Accuracy Of Fault Diagnosis Research Articles

A decision-level sensor fusion scheme integrating ultrasonic guided wave and vibration measurements for damage identification

Structural health monitoring is designed to detect and analyze damage in mechanical, aerospace, and industrial structures to prevent potential catastrophic failures. The effectiveness of identifying structural faults and operational damage significantly relies on the sensing technology. Multisensory data fusion, as one of the promising techniques, combines data from multiple sensor modalities for reliable and accurate fault diagnosis. In this paper, we propose a novel decision-level multisensory data fusion approach. This approach combines data from an ultrasonic guided-wave sensor modality and a vibration sensor modality for the first time, aiming to achieve precise and stable damage identification. The Bayesian probabilistic distributions from each sensor modality are obtained using a multi-level Metropolis–Hastings algorithm. Subsequently, a multilayer perceptron network is trained to automatically allocate confidence scores for each sensor modality. The final fusion results are derived from the proposed decision-level fusion approach, combining the Bayesian probabilistic distributions from each sensor modality with allocated confidence scores. Simulation and experiment results indicate that the decision-level fusion approach produces more accurate and reliable outcomes for damage identification compared to relying on a single modality, especially in the case of progressive damage.

Semi-Supervised Informer for the Compound Fault Diagnosis of Industrial Robots.

The increasing deployment of industrial robots in manufacturing requires accurate fault diagnosis. Online monitoring data typically consist of a large volume of unlabeled data and a small quantity of labeled data. Conventional intelligent diagnosis methods heavily rely on supervised learning with abundant labeled data. To address this issue, this paper presents a semi-supervised Informer algorithm for fault diagnosis modeling, leveraging the Informer model's long- and short-term memory capabilities and the benefits of semi-supervised learning to handle the diagnosis of a small amount of labeled data alongside a substantial amount of unlabeled data. An experimental study is conducted using real-world industrial robot monitoring data to assess the proposed algorithm's effectiveness, demonstrating its ability to deliver accurate fault diagnosis despite limited labeled samples.

Uncertainty‐aware nuclear power turbine vibration fault diagnosis method integrating machine learning and heuristic algorithm

AbstractNuclear power turbine fault diagnosis is an important issue in the field of nuclear power safety. The numerous state parameters in the operation and maintenance of nuclear power turbines are collected, forming a complex high‐dimensional feature space. These high‐dimensional feature spaces contain redundant information, which increases the training cost and reduces the recognition accuracy and efficiency of the fault diagnosis model. To address the aforementioned challenges, a vibration fault diagnosis algorithm in nuclear power turbines is proposed. First, a long short‐term memory‐based denoising autoencoder (LDAE) is designed to enhance the capability of uncertainty awareness. Then, a feature extraction method integrating variational mode decomposition (VMD), L‐cliffs‐based effective mode selection, and sample entropy is devised to extract the latent features from the complex high‐dimensional feature space. Furthermore, using extreme gradient boosting (XGBoost) as the classifier, LDAE‐VMD‐XGBoost model is constructed for fault diagnosis of nuclear power turbines. Considering the impact of multiple hyperparameters of LDAE‐VMD‐XGBoost model on the performance, the pathfinder algorithm is used to optimise the model hyperparameter settings and improve the fault diagnosis accuracy. Experimental results demonstrate the performance of the proposed improved LDAE‐VMD‐XGBoost in accurate nuclear power turbine vibration fault diagnosis.

A model-data combination driven digital twin model for few samples fault diagnosis of rolling bearings

Abstract Deep learning-based fault diagnosis methods for rolling bearings are widely utilized due to their high accuracy. However, they have limitations under conditions with few samples. To address this problem, a model-data combination driven digital twin model (MDCDT) is proposed in this work for fault diagnosis with few samples of rolling bearings. The simulation signals generated by different fault dynamic models of rolling bearings and the measured signals are mixed through MDCDT. The MDCDT generates virtual signals to bridge the gap between the simulated signals and the measured signals by combining their respective advantages. This paper also proposes image coding method based on the Markov transfer matrix (MTMIC) to convert one-dimensional vibration signals into two-dimensional images with both frequency domain information and time domain information, making it easier to extract fault features in neural network training. In the end, the developed MDCDT was evaluated using real rolling bearing data. Experiments show that the MDCDT can generate virtual data for fault diagnosis, and the fault diagnosis accuracy is significantly improved.

