Visual Inspection Technology Research Articles

Development of a standardized data collection and intelligent fabric quality prediction system for the weaving department

The diversity of weaving equipment has led to inconsistencies in communication protocols, impeding data collection and interoperability between devices, and ultimately reducing production efficiency. Additionally, fabric defects significantly impact product quality, while current visual inspection technologies are primarily reactive and traditional quality prediction methods often exhibit considerable errors. This study leverages the standardization and interoperability features of open platform communications unified architecture technology to facilitate data acquisition within the weaving department, establishing a reliable Internet of Things framework that supports subsequent fabric quality prediction, and optimizing the back propagation neural network through the K-means clustering algorithm and particle swarm optimization to predict the type and number of fabric defects. A comparative analysis with traditional BP and PSO-BP prediction models was conducted, ultimately verifying the feasibility of using OPC UA to transmit weaving data for fabric quality prediction. The research results demonstrate that using OPC UA technology enables the unified transmission of weaving equipment data, addressing the issue of heterogeneity in weaving department equipment. The K-means-PSO-BP model can effectively predict defects such as double weft, hundred feet, and broken warp with minimal error, achieving a root mean square error of less than 0.15.

Process planning of repairing and grinding for cylindrical parts based on surface defect detection

Abstract To realize the purpose of grinding and repairing surface defects in cylindrical parts, machine vision inspection technology and automatic grinding technology are integrated in this study. These technologies are combined to detect and repair defects in cylindrical parts using an automatic grinding and repair platform. For various defect types, the dynamic threshold extraction method is used, combined with the image difference method in the spatial and frequency domains through defect screening, sensor calibration and sub-pixel edge detection. The defect features are completely extracted and the defect size is determined to guide the polishing and repair platform to repair the surface defects of parts. A grinding path planning algorithm is proposed to solve the problem of the initial installation eccentricity of the workpiece, which can adjust the grinding wheel feed and grinding position. Finally, the experimental tests show that the designed automatic grinding repair system detects all defects without omission, and the average surface roughness of the cylindrical parts Ra is 3.17 μm after repair and polishing, which meets the grinding quality requirements.

BHC-YOLOV8 : improved YOLOv8-based BHC target detection model for tea leaf disease and defect in real-world scenarios.

The detection efficiency of tea diseases and defects ensures the quality and yield of tea. However, in actual production, on the one hand, the tea plantation has high mountains and long roads, and the safety of inspection personnel cannot be guaranteed; on the other hand, the inspection personnel have factors such as lack of experience and fatigue, resulting in incomplete and slow testing results. Introducing visual inspection technology can avoid the above problems. Firstly, a dynamic sparse attention mechanism (Bi Former) is introduced into the model backbone. It filters out irrelevant key value pairs at the coarse region level, utilizing sparsity to save computation and memory; jointly apply fine region token to token attention in the remaining candidate regions. Secondly, Haar wavelets are introduced to improve the down sampling module. By processing the input information flow horizontally, vertically, and diagonally, the original image is reconstructed. Finally, a new feature fusion network is designed using a multi-head attention mechanism to decompose the main network into several cascaded stages, each stage comprising a sub-backbone for parallel processing of different features. Simultaneously, skip connections are performed on features from the same layer, and unbounded fusion weight normalization is introduced to constrain the range of each weight value. After the above improvements, the confidence level of the current mainstream models increased by 7.1%, mAP0.5 increased by 8%, and reached 94.5%. After conducting ablation experiments and comparing with mainstream models, the feature fusion network proposed in this paper reduced computational complexity by 10.6 GFlops, increased confidence by 2.7%, and increased mAP0.5 by 3.2%. This paper developed a new network based on YOLOv8 to overcome the difficulties of tea diseases and defects such as small target, multiple occlusion and complex background.

