Inspection Time Research Articles

Integration of adaptive segmentation with heuristic-aided novel ensemble-based deep learning model for lung cancer detection using CT images

In recent days people are affected with lung cancer in, and the severe stage of this disease leads to death for human beings. Lung cancer is the second most typical cancer type to be found worldwide. Pulmonary nodules present in the lung can be used to identify cancer metastases because these nodules are visible in the lungs. Cancer diagnosis and region segmentation are the most important procedures because the prosperous prediction-affected area can accurately identify the variation in cancer and normal cell. By analyzing the lung nodules present in the image, the radiologists missed several useful low-density and small nodules, and this may tend to the diagnose process very difficult, and the radiologists needs more time to decide the prediction of affected lung nodules. Due to the radiologist’s physical inspection time and the possibility of missing nodules, automatic identification is needed to address these issues. In order to achieve this, a new hybrid deep learning model is developed for lung cancer detection with the help of CT images. At first, input images like CT images are gathered from the standard data sources. Once the images are collected, it undergoes for the pre-processing stage, where it is accomplished by Weighted mean histogram equalization and mean filtering. Consequently, a novel hybrid segmentation model is developed, in which Adaptive fuzzy clustering is incorporated with the Optimized region growing; here, the parameters are optimized by Improved Harris Hawks Optimization (IHHO). At last, the classification is accomplished by Ensemble-based Deep Learning Model (EDLM) that is constructed by VGG-16, Residual Network (ResNet) and Gated Recurrent Unit (GRU), in which the hyperparameters are tuned optimally by an improved HHO algorithm. The experimental outcomes and its performance analysis elucidate the effectiveness of the suggested detection model aids to early recognition of lung cancer.

Automation of trimming die design inspection by zigzag process between AI and CAD domains

Quality control using artificial intelligence (AI) has led to considerable improvements in the manufacturing industry. However, inspection of computer-aided design (CAD) drawing to prevent potential errors is still performed manually by engineers. The design inspection which involves sequential and repetitive processes is labor-intensive, time-consuming, and prone to human error. In this study, we developed an automatic design inspection system for CAD data by integrating AI module and CAD software. The target product of this study is automobile trimming die design. The AI modules replace the engineers’ judgment, and the CAD software performs the operations requested by the AI modules. The design inspection is completed through a zigzag interaction between the AI modules and CAD software by a one-click operation without the intervention of experts. In the zigzag interaction process, 3D CAD files are converted to 2D images for interaction from the CAD software to the AI modules, and the output of the AI modules is transferred to the CAD software through VBA macros. The AI modules are designed to be CAD-independent and data-efficient; therefore, they can be easily adapted to other CAD software and achieve a high performance, even when trained with a few trimming dies. The length measurement error is only 2.4 % on average, which is at the 14th place out of 18 grades according to ISO 286–1:1988 standard tolerance. Additionally, the inspection time is reduced to approximately one-fifth of the manual inspection time by experts.

Multiple dependent repetitive group sampling plan for Marshall-Olkin logistic-exponential distribution assuring percentile lifetime with applications

Acceptance sampling plans are commonly utilized for planning, process control, and implementation of industrial data sets. In addition to this, they also provide a solution for process quality control. They could be used for executing a decision for acceptance or rejection of a lot. A good acceptance sampling plan can be formulated depending on the requirements of the project. Usually, the plan should follow a defined lifetime distribution. Hence, the appropriate plan would not only determine the plan parameters but would also be cost and time efficient. In this article, an attribute multiple dependent repetitive group sampling (MDRGS) plan is developed assuming that the lifetime of the product follows the Marshall-Olkin logistic-exponential (MOLE) distribution. The parameters of plan are examined by considering a two-point approach. The suggested plan is contrasted with the single sampling and repeated group sampling plans. Finally, the implementation of the proposed plan is discussed using industrial as well as simulated data sets. It is concluded that the proposed plan reduces the sampling inspection cost and time as compared to existing acceptance sampling plans.

