Electromagnetic Acoustic Transducer (EMAT) has become one of the fastest-growing solutions for pipeline weld inspection over the past decade due to its non-contact advantage. One primary problem of EMAT is that it has relatively lower energy transition efficiency compared to widely used piezoelectric transducers, coupled with the effect of lift-off and the non-uniformity issue of welding material, the Signal-to-Noise Ratio (SNR) can be significantly restricted. This brings great difficulty in interpreting the EMAT signal measured from pipeline girth welds. To overcome this challenge, this paper presents a deep learning-based ultrasonic pattern recognition method to identify the pipeline girth weld cracking automatically. The proposed method utilizes a deep Convolution Neural Network (CNN) integrated with a pre-trained Support Vector Machine (SVM) classifier to extract the high-level features from the time-frequency representation of A-scan signals measured by bulk-wave EMAT and classify these signals into defective or non-defective groups. To validate the proposed method, a set of experiments is carried out to classify A-scan signals measured from the girth welds of an ex-service type 813-X70 gas pipeline. A comparative investigation is also undertaken to demonstrate the superiority of the proposed method against the conventional ultrasonic pattern recognition methods for evaluation.

In the SBAS-InSAR process, the conventional approach of determining ground control points (GCPs) can be error-prone. Thus, a new GCP selection approach using the phase derivative variance is proposed. Analyzing 45 descending-orbit Sentinel-1 datasets between October 2014 and June 2017 over the 2017 Xinmo landslide site, we separately identified ~10,600 and 100 GCP candidates with the conventional and proposed approaches. With four GCPs from the conventional method, the time-series displacement curves do not capture the accelerated deformation related to the landslide event. Corresponding to two sets of GCPs from the proposed approach, the displacement curves change gradually and capture the accelerated deformation. Thus, the approach can efficiently identify a small number of reliable and accurate GCP candidates for the SBAS-InSAR analysis.

Atmospheric pressure plasma torch has a wide application prospect in the fields of chemical industry, environmental protection and degradation. The research of its device has attracted extensive attention from all walks of life. Based on the design of an atmospheric pressure microwave plasma reactor, the effect of gas flow field characteristics in the reaction tube on the plasma torch was studied in this paper. The experimental device uses a microwave source with a frequency of 2.45 GHz. The microwave generated by it is fed into the quartz reaction tube through the waveguide compression structure, so as to excite the argon in the tube to generate plasma at atmospheric pressure. The flow field in the reaction tube under different inlet modes was simulated by COMSOL simulation software, and the discharge characteristics under different flow fields are tested in the experiment. The simulation and experimental results show that although different inlet modes have a great influence on the convection field, the flow field can become stable after passing through a section of quartz tube, and the plasma discharge phenomenon is also similar. Therefore, the influence of flow field on plasma torch can be avoided by lengthening the quartz tube, thus reduce the difficulty of flow field design in microwave plasma torch.