Fast Inspection Research Articles

Making electric vehicle batteries safer through better inspection using artificial intelligence and cobots

High quality, safe, and reliable batteries are essential for widespread adoption of electric vehicles. Current Li-ion battery pack manufacturing processes rely on manual inspections to ensure electric vehicle battery quality. Such manual quality control is prone to errors, increasing the chances of defective batteries. This is likely to increase safety and reliability concerns in the public imagination, slowing down the adoption of electric vehicles. Furthermore, manual inspection is time-consuming and likely to become a bottleneck in scaling up electric vehicle battery production. A potential solution to address this need for fast and accurate inspection of batteries is the use of machine vision and robotics. In this study, we use digital twin design and simulation to develop a battery module inspection system that uses cobots and machine vision to inspect electric vehicle batteries for defects. Our proposed system can automate visual quality checks that are currently being done by human operators. The proposed cobotic system has been simulated and validated for a variety of battery defects to achieve fast and reliable detection. Since a digital twin of the cobotic inspection workcell has been used, the battery inspection system, as designed and validated, is ready for immediate implementation.

Cascade Learning Embedded Vision Inspection of Rail Fastener by Using a Fault Detection IoT Vehicle

Fastener needs to be monitored and inspected periodically to ensure the rail’s safety due to its easily damaged accessory for railway infrastructure. Recently, Industrial Internet of Things (IIoT) and artificial intelligence (AI)-based visual inspection techniques have been exploited to realize the online inspection of fastener’s fault by using a fault detection IoT vehicle that is mounted with multitype sensors and cameras according to the design of our research team. However, instead of traditional artificial inspection, the AI-based automatic fastener inspection approach is still faced with some challenges, for example, collection of enough samples of faulted fastener. In this article, we propose a cascade learning embedded vision inspection method of rail fastener based on the deep convolutional neural network (DCNN). The proposed method has two steps: 1) region position and 2) fault detection. First, a modified single shot multibox detector (SSD) model is adopted to locate the fastener regions from the captured railway images. Then, a key component detection (KCD) method based on the improved faster region convolutional neural network (RCNN) is proposed to realize the detection of faulted fastener. Extensive experiments are conducted to demonstrate the performance of the proposed method. The experiment results show that the proposed method achieves an average precision of 95.38% and an average recall of 98.62% on fastener detection, which is much better than the manual operation.

Investigation and Analysis of Crack Detection using UAV and CNN: A Case Study of Hospital Raja Permaisuri Bainun

Crack detection in old buildings has been shown to be inefficient, with many technical challenges such as physical inspection and difficult measurements. It is important to have an automatic, fast visual inspection of these building components to detect cracks by evaluating their conditions (impact) and the level of their risk. Unmanned Aerial Vehicles (UAV) can automate, avoid visual inspection, and avoid other physical check-ups of these buildings. Automated crack detection using Machine Learning Algorithms (MLA), especially a Conventional Neural Network (CNN), along with an Unmanned Aerial Vehicle (UAV), can be effective and both can efficiently work together to detect the cracks in buildings using image processing techniques. The purpose of this research project is to evaluate currently available crack detection systems and to develop an automated crack detection system using Aggregate Channel Features (ACF)that can be used with unmanned aerial vehicles (UAV). Therefore, we conducted a real-world experiment of crack detection at Hospital Raja Permaisuri Bainun using DJI Mavic Air (Drone Hardware) and DJI GO 4(Drone Software) using CNN through MATLAB software with CNN-SVM method with the accuracy rate of3.0 percent increased from 82.94%to 85.94%. in comparison with other ML algorithms like CNN Random Forest (RF), Support Vector Machine (SVM) and Artificial Neural Network (ANN).

In-line inspection technology of oil and gas long-distance pipeline based on alternating current field measurement

Abstract Alternating current field measurement (ACFM) has advantages of fast inspection speed, high efficiency, sensitive inspection, and easy quantification. In this study, a probe based on ACFM has been carried out, trying to inspect cracks on the inner wall of pipeline with high precision. An inspection tool which is working according to ACFM is developed in order to determine the stress corrosion cracking. The lift-off distance and excitation frequency parameters are optimized, and the influence of uneven magnetic permeability of the pipeline on the test results is analyzed. In addition, experiments are carried out to test the practicality of the tool. The minimum axial crack length that the probe can detect is 15 mm and the minimal depth is 1 mm. The research results show that the probe has the ability to quantitatively evaluate the axial cracks on the inner surface of the pipeline, which has certain guiding significance for the design and development of the AC electromagnetic field inspection probe.

