Fault Classification Research Articles

CDTFAFN: A novel coarse-to-fine dual-scale time-frequency attention fusion network for machinery vibro-acoustic fault diagnosis

When the machinery device operates abnormally, it is not sufficient for fault detection only via extracting fault features from a single sensor due to the latent fault information may be scattered across multiple sensors. Multi-sensory fusion techniques with deep learning framework have attracted increasing attention from researchers due to the exploiting and integration of fault information between multiple sensors. Nevertheless, there are two remaining shortcomings in most existing multi-sensory fusion technologies. (1) Most existing fusion methods merely concentrate on conducting multi-sensory information fusion from time-domain or frequency-domain to achieve fault diagnosis, which are often unsatisfactory in the face of strong noise environments. (2) The collaborative fusion between several vibration sensors is generally considered in the past works, whereas the complementary information fusion between multi-sensory vibro-acoustic heterogeneous data are rarely studied. To address these deficiencies, this paper proposes a novel coarse-to-fine dual-scale time-frequency attention fusion network (CDTFAFN) for machinery fault diagnosis, which not only adequately considers the complementary information fusion of vibro-acoustic signal, but also has robust feature learning capabilities in a noisy scenario. Firstly, the signal-to-image encoding unit (SIEU) containing the improved constant-Q non-stationary Gabor transform (ICQ-NSGT) is introduced to convert the collected raw vibro-acoustic heterogeneous signal into time-frequency representation (TFR) and achieve the coarse-grained feature fusion. Secondly, the time-frequency attention feature fusion unit (TFA-FFU) is designed to concurrently learn the fine-grained features at two scales from the low-level fused features which are meaningful for fault diagnosis. Finally, the coarse-to-fine features are sequentially concatenated and fed into softmax classifier to preferably promote the network learning performance and automatically implement fault classification. The performance of the proposed approach is validated against those state-of-the-art results on two groups of multi-sensory vibro-acoustic data in different experimental platforms. Experiment results show that the proposed method with the diagnosis accuracy of 99 % above outperforms other several representative fusion technologies (i.e., 2MNet, MFF-GBFD, MSCNN-BiLSTM, MFAN-VAF, 1D-CNN-VAF, MI-CNN-TFT and TFFN-VAF) in the raw noise-free addition scenario. Moreover, the average testing accuracy of the proposed method can still reach 97 % above in the noisy scenarios with Gaussian white noises, which shows its competitive superiority and strong robustness against noises in machinery fault diagnosis. According to the five ensemble macro-average performance evaluation metrics (i.e., accuracy, precision, sensitivity, specificity and F1-score) and the receiver operator characteristic (ROC) analysis, our findings also emphasize the superiority of applying our method for machinery fault diagnosis under the colored noises compared with other fusion technologies (i.e., 2MNet, MFF-GBFD, MSCNN-BiLSTM, MFAN-VAF, 1D-CNN-VAF, MI-CNN-TFT and TFFN-VAF) reported in this paper.

Avionics Module Fault Diagnosis Algorithm Based on Hybrid Attention Adaptive Multi-Scale Temporal Convolution Network.

Since the reliability of the avionics module is crucial for aircraft safety, the fault diagnosis and health management of this module are particularly significant. While deep learning-based prognostics and health management (PHM) methods exhibit highly accurate fault diagnosis, they have disadvantages such as inefficient data feature extraction and insufficient generalization capability, as well as a lack of avionics module fault data. Consequently, this study first employs fault injection to simulate various fault types of the avionics module and performs data enhancement to construct the P2020 communications processor fault dataset. Subsequently, a multichannel fault diagnosis method, the Hybrid Attention Adaptive Multi-scale Temporal Convolution Network (HAAMTCN) for the integrated functional circuit module of the avionics module, is proposed, which adaptively constructs the optimal size of the convolutional kernel to efficiently extract features of avionics module fault signals with large information entropy. Further, the combined use of the Interaction Channel Attention (ICA) module and the Hierarchical Block Temporal Attention (HBTA) module results in the HAAMTCN to pay more attention to the critical information in the channel dimension and time step dimension. The experimental results show that the HAAMTCN achieves an accuracy of 99.64% in the avionics module fault classification task which proves our method achieves better performance in comparison with existing methods.