A Deep Transfer Learning Model for the Fault Diagnosis of Double Roller Bearing Using Scattergram Filter Bank 1

In this study, a deep transfer learning model was developed using ResNet-101 architecture to diagnose double roller bearing defects. Vibration data were collected for three different load scenarios, including conditions without load, and for five different rotational speeds, ranging from 500 to 2500 RPM. Significantly, the speed condition of 2500 RPM has not previously been investigated, therefore offering a potential avenue for future investigations. This study offers a thorough examination of bearing conditions using multidirectional vibration data collected from accelerometers positioned in both vertical and horizontal orientations. In addition to transfer learning using ResNet-101, four additional models (VGG-16, VGG19, ResNet-18, and ResNet-50) were trained. Transfer learning using ResNet-101 consistently achieved the highest accuracy in all scenarios, with accuracy rates ranging from 90.78% to 99%. Scattergram Filter Bank 1 was used as the image input for training as a preprocessing method to enhance feature extraction. Research has effectively applied transfer learning to improve fault diagnosis accuracy, especially in limited data scenarios. This shows the capability of the method to differentiate between normal and faulty bearing conditions using signal-to-image transformation, emphasizing the potential of transfer learning to augment diagnostic performance in scenarios with limited training data.

Research on bearing fault diagnosis based on novel MRSVD-CWT and improved CNN-LSTM

As a critical component in mechanical equipment, rolling bearings play a vital role in industrial production. Effective bearing fault diagnosis provides a more reliable guarantee for the safe operation of the industrial output. Traditional data-driven bearing fault diagnosis methods often have problems such as insufficient fault feature extraction and poor model generalization capabilities, resulting in reduced diagnostic accuracy. To solve these problems and significantly improve the diagnosis accuracy, this paper proposes a novel fault diagnosis method based on multi-resolution singular value decomposition (MRSVD), continuous wavelet transform (CWT), improved convolutional neural network (CNN) enhanced by convolutional block attention module, and long short-term memory (LSTM). Through MRSVD, the vibration signal is decomposed layer by layer into multiple denoised signals, thus signal noise can be eliminated to the greatest extent to gain the optimal denoised signals; then through CWT, the optimal denoised signals are converted into two-dimensional time-frequency images so that the local and global characteristic information can be fully captured. Finally, through improved CNN-LSTM, feature extraction is greatly enhanced, resulting in high accuracy of fault diagnosis. Lots of experiments are organized to test the performance, and the experimental results show that the proposed method on various datasets has better diagnosis accuracy and generalization ability under different working conditions than other methods.

Rolling bearing fault diagnosis based on DRS frequency spectrum image and improved DQN

Deep learning may encounter challenges in fault diagnosis, such as exploration capability, long-term planning, and handling non-deterministic factors. The paper introduces a novel fault diagnosis method for rolling bearings combining deep Q-network (DQN) with discrete random separation (DRS) frequency spectrum images. DRS can be used to separate the deterministic components and random components of the fault signal and extract the fault feature very effectively. The improved DQN incorporates the atrous spatial pyramid pooling module for multiscale contextual fault feature extraction, enhancing diagnosis accuracy. Various deep networks, including convolutional neural network, ResNet18, traditional DQN, and the improved DQN, are employed with different frequency spectrum images (power spectral density, cepstrum, and DRS) for diagnosing bearing faults. Simulation results demonstrate that combining DRS frequency spectrum images with the improved DQN enhances fault diagnosis accuracy across diverse conditions. Generalization tests reveal strong capability of the proposed method in handling conditions different from the training data. Validation tests on difficult-to-diagnose fault data from the CWRU-bearing dataset demonstrate commendable performance of the improved DQN, even on difficult datasets. Finally, validation tests using the XJTU–SY bearing dataset reaffirm the excellent performance and robust adaptability of the improved DQN in conjunction with DRS frequency spectrum images.

Inter-turn Short Circuit Fault Diagnosis and Severity Estimation for Wind Turbine Generators

While preventive maintenance is crucial in wind turbine operation, conventional condition monitoring systems face limitations in terms of cost and complexity when compared to innovative signal processing techniques and artificial intelligence. In this paper, a cascading deep learning framework is proposed for the monitoring of generator winding conditions, specifically to promptly detect and identify inter-turn short circuit faults and estimate their severity in real time. This framework encompasses the processing of high-resolution current signal samples, coupled with the extraction of current signal features in both time and frequency domains, achieved through discrete wavelet transform. By leveraging long short-term memory recurrent neural networks, our aim is to establish a cost-efficient and reliable condition monitoring system for wind turbine generators. Numeral experiments show an over 97% accuracy for fault diagnosis and severity estimation. More specifically, with the intrinsic feature provided by wavelet transform, the faults can be 100% identified by the diagnosis model.

