Hybrid method combining sensitivity-based algorithm and Transformer–UNet model for 3D electromagnetic tomography: Conductivity-based shape reconstruction and defect detection

In this paper, a challenge in detecting internal defects of high-voltage cables is addressed by proposing an electromagnetic tomography (EMT) technique based on coaxial differential coils. An 8 -coil sensor array is established using COMSOL finite element simulation software. By employing linear back projection (LBP), Tikhonov regularization, and Landweber iteration algorithms, the performance advantages of differential coils in suppressing noise and enhancing image quality are systematically investigated and compared with traditional single-coil structures. The results show that, for the same defect location, the reconstructed images from the differential coils exhibit an improved signal-to-noise ratio and superior visualization.

Carbon fiber-reinforced polymer (CFRP) cables have been widely applied in modern engineering due to their excellent mechanical properties and durability, and their service safety has received increasing attention. However, there is currently a lack of efficient and accurate methods for detecting defects in CFRP cables. This article proposes a CFRP cable defect detection method based on electromagnetic tomography (EMT) technology to provide technical support for ensuring the safe service of cables. Due to the ill-posedness and instability of the inverse problem of EMT, there are reconstruction errors in the image reconstruction results. To address the EMT image reconstruction problem, an L1 regularization image reconstruction algorithm based on the proximal gradient method is proposed, which improves the defect reconstruction ability and reconstruction accuracy of the algorithm. First, the objective function is gradually optimized by combining gradient descent and proximal mapping operations to achieve variable-step-size gradient descent to handle the solution problems caused by the nonsmooth terms of the regularization function. On this basis, the image color mapping is adjusted to suppress the artifacts and noise in the reconstructed image. Finally, the proposed method is verified by carbon fiber composite material cables with different defect distributions. The numerical and experimental results show that the proposed method has stronger defect detection ability and can obtain high-quality defect reconstruction results. Compared with traditional methods, the image evaluation indicators have increased by 29.6% and 51.7%, respectively.

Sparse reconstruction of EMT based on compressed sensing and Lp regularization with the split Bregman method

Purpose. The main goal of this study is to review and systematize the materials and defects of the cylinder block and cylinder liners of internal combustion engines (ICE), as well as to analyze the issues and current trends in defect detection during repair. Methodology. The main problems currently associated with the defect detection of cylinder blocks and liners of ICEs include the following: the rapid growth of motorization, which leads to an increase in the number of cylinder blocks and liners requiring defect inspection; the use of manual labor, which makes the defect detection process labor-intensive and costly; the need for classification of defect types and their automatic recognition; the consideration of operating conditions influencing defect development; the necessity of implementing new defect detection processes; the need for quantitative wear assessment and prediction of component residual life; the adaptation of inspection methods and evaluation criteria to new materials. The study employs the following research methods: theoretical analysis (classification, systematization), review and synthesis of known scientific results, and empirical methods (comparison, observation). Findings. The authors conducted a review and systematization of structural materials and the main defects of cylinder blocks and liners of ICEs. The main issues in modern defect detection were identified as follows: insufficient process automation, low accuracy of visual and instrumental inspection methods, limited adaptability of existing inspection techniques to new materials, and the need for quantitative evaluation of component residual life. The development trends in defect detection systems are defined as the transition to automated and computerized inspection technologies, the creation of databases of typical defects, and the development of algorithms for predicting the residual life of components. Originality. The scientific novelty of this work lies in a comprehensive approach to analyzing structural materials, defects, and modern trends in defect detection of cylinder blocks and liners of ICEs. Materials used in component manufacturing have been systematized, a defect classification has been proposed, and the factors influencing wear intensity and defect formation have been identified. The trends in the development of defect detection systems have been established toward automation, increased sensitivity, and higher inspection accuracy. Practical value. The conducted analysis contributes to improving the efficiency of defect detection and repair processes of cylinder blocks and liners of ICEs, as well as to the development of informational databases of typical defects and the conditions under which they occur.

