On-line Inspection Method Research Articles

Online Inspection Method and System Design for Screw Threads of Rebar Head Based on Machine Vision

An online inspection method based on machine vision was proposed and validated to address the issues of high work intensity, low efficiency, low accuracy, and risk of missed inspection in traditional sampling methods for screw threads of rebar head. Firstly, an industrial camera was used to capture real-time images of the processed rebar thread heads, preprocess the images, and locate the target positions in the images to reduce the complexity and running time of subsequent algorithms. Then, the Canny operator was used to roughly extract the edge feature information of the rebar head, and the Shi–Tomasi algorithm was used for corner inspection to achieve precise optimization of sub-pixel level corners. Based on robust linear regression, the diagonal points were fitted with lines to detect the corresponding size parameters. Finally, an inspection system on screw threads of rebar head parameter was designed and developed, which consisted of an image-acquisition device, Siemens PLC controller, and inspection software. Test results show that this method can achieve online inspection without contact, with inspection accuracy reaching the micrometer level, and 8–10 rebar heads can be inspected per second.

Live Dimension Detection During Machining of Workpiece using Smart Detection Set up on General-Purpose Lathe

In a manufacturing setting, the profile dimensions of the workpiece are key quality factors. Various automatic inspection approaches currently assess dimensions based on characteristics and variables, tool paths as OK or Not OK in CNC, and online inspection methods for other machines after manufacturing. However, continuous on-machine profile dimensions and simultaneous manufacturing were left to focus. An intelligent recognition system based on a laser lines sensor using a smart profile dimension detection algorithm (SPDA) communicates real-time measurement information to the operator. It plots the current status of the Workpiece, mapping linear distance by accurate laser reflection of the exact mid-surface line of the workpiece as profile data of a symmetric shaft. It compares the length-diameter obtained from longitudinal and lateral sensors with the master data provided. The algorithm implements Python libraries for displaying panels and organizing workpieces. The standard image changes color from red to green as it is relevant to the status. The predetermined order of manufacturing parts and gradient descent optimization feature sets benchmarks to display the status of the workpiece. The real-time live measurement is facilitated with an error of less than 10%, i.e., 0.1 mm, saving manufacturing time by 30%. It also eliminates the inspection stage, and no reduced job rejection is found.

DSN-BR-Based Online Inspection Method and Application for Surface Defects of Pharmaceutical Products in Aluminum-Plastic Blister Packages

Ensuring high product quality is of paramount importance in pharmaceutical drug manufacturing, as it is subject to rigorous regulatory practices. This study presents a research focused on the development of an on-line detection method and system for identifying surface defects in pharmaceutical products packaged in aluminum-plastic blisters. Firstly, the aluminum-plastic blister packages exhibit multi-scale features and inter-class indistinction. To address this, the deep semantic network with boundary refinement (DSN-BR) model is proposed, which leverages semantic segmentation domain knowledge, to accurately segment the defects in pixel level. Additionally, a specialized image acquisition module that minimizes the impact of ambient light is established, ensuring high-quality image capture. Finally, the image acquisition module, image detection module, and data management module are designed to construct a comprehensive online surface defect detection system. To validate the effectiveness of our approach, we employ a real dataset for instance verification on the implemented system. The experimental results substantiate the outstanding performance of the DSN-BR, achieving the mean intersection over union (MIoU) of 90.5%. Furthermore, the proposed system achieves an inference speed of up to 14.12 f/s, while attaining an F1-Score of 98.25%. These results demonstrate that the system meets the actual needs of the enterprise and provides theoretical and methodological support for intelligent inspection of product surface quality. By standardizing the control process of pharmaceutical manufacturing and improving the management capability of the manufacturing process, our approach holds significant market application prospects.