An innovative transformer neural network for fault detection and classification for photovoltaic modules

Solar energy from photovoltaic systems (PV) ranks as the third greatest renewable electricity generation resource, expanding quickly through the years as it is free from environmental pollution and has cheap installation costs. Effective performance at high working rates is contingent on the early failure detection of PV modules. This study introduces an innovative deep learning model utilizing a Vision Transformer (ViT) artificial neural network (ANN) for the automatic detection of faults in infrared thermography (IR) images of PV modules. Our approach aims to enhance the accuracy of PV fault detection and classification compared to existing deep learning methods. The proposed framework encompasses three primary stages: (1) image preprocessing, which includes the application of the unsharp mask to sharpen the image’s edges or high-frequency components; (2) data augmentation techniques designed to overcome the problem of unbalanced classes that affect the training process, resulting in learning specific majority classes better than others; and (3) implementing a Vision Transformer deep learning model for its precision in digital image analysis. We evaluated the framework using the public Infrared Solar Modules dataset. The performance was quantitatively assessed using several metrics: accuracy, recall, precision, and F1 score. The dataset is classified into eleven different PV anomalies and another class of no-anomaly PV modules. The results show that our proposed approach has 98.23% accuracy for classifying the dataset into two classes, one for the PV anomaly and the other for the no-anomaly. It also has 96.19% accuracy for classifying eleven PV failures and 95.55% for twelve classes, including the no-anomaly class with the eleven types of anomalies. The experimental results underscore the potential of our model for earlier and more precise detection of PV faults. Furthermore, comparative analysis revealed the superior performance of the proposed approach over other deep learning methods.

A distinguished deep learning method for gear fault classification using time–frequency representation

Fault diagnosis of gearboxes has attracted increasing interest in recent decades due to their ubiquity and importance in the industry. Modern research trends focus on developing a diagnosis system that works automatically with the application of artificial intelligence. These previous studies have used the Deep Learning (DL) network without adequately addressing noise of the input data, requiring more data to achieve effective training. Thus, this work proposes a novel Transfer Learning method using the time–frequency representation of gear vibration signals, which enables more accurate classification in complex working conditions and reduces necessary input data to train. Using fine-tuning techniques proposed in this paper requires only a limited data set while ensuring acceptable classification results. An experiment test rig within different gear faults and load conditions was set up to evaluate the algorithm’s effectiveness.

A holistic semi-supervised method for imbalanced fault diagnosis of rotational machinery with out-of-distribution samples

Fault diagnosis plays a critical role in ensuring the reliability and safety of industrial systems. Despite the success of semi-supervised learning in fault diagnosis, challenges persist in dealing with imbalanced datasets and out-of-distribution (OOD) samples, particularly in industrial settings where fault incidents are rare. The rarity of fault incidents in industrial contexts leads to dataset imbalances, while changes in conditions may introduce OOD samples. To address these challenges, this study proposes a novel semi-supervised fault diagnosis method that simultaneously considers the imbalanced distribution of fault categories and OOD samples. Firstly, the semi-supervised framework has been presented, which combines pseudo-labeling and consistency regularization techniques. Then, the self-adaptive threshold has been devised to balance confidence levels among fault classes using dataset-specific and class-specific thresholds, thereby enhancing the model's robustness in real-world scenarios. Additionally, the OOD detection strategy based on contrastive learning has been proposed, wherein predictions from two different views of each sample estimate its “likelihood” of belonging to in-distribution (ID) or OOD categories. This strategy improves system safety by alerting operators to potential anomalies. Comprehensive experimental validations and comparisons were conducted on two rotational machinery fault datasets, demonstrating that the proposed method achieves superior performance compared to the alternative methods and is applicable for practical application.