An adaptive crack inspection method for building surface based on BIM, UAV and edge computing

Unmanned aerial vehicle (UAV) and building information modeling (BIM) have been applied to inspect building surfaces to improve efficiency and reduce labor costs. However, most of the current research focus on the inspection mode of “first collect and then identify” with limited intelligence. Therefore, this study proposes a “global-local” adaptive inspection method for building surfaces by integrating BIM, UAV (with multifunction camera), and edge computing, enabling real-time synchronization of crack data collection and analysis. First, the building surface area to be inspected is extracted from BIM to generate global inspection points using the selected camera's field of view (FOV) and considering coordinates transformation between BIM and reality. Then, A star algorithm integrating with genetic algorithm (GA) is used to optimize the global flight path based on generated inspection points. Finally, the coordinates of the inspection points based on BIM are converted into real-world coordinates, and the flight parameters such as the flight yaw angle (FYA) and the gimbal yaw angle (GYA) are calculated to generate the inspection mission. During global inspection, a local adaptive inspection is proposed for each FOV through real-time local crack identification and flight replanning using edge computing and zoom camera. In addition, multiple battery supply points are automatically added considering the endurance of the UAV. A real building has been used to validate the proposed “global-local” adaptive inspection method. The experiment results show that the inspection time has been significantly reduced compared with the traditional method, and the crack identification of building surfaces can be implemented with high efficiency, precision, quality, and low cost.

Reducing the time of non-technical inspection of an territory possibly contaminated with explosive objects

A “combined” method of practical research has been developed as part of a non-technical survey of a territory likely contaminated with explosive objects, which will reduce the time of such survey and reduce the risk of injury to personnel of pyrotechnic units due to the absence of physical contact of personnel with the likely contaminated territory. A mathematical model of a “combined” method for practical research of a supposedly contaminated territory with explosive objects during non-technical inspection has been developed. The mathematical model was obtained from the results of collecting indirect evidence, where the status of an explosive object is not determined. A control algorithm for implementing the “combined” proposed method has been developed, which takes into account the area of the suspicious dangerous territory, which is examined by one non-technical survey group based on the collection of direct and indirect evidence. In addition, when constructing the algorithm, indicators such as the number of groups, the level and type of their equipment were taken into account. The algorithm consists of 12 blocks located at 7 hierarchical levels and connected by direct and feedback connections. When determining the area to be cleared of explosive objects, the area of the territory that has received confirmation of the status of a dangerous zone and the area of the territory of a confirmed dangerous zone are taken into account when checking indirect evidence of a possibly contaminated territory by excluding this territory from the total area of a possibly contaminated territory. The implementation of the proposed method (due to visualization of the area in a 3-D projection with the determination of the exact geographical coordinates of local and general zones of the dangerous territory) will reduce the time of non-technical inspection by 3.9 times, as well as reduce the time of complete demining and clearing land from explosive objects, increase the level of security for civilians in cleared areas.

Analysis of one-shot device testing data under logistic-exponential lifetime distribution with an application to SEER gallbladder cancer data

In the literature, the reliability analysis of one-shot devices is found under accelerated life testing in the presence of various stress factors. The application of one-shot devices can be extended to the bio-medical field, where we often evidence that inflicted with a certain disease, survival time would be under different stress factors like environmental stress, co-morbidity, the severity of disease etc. This work is concerned with a one-shot device data analysis and applies it to SEER gallbladder cancer data. The two-parameter logistic-exponential distribution is applied as a lifetime distribution. For robust parameter estimation, weighted minimum density power divergence estimators (WMDPDE) is obtained along with the conventional maximum likelihood estimators (MLE). The asymptotic behaviour of the WMDPDE and the robust test statistic based on the density power divergence measure are also studied. The performances of estimators are evaluated through extensive simulation experiments. Later those developments are applied to SEER gallbladder cancer data. Citing the importance of knowing exactly when to inspect the one-shot devices put to the test, a search for optimum inspection times is performed. This optimization is designed to minimize a defined cost function which strikes a trade-off between the precision of the estimation and experimental cost. The search is accomplished through the population-based heuristic optimization method genetic algorithm.

