Inspection Model Research Articles

Classification and rating of steel scrap using deep learning

To address the issues of high human interference and low efficiency in traditional manual methods for classifying and rating steel scrap, we propose the development of CSBFNet, a deep learning-based model for multi-category steel scrap classification and rating. Firstly, we built a 1:3 physical model of steel scrap quality inspection to simulate the unloading of a truck. We used a high-resolution vision sensor to capture the morphological characteristics of various steel scraps. Next, we trained the CSBFNet model using this data to obtain characteristic information for classifying and judging various types of scrap steel. Finally, we tested and improved the CSBFNet model at a Chinese steel mill. The results demonstrate that the model can effectively determine the automatic rating for different grades of scrap. The average accuracy rate of all types of steel scrap reaches 92.4% for the full category, with an mAP of 90.7%. Compared to traditional artificial quality detection methods, it has clear advantages in accuracy and fairness. This model solves the problem of evaluating the quality of steel scrap in the recycling process.

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.

The environmental quality inspection model of the construction of sea crossing bridges with based on the evolutionary game theory

In order to reduce the impact of sea crossing bridge construction on the environment, it is necessary to adopt the method of multi-party supervision to detect the environmental quality in the construction process. Therefore, this paper constructs an environmental quality inspection model of cross-bridge construction based on evolutionary game theory. The model includes the physical means detection model between the government, the public, and construction enterprises and the tripartite evolutionary game supervision model. A reasonable test method is chosen according to the actual situation, game monitoring on the environmental quality of bridge construction is conducted, and the monitoring points are carefully arranged. Finally, the government needs to improve the basic system of pollution management, put forward effective supervision strategies, strengthen supervision measures, establish a pollution evaluation system, and punish enterprises that do not actively control pollution. The construction environmental quality of the sea crossing bridge is obtained through the actual detection, and the supervision improvement strategy is analyzed through the game model.

A domain adaptation YOLOv5 model for industrial defect inspection

In the process of industrial production, manufactured products are prone to surface defects for a variety of reasons. To overcome the problem of high time cost and the strong demand for large sample data sets, a detector based on transfer learning is commonly utilized. In this paper, a domain adaptation YOLOv5 model, named DAYOLOv5, is proposed for automatic surface defect inspection. The hyperparameter α in DAYOLOv5 for knowledge transfer can be designed specially to achieve better generalization in real-world industrial applications. Meanwhile, in the field of magnetic tile surface defect detection, our DAYOLOv5 outperforms traditional mixed training and pretrain-finetune methods with limited data sets and has great robustness. Overall, the experimental results demonstrate that our DAYOLOv5 model can indeed boost performance on small-scale target data sets and is applicable to practical industrial scenarios.

UAV Aerial Image Generation of Crucial Components of High-Voltage Transmission Lines Based on Multi-Level Generative Adversarial Network

With the aim of improving the image quality of the crucial components of transmission lines taken by unmanned aerial vehicles (UAV), a priori work on the defective fault location of high-voltage transmission lines has attracted great attention from researchers in the UAV field. In recent years, generative adversarial nets (GAN) have achieved good results in image generation tasks. However, the generation of high-resolution images with rich semantic details from complex backgrounds is still challenging. Therefore, we propose a novel GANs-based image generation model to be used for the critical components of power lines. However, to solve the problems related to image backgrounds in public data sets, considering that the image background of the common data set CPLID (Chinese Power Line Insulator Dataset) is simple. However, it cannot fully reflect the complex environments of transmission line images; therefore, we established an image data set named “KCIGD” (The Key Component Image Generation Dataset), which can be used for model training. CFM-GAN (GAN networks based on coarse–fine-grained generators and multiscale discriminators) can generate the images of the critical components of transmission lines with rich semantic details and high resolutions. CFM-GAN can provide high-quality image inputs for transmission line fault detection and line inspection models to guarantee the safe operation of power systems. Additionally, we can use these high-quality images to expand the data set. In addition, CFM-GAN consists of two generators and multiple discriminators, which can be flexibly applied to image generation tasks in other scenarios. We introduce a penalty mechanism-related Monte Carlo search (MCS) approach in the CFM-GAN model to introduce more semantic details in the generated images. Moreover, we presented a multiscale discriminator structure according to the multitask learning mechanisms to effectively enhance the quality of the generated images. Eventually, the experiments using the CFM-GAN model on the KCIGD dataset and the publicly available CPLID indicated that the model used in this work outperformed existing mainstream models in improving image resolution and quality.