Combining Lean Six Sigma and agile approach to optimize order management: action research in a Brazilian company

Purpose This paper aims to assess the combined application of Lean Six Sigma and agile approach for optimizing operational processes of order management in the seed industry. Design/methodology/approach This study is based on an action research case conducted in a multinational Brazilian Seeds Business enterprise. This paper reports on the application of the Lean Six Sigma define-measure-analyze-improve-control (DMAIC), using the steps of DMAIC cycle as a sprint of agile approach. The methodology involves outlining an operational process through sequential activities, each associated with a cycle time, equivalent number of full-time employee and number of orders. Performance metrics for the order management process include continuous monitoring of these activities, using monitoring systems, management software and manual records to collect data. Findings The findings reveal significant improvements in critical-to-quality measures related to customer care, planning and logistics. The implementation of the DMAIC methodology and agile approach resulted in tangible enhancements in cycle time, defects per opportunities and overall process efficiency. The results allow the classification of defects, the identification of their causes and, consequently, the presentation of a control plan to mitigate these problems. Furthermore, the study identifies key causes of operational issues and proposes a prioritized action plan. Research limitations/implications The limitation of this research is its restriction to a single case. The external validity of the results and generalizability to other organizational contexts may be compromised due to the lack of case diversity. The fact that the research focuses on a single company, even if it is a large multinational company, may limit the applicability of the findings to different sectors, sizes and organizational structures, which may be an opportunity for future research. Practical implications The findings suggest that the integrated approach of DMAIC and agile methodology contributes to a culture of continuous improvement and operational efficiency. The systematic collection and analysis of data enhance evidence-based decision-making, providing a robust foundation for strategic and operational choices. Moreover, the successful integration of methodologies presents a comprehensive framework applicable to diverse organizational challenges. Originality/value The paper applies action research to understand and address operational challenges, emphasizing practical solutions. The integration of DMAIC and agile enhances the depth of process analysis, enabling the identification, implementation and control of improvements. This study offers a significant contribution both to practitioners, providing practical implications, and to academics, enriching the Lean Six Sigma and agile body of knowledge.

A GA based SVM-Bayesian technique and its application in process monitoring for mixed distributed data

Traditional data-driven fault diagnosis methods, such as principal component analysis (PCA) and independent component analysis (ICA), have significantly improved condition monitoring and fault diagnosis of industrial process by analyzing process data. However, their accuracy is limited due to the assumption that the data follows Gaussian or non-Gaussian distribution, respectively. In reality, process data is often a mixture of both Gaussian and non-Gaussian distributions, leading to reduced accuracy of the training model and fault diagnosis results. To address this issue, a genetic algorithm-based SVM-Bayesian (GSB) scheme is proposed in this paper for feature combination and model integration. The scheme first employs ICA and PCA to extract the independent/principal components of the original data, and then constructs the corresponding fault features for SVM training to obtain basic models. The extraction of fault features are optimized using genetic algorithms based on defined accuracy and diversity functions. During online monitoring, the final diagnosis result is obtained by combining the results of the basic models through Bayesian inference. The effectiveness of the proposed scheme is evaluated using a numerical example and a case study of the Tennessee Eastman process. The results show that the accuracy of fault classification is improved by about 5% compared with traditional methods.

Fault classification of photovoltaic module infrared images based on transfer learning and interpretable convolutional neural network

In the operation of photovoltaic (PV) power plants, infrared cameras are commonly utilized for monitoring the operational status of PV modules. This study focuses on the performance improvement and complexity reduction of convolutional neural network (CNN) when used for fault classification based on infrared images of PV module. By implementing the transfer learning strategy on some famous CNN models, it is observed that the number of convolutional layers has weak impact on the classification results. Therefore, a transfer-learning-based depth reduction approach for CNN models (TLDR-CNN approach) is proposed, and the VGG16 model is employed for verification. Then, a multi-scale feature extraction module (MSFE module) is developed for efficiently replacing the convolutional layers to reduce model complexity and improve classification performance, and several representative model configurations are employed for convolutional layer replacement. Experimental results demonstrate that the application of the developed MSFE module significantly outperforms the baseline model on both classification performance and model complexity. Specifically, the modified model with a reduction of 5 convolutional layers exhibits notable improvements over the training results, with an accuracy increase of 0.90%, precision increase of 0.98%, F1 score increase of 6.89%, and a Matthews correlation coefficient increase of 1.01%. Finally, the interpretability of the above outperformance is also provided by using the Grad-CAM method. The generated CAM images show that the modified model concentrates its weights more on the regions crucial for the model to learn, so the features can be extracted more efficiently.

