Fault Detection Method Research Articles

Segmentation-assisted classification model with convolutional neural network for weld defect detection

Detecting weld defects in battery trays is crucial for the safety of new energy vehicles. Existing methods for weld surface defect detection, relying on traditional computer vision algorithms and convolutional neural networks with substantial image-level labeled data, face challenges in accurately identifying small defects, especially with limited samples. To address these issues, we developed an innovative Segmentation-Assisted Classification with Convolutional Neural Networks (SACNN) model. SACNN integrates a common feature extraction subnet, a segmentation subnet enhanced by a multi-scale feature fusion module, and a classification subnet specifically designed for precise defect detection. A joint loss function co-trains the segmentation and classification subnets using both image-level and pixel-level labels, enhancing the model’s ability to accurately detect small defect regions. Our model demonstrates notable improvement, achieving accuracy gains ranging from 2% to 18% compared to existing state-of-the-art methods, with an overall accuracy of 94.09% on an industrial dataset of battery tray welds. To further evaluate the generalization capability of our model, we evaluated it on the publicly available Magnetic Tile dataset, achieving state-of-the-art results in this challenging context. Additionally, we conducted comprehensive ablation studies to validate the contribution of each component in our approach and utilized visualization techniques to enhance the interpretability of our model. These advancements represent a significant contribution to the state of the art in aluminum alloy weld defect detection.

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%).

A technology of multiple-harmonic magnetic field excitation and its signal-processing method for noncontact steel pipeline defect detection

A technology of multiple-harmonic magnetic field excitation and its signal-processing method for noncontact steel pipeline defect detection

Research on fault diagnosis for three-phase rectifier device in direct current transmission system based on continuous wavelet transform and vision transformer

Abstract As a core component of photovoltaic power generation systems, the three-phase rectifier device plays a crucial role, and its failure can potentially reduce energy conversion efficiency and output quality. Presently, the performance of fault time-domain signal diagnosis methods based on three-phase rectifier circuits is challenging to enhance. This paper proposes a novel fault detection method for three-phase rectifier devices based on Vision Transformer, referred to as CWT-ViT, to address this issue. This method transforms time-domain fault signals into images through Continuous Wavelet Transform (CWT), subsequently inputting these images into a Vision Transformer model. Relying on its powerful self-attention mechanism and fully connected layers, it realizes the extraction and learning of rectifier device image features. A Simulink simulation model of a three-phase bridge controllable rectifier circuit is established for fault injection to collect fault signals. Fault diagnosis experiments demonstrate that the proposed diagnostic method achieves a prediction accuracy of 98.6%, maintaining a relatively high precision level. In comparison to four excellent classification models currently available: AlexNet, RepVGG, ResNet, and GoogLeNet, the proposed method demonstrates superior diagnostic performance. Additionally, this paper conducts ablation experiments to meticulously analyze the impact of each module in the fault diagnosis process. This research achieves more precise and efficient fault diagnosis in photovoltaic power generation systems, thereby reducing downtime and maintenance costs for actual equipment and enhancing the stability of photovoltaic power generation systems. This research provides an innovative, intelligent solution for the intelligent operations and maintenance of photovoltaic power generation.

Building Material Defect Detection and Diagnosis Method Based on Big Data and Deep Learning

Building Material Defect Detection and Diagnosis Method Based on Big Data and Deep Learning

CRDS‐based measurement of CO/CO2 concentration ratios for assessing transformer insulation aging

AbstractA gas analyzer has been developed using cavity ring‐down spectroscopy (CRDS) technology, designed to simultaneously measure the concentrations of CO2 and CO. These gases are critical indicators of transformer insulation degradation. The analyzer covers a CO2 concentration range from a few ppm to several thousand ppm and can measure CO/CO2 concentration ratios from 0.076 to 0.8. The selected absorption lines for CO and CO2 are centered at 6337.99 and 6338.59 cm−1, respectively. The two candidate lines are proximate to each other and nonoverlapping. The experimental results indicate that the system accurately fits the measured and calculated signals, enabling concentration measurements at the ppm level. This confirms its ability to measure the gas concentrations and ratios critical for assessing the condition of transformer insulation. This CRDS‐based system offers a reliable and sensitive method for early detection of potential transformer faults.

Optimization of steel plate quality inspection driven by PscSE and SPPFELAN

AbstractBased on the improved YOLOv8n, a steel plate defect detection and recognition method is proposed to address the high labor costs and workload of traditional tasks. SPPFELAN processes inputs in parallel to enhance computational efficiency by executing multiple pooling operations simultaneously. The parallel feature fusion module PscSE, using a mixed‐dimension SE attention mechanism (scSE), captures global and channel‐related information better, improving characterization capability. The EIOU loss function addresses the ambiguous aspect ratio definition of CIOU loss, enhancing detection accuracy and accelerating convergence. Results show the YOLOv8n‐PscSE‐SPPFELAN model achieves 76.9% mAP@0.5 on the Northeastern University steel plate dataset, a 4.6% improvement over the original YOLOv8n, with a computation amount of 7.7 GFLOPs, reducing resource usage and greatly improving detection speed.

