Mechanical Fault Detection Research Articles

A novel unsupervised graph wavelet autoencoder for mechanical system fault detection

A novel unsupervised graph wavelet autoencoder for mechanical system fault detection

A self-growth convolution network for thermal and mechanical fault detection with very limited engine data

Severe faults occur infrequently but are critical for the prognostics and health management (PHM) of power machinery. Due to the scarcity of fault data, diagnostic models are always facing a very limited data problem. Basic convolutional neural networks require a large number of samples to train, and widely used data augmentation methods are influenced by data quality, which can exacerbate overfitting. To address this issue, a self-growth convolution network (SGNet) is proposed to make the deep learning process a self-growing scheme in both depth and width dimensions. The direct similarity measurement is utilized to supervise the depth-growth in the layer-by-layer training process. The feature redundancy metric is employed to control the width expansion. The self-growth scheme is proposed to disrupt the coadaptation between layers and that between kernels in order to mitigate the overfitting issue of small-sample cases. The SGNet is verified and implemented in the PHM of a heavy-duty diesel engine. It exhibits remarkable diagnostic capabilities in extremely sample-limited scenarios. With only three training samples per faulty type, the recognition rates of SGNet for the misfire fault and the gear tooth fracture fault are 88.44% and 98.11%, respectively. Further, the feature contrast, the information transmission, the noise resistance, and the frequency domain activation heat of SGNet are discussed by the ablation experiment in detail. The results indicate a novel path to solve the data-limitation problem in the PHM of important power machinery.

A Lightweight and Efficient Multimodal Feature Fusion Network for Bearing Fault Diagnosis in Industrial Applications.

To address the issues of single-structured feature input channels, insufficient feature learning capabilities in noisy environments, and large model parameter sizes in intelligent diagnostic models for mechanical equipment, a lightweight and efficient multimodal feature fusion convolutional neural network (LEMFN) method is proposed. Compared with existing models, LEMFN captures rich fault features at multiple scales by combining time-domain and frequency-domain signals, thereby enhancing the model's robustness to noise and improving data adaptability under varying operating conditions. Additionally, the convolutional block attention module (CBAM) and random overlapping sampling technology (ROST) are introduced, and through a feature fusion strategy, the accurate diagnosis of mechanical equipment faults is achieved. Experimental results demonstrate that the proposed method not only possesses high diagnostic accuracy and rapid convergence but also exhibits strong robustness in noisy environments. Finally, a graphical user interface (GUI)-based mechanical equipment fault detection system was developed to promote the practical application of intelligent fault diagnosis in mechanical equipment.

Enhancing machine learning multi-class fault detection in electric motors through entropy-based analysis

Abstract In the field of electric motor maintenance, this study introduces a transformative approach by integrating entropy-based algorithms with machine learning for enhanced multi-class fault detection. Employing Shannon, Renyi, and Tsallis entropy algorithms on standard fault detection measurements, the research significantly advances predictive maintenance strategies through a robust, early-indication, system-agnostic analysis. Detailed examination is conducted, comparing results derived from datasets that include statistical features (excluding entropy) against the proposed entropy-based datasets, when applied to a multi-layer perceptron classifier (MLPC). Optimization of the MLPC and all compared algorithms’ hyperparameters is done using the state-of-the-art Optuna tool to dynamically explore each search space, ensuring that each methodology performs adequately in a timely fashion while allowing for adaptation. The results showcase significant enhancement in classification accuracy of diverse electric motor operational states, facilitating the differentiation between healthy and various levels of fault conditions under assorted load scenarios. Computational analyses reveal favorable results related to execution time and memory overhead, thereby supporting the practicality in operations constrained by memory resources. Validation of the approach is achieved through laboratory experiments on a purpose-built test bench. Versatility of entropy-based measures through their proposed utilization in diverse fault indications is achieved by a demonstration in the field of mechanical fault detection with a focus on bearing faults through well-respected datasets.