A Novel Method for Rolling Bearing Fault Diagnosis Based on Gramian Angular Field and CNN-ViT.

Fault diagnosis is one of the important applications of edge computing in the Industrial Internet of Things (IIoT). To address the issue that traditional fault diagnosis methods often struggle to effectively extract fault features, this paper proposes a novel rolling bearing fault diagnosis method that integrates Gramian Angular Field (GAF), Convolutional Neural Network (CNN), and Vision Transformer (ViT). First, GAF is used to convert one-dimensional vibration signals from sensors into two-dimensional images, effectively retaining the fault features of the vibration signal. Then, the CNN branch is used to extract the local features of the image, which are combined with the global features extracted by the ViT branch to diagnose the bearing fault. The effectiveness of this method is validated with two datasets. Experimental results show that the proposed method achieves average accuracies of 99.79% and 99.63% on the CWRU and XJTU-SY rolling bearing fault datasets, respectively. Compared with several widely used fault diagnosis methods, the proposed method achieves higher accuracy for different fault classifications, providing reliable technical support for performing complex fault diagnosis on edge devices.

Machine Learning Based Fault Classification in Pilot Plant Batch Reactor: Using Support Vector Machine.

Identifying and diagnosing faults is a critical task in process industries to maintain effective monitoring of process and plant safety. Minimizing process downtime is critical for enhancing the quality of the product and minimizing production costs. Real-time categorization of issues across several levels is essential for the monitoring of processes. However, there are still notable obstacles, that must be addressed, such as the existence of robust correlations, the complexity of the data, and the lack of linearity. This study introduces a novel fault identification technique in batch reactor experimental trials that employs multikernel support vector machines (SVMs) to categorize internal and external issues, specifically reactor temperature, coolant temperature, and jacket temperature. The data set was obtained from empirical research. The classification has been conducted using a multikernel SVM. This article identified that the nonlinear classifier using the radial bias function results in an accuracy that is at least 22.08% superior to other methods.

Efficient Defect Classification Using Few-Shot Image Generation and Self-Attention Fused Convolution Features

Although deep learning has been proven to significantly outperform most traditional methods in the classification of large-scale balanced image datasets, collecting enough samples for defect classification is extremely time-consuming and costly. In this paper, we propose a lightweight defect classification method based on few-shot image generation and self-attention fused convolution features. We constructed a 4-class dataset using welding seam images collected from a solar cell module packaging production line. To address the issue of limited defect samples, especially for classes with less than 10 images, we implemented two strategies. Geometric enhancement techniques were first used to extend the defective images. Secondly, multi-scale feature fusion Generative Adversarial Networks (GANs) were utilized to further enhance the dataset. We then performed the feature-level fusion of convolution neural networks and self-attention networks, achieving a classification accuracy of 98.19%. Our experimental results demonstrate that the proposed model performs well in small sample defect classification tasks. And, it can be effectively applied to product quality inspection tasks in industrial production lines.

An Enhanced Modeling Framework for Bearing Fault Simulation and Machine Learning-based Identification with Bayesian-optimized Hyperparameter Tuning

Abstract Condition monitoring of rotating machinery offers a salient tool for predictive maintenance on rolling elements, subjected to continuous working loads, wear, fatigue, and degradation. In this study, an enhanced computational tool for bearing fault simulation and feature extraction is proposed. A subsequent identification scheme is realized, through Bayesian optimization of hyperparameters, including support vector classifier (SVC), gradient boosting (GBoost), random forest (RF), extreme gradient boosting (XBoost), light gradient boosting machine (LightGBM), and categorical boosting (CatBoost). The proposed hyperparameter optimization technique stands out from traditional methods by offering a more informed and efficient pathway to optimal performance in predictive maintenance. Utilizing Bayesian optimization for hyperparameter tuning of machine learning models, which has not been extensively explored in this field, our approach demonstrates significant advancements. Typical instances of bearing faults, like inner race, outer race, and ball faults are considered. The analysis relies on extraction of statistical and engineering features form collected response signals, including kurtosis, root mean square, peak, and ridge factor. Highly influential variables are highlighted based on feature selection and importance algorithms, allowing bearing fault classification. We demonstrate that SVC and LightGBM produce over 97% of accuracy at low computational cost. This approach constitutes a scalable and robust framework for similar applications in engineering diagnostics.