A sparse data gas sensor array feature mining method for rubber Mooney viscosity measurement

Mooney viscosity is an important index to reflect the performance and quality of rubber. At present, the rubber Mooney test has the problems of large time delay, destructive and unable to detect online, which restricts the development of rubber industry. In this paper, a gas sensor array-based online inspection method for rubber Mooney viscosity is proposed to improve the problems of measurement delay and raw material waste in the traditional method. A multiple generator time series generative adversarial network (MGTSGAN) structure is proposed to address the problem that the lack of sample data volume and uneven data distribution make it difficult to model. Transformer is introduced to solve the problem of traditional generative adversarial networks in dealing with long sequential dependencies. In the experimental part, a rubber Mooney viscosity detection device is built to verify the effectiveness of the proposed method. The performance of different generative models on two gas sensor datasets is compared to verify the advancement and generalization of the proposed method. The experimental results show that the correct rate of this paper’s method for rubber Mooney viscosity classification is higher than 96%. The correct rates are all improved after data enhancement, in which the MGTSGAN proposed in this paper obtains the highest correct rate of 98.35%. For the classification experiments on Gas sensor array under flow modulation dataset also achieved relatively good results. Among them, the highest correct classification rate of 95.63% is achieved after data enhancement using MGTSGAN.

A Single-Frame Deflectometry Method for Online Inspection of Light-Transmitting Components.

Transparent materials are widely used in industrial applications, such as construction, transportation, and optics. However, the complex optical properties of these materials make it difficult to achieve precise surface form measurements, especially for bulk surface form inspection in industrial environments. Traditional structured light-based measurement methods often struggle with suboptimal signal-to-noise ratios, making them ineffective. Currently, there is a lack of efficient techniques for real-time inspection of such components. This paper proposes a single-frame measurement technique based on deflectometry for large-size transparent surfaces. It utilizes the reflective characteristics of the measured surface, making it independent of the surface's diffuse reflection properties. This fundamentally solves the issues associated with signal-to-noise ratios. By discretizing the phase map, it separates the multiple surface reflection characteristics of transparent devices, enabling transparent device measurement. To meet the requirements of industrial dynamic measurement, this technique only needs a simple and low-cost system structure, which contains just two cameras for image capture. It does not require phase shifting to complete the measurement, making it independent of the screen and having the potential for larger surface measurement. The proposed method was used to measure a 400mm aperture automobile glass, and the results showed that it is able to achieve a measurement accuracy on the order of 10 μ m. The method proposed in this paper overcomes the influence of surface reflection on transparent objects and significantly improves the efficiency and accuracy of large-sized transparent surface measurements by using a single-frame image measurement. Moreover, this method shows promise for broader applications, including measurements of lenses and HUD (Heads-Up Display) components, showcasing significant potential for industrial applications.

Non-contact online inspection method for the appearance diameter uniformity of chemical fiber filaments

As chemical fiber filaments diameter variation directly affects spinning quality, spinning condition monitoring becomes more and more important in an intelligent manufacturing environment. Firstly, based on the single-slit Fraunhofer diffraction model and the Babinet principle, the non-contact filaments diffraction model is developed to generate diffraction fringe patterns by irradiating chemical fiber filaments with He–Ne laser. Secondly, for the characteristics of diffraction fringe patterns, a segmentation mask window-based diffraction fringe center of gravity extraction method is proposed, and a zero-phase Butterworth low-pass filter is designed and applied to the diffraction light intensity curves to accurately extract the extreme points positions of the adjacent dark fringe and calculate the diameter information. Finally, the non-contact chemical fiber filaments appearance diameter online inspection experiment platform is built to carry out static and dynamic experiments of filaments. The experimental results show that the maximum absolute value of absolute error is less than 1.1 μm for static measurement and less than 10 μm for dynamic measurement.

Computer vision for hunting stability inspection of high-speed trains

The existing online inspection methods for hunting motion of high-speed trains are mainly based on processing the acceleration of bogie frames, which cannot directly and reliably reflect the safety conditions. This paper proposes a novel computer vision (CV) method, named the virtual point tracking (VPT) method, to detect the hunting motion by processing the dynamic wheel-rail contact video. First, some virtual points are defined on each frame of the captured video, then the coordinates of these virtual points are automatically located by a deep learning model, and finally, the relative displacement between these coordinates is calculated. Two experiments demonstrate that the VPT method can accurately determine the hunting frequency and detect changes in the pixel coordinates corresponding to key positions of the wheel and the rail. Besides, a VPT method with Canny edge detection is introduced for comparison, and the results demonstrate that the VPT method is superior.

