Machine Fault Research Articles

Milling Machine Fault Diagnosis Using Acoustic Emission and Hybrid Deep Learning with Feature Optimization

This paper presents a fault diagnosis technique for milling machines based on acoustic emission (AE) signals and a hybrid deep learning model optimized with a genetic algorithm. Mechanical failures in milling machines, particularly in critical components like cutting tools, gears, and bearings, account for a significant portion of operational breakdowns, leading to unplanned downtime and financial losses. To address this issue, the proposed method first acquires AE signals from the milling machine. AE signals, capturing the dynamic responses of machine components, are transformed into continuous wavelet transform (CWT) scalograms for further analysis. Gaussian filtering is applied to enhance the clarity of these scalograms, effectively reducing noise while maintaining essential features. A convolutional neural network (CNN) based on the VGG16 architecture is utilized for spatial feature extraction, followed by a bidirectional long short-term memory (BiLSTM) network to capture the temporal dependencies of the scalograms. The genetic algorithm (GA) is used to optimize feature selection and ensure the selection of the most relevant features to further improve the model’s performance. The optimized features are finally fed into a fully connected (FC) layer of the proposed hybrid model for fault classification. The proposed method achieves an accuracy of 99.6%, significantly outperforming traditional approaches. This method offers a highly accurate and efficient solution for fault detection in milling machines, allowing for more reliable predictive maintenance and operational efficiency in industrial settings.

Machine fault detection model based on MWOA-BiLSTM algorithm

This paper proposes the Modulated Whale Optimization Algorithm(MWOA), an innovative metaheuristic algorithm derived from the classic WOA and tailored for bionics-inspired optimization. MWOA tackles common optimization problems like local optima and premature convergence using two key methods: shrinking encircling and spiral position updates. In essence, it prevents algorithms from settling for suboptimal solutions too soon, encouraging exploration of a broader solution space before converging, by incorporating cauchy variation and a perturbation term, MWOA achieve optimization over a wide search space. After that, comparisons were conducted between MWOA and seven recently proposed metaheuristics, utilizing the CEC2005 benchmark functions to assess MWOA’s optimization performance. Moreover, the Wilcoxon rank sum test is used to verify the effectiveness of the proposed algorithm. Eventually, MWOA was juxtaposed with the BiLSTM classifier and six other meta-heuristics combined with the BiLSTM classifier. The aim was to affirm that MWOA-BiLSTM outperforms its counterparts, showcasing superior performance across crucial metrics such as accuracy, precision, recall, and F1-Score. The study results unequivocally demonstrate that MWOA showcases exceptional optimization capabilities, adeptly striking a harmonious balance between exploration and exploitation.

Machine Health Monitoring and Fault Diagnosis Techniques (Volume II)

This Special Issue highlights a diverse range of pioneering research dedicated to fault diagnosis, condition monitoring, and defect detection in various engineering systems [...]

INFLUENCIA DE UNA VIBRACIÓN SIMPLE EN EL PERFIL DE ONDULACIÓN DE PIEZAS TORNEADAS

The generation of the surface topography in machining is a complex process whereby the dynamics of the machine-tool and the kinematics of the cutting process are combined. The purpose of developing a surface topography simulation model in turning is to predict the combined effect of the tool geometry, process parameters, and relative tool-workpiece vibration. The simulations demonstrate that a single vibration frequency can generate multiple wavelengths on the workpiece profile. The correlation between machine-tool vibrations and surface topography is applied to accurately diagnose the machine defect that results in poor surface quality in a cylindrical turning process. Key words: surface topography, tool-workpiece vibration, waviness profile

Detection and classification of air gap eccentricity fault in Induction machine using artificial intelligence techniques

Detection and classification of air gap eccentricity fault in Induction machine using artificial intelligence techniques

Evaluative assessment of a five-phase and three-phase permanent magnet synchronous machine at varied loads and fault conditions