A pressure deconvolution technique based on ridge regression with existing convolution features was explored and reinterpreted to frame a new optimization problem structure. We found a way to split the feature matrix into a deconvolution part and a smoothing part that handle each effect independently. The deconvolution part is comprised of a convolution matrix (Toeplitz matrix) for discrete-time convolution while the smoothing part is composed of a basis function of the impulse response. Hence, this formulation preserves linearity (a superposition of pressure solution) and the kernel for nonlinear mapping (e.g., polynomial kernel, radial basis function kernel, etc.) is effective only on the smoothing part (a basis function of impulse response). Importantly, the key idea of existing convolution feature is the modelling of the impulse response with a linear combination of a basis functions.For single-well pressure behavior, ridge regression often struggles with high-frequency measurements that contain multistage responses. An impulse response might share similar functional characteristics, for example wellbore storage and pseudosteady state are both linear responses but there is only one linear basis function in the ridge regression which cannot describe them both. In traditional well test interpretation, the engineer is typically focused on certain parts of the impulse response on a log-scale, to identify reservoir behavior (e.g., early-time for wellbore storage, transient-time for infinite acting radial flow, late-time for boundary effect, etc.). Analogously, a basis function could be formed from multiple pressure responses in each log-interval (inherent from a solution of the diffusion equation) then bridged together with a constraint on function value and its derivative at each interval boundary. This is the basic principle of spline regression that has more flexibility in terms of function expression. In addition, it also subsumes ridge regression with Laplacian regularization.For multiwell pressure behavior, additional basis functions are included to handle interference responses. Typically, the exponential integral is approximated with a logarithm function for single-well pressure response which is also one of the basis functions in previous convolution features. Nonetheless, interference pressure response is more subtle and its solution could not be easily approximated, which previously resulted in a poor fitting using earlier methods. By inspection of the convergent series of the exponential integral, its higher-order terms are associated with 1/tm that can be easily included as a basis function to enhance the capability of the model and capture the detail of the interference test that is essential for multiwell problems. A full extension to multiwell problems is also presented with the additional derivative constraint for the impulse response and symmetry constraint. Finally, we can quantify the sensitivity of the deconvolution process using singular value decomposition (SVD) and Monte Carlo simulation (MCS). Using singular value decomposition, we could reveal the orthogonal basis of the feature matrix and its corresponding singular value that helped us identify the effectiveness of the basis functions as well as their susceptibility to noise of certain pattern. Nevertheless, singular value decomposition is only suitable for noisy pressure measurement problems without inequality constraint. Thus, Monte Carlo simulation is required for full quantification of noisy measurements in both pressure and flow rate. We can observe a propagation of error in measurement to a band in pressure prediction and pressure derivative of the impulse response.This study developed a more robust method for deconvolution of pressure measurements. In addition, the mathematical insights obtained in the study allow for a more general understanding of how the deconvolution problem can be deconstructed into its relevant parts – likely allowing for expanded capability of deconvolution algorithms in industrial practice.

In the process of steel production, the defects on the surface of steel will adversely affect the subsequent processing of a product. Accurate detection of such defects is the key to improve production efficiency and economic benefits. In this paper, an end-to-end steel surface defect detection and size measurement system based on the YOLOv5 model is designed. Firstly, in consideration of the defect location and direction correlation in the production process, a coordinate attention mechanism is added at the head of YOLOv5 to strengthen the spatial correlation of the steel surface and an adaptive anchor box generation method based on defect shape difference feature is proposed, which realizes the detection of three main types of defects on the Pytorch deep learning framework. Secondly, BiFPN is used to strengthen the feature fusion and a transformer encoder is added to improve the performance of detecting small defects. Thirdly, calculate the conversion ratio between the pixel and the actual size according to the standard reference specimen and obtain the actual size through the pixel statistics of the defect area to achieve pixel level size measurement. Finally, the steel surface defect detection and size measurement system are designed in this paper, which consist of various hardware, related measurement, and detection algorithms. According to the experimental results, the comprehensive defect detection accuracy of this method reaches 93.6%, of which the scratch detection accuracy reaches 95.7%. The detection speed reaches 133 fps and the defect size measurement accuracy reaches 0.5 mm. Experimental result shows that the defect detection and size measurement system designed in this paper can accurately detect and measure various industrial production defects and can be applied to the actual production process.