Welding defects on new energy batteries based on 2D pre-processing and improved-region-growth method in the small field of view

The assessment of welding quality in battery shell production is a crucial aspect of battery production. Battery surface reconstruction can inspect the quality of the weld instead of relying on human inspection. This paper proposes a defect detection method in the small field of view based on 2D pre-processing and an improved-region-growth method. A novel approximation-based, high-precision, and simple operation method for line structure optical plane calibration under small field of view is presented, with a measurement error within 0.01 mm. By pre-processing the line scan 2D images, the defect location distribution is obtained, and then the images near the abnormal points are reconstructed in third dimensional (3D). The proposed method enables the extraction of the morphology, size, and other information of the defects with high accuracy. The results of various defect detection experiments demonstrate the stable and reliable performance of the system. The experimental results of defect recognition rate are over 95.3% for defects above 0.5 mm in diameter, and the inspection time is less than 1/2 of the direct 3D defect inspection. Overall, this method has proven to be highly effective in the assessment of welding quality in new energy battery production.

Lean back or lean in? Exploring social loafing in human–robot teams

Introduction: Thanks to technological advances, robots are now being used for a wide range of tasks in the workplace. They are often introduced as team partners to assist workers. This teaming is typically associated with positive effects on work performance and outcomes. However, little is known about whether typical performance-reducing effects that occur in human teams also occur in human–robot teams. For example, it is not clear whether social loafing, defined as reduced individual effort on a task performed in a team compared to a task performed alone, can also occur in human–robot teams.Methods: We investigated this question in an experimental study in which participants worked on an industrial defect inspection task that required them to search for manufacturing defects on circuit boards. One group of participants worked on the task alone, while the other group worked with a robot team partner, receiving boards that had already been inspected by the robot. The robot was quite reliable and marked defects on the boards before handing them over to the human. However, it missed 5 defects. The dependent behavioural measures of interest were effort, operationalised as inspection time and area inspected on the board, and defect detection performance. In addition, subjects rated their subjective effort, performance, and perceived responsibility for the task.Results: Participants in both groups inspected almost the entire board surface, took their time searching, and rated their subjective effort as high. However, participants working in a team with the robot found on average 3.3 defects. People working alone found significantly more defects on these 5 occasions–an average of 4.2.Discussion: This suggests that participants may have searched the boards less attentively when working with a robot team partner. The participants in our study seemed to have maintained the motor effort to search the boards, but it appears that the search was carried out with less mental effort and less attention to the information being sampled. Changes in mental effort are much harder to measure, but need to be minimised to ensure good performance.

Fine‐grained crack segmentation for high‐resolution images via a multiscale cascaded network

AbstractHigh‐resolution (HR) crack images offer more detailed information for assessing structural conditions compared to low‐resolution (LR) images. This wealth of detail proves indispensable in bolstering the safety of unmanned aerial vehicle (UAV)‐based inspection procedures and elevating the precision of small crack segmentation. Nonetheless, achieving a balance between segmentation accuracy and GPU memory consumption poses a substantial challenge for deep learning models when processing HR crack images. To overcome this challenge, a novel “HR crack segmentation framework” (HRCSF) is proposed, specifically designed to meticulously segment crack images with resolutions exceeding 4K. First, a multiscale crack feature extraction network (MsCFEN) was proposed with the embedment of the strip pooling operation to enhance the representation of the transverse and longitudinal crack pixels from the complex backgrounds. Subsequently, two cascaded operations were tailored to MsCFEN, enabling a comprehensive refinement process that incorporates both global and local aspects. Furthermore, to fully leverage the potential of each proposed component in the refinement process, the complete architecture was trained using a loss function with embedded boundary optimization. Conclusively, a UAV‐based case study was conducted on a real bridge in Changsha, demonstrating HRCSF's practicability in segmenting HR crack images. The implementation of HRCSF allows the UAV to perform crack inspection effectively from a distance of 3 m away from the girder, resulting in a significant 50% reduction in inspection time compared to LR segmentation methods while maintaining high detection accuracy.

Best practices for implementing biosafety inspections in a clinical laboratory: Evidence from a multi-site experimental study.

