Reliable Inspection Research Articles

Advancements in PCB Components Recognition Using WaferCaps: A Data Fusion and Deep Learning Approach

Microelectronics and electronic products are integral to our increasingly connected world, facing constant challenges in terms of quality, security, and provenance. As technology advances and becomes more complex, the demand for automated solutions to verify the quality and origin of components assembled on printed circuit boards (PCBs) is skyrocketing. This paper proposes an innovative approach to detecting and classifying microelectronic components with impressive accuracy and reliability, paving the way for a more efficient and safer electronics industry. Our approach introduces significant advancements by integrating optical and X-ray imaging, overcoming the limitations of traditional methods that rely on a single imaging modality. This method uses a novel data fusion technique that enhances feature visibility and detectability across various component types, crucial for densely packed PCBs. By leveraging the WaferCaps capsule network, our system improves spatial hierarchy and dynamic routing capabilities, leading to robust and accurate classifications. We employ decision-level fusion across multiple classifiers trained on different representations—optical, X-ray, and fused images—enhancing accuracy by synergistically combining their predictive strengths. This comprehensive method directly addresses challenges surrounding concurrency, reliability, availability, and resolution in component identification. Through extensive experiments, we demonstrate that our approach not only significantly improves classification metrics but also enhances the learning and identification processes of PCB components, achieving a remarkable total accuracy of 95.2%. Our findings offer a substantial contribution to the ongoing development of reliable and accurate automatic inspection solutions in the electronics manufacturing sector.

DETERMINING THE RECOVERY TIME OF THE FIRE-SAFE CONDITION OF HYDROGEN STORAGE AND SUPPLY SYSTEMS

The fire prevention system can function in passive or active modes. In active mode, such a system implements a set of measures aimed at restoring the fire-safe state of the hydrogen storage and supply system after it is in a fire-hazardous state. The authors consider variants of its functioning for a highly reliable fire prevention system. The first option has the reliability of the fire inspection, which is equal to one, and the second option has the reliability of the fire inspection, which is different from one. Using graphs of the states of the hydrogen storage and supply system, we constructed systems of Kolmogorov equations and derived expressions for the probabilities of finding this system in the corresponding states. The article shows that the time to restore the fire-safe state of the hydrogen storage and supply system in the first variant should not exceed the probability of its being in a fire-hazardous state, reduced to the unit of the intensity of the transition of this system from a fire-safe state to a fire-hazardous state. In the second option, the time to restore the fire-safe state of the hydrogen storage and supply system increases following the law described by a hyperbola of the first order, the argument of which is the reliability of the fire safety inspection of such a system. We have obtained an expression for the reliability of the functioning of the fire prevention system focused on ensuring the fire safety of hydrogen storage and supply systems. We show that the reliability of the functioning of such a prevention system depends significantly on the reliability of the fire-engineering inspection of the hydrogen storage and supply system. We have also derived an expression for the time to restore the fire-safe state of the hydrogen storage and supply system that is determined a priori by the reliability of the fire prevention system functioning, the reliability of the fire inspection, and the intensity of the transition of the hydrogen storage and supply system from the fire-safe to the fire-hazardous state. Keywords: hydrogen storage and supply system, fire prevention, recovery time.

Development and fusion of NDT classifiers for defect detection on underwater structures

Vessel hull inspection is a complex and labor-intensive task, motivating the utilization of data fusion from complementary nondestructive testing (NDT) techniques to boost reliability and reduce detection uncertainties. In this study, an underwater robot equipped with three NDT systems – monocular RGB camera, eddy current (ECT), and ultrasound (UT) – is employed to assess a 12.7 mm thick ASTM-A36 carbon steel plate with artificially induced defects – coating loss, crack, pitting, and generalized corrosion. A classifier is developed for each NDT system for defect classification. Mask R-CNN is used for the camera data, achieving a mean average precision of 67.7% across three defect classes. A multilayer perceptron is used to classify the ECT data into six defect types and the non-defective class, attaining an accuracy of 98.8% on the test set. For UT data, a rule-based classifier based on A-scan-derived features distinguishes four defect classes. Subsequent to spatial synchronization, these classifier outputs are fused at the decision level, where redundancies between the camera and ECT classifiers are eliminated. Their outcomes are concatenated with the UT classifier results, culminating in a comprehensive detection map capable of representing eleven distinct defect classes. The classifiers and fusion are evaluated on a novel plate with unseen artificial defects. The camera and UT classifiers excel in detecting all classes for which they were specifically trained. In contrast, ECT exhibits a more limited capability, detecting only 21% of the specified defect classes. The findings underscore the potential of NDT data fusion to enhance inspection reliability by minimizing redundancies and extending the detection range.

