Narrow Results

Extracting to enhance the accuracy of diagnosing bearing faults in steam turbines, a novel approach focused on extracting key fault features from vibration signals is introduced. Recognizing the complex, non-linear, and non-stationary nature of bearing vibration signals, our strategy involves a sensitivity analysis utilizing a multivariate diagnostic algorithm. The process begins with collecting vibration data from defective bearings via the TMI system. This data is then subjected to Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), enabling the integration of adaptive noise for the extraction of in-depth information. Following this, an analysis in both time and frequency domains — post Fast Fourier Transform (FFT) — is conducted on the decomposed signals, forming the basis of a diagnostic features database. To streamline data analysis and boost the model’s computational efficiency, a combination of eXtreme Gradient Boosting (XGBoost) and Mutual Information Criterion (MIC) is applied for dimensionality reduction. Furthermore, a deep belief network (DBN) is implemented to develop a precise fault diagnosis model for the bearings in rotating machinery. By incorporating sensitivity analysis, a diagnostic matrix is crafted, facilitating highly accurate fault identification. The superiority of this diagnostic algorithm is corroborated by testing with real on-site data and a benchmark database, demonstrating its enhanced diagnostic capabilities relative to other feature selection techniques.

Industrial robots play an indispensable role in realizing intelligent production and industrial upgrading. In order to ensure the healthy and smooth operation of industrial robots, a reliable fault diagnosis system for industrial robots needs to be established. However, many shallow learning fault diagnosis methods rely on manual extraction of signal features and selection of appropriate classifier combinations, which rely heavily on expert experience. The fault diagnosis model optimization process is time-consuming and has poor generalization ability, making it difficult to meet the actual fault diagnosis needs of industrial production. In robot fault diagnosis tasks, problems such as lack of fault data and category imbalance are also faced. Aiming at the difficulty of complex fault diagnosis of industrial robots, we propose an improved one-dimensional (1D) convolutional neural network fault diagnosis model (SRIPCNN-1D). The SRIPCNN-1D model has fewer model layers, fewer training parameters and strong model expression ability, and is suitable for online fault diagnosis of robots. This model achieved a diagnosis accuracy of more than 98% on the multi-axis industrial robot compound fault data set. It was compared with WDCNN, CNN-1D and other models as well as single fault diagnosis models to verify the effectiveness of the proposed model. At the same time, we also studied the impact of different sampling frequency data on the fault diagnosis effect of the model established by this algorithm. Experimental results show that the model is still effective when we adjust the sampling interval to 1 s.

This study investigates the application of Deep Convolutional Neural Networks (DCNNs) in power system signal processing. The research addresses the growing challenges in modern power systems, including increased complexity and data volume. We comprehensively analyze DCNN-based methods for electric load forecasting, fault diagnosis, and power quality assessment. Through extensive experiments and case studies, we demonstrate that DCNNs consistently outperform traditional approaches in accuracy, real-time performance, and robustness. The study explores various DCNN architectures and proposes improvements tailored to power system characteristics. Results show significant enhancements in prediction accuracy and processing speed across different tasks. While challenges such as model interpretability remain, the findings highlight the potential of DCNNs to revolutionize power system signal processing. This research contributes to advancing intelligent power system management and provides a foundation for future developments in smart grid technologies.

