Automatic Fault Detection Research Articles

AdvancingTire Safety: Explainable Artificial Intelligence-Powered Foreign Object Defect Detection with Xception Networks and Grad-CAM Interpretation

Automatic detection of tire defects has become an important issue for tire production companies since these defects cause road accidents and loss of human lives. Defects in the inner structure of the tire cannot be detected with the naked eye; thus, a radiographic image of the tire is gathered using X-ray cameras. This image is then examined by a quality control operator, and a decision is made on whether it is a defective tire or not. Among all defect types, the foreign object type is the most common and may occur anywhere in the tire. This study proposes an explainable deep learning model based on Xception and Grad-CAM approaches. This model was fine-tuned and trained on a novel real tire dataset consisting of 2303 defective tires and 49,198 non-defective. The defective tire class was augmented using a custom augmentation technique to solve the imbalance problem of the dataset. Experimental results show that the proposed model detects foreign objects with an accuracy of 99.19%, recall of 98.75%, precision of 99.34%, and f-score of 99.05%. This study provided a clear advantage over similar literature studies.

Automatic detection of faults in industrial production of sandwich panels using Deep Learning techniques

Abstract The use of technologies like artificial intelligence can drive productivity growth, efficiency and innovation. The goal of this study is to develop an anomaly detection method for locating flaws on the surface of sandwich panels using YOLOv5. The proposed algorithm extracts information locally from an image through a prediction system that creates bounding boxes and determines whether the sandwich panel surface contains flaws. It attempts to reject or accept a product based on quality levels specified in the standard. To evaluate the proposed method, a comparison was made with a sandwich panel damage detection method based on a convolutional neural network and methods based on thresholding. The findings show that the proposed method, which is based on an object detector, is more accurate than the alternatives. The characteristics of the model, which can reject or accept a product according to the standard and limit allowable manufacturing flaws to obtain a quality product, also enable this system to improve industrial standards for producing sandwich panels while increasing speed.

Review of Data Processing Methods Used in Predictive Maintenance for Next Generation Heavy Machinery

Vibration-based condition monitoring plays an important role in maintaining reliable and effective heavy machinery in various sectors. Heavy machinery involves major investments and is frequently subjected to extreme operating conditions. Therefore, prompt fault identification and preventive maintenance are important for reducing costly breakdowns and maintaining operational safety. In this review, we look at different methods of vibration data processing in the context of vibration-based condition monitoring for heavy machinery. We divided primary approaches related to vibration data processing into three categories–signal processing methods, preprocessing-based techniques and artificial intelligence-based methods. We highlight the importance of these methods in improving the reliability and effectiveness of heavy machinery condition monitoring systems, highlighting the importance of precise and automated fault detection systems. To improve machinery performance and operational efficiency, this review aims to provide information on current developments and future directions in vibration-based condition monitoring by addressing issues like imbalanced data and integrating cutting-edge techniques like anomaly detection algorithms.

Performance evaluation of deep learning approaches for fault diagnosis of rotational mechanical systems using vibration, sound, and acoustic emission signals

The present study emphasizes an optimized deep learning algorithm for gearbox fault detection using vibration, sound, and acoustic emission signals. Statistical and acoustic features are extracted from these signals, and various neural network algorithms are explored. The supervised deep feed forward neural network (DFFNN) demonstrates excellent performance with vibration signals but limited accuracy with sound and acoustic emission signals. To address this, unsupervised algorithms are optimized and compared with vibration-based classification. The findings show that unsupervised neural networks, particularly the auto-encoder and stacked auto-encoder architectures, achieve improved classification accuracy by leveraging the unique characteristics of acoustic emission signals. The unsupervised models also effectively overcome the vanishing gradient problem via regularization, enhancing their training efficiency. The stacked auto-encoder, with multiple layers of encoders and decoders, reduces computation time by 40% and memory consumption. These optimized algorithms hold promise for automated fault detection systems. The auto-encoder and stacked auto-encoder, utilizing vibration, sound, and acoustic emission signals, offer enhanced classification accuracy and can facilitate real-time monitoring of rotating mechanical systems. However, further optimization is needed to maximize their performance. In a nutshell, the supervised DFFNN excels in utilizing vibration signals for fault detection, while the unsupervised models exploit the distinctive characteristics of acoustic emission signals. Future research will focus on refining these algorithms to enhance their effectiveness. Implementing these optimized deep learning approaches can lead to autonomous fault detection systems, eliminating the need for continuous human supervision.

