Inspection Problem Research Articles

Real-World Video Denoising for Visual Inspection in High-Dose Radiological Environments

In high-dose radiological environments, where precision and safety are of utmost importance, the ability to acquire accurate and clear visual information is of paramount importance for ensuring safety and reliability in critical industrial processes. However, these environments inherently introduce significant challenges due to the adverse effects of radiation on imaging equipment. As a consequence, inspection videos captured within such high-radiation environments often contain a significant amount of noise. This noise substantially complicates the task of identifying and assessing potential defects in vital components. It also diverts attention and resources toward investigating false positives created by noise, leading to inefficiencies, and for industrial processes on the critical path, this can further prolong the outage. Addressing this noise is essential not only for precision, but also for ensuring safety, reliability, and efficiency in critical industrial processes. In this paper, we present a custom-designed filter utilizing a priori information about camera position and trajectory to remove the noise from the inspection videos, making the defects easier to manually identify. As the camera movement is in one direction at a constant speed, the proposed approach uses this temporal and spatial information to accurately remove the noise. This approach applies to a subset of visual inspection problems throughout the nuclear industry, as well as many other industries where there is knowledge available about the camera speed and direction of travel. The proposed approach is compared with three accepted/well-known approaches, median filtering, bilateral filtering, and fast nonlocal means denoising, and an additional state-of-the-art deep learning model is also used for comparison. It was found that the proposed approach produces the most accurate video denoising in terms of visual quality and the retainment of the defect features throughout the videos tested.

Target detection of helicopter electric power inspection based on the feature embedding convolution model.

This study aims to improve the helicopter electric power inspection process by using the feature embedding convolution (FEC) model to solve the problems of small scope and poor real-time inspection. First, simulation experiments and model analysis determine the keyframe and flight trajectory. Second, an improved FEC model is proposed, extracting features from aerial images in large ranges in real time and accurately identifying and classifying electric power inspection targets. In the simulation experiment, the accuracy of the model in electric power circuit and equipment detection is improved by 30% compared with the traditional algorithm, and the inspection range is expanded by 26%. In addition, this study further optimizes the model with reinforcement learning technology, conducts a comparative analysis of different flight environments and facilities, and reveals the diversity and complexity of inspection objectives. The performance of the optimized model in fault detection is increased by more than 36%. In conclusion, the proposed model improves the accuracy and scope of inspection, provides a more scientific strategy for electric power inspection, and ensures inspection efficiency.

Research of Converter Station Intelligent Inspection System Algorithm

Abstract This article mainly reveals a converter station equipment defect detection system based on the YOLOv5 algorithm. The research encompasses the establishment of a simulated environment for converter station inspection tasks, problem formulation, algorithm design, training process, and experimental evaluation. Key contributions include the enhancement of the YOLOv5 algorithm through improved clustering techniques, dataset preparation, and multi-object detection model training. This highlights the importance of appropriate anchor box initialization in object detection tasks, especially when dealing with small-sized images and varied defect types. In order to verify the correctness of this research, a comparative simulation analysis with mainstream detection algorithms further validates the superiority of the proposed method. The findings of this research contribute valuable insights into the development of AI-driven defect detection systems for power equipment inspection.

A flat sealing test device using water as the medium

Abstract The planar sealing test device uses water as the working medium to determine the sealing of the test plane, Water has a sealing effect and an intuitive visual effect. Fix the test piece on the testing device platform, and the working medium water moves upward under the thrust of the piston rod to fully cover the test piece. Increase a certain amount of air pressure inside the test piece, check for bubbles around the test piece, and determine the sealing of the plane. This design compensates for the shortcomings of flat sealing inspection equipment, and more conveniently and efficiently solves the sealing inspection problem before the assembly of flat sealing components, reducing energy consumption, saving resources, and improving production efficiency.

Optimized structural inspection path planning for automated unmanned aerial systems

Automation in Unmanned Aerial Systems (UAS)-based structural inspections has gained significant traction given the scale and complexity of infrastructure. A core problem in UAS-based inspection is electing an optimal flight path to achieve the mission objectives while minimizing flight time. This paper presents an effective two-stage method that guarantees coverage as a constraint to ensure damage detectability, while minimizing path length as an objective. A genetic algorithm first determines viewpoint positions, and a greedy algorithm calculates the camera poses, as opposed to directly optimizing all degrees of freedom (DOF) simultaneously. A sensitivity analysis demonstrates the range of applicability and superiority of this formulation over direct 5-DOF optimization by at least 30 % shorter path length. Applied examples, including focused and partial space inspections, are also presented, demonstrating the flexibility of the proposed method to meet real-world requirements. The results highlight the feasibility of the approach and contribute to incorporating automation into UAS-based structural inspections.

