DGConv: A Novel Convolutional Neural Network Approach for Weld Seam Depth Image Detection

We propose a novel image segmentation algorithm to tackle the challenge of limited recognition and segmentation performance in identifying welding seam images during robotic intelligent operations.Initially,to enhance the capability of deep neural networks in extracting geometric attributes from depth images,we developed a novel deep geometric convolution operator(DGConv).DGConv is utilized to construct a deep local geometric feature extraction module,facilitating a more comprehensive exploration of the intrinsic geometric information within depth images.Secondly,we integrate the newly proposed deep geometric feature module with the Fully Convolutional Network(FCN8)to establish a high-performance deep neural network algorithm tailored for depth image segmentation.Concurrently,we enhance the FCN8 detection head by separating the segmentation and classification processes.This enhancement significantly boosts the network’s overall detection capability.Thirdly,for a comprehensive assessment of our proposed algorithm and its applicability in real-world industrial settings,we curated a line-scan image dataset featuring weld seams.This dataset,named the Standardized Linear Depth Profile(SLDP)dataset,was collected from actual industrial sites where autonomous robots are in operation.Ultimately,we conducted experiments utilizing the SLDP dataset,achieving an average accuracy of 92.7%.Our proposed approach exhibited a remarkable performance improvement over the prior method on the identical dataset.Moreover,we have successfully deployed the proposed algorithm in genuine industrial environments,fulfilling the prerequisites of unmanned robot operations.

An artificial neural network for detecting weld position in arc welding process

A kind of self organizing artificial neural network used for weld detection is presented in this paper, and its concepts and issues are discussed. The network can transform the weld visual information into typical patterns and match with the weld data collected on line, and so realize the accurate detection of the weld position in arc welding process.

Realizing precision pulse TIG welding with arc length control and visual image sensing based weld detection

Methods of arc length control and visual image based weld detection for precision pulse TIG welding were investigated. With a particular all hardware circuit, arc voltage during peak current stage is sampled and integrated to indicate arc length, deviation of arc length and adjusting parameters are calculated and output to drive a step motor directly. According to the features of welding image grabbed with CCD camera, a special algorithm was developed to detect the central line of weld fast and accurately. Then an application system were established, whose static arc length error is ±0.1 mm with 20 A average current and 1 mm given arc length, static detection precision of weld is 0.01 mm , processing time of each image is less than 120 ms . Precision pulse TIG welding of some given thin stainless steel components with complicated curved surface was successfully realized.

Noise Reduction of Welding Defect Image Based on NSCT and Anisotropic Diffusion

In order to reduce noise effectively in the welding defect image and preserve the minutiae information, a noise reduction method of welding defect image based on nonsubsampled contourlet transform(NSCT) and anisotropic diffusion is proposed. Firstly, an X-ray welding defect image is decomposed by NSCT. Then total variation(TV) model and Catte_PM model are used for the obtained low-pass component and band-pass components, respectively. Finally, the denoised image is synthesized by inverse NSCT. Experimental results show that, compared with the hybrid method of wavelet threshold shrinkage with TV diffusion, the method combining NSCT with P_Laplace diffusion, and the method combining contourlet with TV model and adaptive contrast diffusion, the proposed method has a great improvement in the aspects of subjective visual effect, peak signal-to-noise ratio(PSNR) and mean-square error(MSE). Noise is suppressed more effectively and the minutiae information is preserved better in the image.

Novel welding image processing method based on fractal theory

Computer vision has come into used in the fields of welding process control and automation. In order to improve precision and rapidity of welding image processing, a novel method based on fractal theory has been put forward in this paper. Compared with traditional methods, the image is preliminarily processed in the macroscopic regions then thoroughly analyzed in the microscopic regions in the new method. With which, an image is divided up to some regions according to the different fractal characters of image edge, and the fuzzy regions including image edges are detected out, then image edges are identified with Sobel operator and curved by LSM (Lease Square Method). Since the data to be processed have been decreased and the noise of image has been reduced, it has been testified through experiments that edges of weld seam or weld pool could be recognized correctly and quickly.