Damage detection in the T-welded joint using Rayleigh-like feature guided wave

Steel T-welded joint structures have been largely applied in aerospace and marine infrastructures. The weld length in T-weld joint structures is usually long, and it is difficult to access the weld conditions for damage detection purposes. This is due to the T-welded joint structure possessing a more complex cross-section than the conventional welded plate-like structures. Rather than formed by two plates and joined with a butt weld, the joint regions in the T-welded joint structure are connected to the sides of three plates to form a T-welded joint, and hence cannot be considered as plate-like structures. This makes guided wave modes difficult to be identified and exploited. This paper assesses the feasibility to detect weld defects on a steel T-welded joint structure using the feature guided wave (FGW) technique. FGW technique can provide a fast and long-range inspection for local topographical features, such as welded joints, offering great potential for effective screening of damages. Semi-Analytical Finite Element (SAFE) method is applied to acquire modal solutions in the waveguide. A new algorithm is developed to obtain FGW modes with both high energy concentration and low attenuation from the solutions of SAFE eigenvalue problem. One particular FGW mode with similar mode shape as the Rayleigh surface wave is identified, of which the propagation occurs only in the joint region with small attenuation. This FGW, labelled Rayleigh T-welded wave (RTW), is explored in comprehensive experimental and numerical studies to investigate the propagation and backward scattering characteristics regarding optimal excitation frequency and different sizes of weld defect. The numerical and experimental results are in good agreement. The outcome of the study confirms the capability and robustness of RTW in detecting small weld defects, which allows a long-distance and sensitive screening for the small weld defects at the joint region in the T-welded joint structure.

Fiber Reinforced Polymer Debonding Failure Identification Using Smart Materials in Strengthened T-Shaped Reinforced Concrete Beams.

The favorable contribution of externally bonded fiber-reinforced polymer (EB-FRP) sheets to the shear strengthening of reinforced concrete (RC) beams is widely acknowledged. Nonetheless, the premature debonding of EB-FRP materials remains a limitation for widespread on-site application. Once debonding appears, it is highly likely that brittle failure will occur in the strengthened RC structural member; therefore, it is essential to be alerted of the debonding incident immediately and to intervene. This may not be always possible, particularly if the EB-FRP strengthened RC member is located in an inaccessible area for fast inspection, such as bridge piers. The ability to identify debonding immediately via remote control would contribute to the safer application of the technique by eliminating the negative outcomes of debonding. The current investigation involves the detection of EB-FRP sheet debonding using a remotely controlled electromechanical admittance (EMA)-based structural health monitoring (SHM) system that utilizes piezoelectric lead zirconate titanate (PZT) sensors. An experimental investigation on RC T-beams strengthened for shear with EB-FRP sheets has been performed. The PZT sensors are installed at various locations on the surface of the EB-FRP sheets to evaluate the SHM system's ability to detect debonding. Additionally, strain gauges were attached on the surface of the EB-FRP sheets near the PZT sensors to monitor the deformation of the FRP and draw useful conclusions through comparison of the results to the wave-based data provided by the PZT sensors. The experimental results indicate that although EB-FRP sheets increase the shear resistance of the RC T-beams, premature failure occurs due to sheet debonding. The applied SHM system can sufficiently identify the debonding in real-time and appears to be feasible for on-site applications.

Illumination-robust milling surface roughness machine vision inspection based on MAML++ network

Existing roughness machine vision inspection methods based on designed indices require the artificial construction of features associated with roughness based on image information. Such methods are less universal but highly demanding for the imaging environment and cannot be directly applied to general industrial environments. The roughness machine vision inspection methods based on traditional deep learning, on the other hand, rely heavily on a large number of training samples, and the model needs to be retrained when the recognition of new categories is required by the inspection task. Therefore, a machine vision inspection method for milling surface roughness grade based on the improved model-agnostic meta-learning (MAML++) network was proposed to address the above problems. This method could not only automatically extract the image features associated with roughness but also recognize the surface roughness grade of milling workpieces by a small number of labeled samples. It reduced the need for sample size and can recognize new categories without retraining the model. The experimental results showed that the method exhibited high accuracy in roughness inspection tasks with different sample distributions and had promising robustness to complex light environments. In addition, in terms of the requirement for recognizing new roughness categories, a low-cost and fast roughness inspection task could be accomplished by acquiring fewer labeled samples. In summary, the proposed model has the potential to be a fast inspection system that can be applied to surface roughness inspection for most industrial applications. It provides the technology for inline inspection of machine vision roughness in general industrial lighting environments.

