Inspection Of Parts Research Articles

Development of High-Accuracy Defect Detection Algorithm for X-Ray Welding Image Inspection under Strong Noise, Low Contrast and Few Samples

We have developed an algorithm to accurately detect unclear defects in X-ray image inspection of thick welded parts under low contrast, and strong noise. Statistical Reach Features (SRF) and High-order Local Autocorrelation (HLAC) are used as noise-robust feature extraction methods. In order to deal with a small number of defect samples, pseudo-defect data with actual noise is used for machine learning. When the discriminator is optimized for zero missing, the over-detection is significantly reduced, and the method is ready for practical application.

Automated platform for consistent part realization with regenerative hybrid additive manufacturing workflow

Nowadays, the role of hybridization within the wider manufacturing ecosystem gains significant momentum with multiple commercial solutions already available on the market. Despite the very promising benefits of combining and selectively exploiting the advantages of additive and subtractive technologies on the same machine, hybrid additive manufacturing is far from reaching its full potential. One of the central limitations of existing hybrid process chains is the lack of a harmonized, structured and automated workflows to support an adaptive manufacturing strategy. This work is motivated by the need to bridge this gap and to capture the logic behind an adaptive hybrid process chain with the aim to support the achievement of enhanced product quality and improved operational efficiency in hybrid additive manufacturing. The paper discusses the implementation of a hybrid CAx platform and the underlying methodology aiming at the dynamic reduction of variabilities associated with the laser metal deposition process. The hybrid workflow identifies the most adapted sequence and planning of additive and subtractive operations while considering part inspection as an in-envelope functionality to quantify the geometrical and dimensional part deviations and to trigger the regenerative mechanism. The methodology is demonstrated on a hybrid machine by deploying laser ablation for the in situ removal of build deviations and an adapted deposition operation as part of a regenerative strategy leading to higher part confidence.

IoT-enabled computer vision-based parts inspection system for SME 4.0

This paper presents a Computer vision-based Measurement (CViM) system for three-dimensional (3D) mechanical parts. The system integrates with internet of things (IoT) and demonstrates a low cost and modular implementation of SME 4.0 framework. A complete system design including hardware and software is presented. Three cameras are used to capture various images that expose different dimensions of the mechanical part. Back lighting is used to illuminate the part placed on the V-shaped translucent surface, which results in images with improved contrast thereby improving the measurement accuracy compared to front lighting. The software algorithm performs camera calibration to eliminate the lens distortion and pre-processing for image enhancement and noise elimination. Next, image binarization is performed to highlight the edges of the object. The desired dimensions are extracted from the image followed by pixel to physical measurement mapping. The system is tested by measuring physical dimensions of a drill bit and a screwdriver bit and it achieves an accuracy of tenth of a millimeter (mm). Several dimensions of the test parts are measured, such as, total length, back radius, groove length etc., which are the most number of dimensions considered, compared to previous studies. The results demonstrate that the maximum difference between the measured and the actual dimensions is ± 0.05 mm. A conceptual model of IoT-enabled CViM system for parts inspection in small and medium-sized industries is also presented. The system has a fairly low cost and is very suitable for such industries with similar accuracy requirements for their parts inspection.

Probe Standoff Optimization Method for Phased Array Ultrasonic TFM Imaging of Curved Parts.

The reliability of the ultrasonic phased array total focusing method (TFM) imaging of parts with curved geometries depends on many factors, one being the probe standoff. Strong artifacts and resolution loss are introduced by some surface profile and standoff combinations, making it impossible to identify defects. This paper, therefore, introduces a probe standoff optimization method (PSOM) to mitigate such effects. Based on a point spread function analysis, the PSOM algorithm finds the standoff with the lowest main lobe width and side lobe level values. Validation experiments were conducted and the TFM imaging performance compared with the PSOM predictions. The experiments consisted of the inspection of concave and convex parts with amplitudes of 0, 5 and 15 λAl, at 12 standoffs varying from 20 to 130 mm. Three internal side-drilled holes at different depths were used as targets. To investigate how the optimal probe standoff improves the TFM, two metrics were used: the signal-to-artifact ratio (SAR) and the array performance indicator (API). The PSF characteristics predicted by the PSOM agreed with the quality of TFM images. A considerable TFM improvement was demonstrated at the optimal standoff calculated by the PSOM. The API of a convex specimen’s TFM was minimized, and the SAR gained up to 13 dB, while the image of a concave specimen gained up to 33 dB in SAR.