Automatic detection of sewer defects based on yolov5

As cities modernize, sewer systems continue to expand. However, pipe problems may lead to accidents such as sewage overflow. The traditional sewerage pipe detection technology suffers from low accuracy and inefficiency and mainly relies on manual visual identification, which is prone to subjective errors. In this paper, a new Sewer-Yolov58 model is proposed to solve this problem, which is improved based on the original Yolov5 for real-time detection of sewerage problems to detect pipeline problems in time and is favorable for the subsequent repair work. Through comparison experiments with other models, the results show that the improved Sewer-Yolov58 model has a more efficient and accurate detection effect.

Edge Response and Defect Detectability in Flat Panel Digital Radiography

Defect detectability studies are used in nondestructive testing to ascertain the reliability of the method of inspection. In digital radiography, with the growing prevalence of automation of quality control processes by image processing and machine learning, a threshold detection criterion based on quantifiable data from the digital radiograph could be explored. The use of the parameter contrast-to-noise ratio (CNR) of defect signal as a probability of detection (POD) threshold criterion is explored in this paper. A stainless steel block containing artificial defects of known dimensions and location is radiographed by a flat panel detector, and an empirical POD curve is constructed. Before the POD study, the edge response of the flat panel system is studied to ensure noninterference of adjacent defect signals, gain insights about the lateral spread of the defect signal, and provide information to choose the region of interest for CNR calculation. The effect of noise on the POD using CNR as the threshold criterion is also included in the present study. The use of CNR-based POD models for digital radiography to aid the comparison and development of automatic defect detection models is also discussed.

Deep learning-assisted automatic quality assessment of concrete surfaces with cracks and bugholes

Cracks and bugholes are common factors affecting the quality of concrete surface, thus automatic detection of apparent defects is essential for concrete surface quality assessment. This study proposes an automatic quality assessment method based on deep learning for concrete surfaces with different scales of cracks and bugholes. In particular, a modified cascade mask region-based convolutional neural network (MC Mask R-CNN) with ResNet and feature pyramid network (FPN) is presented. Furthermore, a novel quantitative analysis algorithm for instance segmentation and size quantification of cracks and bugholes is proposed. Multi-scale features extracted by ResNet can be integrated using FPN. Closed operations and fixed elliptical kernels are adopted to reduce inaccuracies associated with crack discontinuities. Datasets collected at construction sites are used for training and testing of the network after data augmentation. Comparison work was carried out to evaluate the proposed model, and the box mean average precision (APbbox) and the mask mean average precision (APmask) index can reach up to 0.588 and 0.553. The overall quantization errors of cracks and bugholes were within acceptable limits. Validation experiments were conducted to illustrate the validity of the quality assessment method.

Automated defect detection in printed circuit boards based on the YOLOv5 neural network

Automated defect detection in printed circuit boards based on the YOLOv5 neural network

Automatic flaw detection in sectoral scans using machine learning

Phased array ultrasonic testing (PAUT) requires highly trained and qualified personnel to interpret and analyze images. It takes a solid understanding of wave propagation physics to comprehend the generated images. As such, the inspector's judgment and level of experience have a significant impact on the analysis's outcome. In addition, the procedure is prone to error and laborious. AI had shown to be effective in computer vision in a variety of classification and detection tasks. Regarding PAUT, studies have also demonstrated that machine learning may be able to identify defects with a level of accuracy that is on par or even superior to that of trained and qualified inspectors. Nonetheless, the use of computer vision in PAUT remains very limited. The primary cause of this is the challenge accessing large databases of labelled inspections. In fact, a considerable amount of training data is required for machine learning. While it is easy to access sizeable, labelled databases of MRI scans or photographs for instance, that is not the case in PAUT because inspection results are usually confidential. In this project, a large database was generated using mock-ups commonly used to train and evaluate inspectors. The different defects contained in these mock-ups were used to train a machine learning model. The data was acquired with several different probes centered at different frequencies. Each acquisition was performed using Full Matrix Capture (FMC). The post-processing of the data contained in the FMC allows to compute any sectoral scan from its focal laws. As a result, a comprehensive database composed of hundreds of thousands of sectoral scans was generated from these few FMC acquisitions. The completeness of this database facilitated robust training of a defect detection model for PAUT sectoral scans. The evaluation of the model demonstrated its ability to generalize even to defect types it had never been trained on. Furthermore, the detection performance remained consistent even in high noise conditions where the Contrast-to-Noise Ratio (CNR) was very low.