Nondestructive analysis of corrosion in ageing hardened AA6351 aluminium alloys

Aluminum alloys have been chosen over other lightweight structural materials because of their advantages regarding strength, long-term durability, and low cost. Aluminum comes under the category of highly reactive metals, where an inherently stable oxide layer can protect against aggressive corrosive conditions. Therefore, this research investigated the application of the ultrasonic nondestructive technique for inspection and monitoring of corrosion behavior of AA6351 heat-treated aluminum alloys. The samples were artificial age hardened at five different conditions. The complementary engineering experiments for materials evaluation included hardness, X-ray diffraction and salt spray tests. Overall findings showed correlations between ultrasonic and destructive data representing a fast, versatile and reliable inspection technique. Furthermore, findings show a significant correlation (>99%), thus supporting the benefits of the multiparametric ultrasonic test for heat treatment inspection and quality control of lightweight structural materials.

Laser Sensing System for Contactless Detection of Subsurface Defects in Concrete Tunnel Lining

Regular inspections of underground infrastructure are mandatory to maintain structural integrity and traffic safety. Standard procedures rely on visual inspection, complemented by testing for internal defects of the tunnel lining with the hammering method. This testing method uses manual excitation with a hammer and interpretation of the perceived sound by an engineer or technician. Result quality is based on the experience of the executing personal and thus highly subjective. The presented project aims at the automation of this procedure to enable a fast and objective inspection covering the whole tunnel lining. To achieve this, a new laser-based measurement system for detecting near surface defects in large concrete structures is developed. Surface vibrations are induced with plasma ignition and measured with a Doppler Vibrometer. The system has motorized mirror adjustment and can thus obtain fast-paced measurements on a grid. We present the experimental setup, the measurements performed on a concrete test block with artificial defects and the algorithms for automated defect detection. From the measured eigenfrequencies, we derive the size and location of defects. Computer vision techniques are adapted to make the system resilient against variable environmental conditions, like noise and temperature, or changes in construction material and age. These sophisticated signal processing methods are applied to extract relevant information from the measurements and are combined with topological data to provide service personnel with detailed maps for maintenance work.

Automatic Tunnel Crack Inspection Using an Efficient Mobile Imaging Module and a Lightweight CNN

Cracks in tunnel linings are the most common tunnel defects. As early indicators of structural deterioration, cracks represent critical problems for the safety of tunnels. Several mobile tunnel inspection systems (MTISs) have been developed for tunnel crack inspection. However, due to the weak signals of cracks, these MTISs require considerable exposure time to capture high-quality tunnel images, necessitating a low travel speed. Meanwhile, traditional crack detection methods encounter difficulties in processing tunnel crack images because of their low contrast and poor continuity. To overcome these challenges, this study presents a new MTIS for fast tunnel crack inspection that consists of a novel mobile imaging module and an automatic crack detection module. The imaging module is composed of an array of high-resolution charge-coupled device (CCD) cameras, a mobile laser scanner, and a lighting array. The core of the crack detection module is a novel lightweight convolutional neural network (CNN) designed for efficient tunnel crack detection, with an effective spatial constraint strategy to guarantee crack continuity. We collected a new tunnel crack dataset consisting of 1,218 images using our mobile imaging module at a driving speed of 80 km/h. Comprehensive experiments were conducted on this dataset to evaluate the performance of our proposed network. The results demonstrate that the presented CNN can effectively detect tunnel cracks with state-of-the-art performance, achieving an F1-score greater than 0.88 and an inference speed of 17 FPS with only 3.4M model parameters. The code and data are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/urban-informatics/LinkCrack</uri> .

X-ray technology in civil engineering

X-ray has the unique ability to reveal what inside a structure and interpret it as a human readable image. This key feature makes X-ray imaging to a preferred inspection method for quality control across everything from food, micro electronics to heavy steel constructions. The newest technology developments towards digital X-ray imaging allow for fast and reliable inspection, addressing the high requirements of steel and concrete inspection. In civil engineering X-ray technology is used for weld seem inspection within construction of pipelines, bridges petrol-chemical plants and nuclear facilities. Quality assurance of steel constructions: X-ray inspection of pipelines and other steel structures are not only done during construction where weld seem inspection is one of the main applications for X-ray but also during maintenance where inspection for hidden corrosion and erosion to identify weaknesses before a breakdown occur. Damage assessment: Another important application is assessment of identified damages, as evaluation of identified cracks in steel constructions. With digital imaging it possible to get an immediate inspection result with high sensitivity and resolution. Inspection of concrete: A new emerging application is X-ray inspection of concrete constructions with X-ray. A modern 300kV portable X-ray system combined with digital image system can be used to inspect up to 20 – 25 cm concrete. With X-ray inspection of concrete, it is possible to identify and evaluate the condition of the reinforcement inside the concrete which is pivotal for the strength of the construction. It is also possible to identify the exact position of electrical installations or other features hidden inside the concrete which can prevent unexpected incidents related to drilling. The latest X-ray technology addresses todays and future challenges of quality control in civil engineering.