The faults in DC microgrid multi-port power electronic circuits are complex and diverse. In order to better adapt to different types of fault data and complex circuit environment, and improve the generalization ability and accuracy of fault diagnosis, a fault diagnosis method for DC microgrid multi-port power electronic circuits based on WOA-KELM algorithm is studied. Through the wavelet packet analysis algorithm, the wavelet coefficient energy of DC microgrid multi-port power electronic circuit signal is extracted as a fault feature, and it is encoded to speed up fault diagnosis efficiency; the WOA algorithm is used to optimize the penalty parameters of KELM algorithm to improve the accuracy of fault diagnosis; in the optimized KELM algorithm, the coded fault feature samples are input, and the fault diagnosis results of DC microgrid multi-port power electronic circuits are output. According to the powerful nonlinear mapping ability of the kernel function, the generalization ability of the KELM algorithm is enhanced, so that it can better adapt to different types of fault data and complex circuit environment. Experiments show that this method can effectively extract fault features of multi-port power electronic circuits and complete feature coding; this method can effectively diagnose the faults of DC microgrid multi-port power electronic circuits; in different complex circuit scenarios, the fault reliability of this method for diagnosing power circuit faults is higher than 0.6, that is, the fault diagnosis accuracy is high.

Predictive maintenance (PdM) helps organizations to reduce equipment downtime, optimize maintenance schedules, and enhance operational efficiency. By leveraging machine learning algorithms to predict when equipment failure will likely occur, maintenance teams can proactively schedule maintenance activities and prevent unexpected breakdowns. Fault detection and diagnosis are essential components of PdM. Fault detection involves analyzing sensor data collected from equipment to identify deviations from normal behavior. Diagnosis, however, involves identifying the root cause of a fault or failure. A dataset of an industrial asset is used to evaluate the proposed study. K-means clustering anomaly detection approach is employed. Implementing machine learning (ML)-based fault categorization approaches revealed that Random Forest had the best results. Significant progress has been made in fault detection and diagnosis using ML, but the degree of their explainability is significantly limited by the “black-box” character of some ML techniques. Less emphasis has been placed on explainable artificial intelligence (XAI) approaches in maintenance. Therefore, the XAI tools, SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) have been used to acknowledge the extent of the variables to analyze the influence of respective features. A stability metric has been included to improve the explanation’s overall quality. The findings of this paper suggest that the utilization of XAI can offer significant contributions in terms of insights and solutions for addressing critical maintenance issues.

The processor failures in a multiprocessor system have a negative impact on its distributed computing efficiency. Because of the rapid expansion of multiprocessor systems, the importance of fault diagnosis is becoming increasingly prominent. The $h$-component diagnosability of $G$, denoted by $c{t}_h(G)$, is the maximum number of nodes of the faulty set $F$ that is correctly identified in a system, and the number of components in $G-F$ is at least $h$. In this paper, we determine the $(h+1)$-component diagnosability of general networks under the PMC model and MM${}^{\ast }$ model. As applications, the component diagnosability is explored for some well-known networks, including complete cubic networks, hierarchical cubic networks, generalized exchanged hypercubes, dual-cube-like networks, hierarchical hypercubes, Cayley graphs generated by transposition trees (except star graphs), and DQcube as well. Furthermore, we provide some comparison results between the component diagnosability and other fault diagnosabilities.

The growing demand in system reliability and survivability under failures has urged ever-increasing research effort on the development of fault diagnosis and accommodation. In this paper, the on-line fault tolerant control problem for dynamic systems under unanticipated failures is investigated from a realistic point of view without any specific assumption on the type of system dynamical structure or failure scenarios. The sufficient conditions for system on-line stability under catastrophic failures have been derived using the discrete-time Lyapunov stability theory. Based upon the existing control theory and the modern computational intelligence techniques, an on-line fault accommodation control strategy is proposed to deal with the desired trajectory-tracking problems for systems suffering from various unknown and unanticipated catastrophic component failures. Theoretical analysis indicates that the control problem of interest can be solved on-line without a complete realization of the unknown failure dynamics provided an on-line estimator satisfies certain conditions. Through the on-line estimator, effective control signals to accommodate the dynamic failures can be computed using only the partially available information of the faults. Several on-line simulation studies have been presented to demonstrate the effectiveness of the proposed strategy. To investigate the feasibility of using the developed technique for unanticipated fault accommodation in hardware under the real-time environment, an on-line fault tolerant control test bed has been constructed to validate the proposed technology. Both on-line simulations and the real-time experiment show encouraging results and promising futures of on-line real-time fault tolerant control based solely upon insufficient information of the system dynamics and the failure dynamics.