USEFULNESS OF VIBRATION ANALYSIS TECHNIQUES AND SENSORS TO IMPROVE THE MONITORING OF INDUSTRIAL EQUIPMENT

The food industry is constantly seeking advanced technologies to improve the efficiency and reliability of machinery, which is critical to improving product quality and manufacturing efficiency. This paper explores the applications of integrating vibration analysis techniques and sensors to improve machine monitoring in the food industry. Vibration analysis is a well-established technique for mechanical fault detection, providing valuable insight into the condition of rotating equipment. By incorporating advanced sensors that can capture a wide range of vibration signals the aim of this research is to improve the accuracy and sensitivity of device health monitoring. The review reviews existing literature on vibration analysis, sensor technology, and applications in the food industry. It explores how traditional vibration analysis methods can be incorporated into advanced sensor technologies such as accelerometers and other sensors. The integration of these technologies will provide a comprehensive understanding of machine behavior, leading to faster abnormal detection and predictive maintenance.

Industrial mechanical equipment fault detection and high-performance data analysis technology based on the Internet of Things

In view of the problems of low detection accuracy, long detection time, and inability to monitor fault data in real time in the fault detection of traditional machinery and equipment, this paper studies the identification and fault detection of industrial machinery based on the Internet of Things (IoT) technology. By using Internet of Things technology to build a mechanical equipment fault detection system, Internet of Things technology can better build diagnostic and early warning modules for the system, so as to achieve the goal of improving the accuracy of equipment fault detection, shortening equipment fault detection time, and remotely monitoring equipment. The fault detection system studied in this paper has an accuracy rate of more than 93.4% to detect different types of fault. The use of Internet of Things technology is conducive to improving the accuracy of mechanical equipment fault detection and realizing real-time monitoring of equipment data.

Transfer learning with cross-domain adaptation of vibro-acoustic signals for electric motor mechanical fault detection and diagnosis.

Contact-based vibration measurement techniques involving accelerometers are typically utilized for machine health monitoring and manufacturing end-of-line quality control. Acoustic signals, encompassing sound pressure and particle velocity, carry crucial information about the operational status of underlying equipment and can be utilized for detecting various machine faults. Utilizing one-dimensional Convolution Neural Networks (1D-CNN) based on deep learning for processing raw acoustic time signals has proven to be a valuable approach in detecting machinery faults, offering an effective alternative to using traditional accelerometer signals. However, the success of deep learning methods is heavily dependent on the quantity and availability of data for robust network training. When transitioning to new non-contact type sensor technology, manufacturers may face challenges due to insufficient data for training deep learning models. In such cases, leveraging existing historical accelerometer-based data becomes crucial. Transfer learning emerges as a promising solution, allowing deep learning models trained on a source domain (SD) to be applied to a separate but related target domain (TD). This paper hence introduces a domain adaptation methodology by implementing transfer learning, where the SD 1D-CNN network is trained on accelerometer signals, then the trained model weights are transferred to the TD 1D-CNN network that can process acoustic signals.

Blade fouling fault detection based on shaft orbit generative adversarial network

To address the challenges of accuracy and interpretability in mechanical fault detection models, this study proposes a shaft orbit generative adversarial network (SOGAN) and applies it to detect blade fouling faults. Variational autoencoder (VAE) is used as the foundational network architecture for extracting high-dimensional latent features from the shaft orbit images. Concurrently, the invariant moments of the shaft orbit images are extracted and embedded in a bypass within the generator, thereby enhancing the accuracy of fault detection. Two sets of real-world blade fouling fault data are collected and meticulously analyzed. The proposed SOGAN model demonstrates significant performance improvements, with average increases of 18.91%, 10.20%, and 26.79% in accuracy compared to the autoencoder, VAE, and GANomaly algorithms, respectively. The F1 scores for both the groups exceed 0.98. The data generated by the proposed SOGAN model exhibit a trend-wise correspondence with the finite element modeling data. In addition, the use of gradient information for the localization and visual analysis of anomalies dynamically tracks the spatial evolution of the rotor shaft orbit throughout its lifecycle. The data generation capability and interpretability of the proposed model can effectively support digital twin modeling and health management of rotating machinery.

