h − 1) 2 + 1 (n ≥ 6 , 1 ≤ h ≤ n − 1). Moreover, we derive that the (h + 1) -component diagnosability of B Q n is (h + 1) (n − 1) − h (h + 1) 2 + 1 under the PMC model and MM⁎ model (n ≥ 7 , 1 ≤ h ≤ n − 3). Furthermore, under the PMC model, we propose the t / k -diagnosis algorithm of B Q n and then derive that B Q n is [ (k + 1) n − k (k + 3) 2 ] / k -diagnosable (n ≥ 6 , 0 ≤ k ≤ n − 2). [ABSTRACT FROM AUTHOR]

A t / s -diagnosable system refers to such a system that all the faulty nodes of the system can be isolated within a set of size at most s in the presence of at most t faulty nodes. Moreover, it increases the allowed faulty nodes, hence enhancing the diagnosability of the system. We can find that the t / s -diagnosability of n -dimensional folded hypercube F Q n has not been studied under the PMC model and MM* model. In this paper, we determine the t / s -diagnosability of F Q n under the PMC model and MM* model. First, we propose some new fault tolerant properties of F Q n. Then we prove that the t / s -diagnosability of n -dimensional folded hypercube F Q n is (n + 1) g − 1 2 (g − 1) (g + 2) for 2 ≤ g ≤ 1 2 (n − 1) where s = (n + 1) g − 1 2 (g − 1) (g + 2) + g − 2 under both the PMC model and MM* model. In addition, we establish two t / s -diagnosis algorithms of complexity O (N l o g 2 N) and complexity O (N (l o g 2 N) 2) to isolate the faulty nodes in a node subset of the system under the PMC model and MM* model, respectively. The comparison analysis results showed that the t / s -diagnosability of F Q n is the largest, and it increases faster than the other types of diagnosability as n increases. [ABSTRACT FROM AUTHOR]

Modern industrial processes are large-scale, highly complex systems with many units and equipment. The complex flow of mass and energy, as well as the compensation effects of closed-loop control systems, cause significant cross-correlation and autocorrelation between process variables. To operate the process systems stably and efficiently, it is crucial to uncover the inherent characteristics of both the variance structure and dynamic relationship. Compared with the original slow feature analysis (SFA) that can only model the one-step time dependence, long-term dependency slow feature analysis (LTSFA) proposed in this paper can understand the longer-term dynamics by an explicit expression of latent states of the process. An iterative algorithm is developed for the model parameter optimization and its convergency is proved. The model properties and theoretical comparison with existing dynamic models are presented. A process monitoring strategy is designed based on LTSFA. The results of two simulation case studies show that LTSFA has better system dynamics extraction capability, which reduces the violation rate of the residual for the 95% confidence interval from 40.4% to 3.2% compared to the original SFA, and can disentangle the quickly- and slowly-varying features. Several typical disturbances can be correctly identified by LTSFA. The monitoring results on the Tennessee Eastman process benchmark show the overall advantages of the proposed method both in the dynamic and nominal deviation detection and the monitoring accuracy • The proposed model, LTSFA, can explicitly model the long-term time dependency. • An iterative algorithm is developed and convergence is proved. • The model properties and theoretical comparison with existing models are presented. • LTSFA can better extract dynamics compared to the original SFA. • The monitoring method based on LTSFA gives better monitoring performance. [ABSTRACT FROM AUTHOR]

In order to recognize the coupling faults of complex industrial processes effectively, this paper proposed an AdaBoost ensemble (AdBE) model based on the reconstruction of local tangent space alignment (RLTSA). First, to obtain the low-dimensional manifold structure embedded in original data space, RLTSA algorithm is designed by constructing the tangent space in the neighborhood of each data point to represent the local geometry and then aligning them to obtain the embedding coordinates. Secondly, to solve the loss of global feature information, an affine matrix is used to inversely map the low-dimensional coordinates to restore the global structure information. Thirdly, based on the above reconstruction of local tangent space alignment, an AdaBoost ensemble (AdBE) classifier is constructed for multiple faults recognition in which the AdaBoost algorithm is used to improve the performance of Decision Tree (DT), and One vs. Rest (OvR) ensemble strategy is introduced to establish the RLTSA-AdBE model. Case studies are conducted using a three-dimensional S_curve data set and the Tennessee Eastman process (TEP) to respectively verify the performance of the RLTSA algorithm and the proposed RLTSA-AdBE model. The simulation results indicate that the proposed method guarantees high diagnosis accuracy and macro_F1 Score of coupling faults recognition. • AdaBoost Ensemble Based on Local Tangent Space Alignment is proposed. • An affine matrix is used to map low-dimensional coordinates to restore global structures. • AdaBoost ensemble (AdBE) classifier is constructed for multiple faults recognition. • Case studies of multi-faults using the Tennessee Eastman process are executed. • The effectiveness and feasibility of the proposed fault diagnosis method is conformed. [ABSTRACT FROM AUTHOR]