The class of 2-bijective connection networks (2BC networks) is defined recursively as follows: Let ${\mathscr{H}}_2=\left\{K_4\right\}$ and for $\text{i}\ge \text{3}$, let ${\mathscr{H}}_i$ be the set of all graphs that can be constructed by taking two (possibly the same) elements ${\text{R}}_{\text{1}}{\text{= (V}}_{\text{1}}{\text{, E}}_{\text{1}}\text{)}$ and ${\text{R}}_{\text{2}}{\text{= (V}}_{\text{2}}{\text{, E}}_{\text{2}}\text{)}$ from ${\mathscr{H}}_{i-1}$ (if we take the same element, we will assume they are two different copies and so ${\text{V}}_{\text{1}}\cap {\text{V}}_{\text{2}}$ remains empty) with two bijections ${\text{f}}_{\text{1}}{\text{: V}}_{\text{1}}\to {\text{V}}_{\text{2}}$ and ${\text{f}}_{\text{2}}{\text{: V}}_{\text{1}}\to {\text{V}}_{\text{2}}$ to form the graph ${\text{H = (V}}_{\text{1}}\cup {\text{V}}_{\text{2}}{\text{, E}}_{\text{1}}\cup {\text{E}}_{\text{2}}\cup {\text{M}}_{\text{1}}\cup {\text{M}}_{\text{2}}\text{)}$ where ${\text{M}}_{\text{1}}{\text{= {(v, f}}_{\text{1}}\text{(v)) : v}\in {\text{V}}_{\text{1}}\text{}}$ and ${\text{M}}_{\text{2}}{\text{= {(v, f}}_{\text{2}}\text{(v)) : v}\in {\text{V}}_{\text{1}}\text{}}$ such that $M_1\cap M_2=\varnothing$. This class of networks includes the class of augmented cubes. We study the structural properties of the resulting graph when “many” edges are deleted from such a network. We then mention some applications.

The conditional diagnosability is an important measure of reliability of interconnection networks. Much progress has been made in the past decade. By consolidating various results, a general scheme can be developed to solve the conditional diagnosability problem for many important classes of interconnection networks; thus eliminating various ad-hoc methods used in earlier studies. The buttery network is an important interconnection network and it has been rediscovered multiple times by different authors. The hyper-buttery network is a graph that amalgamates the buttery network and the hypercube. In this paper, we solve the conditional diagnosability problem for these hyper-buttery networks and their generalizations.

Fault diagnostic analysis is extremely important for interconnection networks. The $t^{\prime }/g$-diagnosis imprecise strategy plays an essential role in the reliability of networks. The $t^{\prime }/g$-diagnosis strategy can detect up to $t^{\prime }$ faulty vertices which might include at most $g$ misdiagnosed vertices. The exchanged hypercube is obtained by systematically removing links from a binary hypercube, which has smaller maximum degree and Wiener index than the hypercube. We use $GEH(s,t)$ to denote the generalized exchanged hypercube, and show in this paper that $GEH(s,t)$ is $[(g+1)s-\frac{g(g+1)}{2}+1]/g$-diagnosable with $1\le s\le t$ and $0\le g\le s-1$ under the PMC model and MM${}^{\ast }$ model. We also propose a $t^{\prime }/g$-diagnosis algorithm on $GEH(s,t)$. As a side benefit, the $t^{\prime }/g$-diagnosability of the dual-cube-like network $D{C}_n$ can be directly obtained from our results.

