Inspection Of Parts Research Articles

Joint optimization of part quality inspection planning, buffer allocation, and preventive maintenance in a serial manufacturing

Joint optimization of part quality inspection planning, buffer allocation, and preventive maintenance in a serial manufacturing

Empowering decentralized production: A distributed manufacturing system for additive manufacturing processes

This work presents a pilot distributed manufacturing system for decentralized additive manufacturing, focusing on the Interdisciplinary Center for Advanced Manufacturing Systems (ICAMS) capabilities at Auburn University. The paper outlines the first phase of a multi-phase implementation plan and demonstrates the developed capabilities. The vision is to coordinate geographically separated manufacturing facilities as a cohesive unit. In our work, we prioritize instantaneous communication for file and information sharing. The Manufacturing Hub and Remote Cell, two facilities within driving distance, are coordinated in terms of part design, printing, and inspection procedures for a distributed Additive Manufacturing process. To enable coordination between the two facilities, ICAMS addresses three technological needs. These needs consider information sharing, process standardization, and data collection and monitoring. A network attached storage facilitates information sharing, a database-connected graphical user interface streamlines and standardizes the manufacturing process, and a data collection system facilitates process monitoring. The graphical user interface allows for order placement, progress monitoring, and communication updates. The developed phased plan, collaborative workflow, technological solutions, and production protocols demonstrate the potential for decentralized additive manufacturing. Successful integration of communication, design, printing, and quality assurance processes sets the foundation for future advancements in decentralized manufacturing systems.

UNMANNED AERIAL VEHICLES AS AN EFFECTIVE TOOL IN THE INSPECTION OF BRIDGE STRUCTURES

Statement of the problem. In today's world, technologies are rapidly being introduced into various spheres of our lives, providing new opportunities and increasing the efficiency of various processes. One such technology is unmanned aerial vehicles, which are gaining more and more popularity in the field of engineering and construction. Drones prove to be extremely useful in surveying bridge structures, where safety and efficiency are critical factors. The purpose of the article is to consider the advantages of using unmanned aerial vehicles in the process of inspecting bridge structures and their impact on improving the safety and productivity of this process, photo materials of the state of some bridge structures on the territory of Ukraine are given Conclusions. Conclusions. In the modern world, one of the most relevant ways to obtain information is unmanned aerial vehicles. Their use, with artificial intelligence technologies, is one of the most effective tools in the inspection of bridge structures. Together, they can quickly inspect the object and accurately determine the possible dimensions of damage according to the built three-dimensional model. The data obtained from the object of inspection allow you to manage resources and rationally plan the maintenance and repair of bridge structures. The quality and pace of inspection of both underwater and ground parts of bridge supports are improving. The UAV is capable of inspecting more than 70 km of the flight route in an hour. Drones are a very effective tool for surveying bridge structures, but it is important to be aware of their limitations and solve related problems based on the specific conditions and requirements of the project. It is easier to analyze and evaluate damaged structures as there is a real picture of the survey, taken from a height of some meters.

Optimization scheme design in production process based on multi-stage decision-making

This paper studies the control of defective rate in the electronic industry chain, designs a small sample binomial distribution sampling detection scheme to verify the supplier 's defective rate statement and optimize the detection cost. Based on the defective rate, the linear programming and dynamic programming / decision tree model are used to optimize the multi-stage production process, including parts inspection, finished product inspection and unqualified product treatment, so as to maximize the profit of the enterprise. A phased optimization strategy is proposed for complex multi-process situations. Finally, according to the sampling test results, the defect rate estimation is adjusted, the problem model is re-optimized, and the cost control reference scheme is provided.

On-machine inspection and compensation for thin-walled parts with sculptured surface considering cutting vibration and probe posture

Abstract On-machine inspection has a significant impact on improving high-precision and efficient machining of sculptured surfaces. Due to the lack of machining information and the inability to adapt the parameters to the dynamic cutting conditions, theoretical modeling of profile inspection usually leads to insufficient adaptation, which causes inaccuracy problems. To address the above issues, a novel coupled model for profile inspection is proposed by combining the theoretical model and the data-driven model. The key process is to first realize local feature extraction based on the acquired vibration signals. The hybrid sampling model, which fuses geometric feature terms and vibration feature terms, is modeled by the lever principle. Then, the weight of each feature term is adaptively assigned by a multi-objective multi-verse optimizer. Finally, an inspection error compensation model based on the attention mechanism considering different probe postures is proposed to reduce the impact of pre-travel and radius errors on inspection accuracy. The anisotropy of the probe system error and its influence mechanism on the inspection accuracy are analyzed quantitatively and qualitatively. Compared with the previous models, the proposed hybrid profile inspection model can significantly improve the accuracy and efficiency of on-machine sampling. The proposed compensation model is able to correct the inspection errors with better accuracy. Simulations and experiments demonstrate the feasibility and validity of the proposed methods. The proposed model and corresponding new findings contribute to high-precision and efficient on-machine inspection, and help to understand the coupling mechanism of inspection errors.