Spiking neural networks (SNNs) have attracted widespread attention due to their unique bio-interpretability and low-power properties, but the non-differentiability of discrete spike sequences fired by spiking neurons brings difficulties to the learning of SNNs. Recently, surrogate gradient (SG) and back-propagation through time (BPTT) have provided an excellent idea for training SNNs constructed by leaky integrate-and-fire (LIF) neuron models. The LIF neuron model has been widely used in previous SNNs due to its simplicity and low computational cost, however, this also limits its simulation of biological neuron dynamics, reducing the biological interpretability of SNNs. In this paper, we generalize SG and BPTT to SNNs constructed by spike response model (SRM) and propose the BP-SRM algorithm. Specifically, we address why BPTT succeeded in LIF neurons-based SNNs but failed in SRM neurons-based SNNs in previous researches. Then we establish an iterative form of the SRM neuron model by selecting different state variables. Based on iterable SRM, we get the spatiotemporal dependencies between the state variables of SRM neurons-based SNNs, which allows us to derive the gradient and update weights in SNN by BP-SRM. Then we design temporal channel normalization for BP-SRM and verify the performance of the SNNs on static image dataset, dynamic image dataset and engineering dataset, including Fashion-MNIST, Weather Dataset, N-MNIST, American Sign Language Dataset and bearing fault diagnosis dataset. The experiment results indicate that BP-SRM achieves the state-of-the-art performance of SNNs. [ABSTRACT FROM AUTHOR]

• A novel paradigm, case learn-based, for quantitative recommendation of fault diagnosis algorithms is proposed, which is quantitative, expert-experience-free, and computation-friendly. • A three-level attribute set is defined and quantified to describe those main elements throughout the diagnosis design process. • The efficiency of the proposed paradigm is verified by an application of gearbox fault diagnosis, which also gives an example for other real PHM algorithm recommendation applications. • Applicable rules of six diagnosis algorithms are learned to realize convenient recommendations. The model has an average recommendation accuracy of 70.40% and almost no time consumption compared to real application, which shows strong capability for various real PHM algorithm design applications. • The paradigm can be extended to multi-type systems and multi-type PHM solutions. Prognostics and Health Management (PHM) is a core technology for condition-based maintenance. The diversity of PHM algorithms and the complexity of design factors make it challenging to choose an appropriate algorithm for a specific application. Consequently, automatic PHM algorithm recommendation (PHM-AR) is of great significance for PHM developers to implement rapid design of PHM systems. However, the two existing paradigms for PHM-AR rely heavily on expert experience and failure data respectively. In this paper, we propose a new third paradigm, called the case-learning-based paradigm, for quantitative recommendation of fault diagnosis algorithms, focusing on diagnosis task attribute analysis, multi-dimensional feature representation, and recommendation model construction. Specifically, to provide a quantitative basis for the recommendation of diagnosis algorithms, we define a three-level attribute set of diagnosis tasks and propose a quantitative representation method to make data structured. Then, a recommendation model based on the Classification and Regression Tree (CART) is proposed. Finally, taking gearbox as an example, we construct a diagnosis case set and verify the effectiveness of the proposed framework. Experimental results show that the average recommendation accuracy of our proposed method reaches 70.40%. These results also elucidate that the proposed method can learn the applicable rules of various diagnosis algorithms. [ABSTRACT FROM AUTHOR]