Automated crack detection and crack depth prediction for reinforced concrete structures using deep learning

Automatic inspection for crack detection and estimation of the crack depth is critical in assessing the damage and determining the appropriate method of repair in concrete structures. Most of the studies which have employed deep learning models for automatic inspection are limited to the detection and estimation of the width, length, area, and direction of cracks. The innovation of this study lies in developing a comprehensive automated crack detection and crack depth evaluation framework for concrete structures using images taken from portable devices. Firstly, a binary-class Convolutional Neural Network (CNN) model was developed to automatically detect the cracks on a concrete surface. Secondly, an integrated CNN model combining the convolutional feature extraction layers and regression models (RF and XGBoost) was developed to automatically predict the depth of the cracks. The proposed framework has been validated on a reinforced concrete (RC) slab. Results indicate the models are accurate and reliable for automated inspection of the cracks which could help in evaluating the condition of a concrete structure and choosing suitable repair methods.

Exploring customers’ perceptions of food adulteration at bazaars and supermarkets in Dhaka, Bangladesh; a qualitative exploration

BackgroundFood adulteration is an increasingly recognized global public health problem. In low- and middle-income countries like Bangladesh, adulteration is difficult to detect and respond to. We explored customers’ perceptions on food adulteration, perception of risk and connections between information, participant characteristics and patterns of adulterated food concerns that impact risk perception in urban Bangladesh.MethodsA formative study was conducted in Dhaka, between June and August 2015 at a supermarket and a wet market. We explored community awareness and response to chemical contaminants (adulterants) among participants from a range of socio-economic backgrounds. The team conducted 38 in-depth interviews with 12 customers and 4 staff from a supermarket, and 12 customers and 10 vendors from a wet market. Participants were selected purposively. Audio recorded data were coded based on thematic content and analyzed manually.ResultsWe asked participants how common foods were likely adulterated, and most gave figures of 70% or more. They reported that foods were adulterated with chemicals or artificial colors, especially fish, milk, and vegetables. The supermarket more commonly sold packaged foods with nutritional and expiry information on the label; and offered convenience in terms of building size, layout, and cleanliness. All customers from the wet market thought that foods were cheaper and fresher than from supermarkets. Supermarket customers expressed greater concern about adulterated foods than wet market customers. Most participants from both markets reported that food adulteration is invisible, adulterated foods cannot be avoided, and have long-term negative health impacts including cancer, diabetes, paralysis, heart attack, and others. Nearly half of customers from both markets were concerned about the poor nutritional value of adulterated food. Participants from both settings expressed the need for access to credible information about adulteration to help choose safe foods. The majority expressed the need for government action against those who are responsible for adulteration.ConclusionsFood adulteration was considered a major health threat. The government could act on food adulteration prevention if provided credible population-based data on disease burden, a model food sampling and testing protocol, a model for inspections, organizational strengthening and training, example social and behavioral change communications with estimated costs.

Sputum smears quality inspection using an ensemble feature extraction approach.

The diagnosis of tuberculosis (TB) is extremely important. Sputum smear microscopy is thought to be the best method available in terms of accessibility and ease of use in resource-constrained countries. In this paper, research was conducted to evaluate the effectiveness of tuberculosis diagnosis by examining, among other things, the underlying causes of sputum smear quality for Ethiopian states such as Tigray, Amahira, and Oromia. However, because it is done manually, it has its limitations. This study proposes a model for sputum smear quality inspection using an ensemble feature extraction approach. The dataset used was recorded and labeled by experts in a regional lab in Bahir Dar, near Felege Hiwot Hospital after being collected from Gabi Hospital, Felege Hiwot Hospital, Adit Clinic and Gondar Hospital, as well as Kidanemihret Clinic in Gondar. We used a controlled environment to reduce environmental influences and eliminate variation. All the data was collected using a smartphone (the standard 15) with a jpg file extension and a pixel resolution of 1,728 × 3,840. Prior to feature extraction, bicubic resizing, and ROI extraction using thresholding was performed. In addition, sequential Gaussian and Gabor filters were used for noise reduction, augmentation, and CLAHE was used for enhancement. For feature extraction, GLCM from the gray label and CNN from the color image were both chosen. Ultimately, when CNN, SVM, and KNN classifiers were used to test both CNN and GLCM features, KNN outperformed them all with scores of 87, 93, and 94% for GLCM, CNN, and a hybrid of CNN and GLCM, respectively. CNN with GLCM outperformed other methods by 0.7 and 0.1% for GLCM and CNN feature extractors using the same classifier, respectively. In addition, the KNN classifier with the combination of CNN and GLCM as feature extractors performed better than existing methods by 1.48%.