Remote post-mortem veterinary meat inspections in bovine and analysis of post-mortem inspection outcomes: preliminary results

The work aimed to collect and analyse data obtained from the routine post-mortem veterinary inspection of bovine viscera and to evaluate the reliability of remote veterinary meat inspections. A comparative study was conducted on viscera belonging to 30 bovines. For each bovine, findings were recorded simultaneously by two veterinarians, one conducting an on-site post-mortem inspection and another performing the remote inspection through a tablet. A total of 10 (33.33 %) bovines were healthy. In a total of 18 (60.00 %) and 11 animals (33.00 %) pulmonary and hepatic lesions were respectively, observed. The most reported finding was pleuritis recorded in 17 animals (56.67 %), followed by pneumonia (16.67 %). The agreement between the two methods used for the post-mortem inspection of bovines was generally high. In an overall 73.33 % of bovines the findings recorded by the veterinarian who conducted the on-site post-mortem inspection and those recorded by the veterinarian performing the remote inspection were overlapping. In conclusion, a move to a remote post-mortem inspection has a negligible negative impact on public health since the most frequently detected lesions recorded were of scarce significance and in most cases, they were effectively detected by the veterinarian through the tablet.

Framework for Integrating the Reliability of the Inspection Technique into Risk-Based Inspection Practice

In compliance with recent (2022) federal legislation found in the Code of Federal Regulations Part 650 Subpart C, risk-based inspection (RBI) practices for determining inspection intervals for highway bridges are now permitted. The RBI approach allows for a systematic assessment of risk and prioritizes inspection resources where they are most needed. However, to ensure an optimal level of safety and serviceability, it is necessary to utilize reliable inspection techniques in conjunction with an appropriate inspection interval, as emphasized by National Cooperative Highway Research Program (NCHRP) Report 782. Utilizing ineffective inspection techniques may lead to uncertainty about the element’s condition and thus increase the risk associated with the component. Therefore, this paper proposes a framework that integrates a new factor, called the inspection effectiveness factor (IEF), into the RBI process to rationally estimate the inspection interval considering the reliability of the inspection technique. The inspection interval in the proposed approach is determined based on the damage mode, associated likelihood, consequences, and effectiveness of the inspection technique, offering a rational approach for decision-makers in estimating the inspection interval of bridges and identifying appropriate inspection techniques for different defects. The effectiveness of the proposed method is validated through experts’ judgment. In addition, the proposed approach is demonstrated through a case study utilizing historical inspection reports.

Explainable attention-based fused convolutional neural network (XAFCNN) for tire defect detection: an industrial case study

Ensuring tire quality is crucial in the manufacturing industry, particularly for race cars, where defective tires present a significant safety risk. Visual inspection for defects in tires is crucial; however, identifying defects in complex, textured tires has been proven to be a challenging task. This paper tackles this challenge by introducing XAFCNN, an Explainable Attention-based Fused Convolutional Neural Network for tire defect detection. XAFCNN’s novel architecture, including a Special Attention Module (SAM) and custom CNN structure, coupled with Grad-CAM visualization, prevents overfitting, enhances local feature mapping, enables detection of small defects, and proffers valuable insights into the model’s reasoning, enabling confident interpretation of its predictions. The model was trained on a dataset from a leading global tire manufacturer, including 38,710 x-ray images of defective tires and 83,985 defect-free tire images, covering 15 defect types and 50 design patterns. The results demonstrate the model’s exceptional performance compared to literature, achieving a recall rate of 86.85%, a precision of 98.5%, an F1 score of 92.31%, and an overall accuracy of 95.40%. This research, with its substantial dataset and high-performing model, advances automated tire defect detection, satisfying the industry’s need for accurate and reliable inspections, ultimately enhancing human safety.