• Active fault-tolerant strategy is introduced to distributed state estimation scheme. • Intermittent fault (IF) detector is designed and the detectability of IF is analyzed. • Estimation errors can remain the prescribed performance under the influence of IF. In this paper, the problem of distributed fault-tolerant state estimation is studied for stochastic systems over sensor networks with intermittent sensor faults. Compared with the traditional state estimation algorithms, the distinct advantage of fault-tolerant state estimation is that the estimator can keep good performance whether sensor faults occur or not. Different from the previous literature concerning with distributed fault diagnosis, the distributed fault diagnosis problem is investigated in this paper for intermittent faults, whose appearing time, disappearing time and magnitude are all nondeterministic. The distributed fault-tolerant state estimation scheme is constructed, in which the appearing time and disappearing time of intermittent faults are detected, intermittent faults are estimated and compensated. By means of the matrix inequality technique, the H ∞ performance of state estimation errors is guaranteed by properly choosing the estimator parameters. Finally, two examples are provided to demonstrate the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The bearing fault impact impulses induced by the contact between components with drawback, is difficult to be detected at sprouting stage due to the interference of background noise, harmonics, random shocks, etc. In this paper, an impulse feature enhanced weighted sparse representation (IFEWSR) algorithm is proposed to accurately detect the weak bearing fault impact feature from incipient stage condition monitoring (CM) signal. Firstly, a modified fault period estimation method is presented to improve the robustness and reduce the computational complexity of recently proposed algorithms. Secondly, a novel weighting strategy on wavelet coefficients, indicated by the period-assisted corelated kurtosis of envelope spectrum (CKSES), is presented to denote the contribution of subband signals for sparse representation calculation framework. In addition, the mean normalized energy-weight deviation (MNEWD) rule is proposed to evaluate the performance of the weighting algorithm on subband signals which is blank at present. Thirdly, a novel fault feature enhancement technique is developed to better capture the bearing fault feature information. The effectiveness and superiority of the proposed method are proved by simulation and experiments. Results show that the proposed IFEWSR method provides higher accuracy for incipient fault feature extraction and outperforms other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

• This paper proposes a novel algorithm for screening EIMFs. • This paper applies EIMFs to signal denoising and feature matrix construction. • This algorithm improves the problem of TVF-EMD to decompose too many imfs. • This algorithm expands the application of TVF-EMD in the field of fault diagnosis. This paper proposes a new narrow-band filtering algorithm to improve the problem of TVF-EMD algorithm decomposing too many narrow-bands. The algorithm uses the energy estimation model of IMFs combined with the energy of noise in each imf and the signal complexity evaluation standard to obtain the effectiveness operator that measures the signal content of each imf, and selects the eimf with a large effectiveness operator as the EIMFs. In this paper, three groups of rotating machine data are used for experiments. The classification accuracy of denoising signals can reach 99.98% when the effectiveness operator is accumulated to 0.9999, and the classification accuracy of the EIMFs feature matrix can reach 97.83%, which are higher than the original data control group. The algorithm only needs to deal with the advantages of EIMFs, which significantly improves the classification accuracy and iteration speed of the classifier. [ABSTRACT FROM AUTHOR]

Federated learning (FL) guaranteeing data privacy is of great interest in decentralized fault diagnosis. However, limited research attention has been paid to the dynamic domain-shift issue due to varying working conditions. This paper proposes an active federated transfer algorithm based on broad learning to address the domain shift issue in FL. First, a central server dispatches a global model to the source clients for collaborative modeling. Subsequently, the global model is initialized with a federated averaging strategy. Next, the initialized global model is used to annotate emerging signals from the target clients based on an active sampling strategy proposed. Finally, an asynchronous update scheme is designed to adapt the global model to the target domain. The performance of the AFTBL algorithm is validated with three datasets, including 24 centralized- and decentralized-modeling tasks. The computational results indicate that the proposed algorithm is more accurate and efficient than the prevalent algorithms. • The cross-domain incremental federated learning problem is investigated. • An active federated broad transfer algorithm is proposed for fault diagnosis. • Automated data annotation and selection are proposed for incremental model update. [ABSTRACT FROM AUTHOR]