A Method for Recognition and Coordinate Reference of Autonomous Underwater Vehicles to Inspected Objects of Industrial Subsea Structures Using Stereo Images

To date, the development of unmanned technologies using autonomous underwater vehicles (AUVs) has become an urgent demand for solving the problem of inspecting industrial subsea structures. A key issue here is the precise localization of AUVs relative to underwater objects. However, the impossibility of using GPS and the presence of various interferences associated with the dynamics of the underwater environment do not allow high-precision navigation based solely on a standard suite of AUV navigation tools (sonars, etc.). An alternative technology involves the processing of optical images that, at short distances, can provide higher accuracy of AUV navigation compared to the technology of acoustic measurement processing. Although there have been results in this direction, further development of methods for extracting spatial information about objects from images recorded by a camera is necessary in the task of calculating the exact mutual position of the AUV and the object. In this study, in the context of the problem of subsea production system inspection, we propose a technology to recognize underwater objects and provide coordinate references to the AUV based on stereo-image processing. Its distinctive features are the use of a non-standard technique to generate a geometric model of an object from its views (foreshortening) taken from positions of a pre-made overview trajectory, the use of various characteristic geometric elements when recognizing objects, and the original algorithms for comparing visual data of the inspection trajectory with an a priori model of the object. The results of experiments on virtual scenes and with real data showed the effectiveness of the proposed technology.

Safe Spacecraft Inspection via Deep Reinforcement Learning and Discrete Control Barrier Functions

While reinforcement learning (RL) offers high-performance solutions to complex tasks, its trial-and-error paradigm presents safety concerns when exploring unsafe states may be unacceptable. Safety filtering or run-time assurance (RTA) approaches can be used to monitor the RL agent’s desired control and prevent the agent from taking unsafe actions by satisfying safety constraints during and after training. This study investigates the problem of on-orbit inspection of a chief spacecraft using a deputy spacecraft controlled by an RL agent with safety constraints. Several constraints on the state space are enforced using discrete control barrier functions and an optimization-based RTA system. This assures the safety of the deputy spacecraft and its sensors even with a neural-network-based primary controller. A detailed analysis of RL agent performance for eight separate experiments is presented, including each safety constraint individually, all constraints simultaneously, and no constraints. Results demonstrate that the RL agent can complete the inspection task while adhering to safety constraints in a simulated RL environment. These results also show that the RTA system can aid the RL agent in learning a successful policy over fewer time steps but may lead to higher fuel usage, depending on the constraint(s) enforced.

Optimal allocation and route design for station-based drone inspection of large-scale facilities

The utilization of drones to conduct inspections on industrial electricity facilities, including large-sized wind turbines and power transmission towers, has recently received significant attention, mainly due to its potential to enhance inspection efficiency and save maintenance costs. Motivated by the advantages of drones for facility inspection, we present a novel station-based drone inspection problem (SDIP) for large-scale facilities. The objective of SDIP is to determine the locations of multiple homogeneous automatic battery swap stations (ABSSs) equipped with drones, assign facility inspection tasks to the ABSSs with operation duration constraints, and design drone inspection routes with battery capacity constraints, such that minimize the sum of fixed ABSS costs and drone travel costs. The SDIP can be regarded as a variant of the location-routing problem, which is NP-hard and difficult to solve optimally. To obtain the optimal solution of SDIP efficiently, we firstly formulate this problem into an arc based formulation and a route based formulation, and then develop a logic-based Benders decomposition (LBBD) algorithm to solve it. The SDIP is decomposed into a master problem (MP) and a set of subproblems (SPs). The MP is solved by a branch-and-cut (BC) procedure. Once a feasible integer solution is found, the linear relaxation of SPs are solved by a stabilized column generation to generate Benders cuts. If the cost of all the SPs’ optimal LP solutions plus the cost of the MP’s solution is less that current best cost, the SPs are exactly solved by a Branch-and-Price (BP) algorithm to generate the logic cuts. The numerical results on five scales of randomly generated instances validate the effectiveness of the LBBD algorithm. Specifically, the LBBD can solve all small- and middle-sized instances, and seven out of ten large-sized instances in 1000 s. Furthermore, we conduct a sensitivity analysis by varying the attributes of ABSSs and drones, and provide valuable managerial insights for large-scale facility inspection.

