Appearance Inspection Research Articles

Evaluation of Quality for Flow Drill Screw (FDS) Joining Process Based on Loosening Torque

Although the SPR process is widely used for joining of multi-materials, the FDS process is used when one-way joining is required, such as space constraints or closed cross-sectional parts. The quality inspection for the FDS process is basically an appearance inspection or cross-sectional inspection. There is no non-destructive test method that can be used in the actual mass production line, and a method of utilizing loosening torque is being studied. In this study, the factors affecting the loosening torque are analyzed, and an experimental equation that can predict the loosening torque is derived. Since friction force between the screw and the upper plate and sticking on the screw thread resist against loosening torque, the prediction equation for each factor is considered and the least square method is used to obtain the coefficients of the experimental equation. The prediction equation of the loosening torque derived through experiments on 36 material combinations predicts the experimental values well. When a quality requirement value with a given margin is applied, it can be used as a non-destructive test method.

Appearance Inspection and Finite Element Analysis of Posttension Concrete Horizontal Curved Box Girder Bridge: Static and Dynamic Analysis

Appearance Inspection and Finite Element Analysis of Posttension Concrete Horizontal Curved Box Girder Bridge: Static and Dynamic Analysis

Chip Appearance Inspection Using Machine Learning Techniques

In recent years, the increasing demand for chips has put forward higher requirements for chip production quality and production efficiency. After the chip manufacturing is completed before leaving the factory, it needs to be detected after packaging, which makes the development of chip detection and localization system difficult due to the small size and large number of chips and the high precision requirements for them. Therefore, this paper aims to design a fast, highprecision chip detection and positioning system for the positioning and detection needs of the chip packaging process, the chip detection and positioning system for in-depth research, to achieve the accurate positioning of the chip as well as the deformation produced by the detection of the main work is as follows: the first chapter is mainly about why this paper is mainly aimed at discovering the problems in the chip packaging process. The second chapter is about how to take pictures of the chip. Chapter 3 focuses on the pre-processing of the pictures. Chapter 4 focuses on determining whether the chip is deformed through different machine learning and deep learning techniques. Finally, the conclusion section summarizes the whole paper.

Development of a Short-Term Embolic Agent Based on Cilastatin for Articular Microvessels.

Background and Objectives: This study aimed to develop an embolic agent with short-term embolic effects using cilastatin as the basic material. Materials and Methods: The particle size distribution of 25 mg cilastatin-based short-term embolic agents was evaluated microscopically under three different mixing conditions. A total of thirty-six healthy male Sprague Dawley rats were divided into four groups. Each group of six rats was injected once into the tail artery with 0.4 mL each of (A) Cilastatin + D-Mannitol Mixture, (B) Iohexol, (C) Prepenem, and (D) embolization promoter (EGgel). Results: A visual inspection of the tail appearance of rats in each group was performed at 0, 3, 7, 15, and 21 days. At weeks 1 and 3, three rats per group were euthanized, and histopathological analyses were performed on the specimens obtained from each group. No significant differences were observed on day 7, but mild inflammation was observed in Group (D) on day 15. Histopathological inflammation scoring of tail central artery embolization was performed using a six-point scale (from 0 = absent to 5 = marked inflammation). Three groups were formed consisting of six male New Zealand white rabbits each: control, positive control, and test groups. The control group received an Iohexol injection (rabbits: 0.8 mL). The positive control and experimental groups were injected with prepenem and cilastatin/D-mannitol compound, respectively (0.8 mL), and vascular angiography was performed. The order of occlusion progression after embolization was as follows: test group, positive control group, and control group. Conclusions: We developed a cilastatin/D-mannitol compound that exhibits characteristics of short-term embolization by utilizing the pharmacokinetic properties of cilastatin and the crystalline material D-mannitol. We evaluated its particle size distribution microscopically, conducted histopathological evaluation including inflammation via animal experiments, and assessed the embolization effect.

A Tobacco Brand Recognition Method Based on HOG and SVM

The appearance inspection system cannot automatically switch the brand, and a person needs to log into the system and manually switch the inspection brand in the process of production and brand change. To address this problem, a deep learning-based automatic cigarette brand recognition method is developed and validated. Experiments show that: the system can automatically detect the production brand, effectively save the time to change the brand, and has important reference significance for the application in the field of brand identification and automatic switching detection of the brand.