The effectiveness of acceptance and commitment therapy (ACT) on neurotic perfectionism and internalized self-criticism in neurotic perfectionist girls: A single-case experimental study

Introduction: Neurotic perfectionism has a variety of psychological consequences that should be considered in psychotherapy applications. Aim: The present study aimed to examine the effectiveness of acceptance and commitment therapy (ACT) on neurotic perfectionism and internalized self-criticism in neurotic perfectionist girls. Method: This study was conducted using a single-case quasi-experimental design with, concurrent multiple baseline. The research population consisted of neurotic perfectionist girls visiting counseling centers in Ahvaz in 2022. The participants were a sample of 5 girls selected using purposive sampling with a minimum cut-off score of 145 in the Neurotic Perfectionism Questionnaire (NPQ). The acceptance and commitment therapy (ACT) (Twohig & et al, 2021) was implemented in eleven 90-minute sessions. The participants completed the Neurotic Perfectionism Questionnaire (1994), and the Levels of Self-Criticism Scale (2004). The data were collected in three baseline, intervention, and three-month follow-up phases and analyzed using reliable change index (RCI), recovery percentage, and visual inspection. Results: The analysis of the recovery percentage showed the participants’ neurotic perfectionism 17.67 and internalized self-criticism 19.73 improved in the intervention phase and their neurotic perfectionism 36.25 and internalized self-criticism 49.90 increased in the follow-up phase. Moreover, the reliability change index of both variables in the post-treatment and follow-up phases was significant (P=0.05). Conclusion: Considering the effectiveness of acceptance and commitment therapy in reducing neurotic perfectionism and internalized self-criticism by increasing psychological flexibility, this therapy can be used as an intervention method in neurotic perfectionist girls.

Fastener hole inspection using 2D phased array

Fastener hole cracks, resulting from stress concentration around the hole, are potential sources of failure in mechanical structures. Traditionally, inspection involves manually moving a single ultrasonic probe around the hole or using an eddy current probe to move through the hole. However, single ultrasonic probe inspection is time-consuming and needs skilful operators. Eddy current inspection requires the removal of the fastener in advance and does not allow easy crack sizing and visualization. This paper proposes a novel approach that combines a 2D phased array with a coupling block to enable complete fastener hole inspection from a single array position. A single full matrix capture (FMC) data set is collected, from which 3D volumetric images are formed. To obtain clear images of the geometry and potential defects, half-skip and multi-skip total focusing method imaging algorithms are investigated together with transmitter–receiver pairs selection methods to detect different target features. Experimental results demonstrate that the proposed inspection approach can eliminate dead zone problems and capture all target information from a single inspection position. These methods show great potential in enhancing the efficiency and reliability of fastener hole inspections.

Automated Crack Identification, to Ease Maintenance of Reinforced Concrete Bridges

One of the critical factors in the regional economic development and sustainability is the regular maintenance of road infrastructure. The preliminary step in the structural maintenance of bridges is in-situ inspection.Accurate and reliable infrastructure inspection plays a vital role in making the further steps’ decision, whether more assessment needs to put into action or the bridge is in good condition.The visual assessment, at the moment, is performed manually by the engineers, being therefore a too time-consuming and expensive operation, and in case of inspecting the critical points puts the engineers in danger, otherwise those parts will be missing of data. Overcoming these barriers, over the past few decades, considerable efforts have been made to construct the fundamental of implementing artificial intelligent techniques as a tool, to do autonomous inspection.This research engages in the data analysis section of the autonomous inspection with segmenting the cracks on the images acquired by them. This goal is achieved by implementing semantic segmentation deep learning development which is being trained on 8192 images and their binary masks as dataset, using the U-Net network. The model prediction shows 98.2% accuracy in crack segmentation. However, the novelty of our research extends beyond these results, we introduce a unique evaluation method named Pixel Average Error Distance (PAED) instead of the commonly used Intersection over Union (IoU) metric for segmentation assessment. Our methodology aims to forego the IoU metrics unreliable results in case of small deviation of crack patterns. It enhances the understanding of our model real performance with the PAED metrics lower than 0.5 which demonstrates a well-designed model, while the average IoU with 0.65 value shows a poor-designed model.Overall, this method will provide the engineer the possibility to observe all surfaces of a bridge and have a reliable and precise evaluation of the existing cracks.

A Study on the Statistical Analysis and Artificial Intelligence Model to Improve the Reliability of Safety Inspection

In this study, safety diagnosis results from underground and nuclear power plant structures were collected to evaluate the reliability of on-site structural safety assessments. The analysis of these results revealed a discrepancy between the compressive strength determined by rebound hardness and the core compressive strength, with the former typically being evaluated higher than the latter. Additionally, existing strength prediction models did not adequately explain field data, whereas artificial intelligence models, particularly the support vector machine model, demonstrated improved accuracy and reduced error rates. This indicated the superior performance of support vector machine models in this context.