Intangible cultural heritage based on finite element analysis: force analysis of Chinese traditional garden rockery construction

In traditional Chinese rockery stacking, the peculiarity of the materials and reliance on the personal experience of artisans during the construction process make it challenging to scientifically quantify the structural stress and use scientific methods to ensure the stability of rockery structures and the safety of the construction process. Therefore, the intangible cultural heritage of rockery stacking technology faces the problem of scientific structural inspection and risk estimation during the construction process. This study uses a finite element analysis to evaluate the structural stress of the rockery-stacking site to contribute to the sustainable development and protection of this intangible cultural heritage. After establishing a three-dimensional digital model, mechanical calculations are carried out for the overall structure of the rockery and its different parts. The analysis identifies three types of structural factors in artificial rockeries: contact, structure, and load. It also effectively and intuitively identifies the weak points in the rockery structures and provides an assessment of risks, offering valuable insights for risk prevention and for the construction and maintenance of the structures. These results contribute to the structural safety inspection of traditional Chinese rockery stacking and the structural evaluation of existing rockery heritage.

Solving inverse problems in magnetic field leakage sensor array inspection of petroleum tank floor

The MFL method is a qualitative inspection tool and is a reliable, fast, and economical nondestructive testing method for tank floors. In this paper, before presenting the defect reconstruction procedure, we studied the effect of defect parameters on the magnetic field leakage measured by a single Hall sensor. As predicted, the study of each parameter has demonstrated that any variation in the geometrical parameters of the studied defect induce a significant influence on the MFL signal amplitude and distribution; for this reason, all the defect parameters must be determined precisely and prudently. After that, we have studied the performance of defect shape reconstruction from MFL array sensor imaging and depth estimation while using an iterative inversion method. Indeed, the first stage consists of determining the defect width and length from magnetic flux leakage mapping reconstructed from the recorded signals of the micro-integrated magnetic sensors. As a second step, after coupling Comsol and Matlab software, the defect depth is obtained by coupling the 3D finite elements method and a fast iterative algorithm recently developed. Consequently, the defect shape and size are obtained after a few iterations with a relative error of less than 2%; which makes this method very appropriate for real-time defect reconstruction and quantification. Furthermore, this method of defect reconstruction and seizing can be extended for irregular shape such as cracks and corrosion. In fact, this can be done while subdividing the affected area of non-constant depth into elementary zones of a constant depths. Then, while modifying the previous algorithm, we determine the corresponding depth of each zone.

Hybrid non-technical-loss detection in fog-enabled smart grids

Electricity theft is one of the major factors contributing to non-technical-losses (NTLs) in power distribution networks. NTL fraud includes frauds in which consumers profit unlawfully by manipulating smart meters (SMs), intruding networks, and so forth. This unlawful act not only undermines people’s efforts to conserve energy but also disrupts the regular billing cycle for power utilities, causing financial losses. In order to help utility companies solve the problems of inefficient electricity inspection and irregular power consumption, two NTL Detection schemes are proposed for NTL fraud prediction. Both schemes employed the auto-regressive integrated moving average (ARIMA) and the machine learning technique to predict the consumer behavior fraud pattern efficiently. Furthermore, extensive simulations are conducted on real-world electricity consumption data sets, which show that the proposed schemes outperformed state-of-the-art solutions and achieved an accuracy of 98%, a precision of 98.6%, a recall of 98.2%, an AUC of 97.9%, and an F1 score of 98.4%.

Reactive UAV-based automatic tunnel surface defect inspection with a field test

This work addresses the problem of automatic tunnel surface defect inspection using unmanned aerial vehicles (UAVs). The research aims at proposing a robust and efficient monitoring method for image data acquisition and processing in complex and dark tunnel environments. A method, called Proximity Move-Pause-Photo for Surface Defect Inspection (PMPP-SDI), is proposed by combining reactive flying control strategies with a grid scanning pattern to capture high-quality image data from multiple views and angles. The image data is then used to generate a 3D point cloud model of the tunnel surface for structural condition assessment. The method is tested in a field experiment in a railway tunnel in Ireland, and the results show that it can achieve stable navigation, high-resolution reconstruction, and accurate defect detection. The paper discusses the advantages and limitations of the method, and suggests improving the control/navigation intelligence, data quality, and defect analysis as the future research directions.

