Inspection Personnel Research Articles

A Study on the Establishment of a Standard for Calculating Optimal Number of Regular Inspection Personnel Considering Safety of Railway Employees

A Study on the Establishment of a Standard for Calculating Optimal Number of Regular Inspection Personnel Considering Safety of Railway Employees

Big administration reforms against Catholic reformist traditions: fusion of state and church mid-level school administrations in early nineteenth-century Prussian Silesia

ABSTRACT In what are often described as modern Western school systems, the supervision of elementary schools generally shifted from the hands of clerical administrators to genuine state officials during the nineteenth century. The Prussian state, like other predominantly Protestant states, relied on clerical personnel and church supervision structures to establish its school supervision administration. Yet, this was also true for the more Catholic parts of the Prussian monarchy, where integration of church structures into state administration caused friction between state and church authorities. Hence, this contribution focuses on appointments of school inspectors in early nineteenth-century Prussian Silesia, when friction arose between the state and the prince-bishop concerning appointment rights. These frictions are reflected in the process of newly introduced mid-level state school administrations taking over episcopal appointment rights, which has been described as a nationalisation or secularisation of Silesian school administration. The article proposes a more nuanced approach to the restructuring of Silesian school administration, driven by consecutive administration reforms resulting in a fusion of church and state administration, rather than a traditional secularisation narrative. It traces the subtle ties between the Prussian state, episcopal administration, and clerical inspection personnel that led to the gradual assertion of state over ecclesiastical structures.

QYOLO: Contextual Query-Assisted Object Detection in High-Resolution Images

High-resolution imagery captured by drones can detect critical components on high-voltage transmission towers, providing inspection personnel with essential maintenance insights and improving the efficiency of power line inspections. The high-resolution imagery is particularly effective in enhancing the detection of fine details such as screws. The QYOLO algorithm, an enhancement of YOLOv8, incorporates context queries into the feature pyramid, effectively capturing long-range dependencies and improving the network’s ability to detect objects. To address the increased network depth and computational load introduced by query extraction, Ghost Separable Convolution (GSConv) is employed, reducing the computational expense by half and further improving the detection performance for small objects such as screws. The experimental validation using the Transmission Line Accessories Dataset (TLAD) developed for this project demonstrates that the proposed improvements increase the average precision (AP) for small objects by 5.5% and the F1-score by 3.5%. The method also enhances detection performance for overall targets, confirming its efficacy in practical applications.

How to Reduce the Number of Inspectors: Operation Mode and Modeling Simulation of Centralized Image Recognition in Railway Passenger Security Inspection

Security inspection is an essential step for passengers entering railway stations in China. Under the existing security inspection operation mode, each X-ray machine needs an image inspector to recognize the X-ray image, which poses the issue of resource optimization for inspectors. Based on the networking of security inspection X-ray machines, an innovative centralized image recognition (CIR) operation mode for railway security inspections is proposed, and it is worth noting that network and device failures are risk factors for this mode. The method for assigning image recognition personnel is designed to reduce labor force needed for security inspection. Using a combination of agent-based modeling method and computer simulation technology, the four elements of passengers, security inspection X-ray machines, X-ray image inspectors, and secondary baggage inspection personnel are modeled, and CIR indicators to study the effectiveness of the operation are designed. Based on the real departing passenger data of the Zhangjiakou section of the Beijing Zhangjiakou Line in China, simulation is conducted in two scenarios: large passenger flow and small passenger flow. The research is conducted from three aspects: operational efficiency, travel experience, and system complexity. Experiments have shown that, with a slight increase in passenger waiting time, the average number of X-ray image inspectors is reduced by more than 70% compared with the existing operation mode. The best pick-up location for passengers is related to passenger flow. The proposed model can analyze the effectiveness of CIR operation mode and provide decisive support for the application of CIR operation mode.