Multiphase machines are very essential for industrial applications that require high reliability of operation. In this paper, a comparative study of three-phase and five-phase inverter fed permanent magnet synchronous motors (PMSMs) was evaluated with respect to their performance characteristics under a healthy state and during transient disturbances such as varied load and double line to ground faults. To avert inherent high oscillations in speed and torque ripples during fault condition, the machine load was significantly reduced to 1/4th of the full load and a post fault current limiting series dynamic braking resistance (SDBR) with a bypassed switch was introduced to enhance the machine fault tolerant level and improve its operational performance. Spectral analyses were carried out to determine the magnitude of harmonic distortion during these conditions. The simulation results show that the five-phase PMSM achieved a reduced oscillatory transient and a faster settling time of speed and torque under a varied load. It also exhibited good harmonic profiles as indicated in the respective % THD values when compared to the three phase PMSM which is prone to high harmonic overheat. However, when subjected to a double line to ground fault, their various %THD values in speed and torque increased with five-phase PMSM still having a reduced %THD values over the three-phase PMSM. Therefore, for a higher fault tolerant capability, greater efficiency with proven reliability, a five-phase PMSM with a fault current limiting series dynamic braking resistance is a better substitute when compared with the three-phase PMSM in industrial applications where safety and loss minimization is a top priority. All simulation processes in this paper were achieved in MATLAB 2015.

A noise-enhanced machine fault diagnosis method with multi-channel information fusion

ABSTRACT Condition health monitoring and fault diagnosis is able to safeguard against potential threats to machines. Nevertheless, the acquired signals by using a plenty of sensors are often accompanied by noise and meanwhile the useful information contained in the signals is not both complete and reliable, thereby together reducing the accuracy and stability of the fault diagnosis. Therefore, this paper proposes a noise-enhanced intelligent fault diagnosis method with multi-channel information fusion. Here, it would inject the varying levels of Gaussian noise into multi-channel input data as well as intelligent diagnostic models, with a view to elucidating the benefits of noise. Furthermore, the proposed method is validated through three experiments. The experimental results demonstrate that the diagnostic accuracy of the hydraulic motor and the two different bearings reaches 99.85%, 99.89%, and 99.85% by using the proposed method, respectively, which are increased by 2.50%, 4.09%, and 2.50%, respectively, compared with one without the injection of noise. In addition, by comparing the diagnostic accuracy of ones with single-channel and multi-channel information fusion under the optimal noise level in both cases, it is found that one with multi-channel information fusion shows an average of 3.20% increase than the single-channel one.

Bearing fault detection in adjustable speed drives via self-organized operational neural networks

AbstractAdjustable speed drives (ASDs) are widely used in industry for controlling electric motors in applications such as rolling mills, compressors, fans, and pumps. Condition monitoring of ASD-fed induction machines is very critical for preventing failures. Motor current signature analysis offers a non-invasive approach to assess motor condition. Application of conventional convolutional neural networks provides good results in detecting and classifying fault types for utility line-fed motors, but the accuracy drops considerably in the case of ASD-fed motors. This work introduces the use of self-organized operational neural networks to enhance the accuracy of detecting and classifying bearing faults in ASD-fed induction machines. Our approach leverages the nonlinear neurons and self-organizing capabilities of self-organized operational neural networks to better handle the non-stationary nature of ASD operations, providing more reliable fault detection and classification with minimal preprocessing and low complexity, using raw motor current data.

Comparative analysis of response surface methodology and adaptive neuro-fuzzy inference system for predictive fault detection and optimization in beverage industry