To explore the key components when designing best practice inspection interventions, so as to induce high compliance with safety guidelines for laboratory workers. Five key components of an inspection intervention, identified from a focus group discussion, were used as the attributes of a discrete choice experiment (DCE). In the DCE, participants were presented with two hypothetical scenarios and asked to choose the scenario in which they were more willing to comply with the laboratory safety guidelines. Data were collected from 35 clinical laboratories in seven healthcare institutes located in Chengdu, China. In total, 188 laboratory workers completed the DCE. The collected data were analyzed using conditional logit regression and latent class analysis. Five key attributes were identified as the most important ones to best ensure laboratory safety: the inspector, the inspection frequency, the inspection timing, the communication of the inspection outcome, and a follow-up with either a reward or a punishment. By investigating the laboratory workers' responses to the attributes, properly implementing the five attributes could improve the workers' compliance from 25.86% (at the baseline case) to 74.54%. Compliance could be further improved with the consideration of the laboratory workers' heterogeneous reactions. In this study, two classes of workers, A and B, were identified. Compliance percentages for Classes A and B would be improved to 85.48% and 81.84%, respectively, when the key attributes were properly implemented for each class. The employment type and the size of the laboratory could be used to predict class membership. The findings indicate the importance of an employee-centered approach in encouraging a worker's compliance. This approach also supports the design of tailored interventions by considering the laboratory workers' heterogeneous responses to the interventions.

A condition-based inspection-maintenance policy for critical systems with an unreliable monitor system

In real-world industrial systems, many critical systems that achieve the main function are typically continuously monitored by a monitor system to ensure their reliability. Both the critical system and the monitor system degrade gradually. Research on the maintenance design of a critical system with an unreliable monitor system is limited. Hence, this paper proposes a condition-based inspection-maintenance policy for this kind of system. When the monitor system functions well, the performance of the critical system is obtained by the monitor system, while the status of the monitor system is detected by periodic inspections. When the monitor system fails, the performance of the critical system and the monitor system are detected by examinations when a warning is given or at each periodic inspection time. The corresponding maintenance actions are performed when their performance exceeds the predefined thresholds. The semi-regenerative process is used to calculate the long-run expected cost of a two-component critical system with a monitor system. The simulation method is introduced for a multi-component critical system with a monitor system. Finally, the proposed policy is applied to the battery pack system with a battery management system in EVs to illustrate the feasibility and efficiency of the proposed policy.

Diagnosis and management of Barrett esophagus: European Society of Gastrointestinal Endoscopy (ESGE) Guideline.