A light-weight defect detection model for capacitor appearance based on the Yolov5

As one of the most important electronic components, capacitors are very important for appearance inspection in the production process. However, the current production process mainly relies on manual inspection, which not only reduces product quality and production efficiency but also increases production costs. The automated detection is limited by the computational resources of the equipment, which is difficult to apply in practice. Therefore, in this paper, we propose a lightweight method for capacitor appearance inspection. We use the YOLOv5 (You Only Look Once Version 5) framework, MobileNet as the backbone network, and GSConv (Ghost convolution) and GSCSP module as the neck depth compression network model to reduce the computational cost. In addition, we incorporate the CBAM (Convolutional Block Attention Module) into the backbone network to improve the network's ability to extract features. For the problem of difficult detection of small targets, we use CIoU (Complete Intersection Union) and NWD (Normalised Gaussian Wasserstein Distance) to design a new loss function. By testing our method on capacitor appearance defect data, compared to the baseline, the model computational cost FLOPs was reduced by 130 %, the model size was reduced by 94 %, the accuracy reached 92.5 %, and the mAP (mean average precision) reached 92.3 %, while the number of frames detected per second was up to 58 frames. The experimental results show that our method is capable of real-time detection of capacitor appearance defects, providing strong theoretical support for practical applications.

Analysis of Bridge Inspection Technology for Highway Reconstruction and Expansion

This article focuses on bridge testing technologies in highway construction and expansion projects. It provides an overview of the inspection process for bridges in highway reconstruction and expansion projects, the main inspections, and strategies for improving the quality of inspections. Relevant units should conduct bridge inspections using appearance inspections, special inspections, and bearing capacity assessments in highway reconstruction and expansion projects. To effectively improve testing quality, relevant units should also focus on establishing and improving testing standards, strengthening material testing, and improving the overall quality of the testing personnel. This research aims to enhance the quality of highway reconstruction and expansion projects by supporting the sensible application of bridge inspection technology.

Safety–Function–Environment Evaluation System for Large-Span Cable-Supported Bridges: Theory and Case Studies

Compared with common bridges, large-span cable-supported bridges contain more components, are located in a more complex environment, and play a more important role in traffic system sustainability. Throughout the service life, it is more necessary to evaluate their safety, functionality, and environmental status. In this study, a comprehensive evaluation system is proposed to fill the gap using advanced sensor-guided structural health monitoring data and probability-based digital twins. Safety evaluation is the basis of the system and can be divided into overall and component levels. The former includes an over-limit analysis of main structural responses and degradation identification of dynamic characteristics. The abnormal areas discovered in this phase and the hot spots prompted by prior information during the design process will be checked in the latter. The functional assessment of this system is mainly based on checklist-type inspection and is often carried out together with appearance inspection and non-main structural component detection. Environmental assessment includes the monitoring and analysis of wind fields, temperature, humidity, foundation scour, and traffic flow and is the source of external information in the aforementioned two modules. The temperature and humidity of the example bridges are basically uniformly distributed along the spatial dimension, fluctuating over a period of one day.

Performance verification and latency time evaluation of hardware image processing module for appearance inspection systems using FPGA

Performance verification and latency time evaluation of hardware image processing module for appearance inspection systems using FPGA

機械学習による外観検査のためのGANと切り貼り手法を組合せた画像生成に関する検討

機械学習による外観検査のためのGANと切り貼り手法を組合せた画像生成に関する検討

Experimental Study and Mechanism Analysis of Composite Insulator Chalking in Extra-High Voltage (EHV) Transmission Line

The chalking of composite insulators is referred to a kind of abnormal aging of the silicone rubber sheds. It has serious adverse effects on the long-term operation of the insulators, but the mechanism behind its generation and development remains unclear. In order to deeply understand the phenomenon of composite insulator chalking, this paper took chalked composite insulators operating on extra-high voltage (EHV) AC 500 kV as samples for research. Appearance inspection, hydrophobicity test and tensile stress test were performed on the samples to determine the change of their surface properties after chalking. It is found that a layer of white powder was formed on the surface of the sheds, the hydrophobicity level of which come to a range from HC1 to HC4, and the tensile stress tolerance and mechanical strength of the silicone rubber decreased significantly. Further, XPS analysis, FTIR detection, and TG analysis were carried out to explore the microscopic process inside the material during its chalking. The results show that the oxidation reaction of Si-C bond transforms the composition of silicone rubber, bringing damage to its apparent performance; the generation of strong polar groups such as –C=O group is the main reason for the decrease in the flexibility of the silicone rubber structure and then the formation of a powdered layer; and above all, the chalking process is based on a series of chemical decomposition reactions, in which the decomposition of polydimethylsiloxane (PDMS) as silicone rubber matrix plays a predominant role, and the decomposition of aluminum hydroxide (ATH) serves as a secondary.