Maintenance is crucial for ensuring equipment reliability and minimizing downtime while managing associated costs. This study investigates a data-driven approach to predicting machine faults using Response Surface Methodology (RSM) and Adaptive Neuro-Fuzzy Inference System (ANFIS). RSM was employed to develop a mathematical model to analyze how operational parameters such as pressure, voltage, current, vibration, and temperature affect fault occurrence. Data were collected at three levels for each parameter using a central composite design. The model identified that faults peaked at a pressure of 28.38 N/m2, an operating voltage of 431.77 V, current consumption of 12.54 A, machine vibration of 47.17 Hz, and temperature of 25°C, with a maximum of 25 faults observed. Conversely, the lowest fault detection occurred at a pressure of 29.42 N/m2, an operating voltage of 441.04 V, current consumption of 12.04 A, machine vibration of 49.46 Hz, and temperature of 46.5°C. A strong correlation was found between these parameters and machine faults, with the model achieving high accuracy (R2 = 98.22%) and statistical significance (p-value <0.05), demonstrating its reliability in predicting faults. The study also compared RSM with ANFIS for fault detection and process optimization in the beverage industry. While RSM effectively optimized parameter relationships, ANFIS, with its adaptive learning capabilities, provided superior fault prediction accuracy. This comparative analysis highlighted the strengths of both methods and suggested that integrating them could enhance predictive maintenance strategies. The findings offer valuable insights for industry practitioners, recommending a combined approach to improve fault detection, optimize production processes, and enhance operational efficiency.

Fault diagnosis method of switch machine based on adaptive neural fuzzy network

Aiming at the problem of a large number of switch machines, harsh working environment and high frequency of equipment failures caused by many factors, in order to accurately diagnose railway switch machine faults, a switch machine fault diagnosis method based on adaptive neural fuzzy network (ANFIS) optimized by dynamic weight particle swarm (DPSO) algorithm is proposed by analyzing the vibration signals generated during the operation of the switch machine. Firstly, the working vibration signal is decomposed into several intrinsic mode functions (IMFs) and selected by using the ensemble empirical mode decomposition (EEMD) algorithm; then, the feature values of IMFs are extracted by using the improved time domain multiscale scatter extraction (ITMDE) algorithm, and then input into the optimized ANFIS model to learn and realize fault diagnosis; finally, the method is compared and analyzed with various diagnostic model algorithms and learning algorithms. The experimental results show that the proposed method can effectively diagnose switch machine faults, which has certain reference significance for intelligent diagnosis of switch machine faults and related research in the future.

A smart WSNs node with sensor computing and unsupervised One-Class SVM classifier for machine fault detection

This paper proposed a novel machine fault detection method based on a smart WSNs node with sensor computing and unsupervised learning. Firstly, sensor computing mode, which achieves machine fault detection on the WSNs node, has been employed to address the limitations of raw data transmission mode, such as huge payload transmission data and node energy consumption. Secondly, a fault classifier based on unsupervised one-class support vector machine (OC-SVM) is designed to overcome the drawbacks of supervised learning, like the requirement of myriad labeled samples for model training. Finally, a smart WSNs node with sensor computing and an unsupervised OC-SVM classifier is developed and fabricated as test beds. A set of experiments has been conducted to verify the proposed method and smart node. The results show that they can reduce 99% of payload transmission data and about 5% of node energy consumption while maintaining acceptable detection accuracy (above 99.2%).

The Use of eXplainable Artificial Intelligence and Machine Learning Operation Principles to Support the Continuous Development of Machine Learning-Based Solutions in Fault Detection and Identification

Machine learning (ML) revolutionized traditional machine fault detection and identification (FDI), as complex-structured models with well-designed unsupervised learning strategies can detect abnormal patterns from abundant data, which significantly reduces the total cost of ownership. However, their opaqueness raised human concern and intrigued the eXplainable artificial intelligence (XAI) concept. Furthermore, the development of ML-based FDI models can be improved fundamentally with machine learning operations (MLOps) guidelines, enhancing reproducibility and operational quality. This study proposes a framework for the continuous development of ML-based FDI solutions, which contains a general structure to simultaneously visualize and check the performance of the ML model while directing the resource-efficient development process. A use case is conducted on sensor data of a hydraulic system with a simple long short-term memory (LSTM) network. Proposed XAI principles and tools supported the model engineering and monitoring, while additional system optimization can be made regarding input data preparation, feature selection, and model usage. Suggested MLOps principles help developers create a minimum viable solution and involve it in a continuous improvement loop. The promising result motivates further adoption of XAI and MLOps while endorsing the generalization of modern ML-based FDI applications with the HITL concept.