APPLICATION OF THE RED PITAYA PLATFORM IN THE TECHNOLOGY OF PROTOTYPING AUTOMATED EDDY CURRENT TESTING SYSTEMS

Automated eddy current non-destructive testing has an important role in the quality inspection system for products made of conductive materials both at the production stage and during their operation. The appearance of novel alloys, the complexity of product geometry and inspection conditions, and the increased requirements for the reliability and accuracy of inspection results stimulate the acceleration process of creating new eddy current inspection tools. The technology of prototyping makes it possible to solve this problem. The purpose of the article is to review the functionality and technical characteristics of Red Pitaya for use in the technology of prototyping eddy current inspection, as well as to create a prototype architecture of an automated eddy current inspection system based on it.The choice of the Red Pitaya platform as a convenient tool for prototyping automated systems was made due to its functionality, reliability, and availability. In general, the article highlights the advantages and prospects of using the Red Pitaya platform in the prototyping of automated eddy current non-destructive testing systems. The aspects of the Red Pitaya hardware and its capabilities for expanding the functionality, which allows to create highly efficient and flexible control systems, are considered in detail. The compatibility of Red Pitaya with other devices and accessories is considered, which significantly increases its versatility and adaptability to various requirements and applications.The article highlights the importance of using the Jupyter Notebook application in combination with Red Pitaya as a convenient tool for software development. This helps to facilitate the process of creating and programmatically implementing complex signal processing algorithms in eddy current control systems, and provides flexibility in creating new software products.Modern trends and prospects for the development of eddy current testing, market needs, and the ability to adapt to different application scenarios are taken into account in the proposed architecture of the prototype automated eddy current testing system.

Study on the application of TLS for bridge deflection inspection in Vietnam

Inspecting defects, geometric size discrepancies compared to the design profile, and displacement under theload of the bridge structure aims to gather information and current data before putting the bridge into operation. However, the quality of inspection on the structure size performed by traditional methods usually takes time consuming and potentially unsafe due to difficulties in accessing because the bridge dimension is high and the rugged terrain is challenging, especially with bridges crossing rivers, deep valleys, etc. Therefore, applying modern, effective, and reliable inspection methods is essentially required. The Terrestrial Laser Scanner (TLS) is a technique to quickly and accurately gather topographic data points of objects’ surfaces. TLS is applied in many survey fields, including surveying the structure of bridge engineering. To evaluate the effectiveness of applying TLS, the research conducted a determination of the main span P61-62’s deflection of the balance casting bridge crossing the Vong intersection of the urban traffic bridge project Ring Road 2, Hanoi city during static load testing. Three methods to determine the deflection of the bridge span structure were implemented (1) Using dial indicators; (2) Using a total station to measure points reflecting attached to the structure of the bridge girder; (3) Applying TLS to inspect the structure at the time of no load and load. The results led to the conclusion that TLS methodology facilitates the determination of the bridge deflection with acceptable accuracy.

Non-destructive corrosion inspection of reinforced concrete structures using an autonomous flying robot

Autonomous non-destructive testing (NDT) on reinforced concrete structures has a large potential to overcome the limitations of current routine inspection techniques, often not capable of detecting corrosion at an early stage. Here, the development and validation of two probes, tailored to acquire contact-based NDT data with the help of a hexacopter, is presented. Each probe allows the combined measurement of two essential parameters in the condition assessment: half-cell potentials and concrete electrical resistivity. Strategies are presented to monitor probe functionality during operation and detect loss of contact between probe and structure, which is considered essential for autonomous NDT. The presented approach enables effective and reliable autonomous corrosion inspection, surpassing traditional visual inspections by localizing corrosion at an early stage, allowing engineers a better planning of maintenance. The successful application in a concrete bridge inspection sets the stage for future research in autonomous inspections with robots in various fields of applications.