Selection of smooth motion profile for a tube locator module of an inspection device

&lt;span lang="EN-US"&gt;The Prototype Fast Breeder Reactor steam generators inspection system has seven modules. In this, tube locator module is a planar serial two-link robotic arm, which is used to place the eddy current probe above the steam generators tube hole in the tube sheet region. The trajectory planning of the two-link robotic arm is one of the important tasks, so the peak velocity, peak acceleration, peak jerk of various motion profiles for a given distance has to be selected properly for smooth motion and to avoid actuator saturation. The fifth-order polynomial gives lower acceleration and velocity than the jerk-limited S-curve. In this paper, the comparison of peak values of kinematic variables (velocity, acceleration, and jerk) for different motion profiles has been presented.&lt;/span&gt;

Aptamer and Ru(bpy)32+‐AuNPs‐based electrochemiluminescence biosensor for accurate detecting Listeria monocytogenes

AbstractAs a widespread foodborne pathogen, Listeria monocytogenes (LM) can potentially cause a large number of food safety incidents, and the mortality rate of humans infected with this pathogen is relatively high. Thus, establishment of a fast and simple inspection technology is imperative. Herein, a solid‐state electrochemiluminescence (ECL) biosensing switch system based on special ferrocene‐labeled molecular beacon aptamer (Fc‐MBA) has been developed for rapid detection of LM. The biosensor consisted of two main parts, an ECL substrate and an ECL intensity switch. ECL substrate was generated by modifying the complex of gold nanoparticle (AuNPs) and ruthenium (II) tris‐(bipyridine) onto Au electrode, and an MBA labeled by Fc that acted as an ECL intensity switch. Moreover, in the presence of LM, the stem‐loop structure of MBA could be opened and the ferrocene was kept away from ECL substrate, which was due to an obvious ECL intensity increment. The limit of detection was 5 CFU/mL, and satisfactory recoveries of 98.1–103.6% were observed. Thus, we propose a novel method for accurate and specific detection of LM.

Four Discriminator Cycle-Consistent Adversarial Network for Improving Railway Defective Fastener Inspection

This article aims to improve the performance of deep learning-based defective fastener inspection method. Due to the defective fasteners are insufficient and far less than the defect-free ones in real railway, it is difficult to train a robust fastener inspection model on such imbalanced dataset. In view of this problem, a novel image generation method called four-discriminator cycle-consistent adversarial network (FD-Cycle-GAN) is proposed to generate the defect fastener images using a large number of defect-free ones. Extensive experiments are conducted on the real fastener images and generated images. Experimental results demonstrate that the defect fastener images generated by our proposed method have better quality and richer diversity than those generated by other state-of-the-art methods. In addition, compared with the CNN-only baseline, the performance of the fastener inspection model trained on the expanded dataset containing the defect fastener images generated by FD-Cycle-GAN is improved significantly. The detection accuracy and relative IMP reach 93.25% and 21.59% respectively.

A System of Rapidly Detecting Escherichia Coli in Food Based on a Nanoprobe and Improved ATP Bioluminescence Technology.

Bacterial contamination is an important factor causing food security issues. Among the bacteria, Escherichia coli is one of the main pathogens of food-borne microorganisms. However, traditional bacterial detection approaches cannot meet the requirements of real-time and on-site detection. Thus, it is of great significance to develop a rapid and accurate detection of bacteria in food to ensure food safety and safeguard human health. The pathogen heat-treatment module was designed in this paper based on the techniques including nanoprobe, pathogen heat-treatment, graphene transparent electrode (GTE), and adenosine triphosphate (ATP) bioluminescence technology. The system mainly consists of two parts: one is the optical detection unit; the other is the data processing unit. And it can quickly and automatically detect the number of bacterial colonies in food such as milk etc. The system uses not only the probe to capture and enrich E. coli by antigen-antibody interaction but also the heat treatment to increase the amount of ATP released from bacterial cells within five minutes. To enhance the detecting accuracy and sensitivity, the electric field generated by GTE is adopted in the system to enrich ATP. Compared to the other conventional methods, the linear correlation coefficient of the system can be reached 0.975, and the system meets the design requirements. Under the optimal experimental conditions, the detection can be completed within 25 min, and the detectable concentration of bacteria is in the range of 3.1 × 101–106 CFU/mL. This system satisfies the demands of a fast and on-site inspection.

