Deep Learning based Intelligent Coin-tap Test for Defect Recognition

TL;DR

This paper introduces an intelligent coin-tap testing method using CNNs with transfer learning to recognize defects effectively across different scenarios, even with minimal labeled data, supported by a new benchmark dataset.

Contribution

It develops transfer learning strategies for coin-tap defect recognition, enabling model adaptation with little labeled data across different scenarios.

Findings

Transfer learning improves defect recognition accuracy.

Domain adaptation and pseudo label learning enhance performance.

A large benchmark dataset was created and published.

Abstract

The coin-tap test is a convenient and primary method for non-destructive testing, while its manual on-site operation is tough and costly. With the help of the latest intelligent signal processing method, convolutional neural networks (CNN), we achieve an intelligent coin-tap test which exhibited superior performance in recognizing the defects. However, this success of CNNs relies on plenty of well-labeled data from the identical scenario, which could be difficult to get for many real industrial practices. This paper further develops transfer learning strategies for this issue, that is, to transfer the model trained on data of one scenario to another. In experiments, the result presents a notable improvement by using domain adaptation and pseudo label learning strategies. Hence, it becomes possible to apply the model into scenarios with none or little (less than 10\%) labeled data adopting the transfer learning strategies proposed herein. In addition, we used a benchmark dataset constructed ourselves throughout this study. This benchmark dataset for the coin-tap test containing around 100,000 sound signals is published at https://github.com/PPhub-hy/torch-tapnet.