Application of optical homogeneity detection technology in glass quality control based on visual inspection technology

Abstract Glass is an advanced material with a wide range of applications. Improving the quality of glass products supports and promotes various industries. This paper discusses the streaks affecting the quality of glass products and focuses on implementing optical homogeneity detection technology for glass. Based on the relationship between optical homogeneity and mechanical properties, this detection technology analyzes the causes of streaks in the production process of glass products and deduces the causes for the streak characteristics through the discussion of the working principle of the homogeneity detection technology, the detection device, the detection steps and the use of technology. In this study, visual inspection technology is introduced into the optical homogeneity inspection technology instead of the traditional manual inspection method, which can make the inspection results faster and more accurate and can find a quick and effective solution to the streaks.

The application and development of drone vision technology in railway inspection industry

The inspection and preventive maintenance of railway facilities and their surrounding environments are critical tasks for ensuring the safety of railway operations. Inspection is the prerequisite for maintenance, and therefore, comprehensive inspection and maintenance methods can effectively reduce operational risks and ensure safe train operations. This paper summarizes the application of drone vision technology in railway inspections, analyzing the use of drones for the inspection of high-altitude equipment and environments, ground-level equipment and environments, and disaster prevention and control. It also reviews the recent applications of drone vision inspection technology in the railway industry, identifies the constraints, and offers a perspective on future developments.

Recent Patents for Machine Vision Inspection in the Machine Tool Sector

Abstract:: In the current modern manufacturing industry, the demand for product quality control is increasing, as is the need for automation. However, the manual inspection may need to be noticed or undetectable in the complex production process. To solve this phenomenon, machine vision-based inspection of machine tools and their product features has become one of the key technologies in intelligent manufacturing. The basic principle of machine tool machine vision inspection is to transmit the object to be inspected to the computer through efficient image acquisition. Then, image processing or deep learning algorithms classify, locate, segment, and process the features of the thing. Finally, the computer makes the judgment of whether it is qualified. According to recent numerical analysis data, compared with traditional methods, machine tool machine vision inspection can improve the inspection efficiency by 30%, and the accuracy has reached 98%, much higher than manual inspection accuracy. This study provides an in-depth review of representative patents and machine tool vision inspectionpatents , and it comprehensively summarizes the research results from various dimensions in recent year. In the past five years, the average annual growth rate of machine tool vision inspection technology has reached 15%, showing the rapid development momentum of this field. The research content mainly focuses on designing vision detection structures, algorithm optimization designs, and personalized solutions for object differences.

A Survey of Vision-Based Methods for Surface Defects’ Detection and Classification in Steel Products

In the competitive landscape of steel-strip production, ensuring the high quality of steel surfaces is paramount. Traditionally, human visual inspection has been the primary method for detecting defects, but it suffers from limitations such as reliability, cost, processing time, and accuracy. Visual inspection technologies, particularly automation techniques, have been introduced to address these shortcomings. This paper conducts a thorough survey examining vision-based methodologies related to detecting and classifying surface defects on steel products. These methodologies encompass statistical, spectral, texture segmentation based methods, and machine learning-driven approaches. Furthermore, various classification algorithms, categorized into supervised, semi-supervised, and unsupervised techniques, are discussed. Additionally, the paper outlines the future direction of research focus.

Research on a Cross-Domain Few-Shot Adaptive Classification Algorithm Based on Knowledge Distillation Technology.

With the development of deep learning and sensors and sensor collection methods, computer vision inspection technology has developed rapidly. The deep-learning-based classification algorithm requires the acquisition of a model with superior generalization capabilities through the utilization of a substantial quantity of training samples. However, due to issues such as privacy, annotation costs, and sensor-captured images, how to make full use of limited samples has become a major challenge for practical training and deployment. Furthermore, when simulating models and transferring them to actual image scenarios, discrepancies often arise between the common training sets and the target domain (domain offset). Currently, meta-learning offers a promising solution for few-shot learning problems. However, the quantity of supporting set data on the target domain remains limited, leading to limited cross-domain learning effectiveness. To address this challenge, we have developed a self-distillation and mixing (SDM) method utilizing a Teacher-Student framework. This method effectively transfers knowledge from the source domain to the target domain by applying self-distillation techniques and mixed data augmentation, learning better image representations from relatively abundant datasets, and achieving fine-tuning in the target domain. In comparison with nine classical models, the experimental results demonstrate that the SDM method excels in terms of training time and accuracy. Furthermore, SDM effectively transfers knowledge from the source domain to the target domain, even with a limited number of target domain samples.