• The fault signals are sparsely represented by shift-invariant dictionary. • The circulant properties of shift-invariant dictionary are analyzed. • Three sparse coefficient fast solution algorithms are derived. • The calculation efficiency is verified by simulation and experimental data. • The fast algorithms can be applied to mechanical fault diagnosis. Sparse coefficient solutions have received continuous attention as one of the core steps of sparse representation. The computational complexity of almost all sparse coefficient solution algorithms is exponentially increased with a signal dimension. In this paper, impact signals caused by localized faults are sparsely represented by a shift-invariant dictionary, which can be Fourier diagonalized based on its circulant structure. Then, the matrix–matrix and matrix–vector multiplications involved in obtaining sparse coefficients are converted into calculation forms that mainly contain the Fourier transform and its inverse to reduce computational complexity. Based on this result, fast solutions of three common sparse coefficient solution algorithms are deduced in detail. Simulation analysis shows that the deduced fast algorithms can significantly fasten running time while maintaining same accuracy as corresponding original algorithms. Localized rolling bearing faults related experiments further verify the effectiveness of the proposed sparse coefficient fast solution algorithms for machine fault diagnosis. [ABSTRACT FROM AUTHOR]

In this paper, a new bio-inspired meta-heuristic algorithm, named artificial rabbits optimization (ARO), is proposed and tested comprehensively. The inspiration of the ARO algorithm is the survival strategies of rabbits in nature, including detour foraging and random hiding. The detour foraging strategy enforces a rabbit to eat the grass near other rabbits' nests, which can prevent its nest from being discovered by predators. The random hiding strategy enables a rabbit to randomly choose one burrow from its own burrows for hiding, which can decrease the possibility of being captured by its enemies. Besides, the energy shrink of rabbits will result in the transition from the detour foraging strategy to the random hiding strategy. This study mathematically models such survival strategies to develop a new optimizer. The effectiveness of ARO is tested by comparison with other well-known optimizers by solving a suite of 31 benchmark functions and five engineering problems. The results show that ARO generally outperforms the tested competitors for solving the benchmark functions and engineering problems. ARO is applied to the fault diagnosis of a rolling bearing, in which the back-propagation (BP) network optimized by ARO is developed. The case study results demonstrate the practicability of the ARO optimizer in solving challenging real-world problems. The source code of ARO is publicly available at https://seyedalimirjalili.com/aro and https://ww2.mathworks.cn/matlabcentral/fileexchange/110250-artificial-rabbits-optimization-aro. • A new bio-inspired artificial rabbits optimization (ARO) algorithm is proposed. • ARO is inspired by the survival strategies of rabbits in nature. • The results on 31 well-known test functions show the efficiency of ARO. • ARO yields superior results over its competitors on 5 engineering problems. • ARO is successfully applied in fault diagnosis of rolling bearing. [ABSTRACT FROM AUTHOR]

• An evaluation scheme is developed to detect the health status of rolling bearing. • Mixed-scale model combining with CEEMDAN and SVDE is constructed to extract fault features adaptively. • Pt-SNE algorithm is provided for high-dimensional features reduction. Accurate and efficient fault diagnosis for rolling bearing is essential to ensure the reliable and safe operation of mechanical equipment. In this paper, a hybrid hierarchical fault diagnosis method based on scale-variable dispersion entropy (SVDE) and parametric t-distributed stochastic neighbor embedding (Pt-SNE) algorithm, systematically combining the statistics analysis principle and machine learning technique, is proposed. First, an initial evaluation scheme with regard to the health state of bearing is implemented by the SVDE theory blended with the statistical analysis technology. Second, if fault appears, a novel mixed-scale model, integrating series mode with multi-scale factor, is established based on the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and SVDE for further improvement of feature extraction performance. Subsequently, a Pt-SNE algorithm is provided to reduce the features for higher accuracy and speed of diagnosis. Finally, the obtained low-dimensional representations after reduction can be imported in Softmax classifier for fault recognition. Two vibration datasets are used for bearing fault diagnosis. The experimental results prove the superior performances of the proposed method, and it has better practicability in engineering problems compared with other existing approaches. [ABSTRACT FROM AUTHOR]