MR1 : ESGE recommends the following standards for Barrett esophagus (BE) surveillance:- a minimum of 1-minute inspection time per cm of BE length during a surveillance endoscopy- photodocumentation of landmarks, the BE segment including one picture per cm of BE length, and the esophagogastric junction in retroflexed position, and any visible lesions- use of the Prague and (for visible lesions) Paris classification- collection of biopsies from all visible abnormalities (if present), followed by random four-quadrant biopsies for every 2-cm BE length.Strong recommendation, weak quality of evidence. MR2: ESGE suggests varying surveillance intervals for different BE lengths. For BE with a maximum extent of ≥ 1 cm and < 3 cm, BE surveillance should be repeated every 5 years. For BE with a maximum extent of ≥ 3 cm and < 10 cm, the interval for endoscopic surveillance should be 3 years. Patients with BE with a maximum extent of ≥ 10 cm should be referred to a BE expert center for surveillance endoscopies. For patients with an irregular Z-line/columnar-lined esophagus of < 1 cm, no routine biopsies or endoscopic surveillance are advised.Weak recommendation, low quality of evidence. MR3: ESGE suggests that, if a patient has reached 75 years of age at the time of the last surveillance endoscopy and/or the patient's life expectancy is less than 5 years, the discontinuation of further surveillance endoscopies can be considered. Weak recommendation, very low quality of evidence. MR4: ESGE recommends offering endoscopic eradication therapy using ablation to patients with BE and low grade dysplasia (LGD) on at least two separate endoscopies, both confirmed by a second experienced pathologist.Strong recommendation, high level of evidence. MR5: ESGE recommends endoscopic ablation treatment for BE with confirmed high grade dysplasia (HGD) without visible lesions, to prevent progression to invasive cancer.Strong recommendation, high level of evidence. MR6: ESGE recommends offering complete eradication of all remaining Barrett epithelium by ablation after endoscopic resection of visible abnormalities containing any degree of dysplasia or esophageal adenocarcinoma (EAC).Strong recommendation, moderate quality of evidence. MR7: ESGE recommends endoscopic resection as curative treatment for T1a Barrett's cancer with well/moderate differentiation and no signs of lymphovascular invasion.Strong recommendation, high level of evidence. MR8: ESGE suggests that low risk submucosal (T1b) EAC (i. e. submucosal invasion depth ≤ 500 µm AND no [lympho]vascular invasion AND no poor tumor differentiation) can be treated by endoscopic resection, provided that adequate follow-up with gastroscopy, endoscopic ultrasound (EUS), and computed tomography (CT)/positrion emission tomography-computed tomography (PET-CT) is performed in expert centers.Weak recommendation, low quality of evidence. MR9: ESGE suggests that submucosal (T1b) esophageal adenocarcinoma with deep submucosal invasion (tumor invasion > 500 µm into the submucosa), and/or (lympho)vascular invasion, and/or a poor tumor differentiation should be considered high risk. Complete staging and consideration of additional treatments (chemotherapy and/or radiotherapy and/or surgery) or strict endoscopic follow-up should be undertaken on an individual basis in a multidisciplinary discussion.Strong recommendation, low quality of evidence. MR10 A: ESGE recommends that the first endoscopic follow-up after successful endoscopic eradication therapy (EET) of BE is performed in an expert center.Strong recommendation, very low quality of evidence. B: ESGE recommends careful inspection of the neo-squamocolumnar junction and neo-squamous epithelium with high definition white-light endoscopy and virtual chromoendoscopy during post-EET surveillance, to detect recurrent dysplasia.Strong recommendation, very low level of evidence. C: ESGE recommends against routine four-quadrant biopsies of neo-squamous epithelium after successful EET of BE.Strong recommendation, low level of evidence. D: ESGE suggests, after successful EET, obtaining four-quadrant random biopsies just distal to a normal-appearing neo-squamocolumnar junction to detect dysplasia in the absence of visible lesions.Weak recommendation, low level of evidence. E: ESGE recommends targeted biopsies are obtained where there is a suspicion of recurrent BE in the tubular esophagus, or where there are visible lesions suspicious for dysplasia.Strong recommendation, very low level of evidence. MR11: After successful EET, ESGE recommends the following surveillance intervals:- For patients with a baseline diagnosis of HGD or EAC:at 1, 2, 3, 4, 5, 7, and 10 years after last treatment, after which surveillance may be stopped.- For patients with a baseline diagnosis of LGD:at 1, 3, and 5 years after last treatment, after which surveillance may be stopped.Strong recommendation, low quality of evidence.

Dynamic multivariate Gamma-Gamma general path model: An alternative approach to time-variant degradation rates

We introduce a general path Gamma-Gamma model for degradation measures, related to different inspection times functions, obtaining flexible forms of degradation paths. One important contribution of the proposed model is the way the degradation rate is modeled. It is composed of two random components: one random effect quantifying the specific features of each device and a dynamic effect, common to all devices, measuring the impact of the environment on the degradation. The model is identifiable under mild constraints. Besides producing gains regarding the interpretability of the parameters, this decomposition generates a parsimonious model, reducing computational time. The relation between degradation and failure time is obtained, allowing a computational approximation for the failure time distribution. The model performance is evaluated through simulation, helping to guide the prior specifications to model identification. The proposed model is applied to analyze fatigue crack growth data. We compare the proposed model with the traditional linear Weibull model and with a dynamic linear Normal model. Results show that the proposed methodology is competitive in predicting failure times and estimating the remaining useful life.