Automatic Quality Inspection and Intelligent Prevention of Prefabricated Building Construction Based on BIM and Fuzzy Logic

The construction industry plays an important role in China's economy. However, traditional construction quality inspection methods have problems such as low efficiency, high leakage rate, and poor real-time performance. Therefore, taking the appearance quality defects of reinforced concrete engineering as an example, this study combines building information models and computer vision technology. By this way, it can achieve automatic quality inspection and intelligent quality problem prevention, to improve the quality management level during the construction process. In this study, ResNet50 network was pre-trained and classified using a self-made defect image database. After transfer learning, the accuracy values of the training and testing sets remained stable at around 0.95 and the loss value remained stable at around 0.10 after 10 epochs, indicating a significant improvement in learning performance. In the defect area quantification experiment, four corner coordinates of the defect image were calculated. These corner coordinates are simultaneously obtained and saved during on-site image acquisition. According to the calculation results, the defect area of honeycomb is approximately 67.67 square centimetres. These results confirm that this method improves the efficiency and accuracy of quality inspection and has potential application in quality inspection of prefabricated building construction.

Adaptive Ultrasonic Full Matrix Capture Process for the Global Imaging of Complex Components with Curved Surfaces.

This work proposes a new global FD-RTM method to solve the problem of ultrasonic inspection of parts with complex geometric shapes. With this method, the frequency domain reverse time migration (FD-RTM) algorithm is used to adapt to the complex refraction of ultrasonic waves by the surface, while an interface solution algorithm based on tangent fitting is used to solve the interface position with high precision through the full matrix reception data. Based on high-precision interface information, a hybrid extrapolation algorithm and a situation-specific probe movement strategy are used to enable the probe to find the next sampling point according to the direction of the workpiece surface, allowing complex surface topography features to be identified without relying on the workpiece CAD drawing. This makes it possible to achieve the automated inspection of workpieces. To verify the proposed method's effectiveness, an aluminum alloy model with side-drilled holes (SDH) is used. The geometry of the model consists of multiple convex and concave surfaces. By comparing the local FD-RTM imaging with images synthesized using the entire scan path, it is shown that gFD-RTM improved the imaging performance. Compared with FD-RTM, the average signal-to-noise ratio of gFD-RTM was increased by 20%, and the array performance index (API) was reduced by 70%, indicating effective detection coverage.

Grasp and Inspection of Mechanical Parts based on Visual Image Recognition Technology

In the process of industrial production, whether the machine can work stably is an important issue related to production efficiency and production safety. The cleaning of mechanical parts is an important factor affecting the stable operation of mechanical equipment, so the cleaning of mechanical parts is one of the important manufacturing links before assembly and manufacturing. The important value of the application of image recognition technology in the quality inspection of mechanical parts is briefly analyzed, and then the common problems in the quality inspection of mechanical parts are studied, the relevant measures of the application of image recognition technology in the quality inspection of mechanical parts are discussed, and finally the case analysis of the quality inspection of mechanical parts is carried out. The main purpose is to rationally use image recognition technology to complete the quality inspection of mechanical parts, so as to improve the overall level of production automation and give full play to the maximum role of this technology. At present, a variety of mechanical parts classification methods based on deep learning are studied. According to the demand of industrial machine parts, the corresponding machine parts data set is created. According to the production requirements, the SPP structure in the traditional YOLOV5 network is improved, and a new SPC structure is proposed: The YOLOv5 network with SPC structure is characterized by no pooling layer, which improves the accuracy and recall rate compared with the traditional YOLOv5 network. Secondly, the control method of robot grasping mechanical parts is studied. Using the camera to capture the image and the upper computer to calculate the mechanical parts under the camera coordinate system; Through camera calibration and hand-eye calibration, the transformation relationship between the grasping coordinates of mechanical parts in the camera coordinate system and the grasping coordinates of mechanical parts in the robot base coordinate system is obtained. The grasping coordinates and part type information of the mechanical parts in the robot base coordinate system are transmitted from the host computer to the robot through Modbus/TCP communication protocol.

Research on Quality Control and Problems of Food Inspection and Testing

At present, the food quality inspection industry has become an important foundation of the national quality development strategy. Combined with China's current food inspection and testing work to implement the status quo analysis, there are still problems in the development stage, the need to grasp the actual situation based on the factors affecting the targeted solution to ensure that the food inspection and testing of the work of the importance of the need for a strong.