An oversampling method based on Gaussian Mixture Model for multi-bolt looseness monitoring using Lamb waves`

The imbalance in the number of healthy and faulty samples poses a significant hindrance to the successful implementation of multi-bolt looseness monitoring and fault classification in engineering applications. The Synthetic Minority Oversampling Technique (SMOTE) is widely used in addressing data imbalance issues. However, traditional SMOTE methods and their improvements have not taken into account the problem of sensor network signals with multiple paths. In this paper, an improved oversampling technique, namely Gaussian Mixture Model (GMM)-SMOTE, is introduced. The proposed SMOTE method is based on GMM and aims to solve the sample imbalance problem under different bolt states and different sensor paths in sensor networks. The GMM is utilized to cluster the minority classes in multi-bolt looseness data. The assignment of weights to different clusters is based on the clustering density function, which is subsequently followed by oversampling. The KL distance is utilized to screen the SMOTE sample data, which improves the quality of the data by achieving inter-class balance and intra-class balance. To verify the effectiveness of the method, a multi-bolt looseness monitoring procedure is implemented. The experimental results demonstrate that the proposed method can improve the accuracy of diagnosing early-stage bolt looseness.

An adaptive detection approach for multi-scale defects on wind turbine blade surface

Multi-scale defects will inevitably appear in wind turbine blade defect detection within practical detection applications. An adaptive multi-scale detection approach is proposed to accurately classify and locate defects on the wind turbine blade surface. The proposed approach includes two main detection procedures: rough detection and precise detection. In the rough detection, the multi-level features extraction module with an adaptive bounding box proposal module is used to depict multi-scale defect regions and train a binary classifier to distinguish defects from non-defects. At the precise detection stage, three defect categories and four coordinates representing defect locations are obtained based on a multi-class defect classifier and regression of rough location boxes. The proposed method is evaluated on a real wind turbine blade surface defect dataset collected in a commercial wind farm and annotated manually. Results show that (1) the proposed model can detect the class of the blade multi-scale defects and outperforms other schemes with 96.89% mAP in the same model training epochs, (2) the positioning performance analysis of the model for multi-scale defects is conducted to validate the accuracy of the proposed model for multi-scale defect location.

Time-Series Data Augmentation for Improving Multi-Class Classification Performance

This paper proposes a new approach to classify and evaluate defects in concrete structures automatically. To overcome the limitations of defect detection methods that traditionally relied on expert visual observation, the reflection signal of electromagnetic pulses is extracted as time-series data and used to analyze the propagation characteristics of each defect. This study uses deep learning models to analyze these time-series data and classify defects. Since anomaly detection data has more normal data than anomaly data, data augmentation methods such as Time Warping, Noise Injection, Smoothing, Trend Shifting, etc., were applied to solve the problem of data imbalance and overfitting. Among them, Noise Injection showed the best performance. The generalization performance of the proposed method was evaluated through performance evaluation using LSTM, GRU, and TCN models, and LSTM models showed the highest performance. The study results show that the proposed method effectively classifies defect types in concrete structures and can solve the limitations of existing methods by automatic classification through deep learning models. In addition, it was confirmed that the model's performance could be improved by improving the amount and diversity of data by selecting and applying appropriate data augmentation methods. The contribution of the research is to present a new approach that automates the defect detection and classification task of concrete structures and provides high accuracy and efficiency.

A novel fault diagnosis method for Bayesian networks fusing models and data

Data-driven methods are the mainstream methods applied in current fault diagnosis research; however, in natural mechanical systems, fault samples are difficult or even impossible to obtain, and physical model-based methods cannot easily model the faults of complex systems. To address the respective limitations of data-driven and model diagnosis methods in fault diagnosis, in this paper, a Bayesian network fault diagnosis method based on a joint model and data modelling is proposed. Conditional Gaussian Bayesian networks are used to fuse discrete and continuous information, and the discrete information in the residuals is used to compensate for the insufficient feature information problem caused by small amounts of data. To address the exponential modeling complexity growth in the case of multiple fault types cases, a single classification method is chosen for fault classification. Meanwhile, the T2 statistics distance suppression method is introduced into the Bayesian network to improve the diagnostic capabilities for new types of faults. By comparing the mainstream methods that address small sample diagnosis and the existing fusion methods, the experimental results show that in cases with small numbers of samples, the method in this paper has good fault diagnosis capabilities by effectively utilizing the model’s diagnostic results to compensate for the diagnostic errors caused by a lack of data, and it has an improved ability to recognize unknown faults.