Welding anomaly detection based on supervised learning and unsupervised learning

In order to solve the problem of automatic defect detection and process control in the welding and arc additive process,the paper monitors the current,voltage,audio,and other data during the welding process and extracts the minimum value,standard deviation,deviation from the voltage and current data.It extracts spectral features such as root mean square,spectral centroid,and zero-crossing rate from audio data,fuses the features extracted from multiple sensor signals,and establishes multiple machine learning supervised and unsupervised models.They are used to detect abnormalities in the welding process.The experimental results show that the established multiple machine learning models have high accuracy,among which the supervised learning model,the balanced accuracy of Ada boost is 0.957,and the unsupervised learning model Isolation Forest has a balanced accuracy of 0.909.

BACKGROUND RECTIFICATION AND FEATURE EXTRACTION OF IMAGE IN A SPOT WELD OF AL ALLOY X-RAY DETECTION

A primary study on Processing in X - ray inspection of spot weld for aluminum alloy spot welding,in- cluding for background simulation,acquisition of ideal binary image, and extraction and identifi- cation of defect features was presented.

WeldNet:A voxel-based deep learning network for point cloud annular weld seam detection

Weld seam detection is an important part of automated welding.At present,few studies have been conducted on annular weld seams,and a lot of defects exist in the point cloud model of the tube sheet obtained by RGB-D cameras and photography methods.Aiming at the above problems,this paper proposed an annular weld seam detection network named WeldNet where a voxel feature encoding layer was adaptively improved for annular weld seams,the sparse convolutional network and region proposal network(RPN)were used to detect annular weld seam position,and an annular weld seam detection loss function was designed.Further,an annular weld seam dataset was established to train the network.Compared with the random sampling consistency(RANSAC)method,WeldNet has a higher detection accuracy,as well as a higher detection success rate which has increased by 23%.Compared with U-Net,WeldNet has been proven to achieve a better detection result,and the intersection over the union of the weld seam detection is improved by 17.8%.

Automated identification of steel weld defects,a convolutional neural network improved machine learning approach

This paper proposes a machine-learning-based methodology to automatically classify different types of steel weld defects,including lack of the fusion,porosity,slag inclusion,and the qualified(no defects)cases.This methodology solves the shortcomings of existing detection methods,such as expensive equipment,complicated operation and inability to detect internal defects.The study first collected percussed data from welded steel members with or without weld defects.Then,three methods,the Mel frequency cepstral coefficients,short-time Fourier transform(STFT),and continuous wavelet transform were implemented and compared to explore the most appropriate features for classification of weld statuses.Classic and convolutional neural network-enhanced algorithms were used to classify,the extracted features.Furthermore,experiments were designed and performed to validate the proposed method.Results showed that STFT achieved higher accuracies(up to 96.63%on average)in the weld status classification.The convolutional neural network-enhanced support vector machine(SVM)outperformed six other algorithms with an average accuracy of 95.8%.In addition,random forest and SVM were efficient approaches with a balanced trade-off between the accuracies and the computational efforts.

Automatic Detection of Weld Defects in Pressure Vessel X-Ray Image Based on CNN

The visual automatic detection method based on artificial intelligence has attracted more and more attention. In order to improve the performance of weld nondestructive defect detection,we propose DRepDet(Dilated RepPoints Detector). First, we analyze the weld defect dataset in detail and summarize the distribution characteristics of weld defect data, that is, the defect scale is very different and the aspect ratio distribution range is large. Second, according to the distribution characteristics of defect data, we design DResBlock module, and introduce dilated convolution with different dilated rates in the process of feature extraction to expand the receptive field and improve the detection performance of large-scale defects. Based on DResBlock and anchor-free detection framework RepPoints, we design DRepDet. Extensive experiments show that our proposed detector can detect 7 types of defects. When using combined dilated rate convolution network in detection, the AP50 and Recall50 of big defects are improved by 3.1% and 3.3% respectively, while the performance of small defects is not affected, almost the same or slightly improved. The final performance of the whole network is improved a large margin,with 6% AP50 and 4.2% Recall50 compared with Cascade RCNN and 1.4% AP50 and 2.9% Recall50 compared with RepPoints.