MultiCogniGraph: A multimodal data fusion and graph convolutional network‐based multi‐hop reasoning method for large equipment fault diagnosis

AbstractAs industrial production escalates in scale and complexity, the rapid localization and diagnosis of equipment failures have become a core technical challenge. In response to the demand for intelligent fault diagnosis in large‐scale industrial equipment, this study presents “MultiCogniGraph”—a multi‐hop reasoning diagnostic method that integrates multimodal data fusion, knowledge graphs, and graph convolutional networks (GCN). This method leverages internet of things (IoT) sensor data, small‐sample imagery, and expert knowledge to comprehensively characterize the equipment state and accurately detect subtle distinctions in fault patterns. Utilizing a knowledge graph to synthesize data from multiple sources and deep reasoning with GCN, “MultiCogniGraph” achieves swift and effective fault localization and diagnosis. The integration of these techniques not only enhances the efficiency and accuracy of fault diagnosis but also its interpretability, marking a new direction in the field of intelligent fault diagnostics.

Calculation method for natural frequency and damping ratio of hydropower units based on motion model separation

Abstract In recent years, the research on characteristic extraction methods for non-stationary and non-linear vibration signals of hydroelectric units has been a hot topic in the fault diagnosis of hydroelectric units. The effectiveness of feature extraction directly affects the accuracy of fault diagnosis. This article proposes a vibration signal feature extraction method for hydroelectric units based on motion model separation and logarithmic attenuation rate method. The under-damped decay oscillation motion trajectory is obtained from the signal after motion model separation. And then, the logarithmic attenuation rate method in the time domain analysis is used to calculate the system damping ratio and natural frequency. In this process, the principle of selecting the envelope interpolation function is proposed, and the effectiveness of the cubic Hermite interpolation function is determined. Based on the calculation effectiveness and accuracy requirements, the effective step length of the vibration signal is determined to be Δt = 0.001, and the effective calculation interval for extracting the decay oscillation characteristics is [ts , tend ]. The results show that the proposed method is more straightforward, efficient, has higher computational accuracy and better signal-to-noise ratio adaptability, and can provide a theoretical basis for practical engineering applications.

A novel adaptive gramian angle field based intelligent fault diagnosis for motor rolling bearings

Abstract The Gramian Angle Field (GAF) can encode one-dimensional vibration signals into two-dimensional feature maps containing time correlation information. However, the feature representation ability of traditional GAF-encoded images is limited, making it challenging to further improve fault diagnosis accuracy. To address these issues, an AGAF-CNN intelligent fault diagnosis method is proposed in this paper. In addition to traditional GAF encoding, an adaptive adjustment parameter is introduced that automatically determines its value based on the dynamic distribution characteristics of the input data. This ensures that the resulting feature map after two-dimensional encoding contains optimal fault discriminant features. By leveraging CNN’s capability to process image data, the proposed method extracts deep-level feature representations from the vibration signal feature map and performs accurate diagnosis. The approach is validated using a rolling bearing dataset from Case Western Reserve University in the United States, and superior diagnostic accuracy is demonstrated compared to other vibration signal coding methods combined with CNN-based fault diagnosis methods. The theoretical and practical advantages of AGAF feature coding are explained comprehensively.

Sparse Wasserstein stationary subspace analysis for fault detection and diagnosis of nonstationary industrial processes

Fault detection and diagnosis of nonstationary processes are crucial for ensuring the safety of industrial production systems. However, the nonstationarity of process data poses multifaceted challenges to them. First, conventional stationary fault detection methods encounter difficulties in discerning evolving trends within nonstationary data. Secondly, the majority of current nonstationary fault detection methods directly extract features from all variables, rendering them susceptible to redundant interference. Moreover, nonstationary trends possess the capacity to conceal and modify the correlations among variables. Coupled with the smearing effect of faults, it is challenging to achieve accurate fault diagnosis. To address these challenges, this paper proposes sparse Wasserstein stationary subspace analysis (SWSSA). Specifically, a ℓ2,p-norm constraint is introduced to endow the stationary subspace model with excellent sparse representation capability. Furthermore, recognizing that fault variables within the sparse stationary subspace influence only a limited subset of stationary sources, this paper proposes a novel contribution analysis method based on local dynamic preserving projection (LDPP), termed LDPPBC, which can effectively mitigate the smearing effect on nonstationary fault diagnosis. LDPPBC establishes a LDPP matrix by extracting the latent positional information of fault variables within the stationary subspace. This allows LDPPBC to selectively analyze the contributions of variables within the latent fault subspace to achieve precise fault diagnosis while avoiding the interference of variable contributions from the fault-free subspace. Finally, the superiority of the proposed method is thoroughly validated through a numerical simulation, a continuous stirred tank reactor, and a real industrial roaster.