Optimal management strategies of renewable energy systems with hyperexponential service provisioning: an economic investigation

The current research proposes optimal management strategies for queueing modeling-based renewable energy systems with hyper-exponentially distributed maintenance/repair under the assumption of an admission control policy. Using the concept and steps of the matrix-analytical method, the steady-state probability distribution associated with energy systems is explicitly presented. A relatively straightforward computation that can help with modeling wind energy generation, investigating wind farm performance, optimizing energy based on system storage, reliability inspection, service maintenance planning, and numerous other purposes can be employed to mathematically derive several system performance indicators. The investigation findings are validated via quantitative outcomes, illustrative possesses, and a step-by-step recursive methodology for efficient management of the renewable energy system. Additionally, considering multiple governing parameter values, the nature-inspired optimization technique, Cuckoo Search (CS), is employed to demonstrate the optimum anticipated cost of renewable energy system. A comparison with other metaheuristics and semi-classical approaches is also presented to establish the best convergence results. In order to help system designers, policymakers, engineers, and researchers, several numerical examples are also provided to construct more practical strategies based on the production of energy, storage, and system management. The economic, parametric, and performance investigation findings are highlighted, and the opportunities and recommendations for further research are provided. In a nutshell, the outcomes of the present analysis can be adopted to formulate the most effective economic strategies and regulate decision-making processes in the energy sectors.

Quantitative Detection Technology for Geometric Deformation of Pipelines Based on LiDAR.

This paper introduces a novel method for enhancing underground pipeline inspection, specifically addressing limitations associated with traditional closed-circuit television (CCTV) systems. These systems, commonly used for capturing visual data of sewer system deformations, heavily rely on subjective human expertise, leading to limited accuracy in detection. Furthermore, their inability to perform quantitative analyses of deformation extent hampers overall inspection effectiveness. Our proposed method leverages laser point cloud data and employs a 3D scanner for objective detection of geometric deformations in underground pipe corridors. By utilizing this approach, we enable a quantitative assessment of blockage levels, offering a significant improvement over traditional CCTV-based methods. The key advantages of our method lie in its objectivity and quantification capabilities, ultimately enhancing detection reliability, accuracy, and overall inspection efficiency.

Benefits of Non-Destructive Evaluation and Probabilistic Damage Tolerance Cosimulation for Fracture Risk Reduction

In the context of the damage tolerance approach used to drive aircraft maintenance operations, it is essential to demonstrate the reliability of NDE inspections in detecting structural damage especially for additively manufactured components since this process produces components that may introduce material anomalies at any location within a component. The Probability Of Detection curve (POD) that links the probability to detect a detrimental flaw to its size is generally used as a key indicator for that purpose by giving the maximum flaw size that a NDE process can miss with a given level of probability and confidence. This information can then be used along with other inputs such as component geometries, mechanical properties, constraints, service and residual stresses and damage evolution speed to assess fracture risk and then adapt maintenance scenarios to optimize safety and component service life. NDE reliability and risk assessment are based on statistical indicators that need a large amount of data to provide reliable metrics. It is difficult to obtain such indicators using a purely empirical approach that is based on physical trials and measurements as it may involve many mock-ups and costly processes. Simulation tools can achieve this goal via their ability to include and precisely monitor many parameters as well as high computing capacities that are now available. The work presented in this paper involved cosimulations performed between the DARWIN® probabilistic damage tolerance software and the CIVA NDE simulation software. DARWIN computes fracture risk levels throughout a component, while CIVA can efficiently provide Probability Of Detection curves at different locations in a component and for various NDE methods. The presented application deals with a titanium gas turbine engine impeller disk and involves an Ultrasonic NDE inspection technique. It appears to be a very interesting approach to connect together NDE and Fracture mechanics simulations, two disciplines that generally work on their own. Indeed, DARWIN helps the user to determine detrimental flaw types, locations and sizes which are key inputs to develop an effective NDE inspection method. CIVA can provide location-specific POD curves that enable DARWIN to quantity the effect of dedicated NDE on potential risk reduction. This highlights the importance of NDE simulation for safety and helps to identify potential changes in the physical NDE process and the maintenance cycle that provide the best compromise between detection performance and cost.

Autonomous Inspection Method of UHV Substation Robot Based on Deep Learning in Cloud Computing Environment

Aiming at the problem that substation robots cannot automatically find and analyze the fault equipment and carry out patrol inspection, a method of autonomous patrol inspection for ultra-high voltage (UHV) substation robots based on deep learning in cloud computing environment is proposed. Firstly, based on the cloud computing environment, an autonomous patrol system is designed to upload the data obtained by robots to the cloud platform for processing, so as to complete data analysis quickly and with high quality. Then, the deep learning algorithm (DL) is used for fault diagnosis, and the FP-growth algorithm is combined to realize the association mining of fault data, so as to clarify the patrol order of fault-related nodes. Finally, the improved ant colony algorithm (IAC) is used to optimize the path of the robot to complete the reliable inspection of the substation in the shortest time. Based on the selected UHV substation, the experimental analysis of the proposed method shows that the fault diagnosis error rate and time are about 4.3% and 14.2[Formula: see text]s, respectively, and the patrol path is only 180.351[Formula: see text]m, and the patrol time is 19.708[Formula: see text]s, which can realize the optimal patrol of the robot.