• A new kind of data-based fault detection method is proposed, which combines adaptive dynamic programming and multiple-modeling. • A stable working state is established by using ADP and history data. Once the system runs out of the stable state, it's known for sure that fault occurs. • A whole stable working space of the system can be built with the method of multi-modeling and data of all working modes, as long as system states remain in the working space, system is working normally, exclude the disturbance of modes switching, and improve the accuracy of the fault detection algorithm. • The fault can be isolated, if the direction and magnitude of the deviate vector are solved, which can be achieved by approximation and iteration using the method of ADP. This paper presents a adaptive dynamic programming-based fault detection and isolation (FDI) scheme to detect and isolate faults in an aircraft jet engine. To this end, the weights in Actor-Critic neural networks are first tuned to learn the input-output map of the jet engine considering its multiple working modes. The convergences of the trainings in Critic-Actor neural networks are strictly proved without knowing the drift dynamics and the input dynamics in the presence of unknown nonlinearities and approximation errors. Using the residuals that are generated by measuring the difference of each network output and the measured engine output, various criteria are established for accomplishing the fault diagnosis task, that addresses the problem of fault detection and isolation of the system components. A number of simulation studies are carried out for combustion chamber of a single-spool jet engine to demonstrate and illustrate the advantages, capabilities, and performance of our proposed fault diagnosis scheme. [ABSTRACT FROM AUTHOR]

The advances of intelligent fault diagnosis in recent years show that deep learning has strong capability of automatic feature extraction and accurate identification for fault signals. Nevertheless, data scarcity and varying working conditions can degrade the performance of the model. More recently, a tool has been proposed to address the above challenges simultaneously. Meta-learning, also known as learning to learn, uses a small sample to quickly adapt to a new task. It has great application potential in few-shot and cross-domain fault diagnosis, and thus has become a promising tool. However, there is a lack of a survey to conclude existing work and look into the future. This paper comprehensively investigates deep meta-learning in fault diagnosis from three views: (i) what to use, (ii) how to use, and (iii) how to develop, i.e. algorithms, applications, and prospects. Algorithms are illustrated by optimization-, metric-, and model-based methods, the applications are concluded in few-shot cross-domain fault diagnosis, and open challenges, as well as prospects, are given to motivate the future work. Additionally, we demonstrate the performance of three approaches on two few-shot cross-domain tasks. Typical meta-learning methods are implemented and available at https://github.com/fyancy/MetaFD. • Review the advances of meta-learning in fault diagnosis for the first time. • Demonstrate deep meta-learning in fault diagnosis via algorithms and applications. • Illuminate meta-learning algorithms by mathematical optimization. • Stimulate future work with open challenges and prospects. [ABSTRACT FROM AUTHOR]

• Proposed cycle envelope spectral segmentation method based to optimize EWT. • Calculate the similarity of the envelope spectra of adjacent signals to optimize the components. • A new indicator called sensitive IMFs assessing index (SIAI) was designed to identify fault information. The empirical wavelet transform (EWT) has made outstanding contributions in the field of fault diagnosis. However, when EWT processes complex signals, there may be modal aliasing or meaningless components. In order to solve the spectral segmentation defect of the EWT method and improve its ability to extract bearing fault features, this paper proposes a new algorithm to improve EWT. In order to weaken the influence of extreme points in the complex Fourier spectrum on modal differentiation, the cycle envelope spectral segmentation method is proposed. The maximum envelope fitting method not only reduces the number of useless extreme points, but also highlights each mode. The number of filters is reduced while suppressing the interference of noise on the modal. The components that contain similar information in the result will be merged based on their correlation. Then sensitive IMFs assessing index (SIAI) is proposed to combine correlation and symmetry of the signal, and obtains the characteristics of time domain, frequency domain, and amplitude domain to extract fault information. Locomotive bearing and wind turbine gearbox bearing fault data verified the effectiveness of the method. [ABSTRACT FROM AUTHOR]