A cooperative model to lower cost and increase the efficiency of methane leak inspections at oil and gas sites

Methane is a potent greenhouse gas that tends to leak from equipment at oil and gas (O&amp;G) sites. Conventional leak detection and repair methods for fugitive methane emissions are labor-intensive and costly because they involve time-consuming close-range, component-level inspections at each site. This has prompted duty holders to examine new methods and strategies that could be more cost-effective. We examined a cooperative model in which multiple duty holders of upstream O&amp;G sites in a region use shared services to inspect on-site equipment using optical gas imaging camera or Method 21. This approach was hypothesized to be more efficient and cost-effective than independent inspection programs by each duty holder in the region. To test this hypothesis, we developed a geospatial simulation model using empirical data from 11 O&amp;G-producing regions in Canada and the United States. We used the model to compare labor cost, transit time, mileage, vehicle emissions, and driving risk between independent and co-op leak inspection programs. The results indicate that co-op leak inspection programs can generate relative savings in labor costs (1.8%–34.2%), transit time (0.6%–38.6%), mileage (0.2%–43.1%), vehicle emissions (0.01–4.0 tCO2), and driving risk (1.9%–31.9%). The largest relative savings and efficiency gains resulting from co-op leak inspection programs were in regions with a high diversity of duty holders, which was confirmed with simulations of fictitious O&amp;G sites and road networks spanning diverse conditions. We also found reducing leak inspection time by 75% with streamlined methods can additionally reduce labor cost by 8.8%–41.1%, transit time by 5.6%–20.2%, and mileage by 2.60%–34.3% in co-op leak inspection programs. Overall, this study demonstrates that co-op leak inspection programs can be more efficient and cost-effective, particularly in regions with a large diversity of O&amp;G duty holders, and that methods to reduce leak inspection time can create additional savings.

AI-powered intrusion detection in large-scale traffic networks based on flow sensing strategy and parallel deep analysis

Current intrusion detection systems, which rely on signature-based detection using rules derived from the inspection of past traffic flows and their signatures, are incapable of detecting new types of attacks. They also face challenges from large-scale traffic networks when deployed in the inline mode. This paper presents the SAID method combining signature-based and AI-powered deep analysis, called PAID, controllable by a flow sensing strategy for accelerating the intrusion detection in large-scale networks. PAID is designed as a parallel ensemble learning of DNN, XGB, and GBM to boost the deep analysis in terms of speed and quality. In order to enhance the performance of PAID, we also propose a method to augment the quality of the training dataset by compressing samples in the majority classes and generating more realistic samples in minority classes. Moreover, SAID includes a flow sensing strategy based on a configurable sampling cycle and window for analyzing the large-scale traffic network. Well-known datasets, such as CSE-CIC-IDS2018 and NSL-KDD, are used to demonstrate the performance of PAID. Our deep experiments prove that PAID obtains the same remarkable precision and F1-score of 99.97% and 99.69%, respectively. It also outperforms the other recent methods, and the typical PAID-based inspection time per flow (i.e., 4.89μs/flow) is fast enough to detect and prevent intrusions in real-time for large-scale networks.

Metro track geometry car routing problem with periodic demands: a case study in Beijing, China

Because of their curvature, age, track type and maintenance history, metro tracks should be inspected periodically during the planning horizon. Metro companies operate track geometry cars to periodically collect measurement data from the tracks by crossing the urban rail transit network. Optimizing the schedule for the track geometry car is a challenge: in addition to minimizing travelling distance, the inspection time interval of the same line should be arranged as equally as possible within the planning horizon. This article proposes a mathematical model for the track geometry car routing problem with periodic demands (TGCRP-PD). To effectively address this problem, a memetic algorithm-based metaheuristic is adopted. The proposed solution approach is applied to a real-world case. The numerical results show that the proposed method could save a dead mileage of 295.016 km (accounting for 48.882%) and greatly improve the level of service intervals.