Inspecting Hard Facing Doesn’t Have to Be Hard: PCI of Chrome Carbide Overlay

Mining equipment needs to be tough to withstand the harsh demands of the mining process. During operation, many mining extraction and processing components are subject to abrasion, often compounded by corrosion. To shield surfaces from wear, they can be protected with a welded layer called hard facing. Chrome carbide overlay (CCO) is a go-to hard-facing solution because of its wear resistance and affordability compared with other overlay options such as tungsten. Regardless of the durability of mining assets, proactive inspection and maintenance of parts that endure the most wear and tear is essential to extend the life of equipment. Ultrasonic testing (UT) is a favored method for this, as it offers a portable nondestructive testing (NDT) option for inspecting CCO and hard facing. Recent advancements in UT technology have produced a technique that has the potential to solve some challenges associated with this inspection application.

Robotical Automation in CNC Machine Tools: A Review

Abstract Robotics and automation have significantly transformed Computer Numerical Control (CNC) machining operations, enhancing productivity, precision, and efficiency. Robots are employed to load and unload raw materials, workpieces, and finished parts onto CNC machines. They can efficiently handle heavy and bulky components, reducing the demand of manual labour and minimizing the risk of injuries. Robots can also be used in CNC machine tools to perform tasks such as automatic tool changing system, part inspection, and workpiece positioning. Automation technologies, including in-line inspection systems and Non-Destructive Testing (NDT) methods, can be integrated into CNC machining cells to enhance accuracy and reduce scrap and rework in machining operations. These systems collect real-time data on process parameters and machine tool performance to predict maintenance, optimize machining parameters, and improve overall efficiency. In the current study, applications of robotics and automation in the modification of CNC machine tools are reviewed and discussed. Different applications of robotics and automation in CNC machine tools, such as automated material handling, automatic tool changing, robotic work cells, adaptive machining, machine tending, quality inspection, data monitoring and analysis, and production line integration, are discussed. Thus, by analysing recent achievements in published papers, new ideas and concepts of future research works are suggested. As a result, accuracy as well as productivity in the process of part production can be enhanced by applying robotics and automation in CNC machining operations.

Application of image processing technology based on field programmable gate array in mechanical part inspection

Introduction: In the field of industrial manufacturing, accurate inspection of mechanical components such as gears and bearings is of Paramount importance. However, the traditional mechanical testing methods are often disturbed by human factors, which not only affects the stability of the test results, but also leads to low efficiency and large error. In order to solve these problems, this research focuses on developing a new edge detection model.Methods: A novel edge detection model based on field-programmable gate array image processing technology was used in this study. The model uses adaptive threshold multi-directional edge detection technology to identify the edge features of mechanical gears and bearings, aiming at improving the precision of detection.Results and Discussion: After performance verification, the running time of the model was controlled within 11 s, and the detection error was limited to less than 9%. Compared with the control group and the experimental group, their performance was superior. Further analysis data show that the detection accuracy of this model is as high as 0.9004, its internal resource utilization rate is 88%, and the detection rate is as high as 91%, which are better than the comparison model.Conclusion: The proposed test model not only significantly improves the efficiency and accuracy of the test, but also fully meets the requirements of the test. This new edge detection model has potential application value in industrial manufacturing field, and provides a new solution for industrial manufacturing quality inspection.

A novel pose calibration method for laser displacement sensor in the five-axis on-machine measurement system

The five-axis on-machine measurement system, equipped with a laser displacement sensor, offers an effective approach for conducting on-site inspections of freeform surface parts. It is crucial to address the calibration error pertaining to the sensor’s pose, encompassing both the beam direction and the zero position, as it directly impacts the measurement accuracy. This paper presents a new approach for the calibration of a laser displacement sensor’s pose, which is mounted on the spindle of a five-axis gantry machine tool. The proposed method utilizes measurements taken from multiple angles of a standard ball. Through the utilization of spherical constraints and coordinate translation transformation, the Levenberg-Marquardt iteration method is employed to derive the sensor’s beam direction, while the least square method is used to determine the sensor’s zero position. Applying this proposed method, the maximum error in the distance between the centers of the standard double ball is below 0.008 mm, which can meet the precision requirements of on-site inspection of freeform surface parts.