Multi-scale quaternion CNN and BiGRU with cross self-attention feature fusion for fault diagnosis of bearing

In recent years, deep learning has led to significant advances in bearing fault diagnosis (FD). Most techniques aim to achieve greater accuracy. However, they are sensitive to noise and lack robustness, resulting in insufficient domain adaptation and anti-noise ability. The comparison of studies reveals that giving equal attention to all features does not differentiate their significance. In this work, we propose a novel FD model by integrating multi-scale quaternion convolutional neural network (MQCNN), bidirectional gated recurrent unit (BiGRU), and cross self-attention feature fusion (CSAFF). We have developed innovative designs in two modules, namely MQCNN and CSAFF. Firstly, MQCNN applies quaternion convolution to multi-scale architecture for the first time, aiming to extract the rich hidden features of the original signal from multiple scales. Then, the extracted multi-scale information is input into CSAFF for feature fusion, where CSAFF innovatively incorporates cross self-attention mechanism to enhance discriminative interaction representation within features. Finally, BiGRU captures temporal dependencies while a softmax layer is employed for fault classification, achieving accurate FD. To assess the efficacy of our approach, we experiment on three public datasets (CWRU, MFPT, and Ottawa) and compare it with other excellent methods. The results confirm its state-of-the-art, which the average accuracies can achieve up to 99.99%, 100%, and 99.21% on CWRU, MFPT, and Ottawa datasets. Moreover, we perform practical tests and ablation experiments to validate the efficacy and robustness of the proposed approach. Code is available at https://github.com/mubai011/MQCCAF.

Bearing Fault Diagnosis Based on SMA-VMD and CNN-LSTM

To address the challenges of manual parameter setting dependency and low accuracy in bearing fault diagnosis using Variational Mode Decomposition (VMD), a method integrating Slime Mould Algorithm (SMA), VMD, and Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) network is proposed. Firstly, the SMA is employed to optimize the critical parameters of VMD using minimum information entropy as the fitness function, which resolves the issues related to manual parameter settings in VMD. Subsequently, the optimal parameter combination is used to process the bearing signals and extract the relevant Intrinsic Mode Functions (IMF). Finally, these IMFs are input into the CNN-LSTM network for fault diagnosis. The results demonstrate that this method significantly enhances the accuracy of motor bearing fault diagnosis, further improving the fault diagnosis accuracy.

Intelligent fault diagnosis of machinery based on hybrid deep learning with multi temporal correlation feature fusion

AbstractWith the advent of intelligent manufacturing era, higher requirements are put forward for the fault diagnosis technology of machinery. The existing data‐driven approaches either rely on specialized empirical knowledge for feature analysis, or adopt single deep neural network topology structure for automatic feature extraction with compromise of certain information loss especially the time‐series information's sacrifice, which both eventually affect the diagnosis accuracy. To address the issue, this paper proposes a novel multi‐temporal correlation feature fusion net (MTCFF‐Net) for intelligent fault diagnosis, which can capture and retain time‐series fault feature information from different dimensions. MTCFF‐Net contains four sub‐networks, which are long and short‐term memory (LSTM) sub‐network, Gramian angular summation field (GASF)‐GhostNet sub‐network and Markov transition field (MTF)‐GhostNet sub‐network and feature fusion sub‐network. Features of different dimensional are extracted through parallel LSTM sub‐network, GASF‐GhostNet sub‐network and MTF‐GhostNet sub‐network, and then fused by feature fusion sub‐network for accurate fault diagnosis. Two fault diagnosis experimental studies on bearings are implemented to validate the effectiveness and generalization of the proposed MTCFF‐Net. Experimental results demonstrate that the proposed model is superior to other comparative approaches.

DCSIAN: A novel deep cross-scale interactive attention network for fault diagnosis of aviation hydraulic pumps and generalizable applications

Channel attention (CA) has been wildly applied to enhance the diagnosis performance of multiscale convolution (MSC)-based diagnosis methods. Nevertheless, most of the existing CA modules only consider the internal local correlation among different channels within each scale feature, but ignore the global correlation among different scales, restricting further improvement. To address this issue, a novel deep cross-scale interactive attention network (DCSIAN) is developed to achieve accurate fault diagnosis for aviation hydraulic pumps under high-noise environments. Specifically, a novel cross-scale interactive attention module (CSIAM) is developed and introduced into MSC to learn complementary and rich multiscale features from original vibration signals. CSIAM adopts two cascaded submodules to focus on local channel correlation and global scale correlation simultaneously. Local channel correlation is used to adaptively measure the importance of different channel feature within each scale, while global scale correlation is used to dynamically determine the contribution of each scale feature to the final diagnostic result. In this way, the fault-related information at different scales can be fully captured and utilized. Finally, the effectiveness of DCSIAN is validated by a series of experimental comparisons on an aviation hydraulic pump dataset and a bearing dataset with various types noise.