Purpose – Laser metal deposition (LMD) is a type of additive manufacturing process in which the laser is used to create a melt pool on a substrate to which metal powder is added. The powder is melted within the melt pool and solidified to form a deposited track. These deposited tracks may contain porosities or cracks which affect the functionality of the part. When these defects go undetected, they may cause failure of the part or below par performance in their applications. An on demand vision system is required to detect defects in the track as and when they are formed. This is especially crucial in LMD applications as the part being repaired is typically expensive. Using a defect detection system, it is possible to complete the LMD process in one run, thus minimizing cost. The purpose of this paper is to summarize the research on a low-cost vision system to study the deposition process and detect any thermal abnormalities which might signify the presence of a defect. Design/methodology/approach – During the LMD process, the track of deposited material behind the laser is incandescent due to heating by the laser; also, there is radiant heat distribution and flow on the surfaces of the track. An SLR camera is used to obtain images of the deposited track behind the melt pool. Using calibrated RGB values and radiant surface temperature, it is possible to approximate the temperature of each pixel in the image. The deposited track loses heat gradually through conduction, convection and radiation. A defect-free deposit should show a gradual decrease in temperature which enables the authors to obtain a reference cooling curve using standard deposition parameters. A defect, such as a crack or porosity, leads to an increase in temperature around the defective region due to interruption of heat flow. This leads to deviation from the reference cooling curve which alerts the authors to the presence of a defect. Findings – The temperature gradient was obtained across the deposited track during LMD. Linear least squares curve fitting was performed and residual values were calculated between experimental temperature values and line of best fit. Porosity defects and cracks were simulated on the substrate during LMD and irregularities in the temperature gradients were used to develop a defect detection model. Originality/value – Previous approaches to defect detection in LMD typically concentrate on the melt pool temperature and dimensions. Due to the dynamic and violent nature of the melt pool, consistent and reliable defect detection is difficult. An alternative method of defect detection is discussed which does not involve the melt pool and therefore presents a novel method of detecting a defect in LMD.

Characterization of the Tikhonov regularization for numerical analysis of inverse boundary value problems by using the singular value decomposition

Background/Objectives: Grain structure of Austenitic Stainless Steel (ASS) weld causes difficulty in defect detection while inspecting using Time of Flight Diffraction (TOFD) method. This study aims at comparing segmentation methods to overcome this difficulty based on defect characterization. Methods/Statistical Analysis: This study makes use of TOFD and Radiographic images of ASS weld pads fabricated with defined linear and volumetric defects. The Region-Based Level Set algorithm and Discontinuity Based Segmentation algorithm were explored for achieving flaw segmentation and quantitative characterization and validation of the result with that of standard radiographic results. Findings: The efficiency of the algorithms was analyzed by comparing and validating the size of defect with that of standard radiographic results in the form of error percentage. The consistency of error percentage in defect sizing (up to 11%) achieved by RegionBased Level Set algorithm for all the test images given in the database indicate that, this algorithm is the best as compared to Discontinuity Based Segmentation algorithm(error percentage up to 47%) for defect segmentation and characterization in TOFD images. Application/Improvements: The segmentation algorithm enables automation of measurement process and enhanced detection and characterization of defects at the initial stage. Further, it reduces human fatigue caused by operator while defect detection as the volume of data increases. The future direction is to fully automate the system in order to save time for interpretation and to modify the algorithm to segment images with multiple defects. Keywords: Defect Characterization, Discontinuity Based Segmentation, Flaw Segmentation, Region-Based Level Set Segmentation, Time of Flight Diffraction (TOFD), Weld Defect

The detection of defects on automotive coated surfaces is of paramount importance to ensure the quality of automotive appearance. However, due to the challenges posed by the lack of sufficient samples of product-specific coated defects, the uneven number of species, and the difficulty of detecting defects in small targets due to the complex background of the body surface. The detection of defects on automotive coated surfaces still relies on experienced manual labor to a significant extent. To address these issues, Poisson fusion is employed to enhance the data for generating defect images, thereby mitigating the limitations of insufficient coated defect samples and an imbalanced distribution of defect species. Based on this, a new YOLOv8-SC defect detection model is proposed, in which the C2f-Star is used to replace the original C2f structure. This aims to improve the model’s ability to extract defects of varying sizes in complex backgrounds, while reducing the number of model parameters and the amount of computation. The content-guided attention fusion (CGAFusion) module, situated before each detection head of the model, has been designed to enhance the model’s capacity to extract defects of varying sizes and complexity. This is achieved through the adaptive fusion of low-level and high-level features. The proposed model’s superiority in terms of detection metrics has been demonstrated through the use of example validation. The experiments were conducted on the enterprise dataset CPD-DET and the public dataset NEU-DET. The results demonstrated that the defective image generation and data enhancement method could significantly improve detection performance and have good generalization. The proposed YOLOv8-SC reduces the model parameters by 12.2% compared to the normal model. Additionally, the mean average precision (mAP) at 50% and 50%–95% thresholds are enhanced by 4.7% and 2.3%, respectively. Furthermore, the accuracy of the model exhibits a discernible positive growth trend with an increase in the sample set size. The design of an automotive coated surface defect detection system is presented at last. When deployed in industrial settings, this system can facilitate the intelligent detection of coated defects.

