In the production and service of pipelines, automated electromagnetic detection is widely employed to diagnose potential defects. However, the single inspection method can hardly meet reliability and multi-position detect detection simultaneously due to limited signal features. In this paper, a novel composite approach of electromagnetic acoustic transducer and eddy current is proposed to detect different kinds of defects combining their technical merits. A comprehensive theoretical analysis of the composite approach is given to derive the modified model of the send-receive mode. The influences of the critical parameters on hybrid signals are discussed and the probe performance is improved over 65% in magnitude. Then, the time-division multiplexing strategy is utilized to separate hybrid signals. Finally, laboratory experiments are conducted to extract independent features and diagnose potential defects in the steel plate. Results indicated that the proposed approach could achieve a good performance in the detection task of inner and outer defects. Compared with existing detection methods, our proposed approach has significant merits in detectability and efficiency.
This paper introduces a new planar matrix pulsed eddy current sensor for non-destructive testing. The sensor consists of multiple independent excitation poles and an array of induction coils. Each induction coil can be regarded as an independent pixel unit. The simulation model of matrix pulsed eddy current sensor is established by finite element simulation software, and the characteristics of the sensor are analyzed. The excitation pole is driven by the pulse generator, and the voltage pulse signal of a certain induction coil in the array is selected by the multiplexer. Then the FPGA is used to perform fast Fourier transform on the collected pulse signal to obtain the frequency domain signal, and the processed signal is amplified and collected. In the experiment, the detected data corresponds to the pixel point to form the defect image of the detected object.
1 October 2026 in Expert Systems with Applications