A computer controlled weld quality assurance system has been developed to detect weld defects ultrasonically whilst welding is in progress. This system, including a flash analogue to digital converter and built-in memories to store sampled data, a peak characters extractor and a welding process controller, enabled welding processes to be controlled automatically and welding defects to be detected concurrently with welding. In this way, the weld quality could be satisfactorily assured if no defect was detected and the welding cost was minimised either through avoiding similar defects to occur or by stopping the welding process if repair was necessary. This work demonstrated that the high temperature field around the weld pool was the major source of difficulties and unreliabilities in defect detection during welding and, had to be taken into account in welding control by ultrasonic means. The high temperatures not only influence ultrasonic characteristic parameters which are the defect judgement and assessment criterion, but also introduce noise into signals. The signal averaging technique and statistical analysis based on B-scan data have proved their feasibility to increase 'signal to noise ratio' effectively and to judge or assess weld defects. The hardware and the software for the system is explained in this work. By using this system, real-time 'A-scan' signals on screen display, and, A-scan, B-scan or three dimensional results can be printed on paper, or stored on disks, and, as a result, weld quality could be fully computerized.

No description available.

Yes / Aiming to detect concrete defects, we propose a new identification method based on stochastic configuration networks. The presented model has been trained by time-domain and frequency-domain features which are extracted from filtering and decomposing ultrasonic detection signals. This method was applied to ultrasonic detection data collected from 5 mm, 7 mm, and 9 mm penetrating holes in C30 class concrete. In particular, wavelet packet transform (WPT) was then used to decompose the detected signals, thus the information in different frequency bands can be obtained. Based on the data from the fundamental frequency nodes of the detection signals, we calculated the means, standard deviations, kurtosis coefficients, skewness coefficients and energy ratios to characterize the detection signals. We also analyzed their typical statistical features to assess the complexity of identifying these signals. Finally, we used the stochastic configuration networks (SCNs) algorithm to embed four-fold cross-validation for constructing the recognition model. Based upon the experimental results, the performance of the presented model has been validated and compared with the genetic algorithm based BP neural network model, where the comparison shows that the SCNs algorithm has superior generalization abilities, better fitting abilities, and higher recognition accuracy for recognizing defect signals. In addition, the test and analysis results show that the proposed method is feasible and effective in detecting concrete hole defects. / This work was supported in part by the Zhejiang Provincial Natural Science Foundation (ZJNSF) project under Grant (No. LY18F030012), the National Natural Science Foundation of China projects (NSFC) under Grant (No. 61403356, 61573311).