Design and construction of a test bench for the manufacture and on-machine non-contact inspection of parts obtained by Fused Filament Fabrication

Industrial application of additive manufacturing (AM) technologies is subjected to limitations related to the lack of dimensional and geometrical accuracy of manufactured parts. Many works were dedicated to improve quality of parts manufactured by AM, but integrated solutions in commercial-type AM machines have not been achieved yet. With this aim, the present work describes the design, manufacture and starting-up of a mechatronic test bench first prototype, with the double capability of 3D printing by Fused Filament Fabrication (FFF) and non-contact inspection of deposited layers. Both systems operate coordinately as the part is constructed. Final tests describe the effectiveness of both integrated systems and state the basis for further research.

An evaluation method of preventive renewal strategies of railway vehicles selected parts

The aim of the work was to develop a method of verification of the preventive renewal strategies, which enables a simulation evaluation of the effects of the application of a specific schedule of inspections of parts that are important in the operation of complex renewable technical objects. Using it requires having an already established schedule of inspections, and the result of applying the method is determined by indicators that assess the usefulness of the strategy, even before implementation. The developed computational tool was used to evaluate the renewal strategy of the current collector contact plates. Based on the real operational data, several renewal intervals were considered, determining the frequency of events involving the plate covering a specific mileage, from exceeding the wear control limit value to the next inspection (replacement). The proposed verification method is an important tool for testing and planning technical inspections for systems and elements with planned wear, and parts are periodically replaced.

Industrial parts change recognition model using machine vision, image processing in the framework of industrial information integration

This paper presents the industrial parts change recognition model using machine vision image processing in the framework of industrial information integration and it is applied research's category. Therefore, this study implements a new industrial information integration engineering (IIIE)system by combining components that have previously been expressed separately by previous research to develop inspection of industrial parts and improve its quality and accuracy of human visual inspection status and this is the innovative aspect of this research. We used machine vision to improve human vision in change recognition in objects such as cracks, fractures… and that has been the research issue. So, this study aims to aggregate different tools identified by other researchers in change recognition in different parts because human vision is weak, and current mechanical tools such as sensors have several problems such as calibration and accurate maintenance and repair and errors. The proposed model can be used in two fields, first, recognition of the difference between family-made industrial parts with the standard sample in the production lines online, second, monitoring and controlling changes in the working industrial parts such as moving rails, train wheels, brake discs, clutch plates, various motor parts, etc. In the first case, every manufacturer needs to produce parts, such as the standard prototype for the production line. Therefore, if the machinery of the production line is out of calibration for any reason, products will be made out of standard, which would mean a reduction in the quality or an increase in production costs. Therefore, online monitoring of production lines with the help of machine vision is important in reducing production costs. In the second case, recognition of the timely change in the working industrial parts can also prevent accidents. In other words, timely detection of failure can be effective in preventing accidents in addition to reducing costs. For example, the timely detection of a train wheel or train rail wear and its timely repair or replacement will prevent the occurrence of a rail accident, which is one of the applications of the proposed model. Since the results of this study are compared with those of industrial parts with standard samples, the results are sufficiently valid. The study was conducted by the authors and no organization was involved.

Registration strategy of point clouds based on region-specific projections and virtual structures for robot-based inspection systems

Current requirements resulting from high quality standards, individualized mass production, and cost pressure call for new concepts in manufacturing metrology. Robot-based optical inspection systems have shown high potential to cope with these challenges. Since the kinematics of robots usually exhibit significant inaccuracies, an alternative approach becomes necessary to register multiple views of a sensor. With the advancement of optical 3D sensors in recent years, registration methods based on measured data (e.g. point clouds with image data) have shown tremendous progress and potential. Therefore, we present a new registration strategy which uses region-specific projections (image data) and virtual structures (point data) to support the alignment process of multiple point clouds. The fine registration is done in a pairwise manner and by means of an Iterative Closest Point (ICP) algorithm. We first introduce a procedure to obtain a set of virtual structures. Subsequently, influencing factors, such as the parametrization of the structures, noise, detection methods for the projected shapes, and the underlying surface, are examined. Based on these results, we identify virtual structures and employ them to evaluate the registration strategy in a real-world use case in the context of geometric quality assurance in the automotive industry. Acquired sphere-to-sphere distances are compared to reference measurements obtained from a coordinate measuring machine (CMM). The virtual structure comprising three point-based “columns” with an increasing point spacing in a triangular arrangement showed the best overall performance. The mean error (34 μm for one registration; 70 μm and 54 μm for two registrations respectively) in comparison to the robot kinematics was reduced by a factor of about 14 to 23 for the different reference distances. We demonstrated that our registration strategy enables a highly accurate and robust alignment of point clouds, which benefits manufacturing metrology for the inspection of sheet metal parts.