Mechanical and electrical faults detection in induction motor across multiple sensors with CNN-LSTM deep learning model

Mechanical and electrical faults detection in induction motor across multiple sensors with CNN-LSTM deep learning model

An online detection method for the mechanical fault of circuit breakers of rural distribution lines based on continuous wavelet transform and vibration signal characteristics

Rural distribution lines are widely distributed and dispersed, involving numerous circuit breaker equipment. Detecting mechanical faults on each circuit breaker requires significant time and human resources. It can bring significant interference and power outage risks to the operation of the line. Therefore, an online detection method is studied for mechanical faults in rural distribution line circuit breakers. Continuous wavelet transform technology is used to extract the characteristics of circuit breaker vibration signals. This feature is used to locate the faulty section. The PNN neural network is introduced to identify fault feature samples and achieve online detection of mechanical faults. To test the application performance of this method, a comparative experiment is designed. The results verified that when using this method to extract the vibration signal of circuit breaker mechanical faults, the error is low, and the fault detection accuracy is high.

Gas-insulated switch-gear mechanical fault detection based on acoustic feature analysis using a multi-state pre-trained neural network

The acoustic-based approach is a prevalent way for non-contact fault diagnosis on gas-insulated switch-gear (GIS). GIS always works under different voltages causing great diversity in acoustic frequency. However, based on the frequency principle, neural networks always focus on a specific frequency, which challenges robust fault detection on GIS. This paper introduces a novel multi-stage training method to improve the robustness of fault detection on GIS. The proposed method consists of three components: a multi-channel based frequency regressor (MCBFR), an audio spectrogram transformer auto-encoder (AST-AE), and a feature interaction module (FIM). MCBFR and AST-AE are optimised to extract specific features from acoustics during the pre-training stage. The FIM fuses components extracted by MCBFR and AST when training the model that can indicate the final result. Also, we apply a multi-stage training strategy during the training stage to reduce the cost of potential model retraining. The efficacy of the proposed method was validated using experimental data from a real GIS, and it shows competitive performance in fault detection compared to existing methods.

Advancing Crack Detection Using Deep Learning Solutions for Automated Inspection of Metallic Surfaces

The deep Convolutional Neural Network (CNN) architecture used in this research study provides a proof of concept for crack detection on the metallic surface of a hex nut. The goal is to create an automated receiving inspection process to supplement human inspections conducted on-site. Conventional image processing techniques (IPTs) have been extensively used for mechanical infrastructure fault detection. These techniques focus on image modification to extract typical features, such as surface fractures in materials like steel and concrete. However, obstacles presented by a variety of real-world variables, such as changes in lighting and shadows, make it difficult to use IPTs. Our suggested vision-based method employs a deep learning CNN to overcome these difficulties, eliminating the need to explicitly compare fault features. CNNs are more resilient to shifting real-world situations than IPTs since they are naturally trained to identify characteristics in images. Following training on a dataset of 1081 images with dimensions of 256 x 256 pixels, the VGG16 CNN architecture achieved an impressive accuracy of around 94.17%. Additional CNN architectures, including ResNet, MobileNet, AlexNet, and LeNet-5, are employed to assess and compare fault detection accuracies in order to select the most appropriate architecture for the model. To evaluate the robustness and flexibility of the suggested method in various situations, we conducted tests with 206 images from an alternative structure that was not part of the training dataset. These images depicted a range of circumstances, such as intense light patches and tiny fissures. The outcomes showed that our proposed method outperforms current approaches, highlighting its usefulness in practical situations involving the identification of metallic defects.