STUDY ON THE ACCELERATED CORROSION BEHAVIOR OF A GALVANIZED X80 PIPELINE STEEL WELDED JOINT DURING A CYCLIC SALT SPRAY TEST

The corrosion behavior of galvanized X80 pipeline steel welded joints in a marine atmospheric environment was studied using the cyclic salt spray accelerated corrosion test. The corrosion weight loss, corrosion morphology and corrosion products of samples under different cycles were characterized by means of appearance inspection, SEM and EDS. The results show that with the rupture of the galvanized layer, cracks first appear when the weld metal is exposed for eight days. With the infiltration of the corrosive liquid, pitting pits first appear in the weld metal. In the early stage of corrosion in the heat-affected zone, the fracture degree of the zinc layer is more serious than that in the other two areas. The corrosion products of the zinc layer accumulate irregularly and more pits appear, resulting in early cracks and pitting pits in the later stage. Compared with the first two regions, the base metal shows better corrosion resistance.

Application Analysis of Artificial Intelligence Technology in Electrical Engineering Teaching

This article combines the characteristics of artificial intelligence technology and educational technology to realize the possibility of application in electrical automatic control systems, and applies artificial intelligence and educational technology to electrical engineering examples such as monitoring fire alarm open circuit design and smoke box appearance inspection in power transformation and distribution systems. Analyze the impact of artificial intelligence on electrical automation technology. The research results show that artificial intelligence and education can make electrical automation technology have the characteristics of simplification, distribution, informatization, diversity, flexibility, continuity, real-time and control complexity. Use artificial intelligence technology and educational technology to effectively analyze and process electrical engineering related parameters and data, reduce the use of lines and transformers, simplify work procedures, reduce error rates, save manpower, material resources and costs, and improve the accuracy of automatic control.

Experimental Testing and Residual Performance Evaluation of Existing Hangers with Steel Pipe Protection Taken from an In-Service Tied-Arch Bridge

Background: Tied-arch bridges’ hangers are crucial load-bearing parts, and their excellent condition directly influences bridge safety. However, assessing in-service hangers’ continuing functional performance is irrelevant and incomplete, particularly for unique hangers covered by outer steel tubes. Objective: This research uses a case study of an under-bearing tied-arch bridge with substantial hanger damage to determine the origin of the damage and analyze the hanger’s remaining operational ability. Methodology/approach: This study presents a set of assessment methodologies and procedures for in-service hangers’ remaining functioning performance using field inspection and indoor tests. First, an appearance inspection of the full bridge hanger’s upper and lower anchor heads was carried out, and the categories of anchor head damage and distribution rules are summarized. The causes of major water damage and the lower anchor head’s water infiltration channel were explored. Then, a full interior test was performed on the disassembled sick hanger to establish its present mechanical qualities. Finally, field inspection and indoor test findings assessed the bridge hanger’s operational performance. The findings suggest that the anchor box drainage prevention system should be improved to prevent rainfall and condensation from pooling in the lower anchor box and causing anticorrosive grease failure and anchor head corrosion. Results: The hanger’s mechanical qualities have deteriorated and no longer meet usage standards. Most of the water accumulated in the anchor head of the conventional construction hanger enters from the bridge deck or rope surface, but because of the outer steel pipe, rainwater can flow into the lower anchor box through the upper anchor box along the gap between the hanger and the outer steel pipe, so the waterproof system of the upper anchor box should be checked. Conclusions: This research may be used for safety evaluation and maintenance of the same hanger in service.

Analysis of cracking characteristics and mechanism of high-strength steel after chemical oxidation

The tooth surface of the 20CrNi2Mo worm underwent cracking after chemical oxidation. The appearance inspection results showed that there were multiple cracks on the tooth surface of the worm slice, and the direction of the cracks was perpendicular to the machining pattern. There were many microcracks on both sides of the main crack. The profile morphology shows that the crack depth reaches 1100 μm. The crack extends perpendicular to the tooth surface to a certain depth and then propagates in two transverse directions. After opening the crack on the tooth surface, observation shows that the overall section is black, and the artificially opened area is silver-white. At the interface between the artificially opened area and the initial fracture surface, the fracture surface changes from intergranular morphology to ductile dimple morphology. The energy spectrum shows that the oxygen content in the intergranular cracking area is much higher than that in the ductile dimple area, indicating that the worm has undergone intergranular corrosion cracking. After the worm tooth surface is ground, there will be certain tensile stress on the surface. During the chemical oxidation process, the worm will be exposed to many corrosive media such as OH−, and NO2 −. Under the combined action of tensile stress and corrosive ions, the tooth surface will undergo stress corrosion cracking. To effectively avoid cracking on the worm gear surface, three measures have been proposed to reduce the risk of cracking: (1) improving machining parameters to reduce grinding feed, (2) increasing destressing before chemical oxidation to reduce residual tensile stress, (3) improving chemical oxidation process to reduce solution concentration, treatment time, and treatment temperature.