Research on slope algorithm based laser welding guidance technology for 3D vision inspection of thin-walled parts

Visual guidance technology advances quickly and so do the technical requirements for weld trajectory, which needs to fulfill performance indices for high precision, anti-interference and quick processing. In this study, the approach of getting 3D point cloud data by directly scanning the workpiece to be welded with a 3D scanner is used because it is more precise and reliable than processing gray-layer data obtained from a depth camera, turning it into a 3D point cloud. The weld boundary is retrieved by slope calculation for the butt weld after preprocessing the three-dimensional point cloud data (cut, down-sampling, and abnormal value removal). The center point is then determined. After that, a welding trajectory is produced by fitting the center point, which is transmitted back to the actuator to guide its welding work and realize the identification and tracking of the weld.

LNMVSNet: A Low-Noise Multi-View Stereo Depth Inference Method for 3D Reconstruction.

With the widespread adoption of modern RGB cameras, an abundance of RGB images is available everywhere. Therefore, multi-view stereo (MVS) 3D reconstruction has been extensively applied across various fields because of its cost-effectiveness and accessibility, which involves multi-view depth estimation and stereo matching algorithms. However, MVS tasks face noise challenges because of natural multiplicative noise and negative gain in algorithms, which reduce the quality and accuracy of the generated models and depth maps. Traditional MVS methods often struggle with noise, relying on assumptions that do not always hold true under real-world conditions, while deep learning-based MVS approaches tend to suffer from high noise sensitivity. To overcome these challenges, we introduce LNMVSNet, a deep learning network designed to enhance local feature attention and fuse features across different scales, aiming for low-noise, high-precision MVS 3D reconstruction. Through extensive evaluation of multiple benchmark datasets, LNMVSNet has demonstrated its superior performance, showcasing its ability to improve reconstruction accuracy and completeness, especially in the recovery of fine details and clear feature delineation. This advancement brings hope for the widespread application of MVS, ranging from precise industrial part inspection to the creation of immersive virtual environments.

Defect detection in additively manufactured AlSi10Mg and Ti6Al4V samples using laser ultrasonics and phase shift migration

Laser ultrasonics (LU) is a non-contact and non-destructive method with a high data acquisition rate, making it a promising candidate for in-situ monitoring of defects in different additive manufacturing (AM) processes, including laser powder bed fusion (LPBF) and directed energy deposition, as well as final part inspection. In order to see the effect of various artificial defect types on an LU sub-surface reconstruction, AlSi10Mg samples with side through-holes, as well as Ti6Al4V samples with bottom blind holes and trapped powder were printed using LPBF, and then ultrasound B-scans of the samples were obtained using an LU system. The resulting scan data was processed using a custom frequency domain phase shift migration (PSM) algorithm, to reconstruct the defects and their locations. Novel ways of pre-processing the B-scan, used as an input to PSM, and taking advantage of its frequency representation, are demonstrated. Newton’s method was used to find a stationary phase approximation, used to account in the frequency domain for the fixed offset emitter-receiver arrangement within the PSM calculation. The Newton’s method calculation time was reduced by 33%, by using an approximation of the phase function to find an initial guess. The smallest defects that were detected using this method were in the size range between 200 to 300μm for the bottom hole defects, using an 8 ns laser pulse duration. The effect of the laser on the surface of a part being built, and the challenges and further work needed to integrate LU in a LPBF machine for in-situ inspection are discussed.

Furnace Tail Weld Failure Analysis of the B35.1-Pressure Vessel

Leakage failure is caused by cracks in the weld joint between the body and flange of a pressure vessel. The container body material is graded as P460NH according to the European standard. It operates at a working temperature of 750 °C and a work pressure of 1.5 MPa. It undergone heating once every half a month. The instrument has been in service for 12 years. The crack is located at the weld joint of the flange connection at the end of the pressure vessel with a significant accumulation of black deposits on the interior surface of the reaction kettle. The medium in the production process is nitrogen, coke steam and asphalt steam mixture (including “S”). Macroscopic analysis, physical metallographic inspection, mechanical property analysis and chemical composition inspection of the failure parts are carried out to determine the cause of fracture failure of the pressure vessel B35.1 furnace tail weld. The results show that there are no detailed corrosion thinning areas in the failure parts, there are corrosion products on the surface and the corrosion cracks are distributed in a spatial network, which has the characteristics of stress corrosion. The corrosion causes should be sulfide stress corrosion caused by environment.

Custom lens design for ultrasonic inspection of immersed anisotropic parts

Inspection of anisotropic parts using immersion ultrasonic waves poses resolution challenges caused by directionally dependent wave properties. Currently, focused lenses with spherical or cylindrical geometries are the standard method for creating convergent, small cross-section, and high amplitude beams within solids. These lenses form a conical beam that uniformly refracts at the fluid-solid interface of the immersed part when the solid is isotropic, producing the desired focusing behavior. However, for anisotropic solids, refraction becomes directionally dependent, which distorts the beam and causes non-uniform focal profiles and, in some cases, multiple foci. In this work, the forward wave propagation for an immersed anisotropic solid is modeled and exploited to develop custom lens geometries. These custom lenses utilize inverted slowness profiles to produce conical beams within the anisotropic solid. By incorporating these lenses, the focused beam behavior is improved and becomes more circular, higher in amplitude, and smaller in the cross-sectional area. These lenses have the potential to improve inspection resolution in anisotropic solids, an effort beneficial to the additive, aerospace, and electronics industries.