Enhanced precision inspection of free-form surface with an improved whale optimization algorithm.

For precision inspection of free-form surface parts using non-contact measurement methods, the registration between the actual measurement model and the ideal design model is necessary.The traditional iterative closure point (ICP) method requires good initial parameters to obtain the global optimal transformation matrix, which is difficult to guarantee in the actual detection process. In order to improve the accuracy and robustness of free-form surface precision inspection, an Improved Whale Optimization Algorithm (IWOA) is proposed in this study.This algorithm can solve the required registration parameters by constantly updating the population. A measurement experimental system is designed to test the accuracy of blade registration. The performance of IWOA is evaluated by the actual measurement experiment, and the results are verified by a comparative study with Whale Optimization Algorithm (WOA), Lévy flight trajectory-based Whale Optimization Algorithm (LWOA), and Adaptive Whale Optimization Algorithm (AWOA). The surface registration errors are 0.1711mm for IWOA, 2.0015 mm for WOA, 1.2656 mm for LWOA, 2.8132 mm for AWOA and 2.1537 mm for ICP. The results show that the accuracy of IWOA is more than 7 times higher than other four algorithms. In general, the experiments indicate that IWOA has a good registration ability and can meet the needs of industrial measurement.

Imaging sensor data modelling and evaluation based on optical composite characteristics

Automated Fibre Placement is a common manufacturing technique for composite parts in the aero-space industry. Therefore, a visual part inspection is required which often covers up to 50% of the actual production time. Moreover, the inspection quality of this manual step fluctuates significantly. A camera-based automated inline inspection is capable of increasing the inspection efficiency and accuracy. However, the interpretability of the acquired data strongly depends on the sensor configuration and the inspected material. Thus, this paper introduces methods for modelling and assessing an imaging sensor on the example of a composite material reflecting a spot laser to a camera sensor. In this context, the reflection properties of the material are incorporated into a simulation and validated in comparison to real camera images from the experimental setup. The EMVA 1288 sensor model in combination with the Cramér–Rao lower bound indicates a feasible estimability of the beam propagation, but shows limitations in the predictability of the number of incident photons. The laser spot analysis indicated that the laser spot can deviate from an exact oval shape but its peak value is suitable for robust spot identification in an image. The outlined methodology is also adaptable to other imaging sensors, illumination sources and materials. Thus, the findings can be useful for other fields and manufacturing processes.

Touch Probe Measurement in Dimensional Metrology: A Review

Coordinate measuring machines (CMMs) are the standard displacement systems used for measurements in dimensional metrology. Since measurement with a touch probe mounted on a CMM provides high accuracy, repeatability, and reliability, it has been widely used for mechanical part inspection in manufacturing. The inspection process requires the use of several sensor orientations and optimal positioning of the part in order to measure all features. Recently, the field of probing path planning has become a huge and active research field. In this paper, various techniques aimed at generating the probe paths for part inspection are reviewed. Multiple issues related to the positioning of the part to maximise accessibility, analysis of probe accessibility to measure all inspection features, optimisation of the measurement sequence, distribution of measurement points, and collision avoidance are mentioned. The common research approaches and potential algorithms in this field are also discussed in this paper.

An Approach to Detect White Spots during Pre-Turning of DA718 Components

The increasing demand for high-performance components is leading to a greater use of advanced alloys such as DA718, which is, e.g., used in engine parts due to its high-temperature strength. The strict quality requirements pose major challenges for the machining of engine components for aircrafts. Quality deviations along the value chain can lead to high costs due to rework and, in the worst case, rejections in order to prevent material failure within a safety-critical environment. These deviations include, e.g., an increased surface roughness, deviations in the shape tolerances as well as increased internal stresses or surface deformations. Material defects are an additional reason to reject the manufactured components. These are usually inspected only at the end of the value chain and—due to measurement limitations—only if they occur close to the surface of the workpiece. Ultrasonic testing is used in order to detect defects near the surface of the raw part. For the evaluation of the finished part, etching and optical inspection of the surface is used. However, defects inside the components cannot be detected in this way. If material defects are located in areas subjected to intense load changes and high temperatures, the components have to be rejected since engine parts require a high level of fatigue strength. Such rejects constitute a significant economic risk, as a large part of the added value has already been completed and a significant amount of machine time has been invested. Thus, an identification of material defects in an earlier stage of the manufacturing process is required. In this paper, fundamental investigations on machining artificially generated material defects in a micro-milling process and the signal analysis during the pre-turning of turbine disks made of nickel-based materials like DA718 will be presented. Based on force measurements, characteristic signals were identified that could indicate material defects during the turning process.