An AI-based fault detection and classification method for hybrid parallel HVAC/HVDC overhead transmission lines

In this paper, a novel method is presented to detect and classify the AC, DC, and AC/DC intersystem faults in hybrid parallel HVAC/HVDC overhead transmission lines (HPOTLs) on the same tower. In HPOTLs lines the presence of electromagnetic coupling between the AC and DC conductors induces components in the AC and DC lines which can affect the performance of their protection systems. To tackle these challenges, a protection method based on the decision tree (DT) algorithm and a fault energy index (FEI) is proposed for HPOTLs. The proposed method uses the sending-end voltages and currents of the AC and DC lines and some transformations to calculate the FEIs. The fault detection and classification algorithms and their criteria are derived by the DT algorithm. PSCAD and MATLAB software are used for HPOTL modeling, and voltage and current signals processing, respectively. Simulation results show that the proposed protection method can detect and classify different faults (AC and DC line faults and AC/DC intersystem faults) accurately, and is able to discriminate between transmission line internal and external faults. Simplicity, high speed and accuracy, robustness to the fault resistance and noise, and not needing a telecommunication channel are important features of the proposed method.

Research on Surface Defect Detection Method of Wire Rope Outer Covering Layer Based on Deep Learning

Abstract Aiming at the requirement of a certain enterprise for the visual inspection accuracy of the surface defects of the outer sheath of the wire rope to reach 95 %, this paper adopts the existing Faster R-CNN algorithm to detect the surface defects of the outer sheath of the wire rope, and its accuracy mAP 0.5 is 8 8.7%. In order to improve the detection accuracy, the Faster R-CNN algorithm is improved. Among them, ResNeXt-101 is obtained on the basis of ResNeXt-50. It is used as the backbone network, and the attention mechanism feature pyramid network ACFPN is introduced to extract multi-scale features to enhance the network’s defect detection ability. The defect detection accuracy mAP 0.5 is improved to 93.2% In view of the diversity and large size differences of the defects of the outer sheath of the wire rope, a new loss function is constructed for the network. At the same time, the BO algorithm is used to optimize the hyperparameters of the stochastic gradient optimizer SGD of the improved network. The final designed ResNeXt101-ACFPN-Faster R-CNN algorithm is used to detect the surface defects of the outer sheath of the wire rope, and the detection accuracy mAP 0.5 reaches 95.8%. The detection goal of the enterprise is achieved. The research results show that the network optimization method proposed in this paper has a good effect on improving the detection accuracy of the surface defects of the outer sheath of the wire rope, and also verifies the effectiveness and feasibility of the algorithm improvement.

Lightweight bearing defect detection method based on collaborative attention and domain adaptive technology

Abstract With the rapid development of industrial manufacturing, bearing defect detection has become a key link to ensure the safe operation of equipment and improve production efficiency. Aiming at the problems of low accuracy and large parameters of traditional bearing defect detection models, this paper proposes a lightweight bearing defect detection method based on collaborative attention and domain adaptive technology. Firstly, the collaborative attention mechanism uses multiple parallel attention heads to extract the features of different regions in the image respectively. Each attention head can independently extract and weigh the features of specific regions, which can capture the complex features of bearing defects more comprehensively, including shape, texture, edge and other key information. At the same time, the domain adaptation technology aims to make the model adapt to the data distribution of different domains. It reduces the difference between the source domain and the object domain by aligning the feature distribution between the source domain and the object domain during the training process, thereby improving the performance of the model on the object domain. The experimental results show that the proposed method is 2.75% higher than the mAP@0.5 of YOLOv7, and has higher computational efficiency and better generalization ability than the traditional method.

YOLO-EF: A lightweight YOLOv7 PCB defect detection algorithm

Abstract This study addresses the challenge of accurate PCB defect detection, considering the computational complexity and excessive model parameters associated with existing methods. To mitigate these issues, we propose an enhanced PCB surface defect detection method called YOLO-EF, which is built upon the YOLOv7 architecture. Firstly, we replace the backbone of YOLOv7 with the lightweight Efficient FormerV2 module. This replacement reduces both the model volume and computational requirements. Secondly, the dynamic head module is introduced to unify the target detection head and improve its performance. Finally, the Wise-IoUv3 function is used to suppress the influence of low-quality samples on the model performance. The experimental results show that the proposed model improves by 2.85% in mAP over the original model. Model computation is reduced from 106.5 GFLOPs to 44.3 GFLOPs. Our YOLO-EF model achieves an optimal balance in terms of precision, computational efficiency, and detection speed.