In-situ quality inspection system of injection parts based on transfer learning

PurposeThis paper aims to realize an in-situ quality inspection system rapidly for new injection molding (IM) tasks via transfer learning (TL) approach and automation technology.Design/methodology/approachThe proposed in-situ quality inspection system consists of an injection machine, USB camera, programmable logic controller and personal computer, interconnected via OPC or USB communication interfaces. This configuration enables seamless automation of the IM process, real-time quality inspection and automated decision-making. In addition, a MobileNet-based deep learning (DL) model is proposed for quality inspection of injection parts, fine-tuned using the TL approach.FindingsUsing the TL approach, the MobileNet-based DL model demonstrates exceptional performance, achieving validation accuracy of 99.1% with the utilization of merely 50 images per category. Its detection speed and accuracy surpass those of DenseNet121-based, VGG16-based, ResNet50-based and Xception-based convolutional neural networks. Further evaluation using a random data set of 120 images, as assessed through the confusion matrix, attests to an accuracy rate of 96.67%.Originality/valueThe proposed MobileNet-based DL model achieves higher accuracy with less resource consumption using the TL approach. It is integrated with automation technologies to build the in-situ quality inspection system of injection parts, which improves the cost-efficiency by facilitating the acquisition and labeling of task-specific images, enabling automatic defect detection and decision-making online, thus holding profound significance for the IM industry and its pursuit of enhanced quality inspection measures.

Calculations of Temperature and Thermo-Elastic Displacement Distributions Generated by Laser-Ultrasonic Inspection System

Calculations of temperature and thermo-elastic displacement distributions generated by laser-ultrasonic inspection system are performed. The goal is to determine temperature distributions created in the test objects by generation laser and the respective thermo-elastic displacement distributions causing the ultrasonic waves propagating within the test objects during laser-ultrasonic inspection of parts. The respective heat propagation equation and thermo-elastic equation of motion are solved analytically for 1D and 3D test objects with different geometries.

Direct voxel classification from x-ray projections for 3D pore detection applied to laser sintered parts

X-ray computed tomography (XCT) is a validated and frequently used tool to verify part geometry and to perform a non-destructive inspection of additive manufacturing parts. However, the acquisition of a large number of x-ray projections generates long inspection times. This conflicts with a high throughput of the production process and hinders the integration of XCT as an in-line quality control procedure for low-end parts. In this paper, we propose a method to obtain three-dimensional (3D) information of the internal pores from a limited view or limited angle scan. The method combines a forward projection model of a cone-beam x-ray system and a deep learning neural network to directly classify each individual voxel, based on the x-ray projections in order to avoid the reconstruction and segmentation step. Accompanying reconstruction artifacts for limited view and limited angle XCT scans are thereby reduced, while preserving 3D information of the pores, defects or inclusions inside the material. The method is validated on real x-ray projections of polymer laser sintered industrial parts and shows a significant reduction in the required x-ray projections, hence acquisition time.

Geometric errors vision inspection and error evaluation method of rudder structural parts

Geometric errors vision inspection and error evaluation method of rudder structural parts

Prototypical Learning Guided Context-Aware Segmentation Network for Few-Shot Anomaly Detection.

Few-shot anomaly detection (FSAD) denotes the identification of anomalies within a target category with a limited number of normal samples. Existing FSAD methods largely rely on pretrained feature representations to detect anomalies, but the inherent domain gap between pretrained representations and target FSAD scenarios is often overlooked. This study proposes a prototypical learning-guided context-aware segmentation network (PCSNet) to address the domain gap, thereby improving feature descriptiveness in target scenarios and enhancing FSAD performance. In particular, PCSNet comprises a prototypical feature adaption (PFA) subnetwork and a context-aware segmentation (CAS) subnetwork. PFA extracts prototypical features as guidance to ensure better feature compactness for normal data while distinct separation from anomalies. A pixel-level disparity classification (PDC) loss is also designed to make subtle anomalies more distinguishable. Then a CAS subnetwork is introduced for pixel-level anomaly localization, where pseudo anomalies are exploited to facilitate the training process. Experimental results on MVTec AD and metal part defect detection (MPDD) demonstrate the superior FSAD performance of PCSNet, with 94.9% and 80.2% image-level area under the receiver operating characteristics (AUROCs) in an eight-shot scenario, respectively. Real-world applications on automotive plastic part inspection further demonstrate that PCSNet can achieve promising results with limited training samples. The code is available at https://github.com/yuxin-jiang/PCSNet.

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

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