Microwave tomography sensing for potential agarwood trees imaging

The theory and implementation of an extreme learning machine (ELM) have proved that it is a simple, efficient, and accurate machine learning methodology. In an ELM, the hidden nodes are randomly initiated and fixed without iterative tuning. However, the optimal hidden layer neuron number ($L_{opt})$ is the key to ELM generalization performance where initializing this number by trial and error is not reasonably satisfied. Optimizing the hidden layer size using the leave-one-out cross validation method is a costly approach. In this paper, a fast and reliable statistical approach called optimum ELM (OELM) was developed to determine the minimum hidden layer size that yields an optimum performance. Another improvement that exploits the advantages of orthogonal projections with singular value decomposition was proposed in order to tackle the problem of randomness and correlated features in the input data. This approach, named projected ELM (PELM), achieves more than 2{\%} advance in average accuracy. The final contribution of this paper was implementing Tikhonov regularization in the form of the L$_{2}$-penalty with ELM (TRELM), which regularizes and improves the matrix computations utilizing the L-curve criterion and SVD. The L-curve, unlike iterative methods, can estimate the optimum regularization parameter by illustrating a curve with few points that represents the tradeoff between minimizing the training error and the residual of output weight. The proposed TRELM was tested in 3 different scenarios of data sizes: small, moderate, and big datasets. Due to the simplicity, robustness, and less time consumption of OELM and PELM, it is recommended to use them with small and even moderate amounts of data. TRELM demonstrated that when enhancing the ELM performance it is necessary to enlarge the size of hidden nodes $(L)$. As a result, in big data, increasing $L$ in TRELM is necessary, which concurrently leads to a better accuracy. Various well-known datasets and state-of-the-art learning approaches were compared with the proposed approaches.

Online defect detection method and system based on similarity of the temperature field in the melt pool

Fabric defect detection has been an active area of research since a long time and still a robust system is needed which can fulfill industrial requirements. A robust automatic fabric defect detection system (FDDS) would results in quality products and more revenues. Many different approaches and method have been tried to implement FDDS. This paper presents a new scheme for automated FDDS implementation using Hilbert-Huang Transform (HHT) and also compares it with O penCV approach. In my implementation of both approaches in same environment, the HHT approach produces higher defect detection accuracies than OpenCV approach and more computationally efficient. The article is divided into four parts, the first part is the introduction of t wo methods, the second part for the two methods defect detection system implementation, the third pa rt is the results and the discussion of two methods, the fourth part is the conclusion. HHT is used to deal with nonlinear and non-stationary signal, the method of its adaptive is good, can be used to analyze all kinds of signals. Compared with the Fourier transform, the HHT has more explicit time- frequency description; filter performance is even more acute. In addition, its implementation is simple and can be real-time calculation. Therefore, for the engineering application and theory research, HHT has very important significance. HHT method has two parts: Empirical mode decomposition and Hilbert spectrum analysis.

The implementation of online, nondestructive quality control (QC) solutions is a key aspect to consider especially in medical device manufacturing, where the production process should comply to relevant quality-related standards to guarantee a safe product for the patient. For metallic implants fabricated using electron beam melting (EBM), the presence of defects (e.g., porosities, cracks, delamination, balling effect) could affect the final part quality in terms of structural integrity and mechanical properties. In this context, we propose an expert system algorithm capable of automated detection of porosities that could occur in prosthetic components, such as tibial trays, printed using a cobalt-chromium alloy. The choice of focusing only on the porosities was done as these defects are particularly critical for orthopedic prosthesis, where they can negatively impact the fatigue behavior of the printed component. The algorithm was developed ad hoc to analyze images of the manufacturing process taken from a camera embedded in the printer (Arcam Q10plus). Images can be used to identify porosities, performing a nondestructive evaluation that supports the process of part qualification. The developed algorithm automates and improves the visual inspection task conducted by human experts, including quantitative assessment on the size and location of the porosities, and reporting the presence of high porosity density areas. The defect detection performance was evaluated through the design of two tasks: The layer-wise defect detection and the large pore identification. The defect detection was performed with a sensitivity of 91% and a precision of 76%. Furthermore, a comparison with the gold-standard nondestructive evaluation technique, that is, computed tomography evaluation, allowed to validate the algorithm (percent agreement of 98%). The developed expert system allows to quickly evaluate an entire printing volume with several components representing a reliable and fast tool for defect detection and QC of EBM-printed prosthetic components.