An enhanced meta-learning network with sensitivity penalty for cross-domain few-shot fault diagnosis

Abstract Big data-driven rotating machine intelligent diagnostic technology has gained widespread applications. In practice, however, fault data are limited as well as inconsistencies in fault categories among different domains are widespread. These make developing robust intelligent diagnostic models a challenge. To this end, this paper develops an enhanced meta-learning network with a sensitivity penalization mechanism (EMLN-SP) for few-shot fault diagnosis in severe domain bias. First, lightweight channel attention is introduced to establish an enhanced feature encoder under meta-learning framework, which elevates the key feature expression to facilitate the extraction of generalized diagnostic knowledge within limited samples. Second, a boundary-enhanced loss calculation method is designed, which boosts the focus for decision boundary information to prevent the model from the overfitting dilemma in the case of few-shot. Finally, a sensitivity penalty mechanism is constructed to adjust the optimization direction, which prevents the model from falling into a local optimum, to boost the generalization of the model performance. The effectiveness of EMLN-SP is validated by three cross-domain diagnostic cases with diverse domain offsets.

DeepSEM-Net: Enhancing SEM defect analysis in semiconductor manufacturing with a dual-branch CNN-Transformer architecture

Due to the increasing complexity of modern semiconductor integrated circuit fabrication processes, various defects may occur at each process step, leading to a semiconductor integrated circuit yield loss as well as reliability problems. This study introduces DeepSEM-Net, a novel dual-branch architecture that harmoniously integrates Convolutional Neural Networks (CNN) with Transformers. This innovative approach significantly enhances defect classification and precise segmentation in Scanning Electron Microscope (SEM) defect images, crucial for semiconductor manufacturing processes. DeepSEM-Net consists of a classification branch, which synergizes CNN and Transformers for robust global feature extraction, and a segmentation branch, which incorporates a Pyramid Attention module to meticulously recalibrate and exploit the feature map, thereby enriching the segmentation quality. A semi-supervised defect analysis system based on this model markedly reduces manual inspection efforts and is adept at operating in both simultaneous and sequential classification-segmentation modes. Rigorously tested on a diverse dataset from a real 12-inch wafer fab, DeepSEM-Net not only demonstrated a commendable classification accuracy of 97.25% on a 5-class dataset and a segmentation IoU of 84.40% but also exhibited remarkable resilience against the introduction of new defect classes in an unbalanced dataset. The dual-branch strategy of DeepSEM-Net, thus, significantly elevates the efficiency and reliability of SEM defect image analysis, offering a substantial leap forward in addressing yield loss and ensuring the reliability of semiconductor products.

Fault classification and identification through machine learning approaches for a solar PV – battery based water pumping system

Fault classification and identification through machine learning approaches for a solar PV – battery based water pumping system

A Complex Analog Circuit Fault Diagnosis Method based on IMODA Improved Deep Belief Network

Aiming at the problems of time-consuming and low diagnosis accuracy during the unsupervised training process of traditional DBN, an analog circuit fault diagnosis method based on Improved Multi-Objective Dragonfly Optimized Deep Belief Network (IMODA-ADBN) is proposed. The method employs an improved MODA algorithm instead of the BP algorithm, which improves the classification accuracy of the network and ameliorates the problem of being prone to falling into local optima. The algorithm is tested on three multi-objective mathematical benchmark problems and compared with three well-known meta-heuristic optimization algorithms such as MODA, MOPSO and NSGA-II, and the results demonstrate the stability of the IMODA-ADBN network model. Finally, IMODA-ADBN is applied to the diagnostic experiments of a two-stage quad op-amp dual second-order low-pass filter, and the results show that the method improves the classification accuracy and diagnostic rate while guaranteeing the convergence speed, and is able to effectively realize the classification and localization of difficult faults.