A Wavelet Packet Transform and Convolutional Neural Network Method Based Ultrasonic Detection Signals Recognition of Concrete

Abstract

This paper proposes a new intelligent recognition method for concrete ultrasonic detection based on wavelet packet transform and a convolutional neural network (CNN). To validate the proposed data-based method, a case study is presented where the K-fold cross-validation was adopted to produce the performance analysis and classification experiments. Moreover, three evaluation indicators, precision, recall, and F-score, are calculated for analyzing the classification performance of the trained models. As a result, the obtained four-classifying CNN reaches more than 99% detection accuracy while the lowest recognition accuracy is not less than 92.5% on the testing dataset for the six-classifying CNN model. Compared with the existing stochastic configuration network (SCN) models, the presented method achieves the design objective with better recognition performance. The calculation results of the six-classifying and five-classifying models and related research clearly indicate the remaining challenging tasks for intelligent recognition algorithms in extracting features and classifying mass data from various concrete defects precisely and efficiently.

Intelligent Detection Method for Concrete Dam Surface Cracks Based on Two-Stage Transfer Learning

“…Residual networks are widely used for this reason. Zhao et al [62] addressed the low recognition accuracy problem of the UNet model by using ResNet18 as the backbone network to enhance the feature extraction capability of the network. Xu et al [63] used the ResNet34 residual network as a model encoder to better extract crack detail information.…”

Near-Surface Defects Identification of Polyethylene Pipes Based on Synchro-Squeezing Transform and Deep Learning

“…Table 4 shows the model's evaluation metrics. [28] 76.50 -74.40 ---SVM [28] 79.40 -77.70 ---Random forest [28] 82.60 -79.40 ---CNN [28] 87.00 -87.40 ---LSTM [28] 81.70 -81.00 ---BiLSTM [28] 80.10 -79.70 ---WPT-CNN [29] 99.78 -99.76 ---CNN [30] 98.20 -----Table 4 reveals that after the model is modified, its performance deteriorates due to the reduced ability to learn key information. The implemented attention mechanism, furthermore, showed a 2% improvement in accuracy under the addition of the CAM, a 0.5% improvement under the addition of the SAM, and a 1.5% improvement under the addition of the SE, revealing the potential for attention modules to enhance the model's learning ability.…”

“…Their findings suggest that CNN was the most performant machine learning approach. Zhao et al [29] proposed an intelligent recognition method based on wavelet packet transform (WPT) and CNN for concrete ultrasonic detection, which resulted in outstanding recognition performance. Shi et al [30] obtained a classification accuracy rate of up to 0.982 using CNN and ultrasonic A-scan to evaluate circumferential welds composed of austenitic and martensitic stainless steel with internal slots.…”