• A double-dictionary is designed for identifying and distinguishing compound-fault of rolling element bearings. • An atom selection strategy based on fault information is constructed by combining the Gini index with envelope periodic modulation intensity. • An estimation method for calculating the residual error in the sparse coding stage is also presented to meet a better result. This paper proposes an improved double-dictionary K-singular value decomposition (IDDK-SVD) algorithm for the compound fault diagnosis of rolling element bearings under complex industrial environments. In the framework, a double-dictionary is first designed for respectively identifying and distinguishing compound-fault features. In addition, an atom selection strategy based on fault information is constructed by combining the Gini index with envelope periodic modulation intensity, which can simultaneously take the periodicity and impulsivity into consideration to find a set of atoms most related to fault for the update of double-dictionary. Finally, an estimation method for calculating the residual error in the sparse coding stage is also presented to meet a better result. Benefitting from these improvements, the proposed IDDK-SVD is effective in the application of compound-fault diagnosis, which is verified by both simulation signals and real signals collected from the locomotive bearing test rig. [ABSTRACT FROM AUTHOR]

Random forest (RF) is an effective method for diagnosing faults of rotating machinery. However, the diagnosis accuracy enhancement under insufficient labeled samples is still one of the main challenges. Motivated by this problem, an improved RF algorithm based on graph-based semi-supervised learning (GSSL) and decision tree is proposed in this paper to improve the classification accuracy in the absence of labeled samples. The unlabeled samples are annotated by the GSSL and verified by the decision tree. The trained improved RF model is applied to the fault diagnosis for the rotating machinery gearbox. The effectiveness of the proposed algorithm is verified via hardware experiments using a wind turbine drivetrain diagnostics simulator (WTDDS). The results show that the proposed algorithm achieves better accuracy of classification than conventional methods in gearbox fault diagnosis. This study leads to further progress in the improvement of machine learning methods with insufficient and unlabeled samples. • An improved RF algorithm is proposed to relieve the small sample problem. • A GSSL based sample labeling method is proposed to label unlabeled samples. • A dual-classier is designed to minimize the side-effects of incorrect labels. • The RF algorithm is improved to realize the semi-supervised function. • An effective method is proposed for fault diagnosis of rotating machinery. [ABSTRACT FROM AUTHOR]

• A JDSDL framework is proposed for bearing intelligent fault classification. • A dictionary extension strategy enables the learned dictionary shift-invariant and significantly improves the classification accuracy. • Applications show that the proposed method is accurate and robust. • We compare the proposed method with competing methods and the proposed method presents respective application scope. Sparse representation is one of the effective approaches for bearing fault diagnosis. Conventional sparse representation only focuses on fault feature extraction from bearing vibration signals while requiring experts to empirically make a diagnosis. This paper investigates bearing intelligent fault classification based on sparse representation based classification (SRC) method. A novel SRC algorithm, named joint discriminative and shared dictionary learning (JDSDL), is proposed for simultaneously characterize the class-specific and common features in vibration signals of bearings with different faults. The JDSDL seamlessly integrates discriminative dictionary learning, shared dictionary learning, and classifier training into a joint model to automatically recognize bearing faults. Moreover, a dictionary extension strategy is embedded within the proposed JDSDL model to make learned discriminative dictionary shift-invariant to improve its classification performance. The main advantages of the proposed method are that the JDSDL not only works well even if the training set is small, but also is robust to corruption of environment noises. Experimental results on three bearing datasets and comparison with competing methods are presented to demonstrate the effectiveness and superiority of the proposed JDSDL in bearing intelligent fault classification. [ABSTRACT FROM AUTHOR]

In this paper, a fault diagnosis problem for Hypersonic Air Vehicle (HAV) with sensor fault is concerned. Existing fault diagnosis models pay less attention to the problems of high-performance real-time diagnosis and Artificial Intelligence (AI) algorithm autonomous optimization. Therefore, a smart real-time fault diagnosis algorithm is put forward to automatically build a more accurate and rapid model in a short time. Based on the Temporal Convolutional Network (TCN) with tuning parameters optimizing by Strengthen Elitist Genetic Algorithm (SEGA), the Auto Temporal Convolutional Network (AutoTCN) is first proposed. To better diagnose the time-sequence sensor fault signal, the Sequential Probability Ratio Test (SPRT) method is introduced afterwards. Additionally, the Wavelet Packet Translation (WPT) is combined with TCN to enhance the mechanism and sensitivity of the extracted fault features. Experimental results from the HAV model with the Reaction Control System (RCS) control simulated under sensor fault are obtained. It is demonstrated that, for typical sensor faults greater than 8.89%, the real-time fault diagnosis accuracy of the proposed method may exceed 96%. The diagnosis delay is less than 0.05 s. Moreover, on the computer equipped with an 8-core CPU, over 87.5% of the working time can be saved. [ABSTRACT FROM AUTHOR]