Two-stage game-theoretic model of inspection and embezzlement in a three-level control system

The subhierarchical two-stage game-theoretic model of embezzlement and bribery is designed, the particular example based on the scheme with six officials on three levels is solved. Theoretic conditions and numerical corruption minimization settings are suggested. The cooperative extension is proposed and the computer simulation is carried out for two different approaches to the isolated components, the results analyzed for stability.

A Surface Defect Inspection Model via Rich Feature Extraction and Residual-Based Progressive Integration CNN

Surface defect inspection is vital for the quality control of products and the fault diagnosis of equipment. Defect inspection remains challenging due to the low level of automation in some manufacturing plants and the difficulty in identifying defects. To improve the automation and intelligence levels of defect inspection, a CNN model is proposed for the high-precision defect inspection of USB components in the actual demands of factories. First, the defect inspection system was built, and a dataset named USB-SG, which contained five types of defects—dents, scratches, spots, stains, and normal—was established. The pixel-level defect ground-truth annotations were manually marked. This paper puts forward a CNN model for solving the problem of defect inspection tasks, and three strategies are proposed to improve the model’s performance. The proposed model is built based on the lightweight SqueezeNet network, and a rich feature extraction block is designed to capture semantic and detailed information. Residual-based progressive feature integration is proposed to fuse the extracted features, which can reduce the difficulty of model fine-tuning and improve the generalization ability. Finally, a multi-step deep supervision scheme is proposed to supervise the feature integration process. The experiments on the USB-SG dataset prove that the model proposed in this paper has better performance than that of other methods, and the running speed can meet the real-time demand, which has broad application prospects in the industrial inspection scene.

Comparative Analysis of the Models of Constitutional Review in Portugal and in Poland

The article critically analyses the models of the constitutionality inspection adopted in Portugal and in Poland. For this purpose the comparative method has been applied, comparing Portuguese and Polish approaches. Theoretical aspects of the constitutionality inspection are discussed and the notions of the centralised and the diffuse inspection model are introduced. Then the paper analysis the actual inspection practices in both countries discussing the diffuse and concentrated inspection separately. Constitutional rules pertaining to the direct effect of the constitutions, constitutional jurisdiction of judges and operation of the constitutional courts are considered. The article concludes that in both countries different models of constitutionality inspection operate. In Portugal operates the mixed constitutionality inspection model while in Poland, despite views advocating for permissibility of the diffuse control, the centralised model functions.

End-to-end point cloud-based segmentation of building members for automating dimensional quality control

A frequent and accurate quality inspection procedure to assess the quality requirements during the life cycle of buildings is crucial. Among different quality measures, the dimensional quality that involves spatial features of buildings is of significant importance. However, the traditional manual inspection of dimensional quality in buildings is unreliable and tedious. Thus, this study presents an end-to-end method for quality inspection of building structural members using point cloud datasets. The proposed method, first, detects and labels structural members within the point cloud based on a set of domain-specific geometric and semantic definitions. Then, each structural member's section width, height, and length are obtained with the proposed bounding box method. Experiments on three real-world buildings' point clouds with various geometric features and noise levels, occlusion, and outliers were also conducted, illustrating the performance efficiency and accuracy of the proposed model for dimensional quality inspection of building structural members.