Crack _ PSTU: Crack detection based on the U-Net framework combined with Swin Transformer

Cracks serve as a significant indicator of aging infrastructure. While the surfaces of traditional infrastructures are visually inspected manually, this approach is labor-intensive, highly subjective, and often surpasses the capabilities of available inspection personnel. Although some researchers have employed traditional image processing and machine learning techniques to address these challenges, the presence of irregular crack shapes, complex lighting conditions, and limitations in detecting only a single type of surface crack complicate automatic crack detection. Recent research indicates that deep learning methods are increasingly leading in image-based feature extraction, object detection, and pixel attribute analysis. This paper introduces a method, Crack_PSTU (Pre-trained Swin Transformer U-Net), which leverages the U-Net framework and Swin Transformer model for infrastructure crack classification and detection tasks. Specifically, we utilize a pre-trained Swin Transformer network as the encoder and implement the decoder using convolution, pooling, and other operations, creating a "U"-shaped model architecture. Our experiments encompassed 11,298 crack images from varied scenes, with 9603 designated for training and 1695 for validation. The findings reveal that our approach surpasses other algorithms for this dataset.

Applying Machine Learning to Construct a Printed Circuit Board Gold Finger Defect Detection System

Machine vision systems use industrial cameras’ digital sensors to collect images and use computers for image pre-processing, analysis, and the measurements of various features to make decisions. With increasing capacity and quality demands in the electronic industry, incoming quality control (IQC) standards are becoming more and more stringent. The industry’s incoming quality control is mainly based on manual sampling. Although it saves time and costs, the miss rate is still high. This study aimed to establish an automatic defect detection system that could quickly identify defects in the gold finger on printed circuit boards (PCBs) according to the manufacturer’s standard. In the general training iteration process of deep learning, parameters required for image processing and deductive reasoning operations are automatically updated. In this study, we discussed and compared the object detection networks of the YOLOv3 (You Only Look Once, Version 3) and Faster Region-Based Convolutional Neural Network (Faster R-CNN) algorithms. The results showed that the defect classification detection model, established based on the YOLOv3 network architecture, could identify defects with an accuracy of 95%. Therefore, the IQC sampling inspection was changed to a full inspection, and the surface mount technology (SMT) full inspection station was canceled to reduce the need for inspection personnel.

Autonomous flight strategy of an unmanned aerial vehicle with multimodal information for autonomous inspection of overhead transmission facilities

AbstractThis study proposes an innovative method for achieving autonomous flight to inspect overhead transmission facilities. The proposed method not only integrates multimodal information from novel sensors but also addresses three essential aspects to overcome the existing limitations in autonomous flights of an unmanned aerial vehicle (UAV). First, a novel deep neural network architecture titled the rotational bounding box with a multi‐level feature pyramid transformer is introduced for accurate object detection. Second, a safe autonomous method for the transmission tower approach is proposed by using multimodal information from an optical camera and 3D light detection and ranging. Third, a simple yet accurate control strategy is proposed for tracking transmission lines without necessitating gimbal control because it keeps the UAV's altitude in sync with that of the transmission lines. Systematic analyses conducted in both virtual and real‐world environments confirm the effectiveness of the proposed method. The proposed method not only enhances the performance of autonomous flight but also provides a safe operating platform for inspection personnel.

Application of indoor and outdoor integrated collaborative positioning technology in power transportation detection

With the continuous acceleration of the construction of electric power Internet of Things, the structure and scale of electric power system is more massive, the complexity and danger coefficient of field operation is enhanced, and the risk of causing safety accidents is further increased. Therefore, based on wireless sensor network, collecting and transmitting information of personnel and site operation environment, establishing power operation tracking system is of great significance to improve the safety and efficiency of operation and inspection personnel. At present, most of the electric power operation and maintenance personnel are positioned by satellite or wireless WIFI, which has a large error or even cannot be positioned, so this paper proposes a 5G+Beidou fusion indoor-outdoor cooperative positioning technology for electric power operation and inspection service. The fusion model of Beidou carrier phase differential positioning and 5G cellular network positioning is established by using the improved Federal Kalman filter algorithm, which can avoid data pollution caused by Beidou receiver failure or 5G communication module failure in a complex environment, and avoid the inability to locate compared with the common Federal Kalman filter. phenomenon.