Dual Weighted-Class Adversarial Network for Rotary Machine Fault Diagnosis Using Multisource Domain with Class-Inconsistent Data

Dual Weighted-Class Adversarial Network for Rotary Machine Fault Diagnosis Using Multisource Domain with Class-Inconsistent Data

Single- and Multiswitch Fault-Tolerant Inverter Topology With Preserved Output Power and Extreme Learning Machine Fault Detector

Single- and Multiswitch Fault-Tolerant Inverter Topology With Preserved Output Power and Extreme Learning Machine Fault Detector

Enhancing induction machine fault detection through machine learning: Time and frequency analysis of vibration signals

The integration of machine learning algorithms into fault diagnosis is regarded as an advanced and effective method for detecting electrical system faults. Vibration signals are identified as valuable and easily accessible data for fault identification in electrical machines. In this study, experiments were conducted to assemble a dataset consisting of 525 × 3 instances, each containing 200 three-axis vibration signal measurements. These measurements were obtained from a laboratory test bench equipped with a customized winding three-phase induction machine. Instead of directly analyzing the vibration signals, a feature extraction approach was employed, calculating a comprehensive set of statistical, harmonic, and impulsive features from the time domain (e.g., ShapeFactor, SINAD, ClearanceFactor, ImpulseFactor, CrestFactor, Kurtosis, Skewness, THD, Std, RMS, Mean, PeakValue, SNR), along with spectral features from the frequency domain (e.g., Peak Frequencies, Amplitudes, BandPower). To improve model efficiency, Analysis of Variance (ANOVA) was applied to select only the most significant features, with F-statistics used to rank feature importance. Features with higher F-statistics were prioritized for their ability to explain more variance in motor fault classification. This selective approach reduced model complexity, helping to minimize overfitting and focus on features that had a substantial impact on predictive accuracy. By concentrating on these high-impact features, a balance between simplicity and performance was achieved. These selected features were then used to train five machine learning classifiers: Ensemble (Bagged Trees), Quadratic Support Vector Machine, Weighted K-Nearest Neighbors, Efficient Logistic Regression, and Neural Networks. The performance of these classifiers was evaluated using various metrics, with validation accuracy rates ranging from 78.3% to 98.8%. A comparative study with similar works in the literature was conducted, demonstrating that high performances were obtained with the proposed approach while maintaining computational efficiency.

Anti-forgetting source-free domain adaptation method for machine fault diagnosis

Unsupervised domain adaptation methods have made significant progress in the field of machine fault diagnosis. However, these methods generally assume the accessibility of source domain data during the cross-domain transfer phase. In practice, this assumption is often impractical due to data privacy requirements and the burden of data transmission and storage. Additionally, a key challenge lies in preventing the forgetting of source domain knowledge while performing cross-domain diagnosis in a source-free scenario. To address these issues, this paper proposes an anti-forgetting source-free domain adaptation method for machine fault diagnosis. Specifically, a prototype-based pseudo-label generation strategy, combined with a nearest-neighbor constraint, is employed to deeply explore diagnosis information in the unlabeled target domain data. Then, a fast nuclear-norm maximization constraint is introduced to reduce the density of target domain samples near the classification boundary, thereby decreasing the probability of misdiagnosis. Furthermore, a weighted Fisher regularization is designed to retain the diagnosis information of healthy states inherent in the source domain, thus mitigating information forgetting. Finally, comprehensive experiments are conducted to validate the superiority of our method in source-free cross-domain diagnosis from multiple perspectives, while also demonstrating its anti-forgetting properties.