Exploration of Visual Inspection and Algorithm Technology for Aerial Transmission Lines

Exploration of Visual Inspection and Algorithm Technology for Aerial Transmission Lines

Optimization study of anomaly detection algorithm in machine vision inspection technology

Abstract In recent years, target detection algorithms based on machine vision have been a hotspot in computer vision research. The You Only Look Once (YOLO) algorithm, as an excellent target detection algorithm, has played an important role in improving detection speed and accuracy with the improvement of the network architecture in its development process. This paper introduces the concept of integrated learning to the YOLOv5 network architecture, incorporating deformable convolution and attention mechanisms. It also chooses the focal EIOU loss function to replace the GIOU loss function, thereby addressing the issue of localization loss, prioritizing abnormally detected targets, and enhancing the detection efficiency of these abnormal targets. Finally, we examine the practical value of the improved YOLOv5 algorithm by testing its performance and applying it to real-world anomaly detection. The results show that the improved YOLOv5 model outperforms the original YOLOv5 model in terms of performance and practical application advantages. In terms of performance, the classification accuracy of sea_person and earth_person in the improved YOLOv5 model is 37% and 26%, respectively, which is a significant performance gain overall. In actual application tests, the proposed method is more accurate than the traditional method. The accuracy is significantly higher.

Sub-micron Assembly Alignment Detection Method and System Based on Optical Diffraction

With the continuous development of manufacturing technology, precision instruments are increasingly moving towards miniaturization, precision, and integration. The assembly accuracy of the product has become a critical factor that limits the performance of the product. Assembly alignment is a significant part of the assembly process, and the accuracy of alignment detection has a significant effect on the final assembly accuracy of the product. Currently, the mainstream technology is to recognize and detect the final image of two parts using microscopic visual inspection technology. However, this method struggles to achieve sub-micron level alignment detection accuracy. In this paper, we presented a sub-micron alignment detection system based on optical diffraction, and the factors influencing the detection accuracy are analysed. Based on this, an experimental assembly alignment detection system was designed based on piezoelectric ceramic drive, laser confocal sensor monitoring feedback, and the mapping relationship between the nanoscale moving position of the diffraction aperture and the diffraction result to achieve sub-micron displacement detection. In addition, experimental tests have been carried out to verify the feasibility of this program. The experimental results indicate that the developed alignment detection method and system can achieve sub-micron alignment detection accuracy, providing a novel device and development concept for high-precision assembly alignment detection.

Efficient segmentation of water leakage in shield tunnel lining with convolutional neural network

Water leakage is a critical factor reflecting the structural safety of shield tunnels. Computer vision provides new opportunities to overcome the shortcomings of manual visual inspection and realize automatic detection of water leakage regions. In this study, we propose a leakage segmentation model with an encoder–decoder structure. The encoder adopts multi-branch convolutional attention for feature fusion, and the decoder adopts a lightweight design that only contains multi-layer perceptron. Standard convolution in multi-branch is decomposed to two depth-wise strip convolutions to realize lightweight design and extract strip-like features. Extensive ablation and comparative studies were conducted to test model performance. Test results show that our model achieves robust detection of water leakage under strong noise background, reaching an intersection over union of 90.75% with performance-computation trade-off. Consequently, the proposed method can be an effective alternative to the current visual inspection technologies, and provide a nearly automated inspection platform for shield tunnels.

Closed-loop Control of Biaxial Fatigue Loading of Wind Turbine Blades Based on Visual Inspection

Based on the inertial vibration excitation device, a biaxial fatigue loading system for wind turbine blades is established by using visual inspection technology and virtual spindle decoupling to control the vibration excitation motion of wind turbine blades. The image feature point tracking method is used to detect the blade vibration state. Considering the system vibration frequency characteristics, the phase difference between the exciting force and the vibration displacement is detected based on the phase detector, and the system resonance frequency is adaptively tracked to achieve accurate control of the double-free amplitude of the blade. The fatigue test shows that the control system can maintain the amplitude error of the blade, the adaptive tracking control method is reliable and effective, and the accuracy and reliability of the fatigue test are improved.