Quality inspection personnel training and team construction research of power plant installation and construction units

Quality inspection personnel training and team construction research of power plant installation and construction units

WDLS: Deep Level Set Learning for Weakly Supervised Aeroengine Defect Segmentation

With the rapid development of the aviation industry, videoscope inspection of aeroengines has become crucial for ensuring aircraft flight safety. Recently, deep learning, particularly convolutional neural networks (CNNs), have shown remarkable efficacy in videoscope inspection tasks. However, these methods usually require large-scale training labels with accurate annotation. In videoscope images, defects are often present at the micrometer level and require manual labeling by professional inspection personnel, posing further challenges to model training. To address these issues, Weakly-Supervised Deep Level Set (WDLS), a fully automatic framework for aeroengine defect segmentation, was proposed in this work. WDLS employs a multi-branch structure and an iterative learning strategy to combine a high-performance CNN architecture with level set evolution. First, the Similarity-Guided Region (SGR) detector was designed to generate class-specific segmentation proposals and initialize the level set function. Second, the Adaptive Local Parameter Prediction (ALPP) algorithm was proposed to integrate local priors and constraints into the energy function and optimize the iterative process. Finally, a self-supervised objective function named Convexified Level Set (CLS) was introduced to represent an improved level set formulation and obtain the final segmentation. The proposed framework is continuously differentiable and unified. Thus, it can be seamlessly embedded in any CNN without postprocessing. Furthermore, the method was evaluated on a new aeroengine dataset Turbo19 and a benchmark dataset. Experimental results demonstrated that the proposed framework meets real-time requirements and achieves better performance than state-of-the-art methods.

Approaches to assess reliability in visual inspection

Non-destructive testing (NDT) plays an important role in quality assurance and ensuring reliable ongoing operations in many industries. Thus, the importance of reliability assessment of inspection results is increasing. Current standards and regulations provide several approaches for this purpose. For example, DIN EN ISO/IEC 17025:2018-03 provides general requirements to determine measurement uncertainty. In contrast, method-related standards such as DIN ISO 19828:2021-03 specify detailed requirements for visual inspection (VT), considering environmental conditions and other factors (for example experience of the inspection personnel). In contrast, VDA Volume 5 defines visual inspection as an attributive method, making measurement uncertainty determinations unnecessary. Instead, the reliability of the inspection process is evaluated by proficiency tests. This paper examines approaches of regulations, based on previous experiments, for their applicability and suitability for considering the reliability of visual inspections. It is shown that individual measurement values (for example illuminance) are not suitable for this purpose. Furthermore, it is shown that human factors (HFs) (for example training or experience of the inspector), considered in isolation, are also not sufficiently suitable. Hence, the combination of the qualification of inspection methods, by means of proficiency tests on reference objects, and the application of Cohen's kappa for evaluating human factors appeared to be more suitable for the investigated issue.

Assessing the Role Ghana's Public Health Act, 2012 (Act 851) Can Play in Oversight of Artificial Intelligence Healthcare Systems to Prevent Medical Errors and Improve Patient Safety

Purpose: Evaluate the possibilities and limitations of implementing the Essential Ghana Public Health Act to manage the growing development of artificial intelligence (AI)-enabled health care in light of the contemporary gap in research so. Methodology: A review of the 2012 public health regulatory provisions and anti-technology surveillance mechanisms document detailing the needs and risks of AI regulation. Results: Current regulations have a customizable foundation for documenting policies, reporting algorithmic errors, creating updated workplace safety audits, and enforcing non-compliance but required by fully implemented investigations that strong material differences are addressed and that AI-specific rules are codified into new legal rules. Conclusions: Ghana currently has the mechanisms in place for an interim administration to flexibly implement long-term healthcare legislation on gaps awaiting reconciliation through investment in specific sectors, staffing and reforms. Recommendations: Immediate training to prepare inspection personnel before the onset of the crisis is guidelines and rules for algorithmic accounting. What really matters is the effective implementation of existing legislation and the informing of strategies for modernization and certainly also the innovation of policy frameworks for the innovation of new health care systems. Scientific contribution: addresses the knowledge gap in maintaining vulnerabilities for emerging technologies that are tracked by regulations in disruption.