Application of continuous wavelet transform and convolutional neural networks in fault diagnosis of PMSM stator windings

Efficiency, reliability, and durability play a key role in modern drive systems in line with the Industry 4.0 paradigm and the sustainability trend. To ensure this, highly efficient motors and appropriate systems must be deployed to monitor their condition and diagnose faults during the operation. For these reasons, in recent years, more and more research has been focused on developing new methods for fault diagnosis of permanent magnet synchronous motors (PMSMs). This paper proposes a novel hybrid method for the automatic detection and classification of PMSM stator winding faults based on combining the continuous wavelet transform (CWT) analysis of the negative sequence component of the stator phase currents with a convolutional neural network (CNN). CWT scalogram images are used as the inputs of the CNN-based interturn short circuits fault classifier model. Experimental tests were carried out to verify the effectiveness of the proposed approach under various motor operating conditions and at an incipient stage of fault propagation. In addition, the effects of the input image format, CNN structure, and training process parameters on model accuracy and classification effectiveness were investigated. The results of the experimental tests confirmed the high effectiveness of fault detection (99.4%) and classification (97.5%), as well as other important advantages of the developed method.

Enhancing robotic manipulator fault detection with advanced machine learning techniques

The optimization of rotating machinery processes is crucial for enhanced industrial productivity. Automatic machine health monitoring systems play a vital role in ensuring smooth operations. This study introduces a novel approach for fault diagnosis in robotic manipulators through motor sound analysis to enhance industrial efficiency and prevent machinery downtime. A unique dataset is generated using a custom robotic manipulator to examine the effectiveness of both deep learning and traditional machine learning in identifying motor anomalies. The investigation includes a two-stage analysis, initially leveraging 2D spectrogram features with neural network architectures, followed by an evaluation of 1D MFCC features using various conventional machine learning algorithms. The results reveal that the proposed custom CNN and 1D-CNN models significantly surpass traditional methods, achieving an F1-score exceeding 92%, highlighting the potential of sound analysis for automated fault detection in robotic systems. Additional experiments were carried out to investigate 1D MFCC features with various machine learning algorithms, including KNN, DT, LR, RF, SVM, MLP, and 1D-CNN. Augmented with additional data collected from the locally designed manipulator, our experimental setup significantly enhances model performance. Particularly, the 1D-CNN stands out as the top-performing model on the augmented dataset.

End-to-end tire defect detection model based on transfer learning techniques

Visual inspection of defective tires post-production is vital for human safety, as faulty tires can lead to explosions, accidents, and loss of life. With the advancement of technology, transfer learning (TL) plays an influential role in many computer vision applications, including the tire defect detection problem. However, automatic tire defect detection is difficult for two reasons. The first is the presence of complex anisotropic multi-textured rubber layers. Second, there is no standard tire X-ray image dataset to use for defect detection. In this study, a TL-based tire defect detection model is proposed using a new dataset from a global tire company. First, we collected and labeled the dataset consisting of 3366 X-ray images of faulty tires and 20,000 images of qualified tires. Although the dataset covers 15 types of defects arising from different design patterns, our primary focus is on binary classification to detect the presence or absence of defects. This challenging dataset was split into 70, 15, and 15% for training, validation, and testing, respectively. Then, nine common pre-trained models were fine-tuned, trained, and tested on the proposed dataset. These models are Xception, InceptionV3, VGG16, VGG19, ResNet50, ResNet152V2, DenseNet121, InceptionResNetV2, and MobileNetV2. The results show that the fine-tuned VGG19, DenseNet21 and InceptionNet models achieve compatible results with the literature. Moreover, the Xception model outperformed the compared TL models and literature methods in terms of recall, precision, accuracy, and F1 score. Moreover, it achieved on the testing dataset 73.7, 88, 80.2, and 94.75% of recall, precision, F1 score, and accuracy, respectively, and on the validation dataset 73.3, 90.24, 80.9, and 95% of recall, precision, F1 score, and accuracy, respectively.