In the Energy Conversion for Next-Generation Smart Cities, intelligent substation plays an important role in the power conversion. As an important guarantee for the stable operation of intelligent substation, the research on fault diagnosis technology is particularly important. In this paper, the acoustic characteristic diagnosis of substation equipment (take transformers for example) is researched and the application of “Voice Recognition + artificial neural network (ANN)” technology in substation fault diagnosis is analyzed. At the same time, the continuous online monitoring of the intelligent substation equipment will produce a large amount of monitoring data, which needs to be analyzed timely and effectively to understand the operating status of the equipment accurately. Because of this, this paper adopts distributed computing by establishing a real-time distributed computing platform, using open source technology to store the online monitoring of sound data into the computing platform for data processing to achieve the purpose of automatic fault detection and analysis. The results show that distributed computing can realize the intelligent analysis, storage, and visualization of equipment data in the substation, which provides data support for fault diagnosis. Besides, the fitting accuracy rates of ANN model are 95.123% for training process and the fitting accuracy rates of ANN model are 99.353% for training process and the overall fitting accuracy rates of ANN model are 95.478% and the error between the predicted value and the actual value of the 5 sound signals is within 5% in the fault diagnosis process. Consequently, the ANN model can accurately identify each fault sound of substation and achieve the purpose of fault diagnosis.

For solving the advanced manufacturing fault diagnosis issue, a novel zonotopes estimation-based fault diagnosis algorithm is proposed in this paper. By using the intersection of the convex polytope and the tight strip, the fault diagnosis problem is changed into the analysis of the set membership outer bound computation. If the feasible set is detected empty, the set membership filters are designed. The minimal volume is also calculated and the selected zonotopes can be viewed as the approximate boundary. The simulation results show the effectiveness and practicability of the presented fault diagnosis algorithm.

In order to improve the fault diagnosis rate and efficiency of diesel engine, the PCA-RBF neural network as a new algorithm was constructed by combing the character extraction ability of PCA with the nonlinear approximation ability of RBF neural network. Firstly, eight factors which affected the fault types of diesel engine were analyzed and three principal components were extracted by PCA. Secondly, the data obtained from the three principal components were taken as the input of RBF neural network which was trained and tested. Finally, the PCA-RBF neural network was verified through simulation. The simulation results show that the network has fewer training steps, less training and higher training accuracy.

It is difficult to extract weak signals in strong noise background, therefore a piecewise asymmetric exponential potential under-damped bi-stable stochastic resonance (PAEUBSR) system is proposed. First, the theoretical analysis of the steady-state probability density (SPD), mean first passage time (MFPT) and output signal-to-noise ratio (SNR) are derived under the adiabatic approximation theory. At the same time, the influence of different system parameters on system performance is explored. Then the PAEUBSR system is applied to the fault signal diagnosis of different types of bearings, and the parameters are optimized through the adaptive genetic algorithm (AGA). The test results are compared with the exponential potential over-damped symmetric bi-stable stochastic resonance (EOSBSR) system and the exponential potential under-damped symmetric bi-stable stochastic resonance (EUSBSR) system. Finally, the detection results on two sets of bearing fault data show that the PAEUBSR system has better effects on the enhancement and detection of bearing fault signals. This provides good theoretical support and application value for this system in subsequent theoretical analysis and practical engineering applications.

The paper proposes a fault diagnosis model based on the HIWO–SVM algorithm given the fact that the basic support vector machines (SVM) cannot solve effectively the problem of fault diagnosis in analog circuit. First of all, the wavelet package technique is adopted for extracting the information of the faults from the test points in the analog circuit. The differential evolution (DE) algorithm is then integrated with the purpose of improving the performance of the basic IWO algorithm, i.e. a hybrid IWO (HIWO) algorithm. The HIWO algorithm is further used to optimize the parameters of SVM in order to avoid the randomness of the parameter selection, thereby improving the diagnosis precision and robustness. The experimental results on a filter circuit show that the method is more effective and reliable than the other methods for fault diagnosis.