Identification method of typical defects in transmission lines based on YOLOv5 object detection algorithm

In order to realize the automatic identification of typical defects in transmission lines, a typical defect identification method for transmission lines based on You Only Look Once (YOLO)v5 algorithm is proposed, which has the advantages of low missing detection rate and false detection rate. Firstly, a transmission line defect image dataset is constructed for three typical defects: bird’s nest defect, insulator defect and shakeproof hammer defect, and the corresponding image labeling strategy is formulated according to the defect characteristics. Secondly, this paper introduces the network structure of YOLOv5 in detail. For the sake of further improving the neural network’s ability to recognize the visual defects of transmission lines, the attention mechanism and small target detection layer are introduced into YOLOv5 neural network. Finally, this paper design transmission line defect recognition cases based on three kinds of typical defects, and the proposed method is compared with the recognition methods based on Faster Region based Convolutional Neural Network (RCNN) and Single Shot MultiBox Detector (SSD) in terms of the proposed performance indexes (missing detection rate and false detection rate). The results show that the missing detection rate and false detection rate of the YOLOv5-based identification method are much lower than those of the Faster RCNN and SSD-based identification methods, and the improved YOLOv5 network recognition rate is higher, which is significant for reducing the workload of transmission line inspection personnel.

Remote robotic system for 3D measurement of concrete damage in tunnel with ground vehicle and manipulator

AbstractTo ensure the safety of a concrete structure, periodic and accurate inspection for damage is necessary. However, there is a high risk of inaccurate diagnosis of the structure condition because the manual inspection method is dependent on operator experience and subjective judgment. Additionally, in future society, it may become increasingly difficult to maintain high‐quality infrastructure, as the number of inspection personnel will also decrease with a decrease in population. For this purpose, the demand for accurate and automated inspection technology is increasing. To meet these issues, in this study, an objective and automated inspection method is proposed by developing an inspection robot and management system. The inspection robot comprises an artificial intelligence sensor, a manipulator, and a ground vehicle; it can autonomously drive inside a tunnel and inspect the damage on concrete surfaces using stereo vision. The management system remotely controls the robot through wireless communication and monitors the inspection status in real time. In addition, damage is automatically restored in three dimensions based on the images, and the physical size of the damage is analyzed with an average relative error of 0.39%. This method is expected to be used as a core technology for unmanned and automated tunnel maintenance in the future.

Safety Management and Preventive Measures for Inspection and Testing Personnel of Chemical Special Equipment

Safety Management and Preventive Measures for Inspection and Testing Personnel of Chemical Special Equipment

Application Research of Inspection System Based on Intelligent Wearable Device in Communication Power Inspection

In order to effectively reduce the difficulty in communication power inspection and further improve the inspection efficiency of inspectors, this paper designs an inspection system based on smart wearable devices. Firstly, based on the analysis of the inspection task requirements of the communication power inspection, the overall structure of the wearable device intelligent inspection system is constructed, and the application of the wearable device intelligent inspection system in power engineering is studied; secondly, according to the inspection situation of the inspection personnel in the traditional inspection method, the key technical composition of the multi-functional inspection intelligent observation wearable lens is designed, and the key texture feature extraction technology of the communication power supply is used to locate the specific image target in the inspection process, and detect the local area. The abnormal sound is discharged, abnormal sound training and identification are completed, and intelligent inspection of the communication power supply is realized. Finally, it is verified by test experiments that the inspection system based on smart wearable devices designed in this paper can realize information transmission, task configuration, and data access in communication power inspection, with high work efficiency.