Design and Implementation of Defect Detection System Based on YOLOv5-CBAM for Lead Tabs in Secondary Battery Manufacturing

According to QYResearch, a global market research firm, the global market size of secondary batteries is growing at an average annual rate of 8.1%, but fires and casualties continue to occur due to the lack of quality and reliability of secondary batteries. Therefore, improving the quality of secondary batteries is a major factor in determining a company’s competitive advantage. In particular, lead taps, which electrically connect the negative and positive electrodes of secondary batteries, are a key factor in determining the stability of the battery. Currently, the quality inspection of secondary battery lead tab manufacturers mostly consists of visual inspection after vision inspection with a rule-based algorithm, which has limitations on the types of defects that can be detected, and the inspection time is increasing due to overlapping inspections, which is directly related to productivity. Therefore, this study aims to automate the quality inspection of lead tabs of secondary batteries by applying deep-learning-based algorithms to improve inspection accuracy, improve reliability, and improve productivity. We selected the YOLOv5 model, which, among deep-learning algorithms, has a benefit for object detection, and used the YOLOv5_CBAM model, which replaces the bottleneck part in the C3 layer of YOLOv5 with the Convolutional Block Attention Module (CBAM) based on the attention mechanism, to improve the accuracy and speed of the model. As a result of applying the YOLOv5_CBAM model, we found that the parameter was reduced by more than 50% and the performance was improved by 2%. In addition, image processing was applied to help segment the defective area to apply the SPEC value for each defective object after detection.

Crack Monitoring from Motion (CMfM): Crack detection and measurement using cameras with non-fixed positions

The assessment of cracks in civil infrastructures commonly relies on visual inspections carried out at night, resulting in limited inspection time and an increased risk of crack oversight. The Digital Image Correlation (DIC) technique, employed in structural monitoring, requires stationary cameras for image collection, which proves challenging for long-term monitoring. This paper describes the Crack Monitoring from Motion (CMfM) methodology for automatically detecting and measuring cracks using non-fixed cameras, combining Convolutional Neural Networks and photogrammetry. Through evaluation using images obtained from laboratory tests on concrete beams and subsequent comparison with DIC and a pointwise sensor, CMfM demonstrates accurate crack width computation within a few hundredths of a millimetre when compared to the sensor. This method exhibits potential for effectively monitoring temporal crack evolution using non-fixed cameras.

Remaining useful life prediction for rolling bearings based on RVM-Hausdorff distance

To address the shortcomings of existing bearing remaining useful life (RUL) prediction process such as low accuracy and reliance on expert experience for parameter estimation, this paper proposes a bearing RUL prediction method combining relevance vector (RV) machine (RVM) and hybrid degradation model. The bearing degradation characteristics are extracted from the acquired vibration acceleration signals, the time-varying 3σ criterion is then used to determine the bearing first predicting time, and the sequence from initial failure time point to the inspection time is regressed by differential kernel parameter RVM to obtain the different sparse RVs. A mixed degenerate model combined single exponential, weighted double exponential, and polynomial is used to fit the sparse RVs to obtain the fitted curve clusters. The similarity based on bidirectional Hausdorff distance is used to select the best degradation curve, and to extrapolate the best degradation curve to the failure threshold. The experimental results indicate that the proposed method overcomes the widespread drawbacks of monotonicity and trend bias in model-based methods, and has better prediction efficiency than the conventional exponential models.

Constraint Programming Approach to Coverage-Path Planning for Autonomous Multi-UAV Infrastructure Inspection

This article presents a constraint modeling approach to global coverage-path planning for linear-infrastructure inspection using multiple autonomous UAVs. The problem is mathematically formulated as a variant of the Min–Max K-Chinese Postman Problem (MM K-CPP) with multi-weight edges. A high-level constraint programming language is used to model the problem, which enables model execution with different third-party solvers. The optimal solutions are obtained in a reasonable time for most of the tested instances and different numbers of vehicles involved in the inspection. For some graphs with multi-weight edges, a time limit is applied, as the problem is NP-hard and the computation time increases exponentially. Despite that, the final total inspection cost proved to be lower when compared with the solution obtained for the unrestricted MM K-CPP with single-weight edges. This model can be applied to plan coverage paths for linear-infrastructure inspection, resulting in a minimal total inspection time for relatively simple graphs that resemble real transmission networks. For more extensive graphs, it is possible to obtain valid solutions in a reasonable time, but optimality cannot be guaranteed. For future improvements, further optimization could be considered, or different models could be developed, possibly involving artificial neural networks.