Automatic Defect Detection of Jet Engine Turbine and Compressor Blade Surface Coatings Using a Deep Learning-Based Algorithm

The application of additive manufacturing (AM) in the aerospace industry has led to the production of very complex parts like jet engine components, including turbine and compressor blades, that are difficult to manufacture using any other conventional manufacturing process but can be manufactured using the AM process. However, defects like nicks, surface irregularities, and edge imperfections can arise during the production process, potentivally affecting the operational integrity and safety of jet engines. Aiming at the problems of poor accuracy and below-standard efficiency in existing methodologies, this study introduces a deep learning approach using the You Only Look Once version 8 (YOLOv8) algorithm to detect surface, nick, and edge defects on jet engine turbine and compressor blades. The proposed method achieves high accuracy and speed, making it a practical solution for detecting surface defects in AM turbine and compressor blade specimens, particularly in the context of quality control and surface treatment processes in AM. The experimental findings confirmed that, in comparison to earlier automatic defect recognition procedures, the YOLOv8 model effectively detected nicks, edge defects, and surface defects in the turbine and compressor blade dataset, attaining an elevated level of accuracy in defect detection, reaching up to 99.5% in just 280 s.

Error Analysis of Common Power Meter Installation Faults on Three-Phase Networks

The article is concerned with the operation of electric power quality meters and analyzers when incorrectly installed on a three-phase electrical network. An analytical study of the meter’s errors under the conditions of faulty installation was carried out. All possible types of installation errors are considered according to the proposed classification, as well as possible combinations of a pair of installation faults simultaneously. Classification of installation faults is also proposed. Matrix expressions are derived that allow modeling of any type of installation faults to quantify power and symmetry measurement errors. The proposed method allows to obtain quantitative signs that can identify a specific installation fault. The results of this study can help the development of an algorithm for the automatic detection of installation faults and their correction. The analytical results were confirmed by simulation studies on a three-phase network model in the MATLAB/SIMULINK environment. Experimental results, obtained from a commercial power quality analyzer operated under controlled laboratory conditions, are also reported.

ECARRNet: An Efficient LSTM-Based Ensembled Deep Neural Network Architecture for Railway Fault Detection

Accidents due to defective railway lines and derailments are common disasters that are observed frequently in Southeast Asian countries. It is imperative to run proper diagnosis over the detection of such faults to prevent such accidents. However, manual detection of such faults periodically can be both time-consuming and costly. In this paper, we have proposed a Deep Learning (DL)-based algorithm for automatic fault detection in railway tracks, which we termed an Ensembled Convolutional Autoencoder ResNet-based Recurrent Neural Network (ECARRNet). We compared its output with existing DL techniques in the form of several pre-trained DL models to investigate railway tracks and determine whether they are defective or not while considering commonly prevalent faults such as—defects in rails and fasteners. Moreover, we manually collected the images from different railway tracks situated in Bangladesh and made our dataset. After comparing our proposed model with the existing models, we found that our proposed architecture has produced the highest accuracy among all the previously existing state-of-the-art (SOTA) architecture, with an accuracy of 93.28% on the full dataset. Additionally, we split our dataset into two parts having two different types of faults, which are fasteners and rails. We ran the models on those two separate datasets, obtaining accuracies of 98.59% and 92.06% on rail and fastener, respectively. Model explainability techniques like Grad-CAM and LIME were used to validate the result of the models, where our proposed model ECARRNet was seen to correctly classify and detect the regions of faulty railways effectively compared to the previously existing transfer learning models.

Automatic Testing Technology of BTB Liquid Crystal Display Advanced Fault Detection in Smart Meter for Smart Machine

In smart meter technology, the reliability of Backplane to Bezel (BTB) Liquid Crystal Displays (LCDs) is crucial for efficient functioning within intelligent grid systems. Defects in these LCD screens can significantly impact overall smart meter performance, necessitating effective detection methods for proper management and utilization. Current detection approaches, which combine manual and automatic methods based on machine vision, have shown unsatisfactory performance. This research addresses this challenge by proposing a novel method for advanced fault detection in BTB LCDs of smart meters, Automatic Testing Technology of BTB Liquid Crystal Display Advanced Fault Detection in Smart Meter for smart machine (BTB-LCD-FD- MCDSGAN) is proposed. The study begins by collecting datasets specifically tailored for LCD screen localization and defect detection. To enhance data quality, a Window Adaptive Extended Kalman Filter (WAEKF) is applied during preprocessing for noise removal. Feature extraction follows, utilizing Parameterized Multi Synchrosqueezing Transforms (PMST) with a primary focus on Gray Level Co-occurrence Matrix features. These extracted features serve as input for classification by a Multimodal Contrastive Domain Sharing Generative Adversarial Network (MCDSGAN), categorizing defects into five types likes normal display, no display, abnormal display, liquid crystal rupture, and incomplete display. Furthermore, the proposed method optimizes the MCDSGAN weight parameter using the Red Fox Optimization Algorithm (RFOA) to achieve accurate LCD fault defect prediction. The entire approach is implemented in Python, performance metrics likes accuracy, precision, recall, F-score, computational time are thoroughly analyzed. Performance of proposed BTB-LCD-FD-MCDSGAN approach attains 20.89%, 33.67% and 25.98% high accuracy, and 17.98%, 23.78% and 33.45% higher recall compared with existing methods such as automatic detection of display defects for smart meters depend on deep learning (AD-AM-DL), deep learning-enabled image content-adaptive field sequential color LCDs by mini-LED backlight (DL-AFSC-LCD) and new multi category defect detection method depend on convolutional neural network technique for TFT-LCD panels (MDF-CNN-LCD), methods respectively.