A two-stage Duffing equation-based oscillator and stochastic resonance for mechanical fault diagnosis

Incipient fault-induced weak impulses will not be detected easily using the existing fault extraction methods. Stochastic resonance can flexibly use noises to enhance the signal-to-noise ratio, but it lacks the ability of anti-interference to obtain robustness and reliability fault detection performance. A two-stage method is presented to diagnose faults in mechanical components. The first is to judge the fault existence according to the characteristics of the phase space trajectory diagram of the Duffing oscillator. The second is to employ stochastic resonance method based on the Duffing equation to improve the signal-to-noise ratio of the raw signal, in which the two barrier parameters in the Duffing equation-based bistable system are carefully selected using the artificial bee colony algorithm. In the present two-stage method, the existence of faults and further the fault types in mechanical components are stepwise detected to make full usages of the advantages of Duffing oscillator and Duffing equation-based stochastic resonance method. Numerical simulations and two experimental cases verify the performance of the proposed method for mechanical components fault detection in a strong noise environment.

A roundtrip probability estimation method for mechanical equipment fault detection under imbalanced samples

Aiming at high misdetection of mechanical faults under imbalanced samples, a roundtrip probability-based method is proposed. By roundtrip mapping between latent variables and real fault data, biased estimation of the probability distribution of real fault data is obtained. Further, virtual fault data are sampled according to such distribution to increase sample amount. For recognition of real and virtual data, loss function based on binary cross-entropy is designed. For reconstruction between fault data and its roundtrip mapped results, objective function based on mean square error is designed. Thus, it preserves boundary data and avoids too many virtual data in central area. Meanwhile, a strategy for eliminating abnormal samples is designed to reduce boundary deviation. For supporting the advantage of roundtrip, in-depth reasons for misdetection are analyzed from empirical risk and structural risk. Experiments on 30 benchmark imbalanced test sets show that fault detection rate increases after amount enhancement. Additionally, it is verified on blade cracking and bearing fault detection. Results show that F1 score increases from 0.485 to 0.51 and 0.725 to 0.775 for such two cases.

Mechanical Fault Sound Source Localization Estimation in a Multisource Strong Reverberation Environment

Aiming at the sound source localization of mechanical faults in a strong reverberation scenario with multiple sound sources, this paper investigates a mechanical fault source localization method using the U-net deep convolutional neural network. The method utilizes the SRP-PHAT algorithm to calculate the response power spectra of the collected multichannel fault signals. Through the utilization of the U-net neural network, the response power spectra containing spurious peaks are transformed into “clean” estimated source distribution maps. By employing interpolation search, the estimated source distribution maps are processed to obtain location estimations for multiple fault sources. To validate the effectiveness of the proposed method, this paper constructs an experimental dataset using mechanical fault data from electromechanical equipment relays and conducts sound source localization experiments. The experimental results show that the U-net network under 0.2 s/0.5 s/0.7 s reverberation time can effectively eliminate spurious peak interference in the response power spectrum. As the signal-to-noise ratio decreases, it can still distinguish the sound sources with a distance of 0.2 m. In the context of multifault source localization, the method is capable of simultaneously locating the positions of four fault sources, with an average localization error of less than 0.02 m. The method in this paper effectively eliminates spurious peaks in the response power spectra under conditions of multisource strong reverberation. It accurately locates multiple mechanical fault sources, thereby significantly enhancing the efficiency of mechanical fault detection.

Gas-insulated switch-gear mechanical fault detection based on acoustic using feature fused neural network

The acoustic-based method is a prevalent way for non-contact fault diagnosis on gas-insulated switchgear. Gas-insulated switchgear always work under different voltages causing great diversity in acoustic frequency, which challenges robust fault detection. This paper proposed a novel feature-fused method to improve the robustness of fault detection on gas-insulated switchgear. The proposed method consists of four components: wave reduction module, spectrogram reduction module, fusion module and classifier. Wave reduction module extracts operating voltage information from acoustic emissions in the gas-insulated switchgear; spectrogram reduction module uses auto-encoder training schedule for feature extraction on spectrogram; fusion module fuses extracted features; classifier makes final classification. Also, we proposed an objective function for thoroughly utilizing spectrogram information. The efficacy of the proposed method was validated using experimental data from a real gas-insulated switchgear, and it shows competitive performance in fault detection compared to existing methods.