TCS-YOLO model for global oil storage tank inspection

åŽŸæ²¹ä½œä¸ºä¸€ç§é‡è¦çš„æˆ˜ç•¥ç‰©èµ„ï¼Œåœ¨æˆ‘å›½ç»æµŽå’Œå†›äº‹ç­‰å¤šä¸ªé¢†åŸŸå‡èµ·åˆ°é‡è¦ä½œç”¨ã€‚æœ¬æ–‡æå‡ºä¸€ç§åŸºäºŽæ·±åº¦å­¦ä¹ çš„ç›®æ ‡æ£€æµ‹æ¨¡åž‹TCS-YOLO（Transformer-CBAM-SIoU YOLO），该模型在YOLOv5çš„åŸºç¡€ä¸Šè¿›è¡Œä¼˜åŒ–ï¼ŒåŒæ—¶åŸºäºŽå‰æž—ä¸€å·å ‰å­¦é¥æ„Ÿå«æ˜Ÿå½±åƒæ•°æ®é›†è¿›è¡Œå®žéªŒï¼Œå¯¹å ¨çƒèŒƒå›´å† çš„å‚¨æ²¹ç½è¿›è¡Œè¯†åˆ«ä¸Žåˆ†ç±»ã€‚ä¼˜åŒ–å† å®¹åŒ æ‹¬ï¼šæ·»åŠ åŸºäºŽTransformer架构的C3TR层对网络进行优化；使用CBAM（Convolutional Block Attention Moduleï¼‰åœ¨ç½‘ç»œå±‚ä¸­æ·»åŠ æ³¨æ„åŠ›æœºåˆ¶ï¼›ä½¿ç”¨SIoU（Scale-Sensitive Intersection over Union） loss代替CIoU（Complete Intersection over Union） loss作为定位损失函数。实验结果表明：与YOLOv5相比，TCS-YOLO的模型复杂度（Giga Floating Point of Operations，GFLOPs）平均减少3.13%，模型参数量（Parameters）平均减少0.88%，推理速度（Inference Speed）平均降低0.2 ms，mAP0.5（mean Average Precision）平均提升0.2%，mAP0.5∶0.95平均提升1.26%。与此同时，将TCS-YOLOæ¨¡åž‹ä¸Žé€šç”¨ç›®æ ‡è¯†åˆ«æ¨¡åž‹YOLOv3，YOLOv4，YOLOv5和Swin Transformer进行对比实验，TCS-YOLO均体现出了更高效的特点。TCS-YOLOæ¨¡åž‹å¯¹å ¨çƒå‚¨æ²¹ç½çš„ç›®æ ‡è¯†åˆ«å ·æœ‰é€šç”¨å¯è¡Œæ€§ï¼Œå¯ä¸ºé¥æ„Ÿæ•°æ®åœ¨èƒ½æºæœŸè´§é¢†åŸŸæä¾›æŠ€æœ¯å‚è€ƒã€‚

Stochastic optimization model for ship inspection planning under uncertainty in maritime transportation

<abstract><p>Maritime transportation plays a significant role in international trade and global supply chains. Ship navigation safety is the foundation of operating maritime business smoothly. Recently, more and more attention has been paid to marine environmental protection. To enhance maritime safety and reduce pollution in the marine environment, various regulations and conventions are proposed by international organizations and local governments. One of the most efficient ways of ensuring that the related requirements are complied with by ships is ship inspection by port state control (PSC). In the procedure of ship inspection, a critical issue for the port state is how to select ships of higher risk for inspection and how to optimally allocate the limited inspection resources to these ships. In this study, we adopt prediction and optimization approaches to address the above issues. We first predict the number of ship deficiencies based on a k nearest neighbor (kNN) model. Then, we propose three optimization models which aim for a trade-off between the reward for detected deficiencies and the human resource cost of ship inspection. Specifically, we first follow the predict-then-optimize framework and develop a deterministic optimization model. We also establish two stochastic optimization models where the distribution of ship deficiency number is estimated by the predictive prescription method and the global prescriptive analysis method, respectively. Furthermore, we conduct a case study using inspection data at the Hong Kong port to compare the performances of the three optimization models, from which we conclude that the predictive prescription model is more efficient and effective for this problem.</p></abstract>

Sailfish Optimizer with EfficientNet Model for Apple Leaf Disease Detection

Recent developments in digital cameras and electronic gadgets coupled with Machine Learning (ML) and Deep Learning (DL)-based automated apple leaf disease detection models are commonly employed as reasonable alternatives to traditional visual inspection models. In this background, the current paper devises an Effective Sailfish Optimizer with EfficientNet-based Apple Leaf disease detection (ESFO-EALD) model. The goal of the proposed ESFO-EALD technique is to identify the occurrence of plant leaf diseases automatically. In this scenario, Median Filtering (MF) approach is utilized to boost the quality of apple plant leaf images. Moreover, SFO with Kapur's entropy-based segmentation technique is also utilized for the identification of the affected plant region from test image. Furthermore, Adam optimizer with EfficientNet-based feature extraction and Spiking Neural Network (SNN)-based classification are employed to detect and classify the apple plant leaf images. A wide range of simulations was conducted to ensure the effective outcomes of ESFO-EALD technique on benchmark dataset. The results reported the supremacy of the proposed ESFO-EALD approach than the existing approaches.

MFCP-Net: Multiscale Feature Correlation Perception Network for Image Segmentation Based on Background Prior

Due to their exceptional capacity to extract features, methods based on deep learning have demonstrated good performance in industrial vision inspection applications. However, the generalizability and robustness of inspection models are challenged by factors such as insufficient data, great differences in data types, and complex illumination. To address these problems, multiscale feature correlation perception network (MFCP-Net), a semantic segmentation model with variable topology, is proposed to segment images with prior background. MFCP-Net uses a Siamese structure with shared weights to extract the multiscale features of the template and test images. A feature correlation perception (FCP) block is designed to measure the correlation of latent representation between the template and test images at multiscales, using background information more effectively. In addition, MFCP-Net provides different topological structures for the training and testing phases. A background auto-correlation branch is included during the testing phase to eliminate false positives observed in the background. MFCP-Net was compared with the state-of-the-art models on the proposed automobile instrument detection system, demonstrating that it offers superior accuracy and generalizability, especially in the case of insufficient data and big variances across data.