Automatic Detection of Pavement Marking Defects in Road Inspection Images Using Deep Learning

Automatic Detection of Pavement Marking Defects in Road Inspection Images Using Deep Learning

Research on Online Measurement Method for Small Workpiece Circular Holes Based on Machine Vision

<p>In modern manufacturing, due to the narrow format, short size, and complex surface structure of small-sized workpieces, automatic detection of surface defects, dimensions, etc. on small-sized workpieces faces difficulties, making it difficult to meet the requirements of fully automated production lines. Especially, there is no good solution to the problem of high-precision automatic measurement of geometric features of circles and arcs on small-sized workpieces. This article takes the engine end cover circular hole thermal component as the research object, builds a hardware platform for image acquisition of small-sized workpieces based on machine vision, proposes an online size measurement method for small-sized circular holes, and realizes the measurement of the position size and aperture size of small-sized product shell workpieces. In order to achieve the above methods, this article builds a visual detection hardware system and describes a detailed machine vision hardware selection scheme. Then, the images collected by the system are preprocessed, including image denoising, image correction, and image feature extraction. Then, for the processed images, an improved Hough transform fitting method is used to obtain the online size of features. In order to visualize the results, the detection system and software are designed according to the actual application scenario. The overall scheme of this article is efficient and reasonable, and the detection result error is within a reasonable range.</p> <p> </p>

Variational Mode Decomposition-Based Processing for Detection of Short-Circuited Turns in Transformers Using Vibration Signals and Machine Learning

Transformers are key elements in electrical systems. Although they are robust machines, different faults can appear due to their inherent operating conditions, e.g., the presence of different electrical and mechanical stresses. Among the different elements that compound a transformer, the winding is one of the most vulnerable parts, where the damage of turn-to-turn short circuits is one of the most studied faults since low-level damage (i.e., a low number of short-circuited turns—SCTs) can lead to the overall fault of the transformer; therefore, early fault detection has become a fundamental task. In this regard, this paper presents a machine learning-based method to diagnose SCTs in the transformer windings by using their vibrational response. In general, the vibration signals are firstly decomposed by means of the variational mode decomposition method, where a comparison with the empirical mode decomposition (EMD) method and the ensemble empirical mode decomposition (EEMD) method is also carried out. Then, entropy, energy, and kurtosis indices are obtained from each decomposition as fault indicators, where both the combination of features and the dimensionality reduction by using the principal component analysis (PCA) method are analyzed for the global effectiveness improvement and the computational burden reduction. Finally, a pattern recognition algorithm based on artificial neural networks (ANNs) is used for automatic fault detection. The obtained results show 100% effectiveness in detecting seven fault conditions, i.e., 0 (healthy), 5, 10, 15, 20, 25, and 30 SCTs.

Automatic detection of quartz glass subsurface defects by laser scattering method based on an ellipsoidal mirror.

With the improvement of quality requirements of optical components, the detection of subsurface defects of optical components has become a key technology. The existing detection methods still have some limitations in detection depth and detection efficiency. In this paper, a defect scattering light collection method based on ellipsoidal mirror model is used to analyze the scattering light collection efficiency under different experimental conditions theoretically, and the favorable conditions for improving the scattering light collection are proposed. After simulation verification, the use of ellipsoidal reflectors to collect scattered light can effectively avoid the impact of surface defects compared to lenses. At the same time, an experimental system based on this method is set up to filter the stray light by mean filtering method. The system detected three scratches (2μm in width and 252nm in depth) on the underside of a piece of quartz glass. The results show that the system can clearly detect the subsurface defects of optical components.