Advancing Fault Detection in Building Automation Systems through Deep Learning

This study proposes a deep learning model utilizing the BACnet (Building Automation and Control Network) protocol for the real-time detection of mechanical faults and security vulnerabilities in building automation systems. Integrating various machine learning algorithms and outlier detection techniques, this model is capable of monitoring and learning anomaly patterns in real-time. The primary aim of this paper is to enhance the reliability and efficiency of buildings and industrial facilities, offering solutions applicable across diverse industries such as manufacturing, energy management, and smart grids. Our findings reveal that the developed algorithm detects mechanical faults and security vulnerabilities with an accuracy of 96%, indicating its potential to significantly improve the safety and efficiency of building automation systems. However, the full validation of the algorithm’s performance in various conditions and environments remains a challenge, and future research will explore methodologies to address these issues and further enhance performance. This research is expected to play a vital role in numerous fields, including productivity improvement, data security, and the prevention of human casualties.

Research on the Application of Image Feature Extraction in Mechanical Structure Recognition and Fault Diagnosis

Abstract With the rapid development of modern industry and science and technology, in recent years the fault diagnosis method based on image processing has become a research hotspot in the field of mechanical fault diagnosis. In this paper, image characteristics are extracted from multiple aspects such as image texture, color, shape, etc. A grayscale symbiotic matrix image feature extraction method is proposed. On this basis, the algorithm for extracting gray symbiotic matrix time-frequency image features is designed. At the same time, the algorithm and parameters of mechanical structure identification are optimized to identify and diagnose mechanical faults. The results show that the grayscale symbiotic matrix time-frequency image feature extraction algorithm is able to accurately diagnose the wear-type faults, overwork-type faults, and short-circuit-type fault behavior of the mechanical equipment. All of them are able to obtain more than 80% accuracy, and all of them are able to reach 99.99% accurate detection of mechanical faults, which proves the effectiveness of the method of this research.

Deep learning-based mechanical fault detection and diagnosis of electric motors using directional characteristics of acoustic signals

Early identification of rotating machinery faults is crucial to avoid catastrophic fail- ures upon installation. Contact-based vibration acquisition approaches are traditionally used for the purpose of machine health monitoring and end-of-line quality control. In complex working conditions, it can be difficult to perform an accurate accelerometer based vibration test. Acoustic signals (sound pressure and particle velocity) also contain important information about the operating state of mechanical equipment and can be used to detect different faults. A deep learning approach, namely, one-dimensional convolutional neural networks (1D-CNNs) can directly process raw time signals, thereby eliminating the human dependence on fault feature extraction. An experimental research study is conducted to test the proposed 1D-CNN methodology on three different electric motor faults. The results from the study indicate that the fault detection performance from the acoustic-based measurement method is very effective and thus can be a good replacement to the conventional accelerometer-based methods for detection and diagnosis of mechanical faults in electric motors.

A Novel Mode Un-Mixing Approach in Variational Mode Decomposition for Fault Detection in Wound Rotor Induction Machines

Condition monitoring of induction machines (IMs) with the aim of increasing the machine’s lifetime, improving the efficiency and reducing the maintenance cost is necessary and inevitable. Among different types of methods presented for mechanical and electrical fault tracing in induction machines, stator current signature analysis has attracted great attention in recent decades. This popularity is mainly due to the non-invasive nature of this technique. A non-recursive method named variational mode decomposition (VMD) is used for the decomposition of any signal into several intrinsic mode functions (IMFs). This technique can be employed for detection of faulty components in a current signature. However, mode mixing of extracted IMFs makes the mechanical and electrical fault detection of IMs complicated, especially in the case where fault indices emerge close to the supply frequency. To achieve this, we rectify the signal of stator current prior to applying VMD. The main advantage of the presented approach is allowing the fault indices to be properly demodulated from the main frequency to avoid mode mixing phenomenon. The method shows that the dominant frequencies of the current signal can be isolated in each IMFs, appropriately. The proposed strategy is validated to detect the rotor asymmetric fault (RAF) in a wound rotor induction machine (WRIM), in both transient and steady-state conditions.