Quality Inspection Method of Agricultural Products Based on Image Processing

Farmers should provide high-quality agricultural products and companies should receive high-quality agricultural products, which is the purpose and pursuit of the business model of "companies plus farmers". In order to increase the stability of the cooperation mode between companies and farmers, it is necessary to detect the quality of agricultural products accurately, objectively and efficiently. Therefore, this article studies the quality inspection method of agricultural products based on image processing. Firstly, the traditional threshold calculation method and threshold function are improved to obtain more ideal denoising effect of agricultural products images. Aiming at the problem that the traditional image processing model cannot obtain fine-grained feature information of image objects, a multi-level feature dependence extraction network is constructed, and the structure and working principle of the network model are introduced in detail. Experimental results verify the effectiveness of the proposed algorithm and model for agricultural product quality inspection.

Real-Time Personal Protective Equipment Compliance Detection Based on Deep Learning Algorithm

The construction industry is one of the most dangerous industries in the world due to workers being vulnerable to accidents, injuries and even death. Therefore, how to effectively manage the appropriate usage of personal protective equipment (PPE) is an important research issue. In this study, deep learning is applied to the PPE inspection model to verify whether construction workers are equipped in accordance with the regulations, and this is expected to reduce the probability of related occupational disasters caused by the inappropriate use of PPE. The method is based on the YOLOv3, YOLOv4 and YOLOv7 algorithms to detect worker’s helmets and high-visibility vests from images or videos in real time. The model was trained on a new PPE dataset collected and organized by this study; the dataset contains 11,000 images and 88,725 labels. According to the test results, can achieve a 97% mean average precision (mAP) and 25 frames per second (FPS). The research result shows that the detection and counting data in this method have performed well and can be applied to the real-time PPE detection of workers at the construction job site.

Risk-based maintenance optimization of aircraft gas turbine engine component

The integrity of an aircraft gas turbine engine is critical for safety of flight. Although the reliability of engines has improved considerably, a large number of legacy engines continue to operate. The maintenance of legacy engines is a major burden for their operators owing to the high cost involved, and the engines pose a high risk to flight safety. In this study, we developed a comprehensive approach for risk-based maintenance optimization of aircraft engine components. The approach involved the use of a physics-informed data-driven model incorporated with the Weibayes model and a simple fatigue crack growth model. The crack length distribution and corresponding risks were evaluated using Bayesian updating and knowledge of nondestructive inspection reliability. The model was used for the computation of the fatigue reliability of the first-stage blisk of a CT7-9C turboprop engine. A single failure was used for the Weibayes analysis, and a master crack growth curve was obtained through quantitative-fractography-based crack growth analysis. Furthermore, an inspection model based on the evaluation of field inspectors was used to obtain the posterior crack length distribution, and through a sensitivity analysis, important factors were identified. Finally, optimal inspection and replacement plans were formulated using approximated objective and constraint functions. In particular, the life-cycle cost was minimized while maintaining the risks within strict limits.

Model of Critical Success Factors (CSFs) Influencing Food Inspection Management in UAE

Muslims abide by strict dietary regulations that specify that the foods must be Halal for the consumption by Muslims. Previous research has shown that there is no definite or appropriate model of Critical Success Factors (CSFs) related to halal food inspection. The success of a project is largely dependent on critical factors, which primarily track the project's development from the ground up (Ahsen et al. 2021). As a result, this study employed a quantitative approach to formulate a structural model of success factors that halal food authorities can use to optimise their inspection model, with a focus on training and development. The factors that affect/influence halal food inspection management, particularly when dealing with packaged food and halal certificates were identified through literature work. Questionnaire survey was conducted to collect data that was used in the formulation of the model. The Critical Success Factors (CSFs) model, which was created tested and validated using SEM-AMOS software. The model has seven constructs (independent variables) and one dependent variable of the management of halal food inspection, thus having seven hypotheses. It was discovered that five out of seven of the hypotheses are were supported. These findings aid in the discovery of new information to several parties like managers, employees with progressively less experience, and local and foreign halal food inspectors, as well as curriculum and infrastructure beliefs, and how these effects affect opportunities and motivation. The study contributes significantly to UAE and global research community.