Current Situation Analysis for the Integration and Detection Methods of the Primary and Secondary Switch

The distribution equipment is core to intelligent distribution and directly determines the reliable operation of distribution networks. The primary and secondary integrated switchgear is an integration of the traditional primary switch, sensor, and secondary controlling terminal. It is influenced by temperature, pressure, electromagnetic interference, etc. To guarantee the quality of the primary and secondary integrated switchgear which is accessed to the power grid, the inspection outline of the primary and secondary integrated switchgear in the State Power Grid includes the structure and configuration, appearance inspection, insulation resistance test, power frequency voltage withstand test, and lightning impulse test.

Environment-friendly, efficient process for mechanical recovery of waste lithium iron phosphate batteries.

Technology for recycling retired lithium batteries has become increasingly environment-friendly and efficient. In traditional recovery methods, pyrometallurgy or hydrometallurgy is often used as an auxiliary treatment method, which results in secondary pollution and increases the cost of harmless treatment. In this article, a new method for combined mechanical recycling of waste lithium iron phosphate (LFP) batteries is proposed to realize the classification and recycling of materials. Appearance inspections and performance tests were conducted on 1000 retired LFP batteries. After discharging and disassembling the defective batteries, the physical structure of the cathode binder was destroyed under ball-milling cycle stress, and the electrode material and metal foil were separated using ultrasonic cleaning technology. After treating the anode sheet with 100 W of ultrasonic power for 2 minutes, the anode material was completely stripped from the copper foil, and no cross-contamination between the copper foil and graphite was observed. After the cathode plate was ball-milled for 60 seconds with an abrasive particle size of 20 mm and then ultrasonically treated for 20 minutes with a power of 300 W, the stripping rate of the cathode material reached 99.0%, and the purities of the aluminium foil and LFP reached 100% and 98.1%, respectively.

Spacecraft Matrix Cable Assembly Process Research

The matrix calbe can effectively realize lightweight and high reliability of spacecraft cable network. This paper focus on the assembly process of matrix cable which has multi-line characteristics, introduce the assembly process and related parameters. The result was verified by appearance inspection, tensile test, voltage drop test and metallographic experiment. Make sure that the assemble process of the cable is high quality and reliability.

IDDM: An incremental dual-network detection model for in-situ inspection of large-scale complex product

Appearance inspection is crucial for quality control during the manufacturing of large complex products. In-situ visual inspection based on image processing and machine learning can significantly reduce the production costs by avoiding the stages of transshipment and relocation, etc. However, imaging and model training are challenged by the complex background, illuminance, and changing environment of the production site. In addition, large dataset is hard to be obtained with object-level annotations owing to the high cost of manual annotation in practical situations. In this paper, we proposed an Incremental Dual network Detection Model (IDDM) for efficient and high-precision inspection of the appearance of large complex product base on in-situ images. A dual network structure is used to implement the incremental training of the model based on metric learning and batch labeling of unlabeled data during the training on a small number of well-labeled samples. The regions of interest are extracted based on multi-feature and refined to improve the positional accuracy of the defects in complex background. On the public dataset, the experimental results derived on various annotation scales showed a better performance of the proposed IDDM compared to the supervised object-detection baselines. The mean Average Precision (mAP) was 51.8% with a 25% labeled ratio and the processing speed was 22 frames per second (FPS). In addition, the proposed method was applied to the defect detection of the snow groomer surface as an industrial case.

SSD-Based Carton Packaging Quality Defect Detection System for the Logistics Supply Chain

Abstract With the deepening of green and sustainable development and the rapid development of the social economy, the modern logistics industry has also developed to an unprecedented level. In the logistics supply chain, due to the high value of the items inside the arrival carton, appearance inspection must be carried out before warehousing. However, manual inspection is slow and ineffective, resulting in the waste of manpower and packaging carton resources, which is not conducive to sustainable development. To address the above problems, this paper designs a logistics supply chain carton packaging quality defect detection system based on improved Single Shot MultiBox Detector (SSD) in the context of green sustainable development. The Implicit Feature Pyramid Network (IFPN) is introduced into SSD to improve the feature extraction ability of the model; the multiscale attention mechanism is introduced to collect more feature information. The experiment shows that the mAP and FPS of the system on the self-built data set reach 0.9662 and 36 respectively, which can realise the detection of the appearance defects of logistics cartons and help promote green sustainable development.