Domain Adaptation in Intelligent Ultrasonic Logging Tool: from Micro-Seismic to Pulse-Echo

With high temporal resolution demand under noise contamination, the travel time estimation for the pulse-echo is noticed in the acoustic logging instrument design. To this end, an intelligent ultrasonic logging system is built to collect borehole information, and a framework with domain adaptation theory is proposed. The modified maximum mean discrepancy minimization combined with spatial pyramid pooling is constructed on different deep neural networks, where the transfer from the microseismic P-wave picking to the estimation of echo travel time is achieved. Versus the conventional travel time extraction algorithms, the proposed scheme improves the picking accuracy to 83.55% of the 10-dB signal-to-noise ratio. Experiments over the ultrasonic logging tool demonstrate the feasibility of the confusion domain, the effectiveness of travel time estimation, and the versatility of algorithm application.