Advancements in Roundness Measurement Parts for Industrial Automation Using Internet of Things Architecture-Based Computer Vision and Image Processing Techniques

In the era of Industry 4.0, the digital capture of products has become a critical aspect, which prompts the need for reliable inspection methods. In the current technological landscape, the Internet of Things (IoT) holds significant value, especially for industrial devices that require seamless communication with local and cloud computing servers. This research focuses on the advancements made in roundness measurement techniques for industrial automation by leveraging an IoT architecture, computer vision, and image processing. The interconnectedness enables the efficient collection of feedback information, meeting the demands of closed-loop manufacturing. The accuracy and performance of assemblies heavily rely on the roundness of specific workpiece components. In order to address this problem, automated inspection methods are needed. A new method of computer vision for measuring and inspecting roundness is proposed in this paper. This method uses a non-contact method that takes into account all points on the contours of measured objects, making it more accurate and practical than conventional methods. The system developed by AMMC Laboratory captures Delrin work images and analyzes them using a specially designed 3SMVI system based on Open CV with Python script language. The system can measure and inspect several rounded components in the same part, including external frames and internal holes. It is calibrated to accommodate various units of measurement and has been tested using sample holes within the surface feature of the workpiece. According to the results of both techniques, there is a noticeable difference ranging from 2.9 µm to 11.6 µm. However, the accuracy of the measurements can be enhanced by utilizing a high-resolution camera with proper lighting. The results were compared to those obtained using a computer measurement machine (CMM), with a maximum difference of 8.7%.

Dynamic civil facility degradation prediction for rare defects under imperfect maintenance

PurposeThis paper aims to develop a dynamic civil facility degradation prediction model to forecast the reliability performance tendency and remaining useful life under imperfect maintenance based on the inspection records and the maintenance actions.Design/methodology/approachA real-time hidden Markov chain (HMM) model is proposed in this paper to predict the reliability performance tendency and remaining useful life under imperfect maintenance based on rare failure events. The model assumes a Poisson arrival pattern for facility failure events occurrence. HMM is further adopted to establish the transmission probabilities among stages. Finally, the simulation inference is conducted using Particle filter (PF) to estimate the most probable model parameters. Water seals at the spillway hydraulic gate in a Taiwan's reservoir are used to examine the appropriateness of the approach.FindingsThe results of defect probabilities tendency from the real-time HMM model are highly consistent with the real defect trend pattern of civil facilities. The proposed facility degradation prediction model can provide the maintenance division with early warning of potential failure to establish a proper proactive maintenance plan, even under the condition of rare defects.Originality/valueThis model is a new method of civil facility degradation prediction under imperfect maintenance, even with rare failure events. It overcomes several limitations of classical failure pattern prediction approaches and can reliably simulate the occurrence of rare defects under imperfect maintenance and the effect of inspection reliability caused by human error. Based on the degradation trend pattern prediction, effective maintenance management plans can be practically implemented to minimize the frequency of the occurrence and the consequence of civil facility failures.

CT-Based Dimensional Metrology for Quality Assessment of the Internal Structure of Additive Manufactured Aluminum Parts

Two common types of internal defects of additively manufactured (AM) samples are lack-of-fusion and gas-entrapped porosities. These internal defects can have different physical origins and particular local characteristics (e.g., different shape, size). Thus, the use of reliable non-destructive inspection techniques is essential for the accurate assessment of integrity, allowing the applicable AM processing parameters correction. To overcome this challenge, this work aims to evaluate the accuracy of volumetric characteristics measured by computed tomography for porosity evaluations in AM samples, including assessment of measurement uncertainty. The effect of different cumulative thickness on the evaluated measurements accuracy is also assessed. The results show that deviations of defect size measurements can be below 2% if the proposed procedure is followed. In addition, the expanded uncertainty can be up to 10% of the measured magnitude when the cumulative thickness is increased to 70 mm. The physical relationships obtained between the cumulative thickness and the individual measurements are also presented.