Online optical inspection of electrolytic copper plate based on digital moiré

The application of automatic inspection plays an important role in improving the quality of industrial products. Aiming at nodules on the surface of electrolytic copper plate, this article introduces a comprehensive optical online inspection method. In order to obtain dynamic information of product and overcome the interference of random factors such as large-curvature deformation, position deviation and tilt, the system integrates a variety of single technologies including digital moiré, image recognition and spatial transformation. The online test results show that the system can effectively extract the information of nodules and automatically classify the products according to the set threshold.

Ultra-fast laser ultrasonic imaging method for online inspection of metal additive manufacturing

In this paper, an ultra-fast laser ultrasonic imaging method is proposed to provide an efficient online monitoring of additive manufacturing (AM) processing. The innovations of the proposed ultrafast imaging method in this research mainly include two parts. Firstly, multi-circle combined scanning strategy and defect location algorithm is constructed to improve the detection efficiency. Secondly, a surface wave focusing algorithm (SWFA) is established to solve the problem of low SNR induced by rough surface signals. The AM samples containing four types of surface and inner defects are designed and manufactured to verify the detectability and quantitative accuracy of the proposed method. Systematically comparisons between our proposed method with the traditional laser ultrasonic imaging are also discussed. The result indicated that the proposed ultra-fast imaging method is efficient for detecting the surface and sub-surface defects in the condition of low SNR caused by rough surface of AM components. The minimum detectable defect reaches 0.1 mm and the quantitative error could low down to 6.46% when the defect size is larger than 0.2 mm. Compared with the C-scan imaging method, the method proposed in this paper can improve the scanning efficiency of single-layer inspection by more than 300%, which is meaningful to improve the efficiency of metal additive manufacturing.

An on-line inspection method for abrasive distribution uniformity of electroplated diamond wire saw

Electroplated diamond wire saws are widely used in the field of slicing hard and brittle materials. The slicing quality and efficiency are directly affected by the abrasive distribution uniformity of the wire saw. At present, the abrasive distribution uniformity can only be qualitatively analyzed manually. In this paper, the expanded circumferential surface image of the wire saw is obtained by the method of cylindrical unwrapping and image stitching. Then the image is segmented by the Voronoi diagram. On this basis, the quantitative characterization and the online inspection method of the abrasive distribution uniformity are proposed. Finally, the real-time performance of the method is tested through experiments. The results show that under the hardware environment of this paper, this method takes 0.156 s to detect a sampling point, which meets the online detection requirements of the wire saw.

Shaft system profile reconstruction method based on L-shaped axial four-probe method

The inability to extract spatial axis and radial multi-error coupling phenomenon exists in the process of axial profile reconstruction, which is essentially a first harmonic suppression problem as well as a multi-error decoupling problem. In this paper, a four-probe system is constructed based on an L-shaped arrangement in two adjacent planes. First, the mathematical model of the first harmonic suppression problem of the shaft system is established in the first plane, and the first harmonic component of roundness error is used as the axial reference for reconstructing the profile, and the value of the first-order harmonic component is solved by theoretical derivation, and the spatial axis of the reconstructed shaft system profile is fitted with it, which proves the correctness of the established mathematical model by the data simulation. Then, the radial mixed error detection is carried out in two adjacent planes in the axial direction, and the results measured at the two measurement positions are analyzed theoretically to obtain the tilt error decoupling formula. It breaks through the limitation that the error separation online detection cannot be performed in the standard ball measurement method. The experiment verifies that the accuracy of the spatial axis is improved by up to 0.5 μm after decoupling the tilt error, and the accuracy of the reconstructed circularity profile of a single section is improved by up to 2.657 mm. In the comparison experiment with the standard ball measurement method, the difference of the measured roundness error between the two methods does not exceed 1.2 μm, which proves that the online inspection method proposed in this paper can guarantee the accuracy of the reconstructing circularity profile.