• A new technique is proposed to detect and classify the PV system fault states. • The technique based on mapping the rate of changes of voltage and current. • The design of the PV system is implemented by installing one diode in every string. • The proposed technique is verified by modelling and experimentally. • This technique is sensitive to internal and stable for external PV array faults. This paper proposes a new simple technique to detect and discriminate the abnormal states of the grid-connected photovoltaic (PV) solar system based on the rate of change of voltage and current trajectory. The design of the PV system is developed by implementation of only one diode in every PV string. The diode prevents the reverse direction of the fault current in case of faulty strings. On the other hand, the installation of a diode reduces the ability of faults detection and diagnosis depending on currents in each string. The proposed technique depends on the rate of change of voltages and current trajectory during the fault transient period. The proposed algorithm can detect various fault cases such as cell-to-cell and string to string faults in addition to partial and full shadow faults. Also, the algorithm differentiates between high and low fault cases for each fault types. Moreover, the proposed technique is characterized by high sensitivity for internal abnormal states within certain array with high security level for the external abnormal conditions and normal load changing. The proposed technique is applied for a four-array PV system, which has a power rating of 400 kW connected to an AC grid. The simulation results and validation of the proposed technique are implemented by MATLAB/Simulink toolbox. The proposed technique is experimentally applied for a small PV system of a rating of 1.25 kW to prove its validity. [ABSTRACT FROM AUTHOR]

In the current artificial immune algorithms, the process of activation calculation considers the affinity only, but fails to take into account the relationship between sample features. In response to this deficiency, this paper proposes a new Relation B-cell and Relation B-cell Network Model (RBNM), which is basing on the immune mechanism of clone, mutation and network inhibition. In the method, this relation B-cells were calculated by the relationship between sample features. As a result, in the training and diagnosis process, combining with the relation B-cells, the algorithm can effectively improve the ability of cell association monitoring and finally generate efficient detectors. According to the following performance tests, RBNM classification result is not sensitive to its five parameters and results of the method are competitive among comparison methods. Finally, the algorithm was also applied to the reciprocating compressor faults dataset, and the result reached 99.7%. [Display omitted] • The proposed method can extract the correlation between features. • RBNM has stable performance and strong robustness within the given parameter range. • The method has good performance in the reciprocating compressor dataset. [ABSTRACT FROM AUTHOR]

With the development of power systems, fault diagnosis in infrared images has become increasingly important for ensuring the stability of these systems. In this paper, we propose a multi-objective multilevel threshold image segmentation method based on the boost marine predators algorithm (BMPA) for infrared-image fault diagnosis. As fault points are small, it is difficult to detect the target in an infrared image using existing segmentation methods. To address this, we use 9DKapur as the fitness function and obtain a many-objective optimization problems (MaOPs). Then, we use adaptive weights and opposition-based learning to boost the optimization ability of the MPA and solve the MOP so that a Pareto front is obtained. The DTLZ and WFG test suits are used as benchmarks to evaluate the performance of the BMPA, and electric equipment in infrared images was used to assess the fault-diagnostic ability of the proposed method. The results demonstrate that the BMPA performs better than other optimization algorithms in terms of uniformity measurement, peak signal-to-noise ratio, feature similarity, hypervolume, spacing, and CPU time. On the actual test data, the recall rate and fault detection accuracy of the proposed method were 94.29% and 92.38%, respectively. Insulator faults under various circumstances can be correctly detected in infrared images. • A many-objective multilevel threshold image segmentation based on BMPA is proposed. • The opposition based learning and adaptive weight improve Marine Predators Algorithm. • We use 9DKapur as the fitness function and obtain a MOPs. • The algorithm has good performance in infrared images fault diagnosis. [ABSTRACT FROM AUTHOR]