Frequency domain attention network for copper chain defect detection in tobacco cutting machine

AbstractThe detection of defects on the copper chain in the production process of tobacco cutters is crucial for ensuring product quality. Traditional defect detection methods often rely on spatial domain image analysis, which not only has a large computational load but also performs poorly in handling high‐frequency noise and complex backgrounds. To address this issue, this paper proposes a novel neural network model based on frequency domain analysis, called frequency domain attention network. This network first utilizes discrete cosine transform to transform the image from the spatial domain to the frequency domain, effectively reducing computational complexity and improving processing speed. Subsequently, through the innovative frequency domain attention module, the network automatically identifies and enhances key discriminative features in the frequency domain, thereby strengthening the model's ability to identify defects. Finally, the frequency domain attention map, after feature extraction and integration, is inputted into the coupling detection head to achieve high‐precision defect detection. The experimental results show that our method outperforms the SOTA method with an increase of 0.03 in AP and 21 in FPS.

Unsupervised motor incipient fault detection using lightweight network and orthogonal low-rank embedding

Abstract Electrical motor is a key component in industrial systems. Detecting incipient fault of motor is critical to system reliability. However, the characteristics of faults and normal stages are difficult to distinguish, Meanwhile, the lightweight requirements of the model and the imbalance of the samples also make incipient fault detection challenged. To address these problems, this paper proposes an unsupervised fault detection method combines lightweight network and orthogonal low-rank embedding (OLE). The raw signals are firstly transformed into time-frequency images and fed into lightweight convolution network for feature extraction. Then, the features are clustered into orthogonal subspaces to enhance inter-class separability. Finally, a detection module based on distance metric is designed to identify the incipient fault of motor. The effectiveness of the proposed method is validated on four industrial motor dataset and compared with other methods.

Fault diagnoses of a nonlinear cracked rotor-bearing system based on vibration energy space and incremental learning approach

Health services of rotor-bearing systems are directly related to safe and stable works of rotating machineries in the industrial production. To address the issues of a low impact on vibration characteristics caused by faults in the higher rotational speed region, narrow and weak excitation signals, high dimensionality related to fault induction mechanisms, and difficulty in diagnosing using artificial intelligence technology due to the small number of fault samples in rotor systems, a novel fault detection method of nonlinear rotor systems through the incremental two-dimensional principal component analysis (I2DPCA) of the machine learning on the vibration energy space is proposed. Unlike mainly analyzing dynamic characteristics of rotor-bearing systems in vibration space, the method applies signals of the vibration energy space such as energy tracks, energy-time histories and energy-frequency spectra to have more advantages in vibration amplitudes caused by cracks in the higher rotational speed region and to overcome narrow and weak signals in the early fault stage. Then, the I2DPCA is applied to extract online low dimensional fault features and to process small vibration features of the rotor system. Simulation and experiment results show that performances of between-class margins and within-class clusters of different health conditions on the vibration energy space are more perfect than that on the vibration space. Based on the I2DPCA algorithm and the energy space method, the recognition rate of crack faults within the high rotational speed region is up to 99.6%, and it has good convergence and online learning ability in the case of small samples. The achieved conclusions of the method could provide a novel reference direction for fault diagnoses of rotor systems.

A Fault Detection Method Based on the Dynamic k-Nearest Neighbor Model and Dual Control Chart

A Fault Detection Method Based on the Dynamic k-Nearest Neighbor Model and Dual Control Chart

Comprehensive Analysis of Faults and Diagnosis Techniques in Cascaded Multi-Level Inverters

Reliability is a crucial factor to consider for multi-level inverters (MLIs) used in industrial applications. With the increasing number of power semiconductor devices, the potential for defects to significantly degrade the overall system is heightened. A highly effective fault-detection technique is required to minimize the impact of faults. This paper provides a comprehensive overview of the fundamental principles of multi-level inverters and the various sorts of faults that can occur in multi-level inverters. This study provides a comprehensive analysis of five-level cascaded H-bridge multilevel inverters (MLIs) under both normal and defective conditions. The paper outlines a fault-detection method that utilizes total harmonic distortion and a normalized output voltage factor. In addition, the paper discusses a fault-isolation strategy that relies on reducing amplitude modulation. This method leads to the development of a fault-tolerant inverter. The utilization of level-shifted pulse-width modulation (LSPWM) technology is employed for the purpose of switching operations. LSPWM is the most appropriate technique for MLIs that require a low amount of computational resources. The fault-diagnosis approach given is suitable for MLI-based drives, grid-connected operations, and other applications. This paper presents a comprehensive examination of the 5L-CMLI (5-Level Cascaded Multi-Level Inverter) under various fault scenarios in CMLI. Subsequently, various fault diagnosis approaches will be examined, including their advantages and disadvantages. The paper discusses several defects that can occur in the Insulated Gate Bipolar Transistor (IGBT) of a Current Mode Logic Inverter (CMLI), and also presents a design for a reliable fault diagnosis system. Furthermore, this analysis examines several fault detection strategies in CMLI, categorized according to open-loop and closed-loop dynamic systems fault classifications.