A Deep Convolutional Neural Network-Based Method for Self-Piercing Rivet Joint Defect Detection

Abstract The self-pierce riveting process for alloy materials has a wide range of applications in the automotive manufacturing industry. This will not only affect the operation performance but also cause accidents in severe cases when there are defects in the riveted parts. A deep learning detection model is proposed that integrates atrous convolution and dynamic convolution to identify defects of self-piercing riveting parts efficiently to overcome the problem in quality inspection after the body self-piercing riveting process. First, a backbone network for extracting riveting defect features is constructed based on the ResNet network. Second, the center area of each riveting defect is located preferentially by the center point detection algorithm. Finally, the bounding box of riveting defects is regressed to achieve defect detection based on this central region. Among them, atrous convolution is used in the external network to increase the receptive field of the model, which combined with an active convolution so that a dynamic atrous convolution module is designed. This module is used to enhance the correlation between feature points of individual pixel in the image, which helps to identify defects with incomplete image edges and suppress background interference. Ablation experiments show that the proposed method achieves the highest accuracy of 96.3%, which is 3.9% higher than the original method. It is found that the proposed method is less affected by the background interference from the qualitative comparison. Moreover, it can also effectively identify the riveting defects on the surface of each area.

Thermal Image Analysis of Photovoltaic Panel for Condition Monitoring Using Hybrid Thermal Pixel Counting Algorithm and XGBoost Classifier

The use of thermal infrared imaging and the advancement of image processing techniques have developed fault diagnosis of Photo Voltaic (PV) panels without the need to incorporate expensive electrical detection circuitry. PV thermal image processing, supports in continuous monitoring of panels without disturbing the continuity of operation and mitigates the problem of manual inspection involved over a large area. The thermal pictures of photo voltaic panels are used to identify the nature of faults such as bypass diode, cell under fault condition, circuit which is under open condition, hot spot, polarization, Cracking, Corrosion, discoloring and delamination. An automatic PV Computer Aided Diagnosis (CAD) based condition monitoring systems with thermal image analysis is developed to identify and classify the different fault conditions such as Hotspot, Ethylene Vinyl Acetate (EVA) Discoloration, Delamination and Open Circuit. The proposed system involves a hybrid thermal pixel counting algorithm to identify the thermal patterns. The Extreme Gradient Boosting algorithm (XGBoost) is used to detect the numerical characteristics of the captured image thermal variations to support in classification. The experimental results show that the proposed Hybrid Thermal Pixel Counting (HTPC) Algorithm with XGBOOST Classifier gives better detection accuracy with improved computational speed.

Hide-and-Seek Game with Capacitated Locations and Imperfect Detection

We consider a variant of the hide-and-seek game in which a seeker inspects multiple hiding locations to find multiple items hidden by a hider. Each hiding location has a maximum hiding capacity and a probability of detecting its hidden items when an inspection by the seeker takes place. The objective of the seeker (respectively, hider) is to minimize (respectively, maximize) the expected number of undetected items. This model is motivated by strategic inspection problems, where a security agency is tasked with coordinating multiple inspection resources to detect and seize illegal commodities hidden by a criminal organization. To solve this large-scale zero-sum game, we leverage its structure and show that its mixed-strategy Nash equilibria can be characterized using their unidimensional marginal distributions, which are pure equilibria of a lower dimensional continuous zero-sum game. This leads to a two-step approach for efficiently solving our hide-and-seek game: First, we analytically solve the continuous game and derive closed-form expressions of the equilibrium marginal distributions. Second, we design a combinatorial algorithm to coordinate the players’ resources and compute equilibrium mixed strategies that satisfy the marginal distributions. We show that this solution approach computes a Nash equilibrium of the hide-and-seek game in quadratic time with linear support. Our analysis reveals novel equilibrium behaviors driven by a complex interplay between the game parameters, captured by our closed-form solutions. Funding: This work was supported by the Georgia Tech Stewart Fellowship and the Georgia Tech New Faculty Start Up Grant. Supplemental Material: The online appendix is available at https://doi.org/10.1287/deca.2023.0012 .

Relative orbit design of CubeSats for on-orbit visual inspection of China space station

This paper presents a novel relative orbit design method for CubeSats flying around the space station to perform visual inspection considering the Field-Of-View (FOV) constraints and occlusion effect. Firstly, a parametric model for Periodic Relative Orbits (PROs) is established by using the well-known Clohessy-Wiltshire equations. Based on this model, the relative orbit design problem for orbital target inspection is successfully integrated into a problem of two-parameters determination, one of which is the correlation coefficient and the other is the orbital amplitude. Secondly, by categorically evaluating the range of design variables, the design method for generating feasible solutions of PROs to satisfy the FOV constraints is proposed. Thirdly, considering the existence of the occlusion effect of large space structure, this paper presents an efficient calculating method to evaluate the degree of occlusion based on the analysis of line-of-sight blockage. Then, to avoid the occlusion effect, an improved relative orbit design method is developed. Finally, the designed algorithms are testified by carrying out some typical simulations with the China Space Station as the observed object and a small CubeSat assumed to perform the required inspection mission. The results illustrate well the validity and practicability of the proposed method.