Quantitative Inspection of Complex-Shaped Parts Based on Ice-Coupled Ultrasonic Full Waveform Inversion Technology

Ultrasonic methods have been extensively developed in nondestructive testing for various materials and components. However, accurately extracting quantitative information about defects still remains challenging, especially for complex structures. Although the immersion technique is commonly used for complex-shaped parts, the large mismatch of acoustic impedance between water and metal prevents effective ultrasonic transmission and leads to a low signal-to-noise ratio(SNR). In this paper, a quantitative imaging method is proposed for complex-shaped parts based on an ice-coupled full waveform inversion (FWI) method. Numerical experiments were carried out to quantitatively inspect the various defects in a turbine blade. Firstly, the k-space pseudospectral method was applied to simulate ice-coupled ultrasonic testing for the turbine blade. The recorded full wavefields were then applied for a frequency-domain FWI based on the Limited-memory Broyden–Fletcher–Goldfarb–Shanno (L-BFGS) method. With a carefully selected iterative number and frequency, a successive-frequency FWI can well detect half wavelength defects. Extended studies on an open notch with different orientations and multiple adjacent defects proved its capability to detect different types of defects. Finally, an uncertainty analysis was conducted with inaccurate initial velocity models with a relative error of ±2%, demonstrating its robustness even with a certain inaccuracy. This study demonstrates that the proposed method has a high potential to inspect complex-shaped structures with an excellent resolution.

Phased Array Ultrasonic Testing of Inconel 625 Produced by Selective Laser Melting

Abstract We investigate the use of phased array ultrasonic testing (PAUT) as an offsite non-destructive quality assurance technique for parts made by selective laser melting (SLM). SLM is a popular additive manufacturing (AM) approach for fabricating high-value metallic components with complex geometries. Slight variations in the laser power during fabrication might lead to internal defect development within the part, which could compromise its mechanical strength and fatigue life. PAUT is employed to detect typical internal porosity generated in Inconel 625 samples due to laser power fluctuation during SLM. The typical defect size, shape, and distribution are first identified using metallography and X-ray computed tomography (XCT). B-Scan images of the defect region is then generated experimentally using a 5-MHz linear UT phased array probe. Finite elements simulate wave propagation using geometries obtained from XCT images. The simulation results are compared to the experimental imaging of large defect regions and then used to generate total focusing method images of isolated clusters of 50–200 μm defects. The testing technique illustrates a successful application of PAUT for quality inspection of SLM parts.

Evaluation of probabilistic characteristics of measurement results during parts inspection

The features of control of linear dimensions in repair production have presented. The main factors influencing the measurement results have identified. Possible consequences of the influence of the measurement error in the control of linear dimensions have indicated. The analysis of existing methods for assessing the probabilistic characteristics of measurement results has carried out. A diagram of the control of parts such as a hole, has been drawn up, which reflects the probabilistic characteristics of the measurement results, taking into account the influence of the error on the sorting results. The results of approbation of the developed technique have presented on the example of measuring the diameters of the restored main and connecting rod journals of the engine crankshafts.

A Systems Approach to Estimating the Uncertainty Limits of X-Ray Radiographic Metrology

Abstract Micro- and nanomanufacturing capabilities have rapidly expanded over the past decade to include complex three-dimensional (3D) structure fabrication; however, the metrology required to accurately assess these processes via part inspection and characterization has struggled to keep pace. X-ray computed tomography (CT) is considered an ideal candidate for providing the critically needed metrology on the smallest scales, especially internal features, or inaccessible regions. X-ray CT supporting micro- and nanomanufacturing often push against the poorly understood resolution and variation limits inherent to the machines, which can distort or hide fine structures. We develop and experimentally verify a comprehensive analytical uncertainty propagation signal variation flow graph (SVFG) model for X-ray radiography in this work to better understand resolution and image variability limits on the small scale. The SVFG approach captures, quantifies, and predicts variations occurring in the system that limit metrology capabilities, particularly in the micro/nanodomain. This work is the first step to achieving full uncertainty modeling of CT reconstructions and provides insight into improving X-ray attenuation imaging systems. The SVFG methodology framework is applied to generate a complete basis set of functions describing the major sources of variation in radiographs. Five models are identified, covering variation in energy, intensity, length, blur, and position. Radiographic system experiments are defined to measure the parameters required by the SVFGs. Best practices are identified for these measurements. The SVFG models are confirmed via direct measurement of variation to predict variation within 30% on average.