FDADNet: Detection of Surface Defects in Wood-Based Panels Based on Frequency Domain Transformation and Adaptive Dynamic Downsampling

The detection of surface defects on wood-based panels plays a crucial role in product quality control. However, due to the complex background and low contrast of defects in wood-based panel images, features extracted by traditional deep learning methods based on spatial domain processing often contain noise and blurred boundaries, which severely affects detection performance. To address these issues, we have proposed a wood-based panel surface defect detection method based on frequency domain transformation and adaptive dynamic downsampling (FDADNet). Specifically, we designed a Multi-axis Frequency Domain Weighted Information Representation Module (MFDW), which effectively decoupled the indistinguishable low-contrast defects from the background in the transform domain. Gaussian filtering was then employed to eliminate noise and blur between the defects and the background. Additionally, to tackle the issue of scale differences in defects that led to difficulties in accurate capture, we designed an Adaptive Dynamic Convolution (ADConv) module for downsampling. This method flexibly compressed and enhanced features, effectively improving the differentiation of the features of objects of varying scales in the transform space, and ultimately achieved effective defect detection. To compensate for the lack of data, we constructed a dataset of wood-based panel surface defects, WBP-DET. The experimental results showed that the proposed FDADNet effectively improved the detection performance of wood-based panel surface defects in complex scenarios, achieving a solid balance between efficiency and accuracy.

Solar photovoltaic module defect detection based on deep learning

Abstract Defect detection for photovoltaic (PV) modules is crucial in their production process, but the dataset quality and complex defects limit the accuracy and speed of the detection. In this paper, a solar PV module defect detection method was investigated using electroluminescence (EL) images. To reduce useless information in the EL images, a PV module segmentation method was proposed to segment PV cells from PV modules. Next, aiming at the insufficient sample size and the imbalance between classes in the dataset, a hybrid data augmentation method was proposed. Then, we proposed an improved YOLOv8n model for PV cell defects with different shapes and small sizes. Experiments showed that the proposed model has good comprehensive performance compared with other SOTA models, with mAP50 reaching 0.943 at only 7.6 G Flops. In addition, the proposed method can complete the defect detection of a PV module EL image containing 144 PV cells within 3 s. Overall, the proposed method meets the requirements of accuracy and real-time detection, providing a feasible solution for defect detection in PV modules.

A Surface Defect Detection Method for Cold-rolled Strip Steel Based on Improved YOLOv8

Cold-rolled strip steel has excellent mechanical properties, and it is widely used in the fields such as automotive manufacturing, construction industry, aircraft manufacturing and electronic product manufacturing. However, many different processing defects occur in the manufacturing process of cold-rolled strip steel, and this article proposes a visual detection method based on YOLOv8 to identify the surface defects on cold-rolled strip steel more accurately. Firstly, several common types of defects in cold-rolled strip steel were analyzed. Then, in order to enrich the dataset for subsequent detection, wavelet transform was used for filtering, denoising, and canny edge detection in the image processing stage for obtaining the clearer input model image with the more prominent graphics. Lastly, the CA attention mechanism was added into the YOLOv8 which is useful to improve the features recognition ability of the model, at the same time, the original standard convolution was replaced by DCS convolution and the loss function was optimized which is useful to get the lightweight models. The improved YOLOv8 model was validated on the NEU-DET dataset, the overall detection performance of the model such as the recall, the accuracy, and the average precision has significantly improved.

A Convolutional Neural Network-Based Defect Recognition Method for Power Insulator

As the scale of the power grid rapidly expands, its operation becomes increasingly complex, with higher demands on personnel proficiency, grid stability, equipment safety, and operational efficiency. In this study, a novel power insulator defect detection method based on convolutional neural networks (CNNs) is proposed. This method innovatively combines the feature extraction advantages of deep learning to build an efficient binary classification model capable of accurately detecting defects in power insulators in complex backgrounds. To avoid the impact of a small dataset on model performance, transfer learning was employed during model training to enhance the model’s generalization ability. A combination of Grid Search and Random Search was used for hyperparameter tuning, and the Early Stopping strategy was introduced to effectively prevent the model from overfitting to the training set, ensuring generalization performance on the validation set. Experimental results show that the proposed method achieves an average accuracy of 98.6%, a recall of 96.8%, and an F1 score of 97.7% on the test set. Compared to traditional Faster RCNN and PCA-SVM methods, the proposed CNN model significantly improves detection accuracy and computational efficiency in complex backgrounds, exhibiting superior recognition precision and model generalization ability for efficiently and accurately identifying defective insulators.