• A DcCNN is used to extract fault features from PVA normalized current and voltage. • A feature selection structure is proposed to evaluate extracted features. • A penalty is developed to train the proposed model in an end-to-end way. • Results show that the DcCNN can extract high-discriminative features. • The DcCNN has superior performance for different faults even LLF under complex conditions. The effective fault diagnosis algorithm for the DC side photovoltaic (PV) array of a PV system (PVS) plays an important role in the operation efficiency and safety for PV power plants. But for fault diagnosis models it may fail to diagnose PV array (PVA) faults without detailed and quite fine fault features, especially line-line faults (LLF) occurring in the PVS that works under complex working conditions like low irradiance conditions and LLF with fault impedance. To address these challenges, this paper proposes a fault diagnosis scheme to diagnose different PVA faults using a proposed Dual-channel Convolutional Neural Network (DcCNN), which is able to automatically extract features and weight these features for fault classification. The important and fine features from the current and voltage electrical time series graph (ETSG) are extracted respectively by DcCNN in a double input way. Then, a proposed feature selection structure (FSS) is designed to improve the proposed fault diagnosis model capacity for diagnosing PVA faults under various conditions, including LLF, partial shading condition (PSC) and open circuit faults (OCF). Comparing to manually designed features, FSS not only helps DcCNN extract important features from PVA current and voltage automatically but also evaluates extracted features for further classification of DcCNN. Moreover, in the training stage, a proposed penalty is applied on DcCNN to constrain FSS, resulting in its sparse weight distribution. A comprehensive experiment based on a laboratory roof grid connected PVS is conducted. The results demonstrate the superior performance of the proposed approach compared with other algorithms as it can extract high-discriminative features from PVA current and voltage for different PVA faults, which is also effective on diagnosing LLF under low irradiance conditions and LLF with fault impedance. [ABSTRACT FROM AUTHOR]

• A novel multi-representation-based network is proposed for fault diagnosis. • Three time–frequency representations are designed to reflect machine health status. • An improved inception module extracts multiple domain-invariant representations. Deep learning-based domain adaptation algorithms with various representations have been recently developed to address the domain shift problem in mechanical fault diagnosis. However, few research have focused on potential improvements through multiple representations. Thus, a multi-representation-based domain adaptation network is proposed in this paper. Three complementary time–frequency representations are first proposed to serve as input-based multiple representations for the subsequent parallel models. Then, parallel models with improved inception modules are trained to obtain feature-based multiple domain-invariant representations. Finally, ensemble learning through majority voting is used to obtain the final results. Comprehensive experimental results on two test rigs reveal that the proposed algorithm outperforms state-of-the-art single-representation-based domain adaptation algorithms in terms of cross-domain fault diagnosis. Furthermore, visualization results demonstrate that the proposed algorithm extracts transferable features and takes advantage of ensemble learning to achieve high-precision diagnosis. [ABSTRACT FROM AUTHOR]

[Display omitted] With the development of smart sensors, large amount of operating data collected from a complex system as a high-speed train providing opportunities in efficient and effective fault detection and diagnosis (FDD). The data brings also challenges in the FDD modelling process, since the various signals may be redundant, useless and noisy for the FDD modelling of a specific sub-system. The data-driven methods suffer also from the curse of dimensionality. Feature dimension reduction can reduce the dimension of the monitoring dataset and eliminate the useless information. Different from the classical methods based on the correlation among variables, recent studies have shown that causality-based methods can make the FDD model more explanatory and robust. From the adjacency matrix of the causal network diagram, three unsupervised causality-based feature extraction methods for FDD in the braking system of a high-speed train are proposed in this paper. By constructing the causal network diagram among the raw monitoring feature variables through the causal discovery algorithm, the proposed methods extract informative features based on the causal adjacency matrix or the full causal adjacency matrix proposed in this work. These methods are adopted for fault detection with real dataset collected from the braking system in a high-speed train to verify their effectiveness. The experimental results show that the proposed causality-based feature extraction methods are effective and have certain advantages in comparison with the classical correlation-based methods. Especially, the feature extraction method based on the correlation matrix constructed from full causal adjacency matrix achieves better and stable results than the benchmark methods in the experiment. [ABSTRACT FROM AUTHOR]