Coupling mechanical model and failure of aeroengine ceramic matrix composite based on genetic algorithm

In order to understand the coupling mechanical model of aeroengine ceramic matrix composite, the author proposed a coupling mechanical model and failure study of aeroengine ceramic matrix composite based on genetic algorithm. The author first analyzed that the real-time model of an aircraft engine and the matching accuracy of the engine directly affect the accuracy of aircraft engine fault diagnosis, a least squares support vector regression (AGA LSSVR) method based on adaptive genetic algorithm was proposed to modify the real-time model of an aircraft engine, effectively improving the matching accuracy of the model. Secondly, the impact of parameter selection in least squares support vector machines on model correction was analyzed, and an adaptive genetic algorithm was used to search for the optimal parameters in the parameter selection space. Finally, compare the correction effects of methods such as (BP) neural network, support vector regression machine, AGA LSSVR in airborne models. The results indicate that: The proposed AGA LSSVR has good correction accuracy, which verifies the effectiveness of the correction model.

Research on a Wind Turbine Gearbox Fault Diagnosis Method Using Singular Value Decomposition and Graph Fourier Transform.

Gearboxes operate in challenging environments, which leads to a heightened incidence of failures, and ambient noise further compromises the accuracy of fault diagnosis. To address this issue, we introduce a fault diagnosis method that employs singular value decomposition (SVD) and graph Fourier transform (GFT). Singular values, commonly employed in feature extraction and fault diagnosis, effectively encapsulate various fault states of mechanical equipment. However, prior methods neglect the inter-relationships among singular values, resulting in the loss of subtle fault information concealed within. To precisely and effectively extract subtle fault information from gear vibration signals, this study incorporates graph signal processing (GSP) technology. Following SVD of the original vibration signal, the method constructs a graph signal using singular values as inputs, enabling the capture of topological relationships among these values and the extraction of concealed fault information. Subsequently, the graph signal undergoes a transformation via GFT, facilitating the extraction of fault features from the graph spectral domain. Ultimately, by assessing the Mahalanobis distance between training and testing samples, distinct defect states are discerned and diagnosed. Experimental results on bearing and gear faults demonstrate that the proposed method exhibits enhanced robustness to noise, enabling accurate and effective diagnosis of gearbox faults in environments with substantial noise.

Catalytic Pyrolysis of Polypropylene for Cable Semiconductive Buffer Layers.

With the progress of the power grid system, the coverage area of cables is widening, and the problem of cable faults is gradually coming to affect people's daily lives. While the vast majority of cable faults are caused by the ablation of the cable buffer layer, polypropylene (PP), as a common cable buffer material, has pyrolysis properties that critically impact cable faults. Studying the semiconductive buffer layer of polypropylene (PP) and its pyrolysis properties allows us to obtain a clearer picture of the pyrolysis products formed during PP ablation. This understanding aids in the accurate diagnosis of cable faults and the identification of ablation events. In this study, the effects of temperature and catalyst (H-Zeolite Standard Oil Corporation Of New York (Socony) Mobil-Five (HZSM-5)) content on the PP thermolysis product distribution were studied by using an online tubular pyrolysis furnace-mass spectrometry (MS) experimental platform. The results showed that PP/40% HZSM-5 presented the highest thermolytic efficiency and relative yield of the main products at 400 °C.

A Reviewed Turn at of Methods for Determining the Type of Fault in Power Transformers Based on Dissolved Gas Analysis

Since power transformers are the most important pieces of equipment in electricity transmission and distribution systems, special attention must be paid to their maintenance in order to keep them in good condition for a long time. This paper reviews the main steps in the process of diagnosing the health of power transformer insulation, which involves the science of analysing the gases dissolved in power transformer oil for effective identification of faults. An accurate diagnosis of incipient faults is favourable to sustainable development and necessary to maintain a reliable supply of electricity. The methods presented for fault diagnosis in mineral-oil-immersed power transformers are divided into analytical and graphical methods and have been found to be simple, economical and effective. After describing the methods, both their strengths and weaknesses were identified, and over the years, the methods were complemented to provide highly accurate information, validated by field inspections. This paper focuses on practical information and applications to manage maintenance based on accurate and up-to-date data. The contents of this paper will be of particular use to engineers who manufacture, monitor and/or use high-power transformers in the energy sector, as well as to undergraduate, master’s and PhD students interested in such applications.