Machine Vision based quality inspection for automotive parts using edge detection technique

This paper discusses the way in which the efficacy of inspection process can be improved. In the existing system the products are inspected manually to identify the defects. However, existing methodology is not efficient or accurate. On account of this the product is at a high risk of being rejected due to its low quality. This can lead to a hike in the production cost. In present industrial conditions there is an enormous competition in the manufacturing industry, therefore it is a necessity to maintain a high-quality inspection process to cope up with the competition. This can be achieved with the help of advanced technologies like machine vision. This technology uses a non-contact method of inspection. Compared to the existing technology this technology has improved efficiency and accuracy, while consuming less time. Thus, allowing the industries to keep up with the current competitive environment.

Statistical point cloud model to investigate measurement uncertainty in coordinate metrology

In this work an approach to investigate measurement uncertainty in coordinate metrology is presented, based on fitting Gaussian random fields to high-density point clouds produced by measurement repeats. The fitted field delivers a depiction of the spatial distribution of random measurement error over a part geometry, and can incorporate local bias information through further measurement or with the use of an external model to obtain a complete, spatial uncertainty map. The statistical model also allows the application of Monte Carlo simulation to investigate how error propagates through the data processing pipeline ultimately affecting the determination of features of size and the verification of conformance to specifications. The proposed approach is validated through application to simulated test cases involving known measurement error, and then applied to a real part, measured with optical and contact technologies. The results indicate the usefulness of the approach to estimate measurement uncertainty and to investigate performance and behaviour of measurement solutions applied to the inspection and verification of industrial parts. The approach paves the way for the implementation of automated measurement systems capable of self-assessment of measurement performance.

Automotive Brake Part Inspection and Fault Localization using Deep Learning

Inspection of brake components is very essential to detect the damaged manufactured parts before it is assembled in any vehicle. Manual inspection of brakes is extremely difficult since most of defects are very minute and cannot be identified by human eyes. Therefore, automatic inspection of manufactured brakes is indispensible to prevent failure of brakes and accidents. Previously, various research articles perform inspection of brake through conventional image processing and traditional image processing algorithms. However, these techniques are capable of identifying a single fault only and are less robust to detecting numerous faults. Further, the existing techniques hardly localize the exact location of faults in the surface of brake. In order to over these drawbacks, in this research we utilize deep learning object detection algorithms namely Single Shot Detector and Faster RCNN to identify and localize the exact location of fault on the brake surface. Furthermore, the proposed system is capable to detect different types of faults in a single algorithm and is robust to brake’s material surface, environmental and lightening factors. The deep learning algorithms are trained using transfer learning on custom collected dataset. The proposed algorithms deliver an accuracy of 95.64% and mAP of 73.2% on cylindrical grey shade brakes.

A functional modeling approach for quality assurance in metal additive manufacturing

Purpose Due to the complexity of and variations in additive manufacturing (AM) processes, there is a level of uncertainty that creates critical issues in quality assurance (QA), which must be addressed by time-consuming and cost-intensive tasks. This deteriorates the process repeatability, reliability and part reproducibility. So far, many AM efforts have been performed in an isolated and scattered way over several decades. In this paper, a systematically integrated holistic view is proposed to achieve QA for AM. Design/methodology/approach A systematically integrated view is presented to ensure the predefined part properties before/during/after the AM process. It consists of four stages, namely, QA plan, prospective validation, concurrent validation and retrospective validation. As a foundation for QA planning, a functional workflow and the required information flows are proposed by using functional design models: Icam DEFinition for Function Modeling. Findings The functional design model of the QA plan provides the systematically integrated view that can be the basis for inspection of AM processes for the repeatability and qualification of AM parts for reproducibility. Research limitations/implications A powder bed fusion process was used to validate the feasibility of this QA plan. Feasibility was demonstrated under many assumptions; real validation is not included in this study. Social implications This study provides an innovative and transformative methodology that can lead to greater productivity and improved quality of AM parts across industries. Furthermore, the QA guidelines and functional design models provide the foundation for the development of a QA architecture and management system. Originality/value This systematically integrated view and the corresponding QA plan can pose fundamental questions to the AM community and initiate new research efforts in the in-situ digital inspection of AM processes and parts.