Variable Bleed Valve (VBV) system is an important component of civil aviation engine which can be used to adjust the opening degree of bleed valve. By adjusting the opening degree of bleed valve, a part of outlet air from low-pressure compressor can flow into the fan so as to improve the working stability of low-pressure compressor. VBV system was chosen as the research object in this paper, which internal structure and composition were analyzed and its model was established from part to the whole at first. Then, the negative selection algorithm of variable radius detectors was researched to achieve VBV system faults diagnosis by selecting characteristic parameters and setting up multi-type fault diagnosis process. At last, electrohydraulic servo valve fault, VBV system controller fault and linear variable differential transformer fault were intentionally set up to verify the effectiveness of fault diagnosis method. Through the process of detector generation and fault recognition, the faults in VBV system can be diagnosed effectively.

In the rolling bearing fault detection, the Hilbert–Huang transform (HHT) has made remarkable achievements, but at present, the HHT still has the end effect problem, which will cause a lot of data distortion, spectrum confusion that will affect fault diagnosis result and error in the detection of rolling bearing faults in a serious manner. In response to this problem, this paper proposes a method of multi-point continuation at both ends of the signal to suppress the endpoint effectExtend at both ends of the signal, then perform empirical mode decomposition (EMD). The experimental comparison shows that the method has an effect on the endpoint effect.

To obtain the fault features of the bearing, a method based on variational mode decomposition (VMD), singular value decomposition (SVD) is proposed for fault diagnosis by Gath–Geva (G–G) fuzzy clustering. Firstly, the original signals are decomposed into mode components by VMD accurately and adaptively, and the spatial condition matrix (SCM) can be obtained. The SCM utilized as the reconstruction matrix of SVD can inherit the time delay parameter and embedded dimension automatically, and then the first three singular values from the SCM are used as fault eigenvalues to decrease the feature dimension and improve the computational efficiency. G–G clustering, one of the unsupervised machine learning fuzzy clustering techniques, is employed to obtain the clustering centers and membership matrices under various bearing faults. Finally, Hamming approach degree between the test samples and the known cluster centers is calculated to realize the bearing fault identification. By comparing with EEMD and EMD based on a recursive decomposition algorithm, VMD adopts a novel completely nonrecursive method to avoid mode mixing and end effects. Furthermore, the IMF components calculated from VMD include large amounts of fault information. G–G clustering is not limited by the shapes, sizes and densities in comparison with other clustering methods. VMD and G–G clustering are more suitable for fault diagnosis of the bearing system, and the results of experiment and engineering analysis show that the proposed method can diagnose bearing faults accurately and effectively.

In order to realize the diagnosis of the state of the high-voltage circuit breaker in the smart grid, the wavelet-packet technique is used to extract the characteristic value of the signal of the dynamic contact of the high-voltage circuit breaker. The characteristic value of the obtained signal is processed by fuzzy clustering, which inputs the processed feature values into the Support Vector Machine (SVM) to implement fault diagnosis. The high-voltage circuit breakers that need to be identified have the following faults: contact spring failure, trip spring shaft pinout, and trip spring failure. After the above series of processes, the paper reached the conclusion that it is feasible to use SVM to diagnose the high voltage circuit breaker fault system, which has a good diagnostic effect.

With the development of information theory and image analysis theory, the studies on fault diagnosis methods based on image processing have become a hot spot in the recent years in the field of fault diagnosis. The gearbox of wind turbine generator is a fault-prone subassembly. Its time frequency of vibration signals contains abundant status information, so this paper proposes a fault diagnosis method based on time-frequency image characteristic extraction and artificial immune algorithm. Firstly, obtain the time-frequency image using wavelet transform based on threshold denoising. Secondly, acquire time-frequency image characteristics by means of Hu invariant moment and correlation fusion gray-level co-occurrence matrix of characteristic value, thus, to extract the fault information of the gearing of wind turbine generator. Lastly, diagnose the fault type using the improved actual-value negative selection algorithm. The application of this method in the gear fault diagnosis on the test bed of wind turbine step-up gearbox proves that it is effective in the improvement of diagnosis accuracy.