Automated Product Inspection in Industry 4.0 Environment

The emergence of Industry 4.0 technologies demands new techniques of measurement which would facilitate seamless integration with other devices in the wireless IoT network. Many of the existing product inspection methods cannot be deployed directly in the IoT environment. Thus, there is a need for innovative inspection techniques in the Industry 4.0 environment. In this context, the proposed inspection technique assumes special significance. Surface irregularities observed in product manufacturing can be due to chatter, vibration, worn-out cutting tools, condition of the machine tools, etc. Evaluation of surface texture helps in predicting a product’s functionality. In this work, an attempt has been made to identify the surface texture images acquired from Shaping, Milling, Electric discharge machining (E.D.M.) and Sand Blasting processes during online inspection. In addition to surface texture identification, the proposed method will also measure surface roughness and component dimensions. Thus, entire product inspection can be done online, and in a single setup. This is also an 100% online inspection method. The main contribution of this proposed research work is that all types of inspection are completed in a single set up, resulting in significant savings.

Laser ultrasonic imaging for defect detection on metal additive manufacturing components with rough surfaces.

Defects or discontinuities are inevitable during the melting and consolidation process of metal additive manufacturing. Online inspection of microdefects during the processing of layer-by-layer fusion is urgently needed for quality control. In this study, the laser ultrasonic C-scan imaging system is established to detect the surface defects of selective laser melting (SLM) samples that have a different surface roughness. An autosizing method based on the maximum correlation coefficient and lag time is proposed to accurately measure the defect length. The influences of the surface roughness on the laser ultrasound signal-to-noise ratio distribution and defect sizing accuracy are also studied. The results indicate that the proposed system can detect notches with a depth of 50 µm and holes with a diameter of 50 µm, comparable in size to raw powder particles. The average error for the length measurement can reach 1.5% if the notch is larger than 2 mm. Meanwhile, the sizing error of a 1 mm length notch is about 9%. In addition, there is no need to remove the rough surface of the as-built SLM samples during the detection process. Hence, we propose that the laser ultrasonic imaging system is a potential method for online inspection of metal additive manufacturing.

Online dimensional control of rolled steel profiles using projected fringes

Fringe projection is a versatile method for mapping the topography of surfaces. In this paper, it is used to measure the defects on the head of railroad rails while the rails are moving. Railroad rails are made by hot rolling. The quality of the finished product is generally good, but surface texture will deteriorate with increasing temperature. A method for online inspection therefore is very desirable. In the present experiment, dimensional inspection of the railroad rails was made online while moving at a speed of 1–2 m/s. Therefore, it is important to minimize the registration time. To achieve this, we apply a method of fringe location with sub-pixel accuracy that requires only a single exposure for each registration.

Online Inspection Method of Defect Dimension of Stainless Steel Precision Blanking Sheet Contour

In this study, a new method of online inspection of contour defects is proposed for stainless steel precision blanking sheet to address problems in the use of the current method to obtain detect information: the recognition system is complex, and the measurement error of defect dimension is large. The images of defect blanking sheet are obtained by the established image collection system. The results of image analysis show that the defect contour of blanking sheet has the correspondence and similarity characteristics. An improved sequential similarity detection algorithm and the measurement algorithm are developed. The measurement experiments show that the online inspection system is stable and reliable, and the maximum measurement error is 0.0362mm. The results of this study will lay a foundation for the online inspection of precision machining.

Optic flaws detection and location based on a plenoptic camera

In this Letter, we propose an on-line inspection method based on a plenoptic camera to detect and locate flaws of optics. Specifically, due to the extended depth of field of the plenoptic camera, a series of optics can be inspected efficiently and simultaneously. Moreover, the depth estimation capability of the plenoptic camera allows for locating flaws while detecting them. Besides, the detection and location can be implemented with a single snapshot of the plenoptic camera. Consequently, this method provides us with the opportunity to reduce the cost of time and labor of inspection and remove the flaw optics, which may lead to performance degradation of optical systems.