Research on the application effect of machine vision technology based on simulation analysis in 3D inspection of torque converter welds

AbstractWith the development of machine vision technology, visual inspection technology has been widely used in many fields. Among them, the 3D visual detection technology based on line structured light has attracted the attention of relevant scholars because of its advantages of the easy acquisition of image information and high detection accuracy. Therefore, applying machine vision technology to the field of three‐dimensional weld inspection can improve the inspection effect, so a machine vision technology based on simulation analysis was proposed. First, the model parameter calibration and algorithm of the structured light imaging system are studied, and then a structured light‐based torque converter weld height detection system is designed and related models are constructed. Finally, the detection accuracy and speed of the constructed 3D vision measurement system are verified. The results show that the calibration parameters obtained by the optimization algorithm of this study are as follows, focal length = 17.16376; = 1798.55439; = 1276.85505; = 0.14072; Secondly, in the comparative experiment, the height of the wave crest coordinates of the measurement results of the three‐dimensional detection system of the torque converter weld seam in the global feature extraction process based on the machine vision technology based on simulation analysis is 9.1330 mm, and the maximum error value is 1.0403 mm; As a result of the calibration algorithm, the peak coordinate height is 10.3526 mm, and the maximum error value is 2.7482 mm. The error of the research system is better than Zhang Zhengyou's calibration method. The research content has important reference value for improving the three‐dimensional inspection effect of torque converter welds.

An Automatic Visual Inspection of Oil Tanks Exterior Surface Using Unmanned Aerial Vehicle with Image Processing and Cascading Fuzzy Logic Algorithms

This paper presents an automatic visual inspection of exterior surface defects of oil tanks using unmanned aerial vehicles (UAVs) and image processing with two cascading fuzzy logic algorithms. Corrosion is one of the defects that has a serious effect on the safety of the surface of oil and gas tanks. At present, human inspection, and climbing robots inspection are the dominant approach for rust detection in oil and gas tanks. However, there are many shortcomings to this approach, such as taking longer, high cost, and covering less surface area inspection of the tank. The purpose of this research is to detect the rust in oil tanks by localizing visual inspection technology using UAVs, as well as to develop algorithms to distinguish between defects and noise. The study focuses on two basic aspects of oil tank inspection through the images captured by the UAV, namely, the detection of defects and the distinction between defects and noise. For the former, an image processing algorithm was developed to improve or remove noise, adjust the brightness of the captured image, and extract features to identify defects in oil tanks. Meanwhile, for the latter aspect, a cascading fuzzy logic algorithm and threshold algorithm were developed to distinguish between defects and noise levels and reduce their impact through three stages of processing: The first stage of fuzzy logic aims to distinguish between defects and low noise generated by the appearance of objects on the surface of the tank, such as trees or stairs, and reduce their impact. The second stage aims to distinguish between defects and medium noise generated by shadows or the presence of small objects on the surface of the tank and reduce their impact. The third stage of the thresholding algorithm aims to distinguish between defects and high noise generated by sedimentation on the surface of the tank and reduce its impact. The samples were classified based on the output of the third stage of the threshold process into defective or non-defective samples. The proposed algorithms were tested on 180 samples and the results show its superiority in the inspection and detection of defects with an accuracy of 83%.

Visual inspection intelligent robot technology for large infusion industry

Abstract The application of intelligent technology has realized the transformation of people’s production and lifestyle, and it has also promoted the development of the field of medicine. At present, the intensity of intelligence in the field of medicine is increasing. By using its cash methods and techniques combined with the mechanical field, this article proposes to use visual inspection technology to understand the fusion of the medical field and the mechanical field. It is helpful to analyze and solve objective problems such as low efficiency in current infusion and insufficient rigidity of large infusion plastic bottles. Drawing on the principles and laws of deep learning algorithms and neural networks, the technical research of intelligent robots for visual inspection is carried out to realize the intelligence of infusion robots. In the research accuracy of detection, the detection rate of standard particles higher than 85 µM has reached almost 100%, and the rate of 50 µM standard particles is lower and unstable. The detection effect of the control light bulb control was different, and the detection rate was between 50 and 80%, which was obviously worse than the detection robot effect. Therefore, the current research on the technology of intelligent robots is very important.