Image sequence-based risk behavior detection of power operation inspection personnel

A novel image sequence-based risk behavior detection method to achieve high-precision risk behavior detection for power maintenance personnel is proposed in this paper. In this method, the original image sequence data is first separated from the foreground and background. Then, the free anchor frame detection method is used in the foreground image to detect the personnel and correct their direction. Finally, human posture nodes are extracted from each frame of the image sequence, which are then used to identify the abnormal behavior of the human. Simulation experiment results demonstrate that the proposed algorithm has significant advantages in terms of the accuracy of human posture node detection and risk behavior identification.

Introduction to DIN 4871: Qualification of NDT Personnel in Civil Engineering (NDT-CE)

Recently, non-destructive testing in civil engineering (NDT-CE), in particular of concrete components, has successfully mastered the leap from research to practice. Several methods have been established for field inspections to determine the concrete cover of reinforcement or to estimate the compressive strength as well as other parameters related to the concrete material. In addition, the application of nondestructive testing is indispensable, if information about the inner structure - such as the location of rebars and tendon ducts or the damage-related condition assessment to detect grouting defects, honeycombs, delamination, or corrosion - is required. Besides the selection of a suitable NDT method and an appropriate inspection system, the reliability of the results depends largely on the person who applies the non-destructive inspection technique and evaluates the inspection results. To ensure a high quality of non-destructive concrete evaluation as well as to keep the uncertainty caused by the inspection personnel to a minimum, structured, consistent and regulated theoretical as well as practical training of inspection personnel is essential. To close this gap, the subcommittee of education (UA-A) within the committee for NDT-CE of the German Society for Nondestructive Testing (DGZfP) has been reactivated in 2018 to establish uniform training standards for nondestructive concrete inspections in the long term. The subcommittee consists of scientists, practitioners, authorities, and clients. So far, the national standard DIN 4871 “Non-destructive testing - Qualification and Certification of NDT personnel in Civil Engineering (NDT-CE)” was developed and is currently under review. This standard considers the civil-industry-specifics, for example, that standards for NDT of concrete, as well as related product standards with a few exceptions, still do not exist at the moment. Within this presentation, the concept, the connection to ISO 9712 and other standards as well as an overview of the developed German standard DIN 4871 will be presented.

The positive effect on compliance, security, and efficiency by the use of state-of-the-art NDT management software

The Digitalization and the associated networking of systems is progressing continuously in the NDT industry. In terms of workflow management, however, a combination of several tools such as Excel spreadsheets, Word documents, a wide variety of software and even paper documents are still often used. There is therefore enormous potential for improvement through digitalization. Recent NDT workflow management systems are the key, efficiently integrating all NDT test methods and associated processes into a single system. All information is available centrally and digitally for every stakeholder involved. This guarantees compliance and enables comprehensive transparency and control of the entire NDT workflow and real-time status overview of all inspections. Inspection personnel can be managed, as well as customers, equipment, test objects, inspection procedures and standards. All processes and test results are and will remain traceable at all times. This paper describes the application of such management software and it discusses the significant increases in compliance, security, and efficiency along the basic NDT workflow.

Development of an Intelligent Defect Detection System for Gummy Candy under Edge Computing

<p>Gummy candies are one of the products of the food industry. It has invested more resources in all aspects of the food production chain to improve production processes. The defective candies cause the unevenness of the product that will cause the appearance, taste and flavor poor. That will lead to economic losses for the company. Most traditional candy companies set up product inspection personnel to eliminate defective product. In this paper, an intelligent defect detection system for gummy candy industry under edge computing environment is proposed. It can replace manual visual inspection, even shorten the processing time to reduce production costs, thereby improving product quality, the efficiency of the production line, and the number of inspections. The system includes: (1) The intelligent defect detection system by deep learning algorithms. (2) The edge computing architecture with AIoT. The proposed system adopted the YOLO deep learning algorithm. The results show that the Precision is 93%, Recall is 87% and the F1 Score is 90. It has certain empirical reference significance for the intelligent defect detection system of candies products. By adopting deep learning algorithm in the detection system, it can reduce the inspection man-power needs and long-term data collection.</p> <p> </p>