Domain generalization for machine compound fault diagnosis by Domain-Relevant Joint Distribution Alignment

In machine fault diagnosis, domain generalization methods have gained significant attention due to their advantage in non-requirement of priori target domain distribution. However, they pose great challenges in domain-relevant feature learning and incurs inferior unseen-domain classification when large domain divergence exists. To address this issuse, we propose a novel distribution alignment strategy named DRJDA (Domain-Relevant Joint Distribution Alignment) that matches the domain-joint distribution and domain-relevant distribution for domain generalization fault diagnosis. Specifically, the α-PE divergence is employed to minimize the distribution discrepancy, which is demonstrated to be explicitly derived as the maximum value of a quadratic function. Additionally, a parameter-free plug-and-play data augmentation module that performs feature-level instance mixture and style transfer to increase the generalization ability. Finally, data from the China Light-duty Vehicle Test Cycle (CLTC) tests are used as case studies, and the experiments carried out across 14 different domains prove the proficiency of the proposed DRJDA in learning domain-invariant feature when significant domain divergence exists, indicating its remarkable potential in compound fault diagnosis for industrial machinery.

Optimal weighted multi-scale entropy-energy ratio feature for machine fault diagnosis

Identifying the sensitive characteristics of mechanical equipment components is crucial for effective fault diagnosis. However, focusing solely on a specific feature at a single time scale fails to comprehensively capture the device’s operational state. Inspired by the concept of multi-scale analysis and recognizing the complementary strengths of permutation entropy (PE) and root mean square (RMS) in fault characterization, we propose a novel feature called the Optimal Weighted Multi-Scale Entropy-Energy Ratio (OWMEER). This feature aims to enhance fault characterization by optimally combining the strengths of PE and RMS, thereby providing a more comprehensive assessment of the device’s condition. The effectiveness and superiority of OWMEER in fault characterization have been validated through experimental data, including both public and self-test datasets, when combined with the commonly used pattern recognition methods such as random forest (RF) and support vector machine (SVM). The results demonstrate that using OWMEER as a fault feature not only yields better results than using the original features RMS and PE, but also maintains strong diagnostic performance across different classifiers and datasets.

Multi-sensor temporal-spatial graph network fusion empirical mode decomposition convolution for machine fault diagnosis

Multi-sensor time-series data at different locations contains not only temporal correlation information but also spatial correlation information which is treasure for machine fault diagnosis. Existing graph construction methods mainly apply different data analysis methods to connect nodes and edges. Few works, however, consider the location of the sensor itself and temporal correlation information of multi-sensor time-series data. To mine the relationship between spatial information and temporal information, the multi-sensor temporal-spatial graph is constructed in this paper. Hereinto, the different data points of multi-sensor are severed as different nodes which represents the spatial feature information. The temporal information is contained between different nodes of the same sensor. Moreover, an empirical mode decomposition graph convolution network (EGCN) is proposed to extract the feature. Specifically, the traditional graph convolution operator is changed to empirical mode decomposition which can decompose the input features into multiple intrinsic modal features to achieve adaptive feature extraction and improve the representation capability of the network. Finally, the different fault types can be classified by fully connected layers. Experiments from different test rigs demonstrate that the proposed method achieves a diagnostic accuracy exceeding 99 % under limited fault samples.

Rainforest: A three-stage distribution adaptation framework for unsupervised time series domain adaptation

Solving the unsupervised domain adaptation (UDA) task in time series is of great significance for practical applications, such as human activity recognition and machine fault diagnosis. Compared to UDA for computer vision, UDA in time series is more challenging due to the dynamics of time series data and the complex dependencies among different time steps. Existing UDA methods for time series fail to adequately capture the temporal dependencies, limiting their ability to learn domain-invariant temporal patterns. Furthermore, most UDA methods only focus on distribution adaptation on the backbone network without considering how the classifier adapts to the data distribution of the target domain. In this paper, we propose Rainforest, a three-stage UDA framework for time series. We first pre-train the backbone network through a self-supervised method called bidirectional autoregression, so that the model can comprehensively learn the temporal dependencies in time series. Next, we propose a novel meta-learning-based distribution adaptation method to achieve the joint alignment of the global and local distributions while encouraging the model to adaptively reduce the temporal dynamic differences among different domains. Finally, we design a pseudo-label-guided fine-tuning strategy to help the classifier estimate the data distribution of the target domain more accurately. Extensive experiments on four real-world time series datasets show that our Rainforest outperforms state-of-the-art methods, with an average improvement of 2.19% in accuracy and 2.41% in MF1-score.