Color and Texture Feature Recognition of Traditional Pen and Ink Painting Based on Visual Sensor

<p>Visual inspection technology testing is an application of machine vision theory. In recent years, this field has become an important and rapidly developing field of instrumentation and engineering research. Based on the vision sensor technology, this paper launches the research on the color and texture feature recognition of pen and ink painting. This article first researches the power supply system and obtains the power supply scheme diagram, and then tests the visual sensor in five steps and appropriately optimizes the parameters. Finally, 6 sets of comparative experiments were carried out, each of which was 100 times to identify the color and texture of the pen-and-ink painting. The experimental results are as follows: the number of successful color recognition is 97, 95, 90, 94, 92, and 96 times, and the number of successful texture recognition is 84, 87, 82, 91, 96, and 97 times.</p> <p> </p>

Insulator fault feature extraction system of substation equipment based on machine vision

AbstractThe artificial intelligence technology and intelligent automation are more and more widely used, the insulators play a supporting and insulating role in the operation of the grid. The use of machine vision inspection technology to detect insulator faults has become an inevitable trend of the times. In this study, based on BP neural network, the fault feature extraction system of substation insulator is studied, and then the system has some shortcomings in target detection algorithm. It then introduced two target detection algorithms, YOLOv3 and Canny, to improve the system. This study then analyses and compares the various indicators. It also analyses some external interference factors that exist when detecting insulator faults. It then further analyses the slenderness ratio of the smallest circumscribed rectangle of the insulator and the background region and the duty cycle of the insulator and the background region. The experimental results show that the recognition rates of both YOLOv3 and Canny target detection algorithms are around 90%. In this study, the influence of external factors is considered, and the fault features are further introduced, so that the true positive rate and accuracy of the algorithm have been improved.

Non-Destructive Defect Detection Using MASK R-CNN on Industrial Radiography of Machines

Abstract: Many industrial processes, particularly those requiring casting or welding, rely heavily on quality control. Manual quality control processes, on the other hand, are frequently time-consuming and error-prone. To address the increased demand for high-quality products, sophisticated visual inspection technologies are becoming increasingly important in manufacturing lines. Convolutional Neural Networks have recently demonstrated exceptional performance in image classification and localization tasks. Based on the Mask Region-based CNN architecture, this research proposes a solution for detecting casting errors in X-ray pictures. The suggested defect detection system conducts flaw identification and segmentation on input pictures at the same time, making it appropriate for a variety of defect detection jobs. It is demonstrated that training the network to conduct defect detection and defect instance segmentation at the same time leads in greater defect detection accuracy than training on defect detection alone. Transfer learning is used to minimizetraining data requirements while increasing the trained model's prediction accuracy. More precisely, the model is trained using two huge publically available picture datasets before being fine-tuned using a relatively modest metal casting X-ray dataset.The trained model's accuracy outperforms state-of-the-art performance on the GRIMA database of Xray images (GDXray) Castings dataset and is quick enough to be deployed in production. On the GDXray Welds dataset, the system likewise works well.A variety of in-depth research are being undertaken to investigate how transfer learning, multi-task learning, and multi-class learning affect the trained system's performance.

Image processing of Casting defects based on Convolutional neural network

At present, there are numerous losses caused by corrosion cracking of metal castings in engineering in China. In order to detect the possible defects of metal castings in engineering, the laser ultrasonic vision inspection technology is used to image the castings, and then the identification efficiency is low. In order to process these images efficiently and quickly, convolutional neural network image processing technology is introduced. According to the actual needs, a convolutional neural network architecture is designed to recognize images, and whether the architecture meets the requirements is verified. Experimental results show that the performance of the architecture meets the design requirements. Under the same conditions, this structure provides a solution for casting defect detection combined with artificial intelligence.