Non-Destructive Inspection of Insects in Chocolate Using near Infrared Multispectral Imaging

Foreign matters in food products strongly affect the commercial viability of food production companies. To monitor and improve the reliability of food production processes, fast and non-destructive online inspection methods are urgently required. In this study, we exploited the high transmittance of near infrared (NIR) light, and designed an NIR transmission-type imaging device that detects low-density foreign matters (such as insects) inside chocolate. Insect parts had consistently lower transmittance than chocolate parts. To enhance the important differences between the two parts, the images were processed using principal component analysis. Furthermore, an algorithm for detecting the insect parts was developed in conjunction with image threshold processing and Laplacian of Gaussian edge detection. A favourable detection rate (93%) was achieved using spectral regions 840–870 nm, 870–900 nm and 900–930 nm. The results suggested that NIR multispectral imaging is useful for detecting low-density matter (insects) in the chocolate manufacturing industry.

Thermographic, ultrasonic and optical methods: A new dimension in veneered wood diagnostics

Modern production techniques in the wood-based industry reached a high quality standard at high output rates. While the speed of the production machines increases, it is necessary to introduce modern and faster working online inspection methods to supervise constantly the material for defects. For example, thermographic cameras are able to detect not only invisible defects within wood-based materials like laminated particle and fiberboards, but can be used also to detect defects in lumber and veneered wood [1–4]. In the latter case, there is the need to inspect more accurately the final pieces, given the exponential growth in worldwide sales. Therefore, in order to minimize adhesion problems [5], detecting surface and sub-surface cracks, define the geometry of the sub-surface detachment, in the veneered wood products, an integrated non-destructive test method is needed both during the production process that after to it [6]. Our system can provide a continuous control of the process and the product. In fact, this study compares the performance of transient thermography, three optical methods and ultrasonic testing applied together on a veneered wood sample with real and fabricated defects. The use of phase-shifting holography correlated to Double-Exposure HI and the wavelet transform applied as fusion of images between Thermographic Signal Reconstruction and Double-Exposure HI, are explored in this work.

基于双目立体视觉的图像面积测量算法与技术<br>Algorithm and Technology of Image Area Measurement Based on Binocular Stereo Vision

本文基于双目立体视觉测距原理，用普通的USB摄像头搭建双目立体视觉系统，提出了图像面积的非接触在线测量方法。首先对摄像头进行标定，得到摄像头的内参数，然后根据OpenCV的模板匹配算法，求出两幅图像中对应匹配点的水平视差，得到距离参数，最后根据平行双目视觉的成像原理，求得实际图像与其在成像平面上的图像之间的空间几何关系，进而求出图像的实际面积。该方法实现简单、成本低、实时性好。经过实验验证，该算法在一定测量范围内达到精度要求。 A binocular stereo vision system with a common USB camera is developed based on the distance measurement principle of binocular stereo vision, and the non-contact and on-line inspection method for the area of image is studied. First, we calibrate the camera and obtain the internal parameters of the camera. Second, horizontal parallax of the cor- responding points in two images is calculated by template matching based on OpenCV, and then the distance parameter is obtained. Finally, we find the spatial geometrical relationship between the image of the imaging plane and the actual image, and then the actual area of image is gotten. This method is easy to realize with low cost and real-time perform- ance. The experiment indicates that the algorithm meets the accuracy requirements within certain range of measurement.

Error Analysis of Machining Accuracy of Free-form Surfaces Using On-line Inspection Method

In this paper error sources existing in the on-line inspection system for numerical control machines are analyzed. A mathematical model of the geometric errors of a three-axis machining center is created and the pretravel variations are obtained in different directions. Then an error compensation is applied to improve the accuracy of the on-line inspection system. A methodology of spatial statistical analysis of machining errors for free-form surfaces is proposed. Through the on-line inspection of a machined workpiece, the measured points and their machining errors are obtained. By analysis of these machining errors using the spatial statistical analysis, the machining errors are decomposed into systematic errors and random errors, which will provide the basis for machining error compensation during the subsequent process. DOI: http://dx.doi.org/10.11591/telkomnika.v10i8.1969 Full Text: PDF