Pose Estimation and Damage Characterization of Turbine Blades during Inspection Cycles and Component-Protective Disassembly Processes.

Inspection in confined spaces and difficult-to-access machines is a challenging quality assurance task and particularly difficult to quantify and automate. Using the example of aero engine inspection, an approach for the high-precision inspection of movable turbine blades in confined spaces will be demonstrated. To assess the condition and damages of turbine blades, a borescopic inspection approach in which the pose of the turbine blades is estimated on the basis of measured point clouds is presented. By means of a feature extraction approach, film-cooling holes are identified and used to pre-align the measured point clouds to a reference geometry. Based on the segmented features of the measurement and reference geometry a RANSAC-based feature matching is applied, and a multi-stage registration process is performed. Subsequently, an initial damage assessment of the turbine blades is derived, and engine disassembly decisions can be assisted by metric geometry deviations. During engine disassembly, the blade root is exposed to high disassembly forces, which can damage the blade root and is crucial for possible repair. To check for dismantling damage, a fast inspection of the blade root is executed using the borescopic sensor.

Localization of cavities in cast components via impulse excitation and a finite element analysis

In this work, the acoustic resonance testing method has been extended by a finite element analysis of the examined component to localize cavities within die casting parts. This novel method aims at a fast and efficient quality inspection which allows hidden cavities in cast components to be detected, which is only possible with X-ray technology at the moment. The promising results show that this method enables the localization of shrinkage cavities. Furthermore, the influence of product scatter has been analyzed regarding the accuracy of the calculated position of artificial defects.

Research on bearing surface defect detection system based on machine vision

Aiming at the shortcomings of manual detection methods for surface defects of bearing outer rings, a surface defect detection method based on machine vision is proposed. The common defects on the bearing surface are scratches, cracks, and peeling. The defect images are analyzed by the LabVIEW image processing module. Make fast and accurate inspections. In this paper, a CMOS industrial camera is used to obtain the bearing image, and the gray histogram of the image is analyzed to determine whether it is a defective bearing. In order to solve the problem of uneven illumination in image segmentation, it is proposed to first use morphological processing for background. Then, the difference map containing defect information is obtained, and then the Otsu method is used for image segmentation; an edge detection method is designed based on morphology, which can achieve complete edge extraction and good denoising effect. Experiments show that the method has strong practicability and self-adaptability, and can accurately detect bearing surface defects.

Non-destructive evaluation of uneven coating thickness based on active long pulse thermography

Non-destructive detection of coating thickness is important after coating deposition and during service. The present work is to establish a measurement method for fast inspection, large area detection of coating thickness with an active long pulse thermography. The measurement method was theoretically analyzed based on the equation of 1D heat transfer in the depth direction, accordingly coating thickness can be quantitively evaluated by recording the temperature decay curve in the cooling stage and computing the time at the minimum of its 2nd derivative. Then, the proposed method was experimentally validated by uniform coating specimen with different thicknesses. Furthermore, the thickness measurement method was successfully applied to measure thickness of an uneven coating specimen within a relative error of 5% with sufficient sampling rate. Finally, some key techniques were discussed for accurate measurements including thermal excitation, sampling rate of thermography, thickness ratio of coating and substrate, etc. The results verify that active long pulse thermography is a powerful tool for non-contact and full-field measurement of coating thickness with merits of safe and easy to implement.

Convolutional Neural Networks for vehicle damage detection

Vehicle damages are increasingly becoming a liability for shared mobility services. The large number of handovers between drivers demands for an accurate and fast inspection system, which locates small damages and classifies these into the correct damage category. To address this, a damage detection model is developed to locate vehicle damages and classify these into twelve categories. Multiple deep learning algorithms are used, and the effect of different transfer learning and training strategies is evaluated, to optimize the detection performance. The final model, trained on more than 10,000 damage images, is able to accurately detect small damages under various conditions such as water and dirt. A performance evaluation with domain experts shows, that the model achieves comparable performance. In addition, the model is evaluated in a specially designed light street, indicating that strong reflections complicate the detection performance.