Multi-Feature Extraction-Based Defect Recognition of Foundation Pile under Layered Soil Condition Using Convolutional Neural Network
If the layer of soil surrounding a pile is not taken into account during the engineering detection process, the velocity-time curve might show asymptotic diameter shrinkage or diameter expanding features, which would alter the interpretation of the test findings. In this study, we suggest combining...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-09-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/19/9840 |
_version_ | 1797480605420617728 |
---|---|
author | Chuan-Sheng Wu Tian-Qi Hao Ling-Ling Qi De-Bing Zhuo Zhen-Yang Feng Jian-Qiang Zhang Yang-Xia Peng |
author_facet | Chuan-Sheng Wu Tian-Qi Hao Ling-Ling Qi De-Bing Zhuo Zhen-Yang Feng Jian-Qiang Zhang Yang-Xia Peng |
author_sort | Chuan-Sheng Wu |
collection | DOAJ |
description | If the layer of soil surrounding a pile is not taken into account during the engineering detection process, the velocity-time curve might show asymptotic diameter shrinkage or diameter expanding features, which would alter the interpretation of the test findings. In this study, we suggest combining multi-feature extraction and a convolutional neural network (CNN) to increase accuracy in pile defect recognition for layered soil conditions and traditional deep learning flaws. First, numerical simulations are run to create velocity–time curves for foundation piles under layered soil conditions. Then, the data are extracted from three dimensions: time domain, frequency domain, and time-frequency domain, respectively, and fused into a set of feature vectors. Finally, a foundation pile defect identification model combining multi-scale features and CNN is established. The findings demonstrate that the CNN model has 97.8% accuracy while the PNN has 28.6% accuracy, demonstrating that the approach is very reliable. |
first_indexed | 2024-03-09T22:02:29Z |
format | Article |
id | doaj.art-5228c76c44d14c2aa24eeb50a5d5d6ad |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T22:02:29Z |
publishDate | 2022-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-5228c76c44d14c2aa24eeb50a5d5d6ad2023-11-23T19:46:32ZengMDPI AGApplied Sciences2076-34172022-09-011219984010.3390/app12199840Multi-Feature Extraction-Based Defect Recognition of Foundation Pile under Layered Soil Condition Using Convolutional Neural NetworkChuan-Sheng Wu0Tian-Qi Hao1Ling-Ling Qi2De-Bing Zhuo3Zhen-Yang Feng4Jian-Qiang Zhang5Yang-Xia Peng6School of Economics and Management, Chongqing Jiaotong University, Chongqing 400074, ChinaSchool of Civil Engineering, Chongqing Jiaotong University, Chongqing 400074, ChinaSchool of Management Science and Real Estate, Chongqing University, Chongqing 400044, ChinaSchool of Civil Engineering and Architecture, Jishou University, Zhangjiajie 427000, ChinaHousing and Urban and Rural Construction Commission, Chongqing 401320, ChinaSchool of Civil Engineering, Chongqing Jiaotong University, Chongqing 400074, ChinaSchool of Civil Engineering, Chongqing Jiaotong University, Chongqing 400074, ChinaIf the layer of soil surrounding a pile is not taken into account during the engineering detection process, the velocity-time curve might show asymptotic diameter shrinkage or diameter expanding features, which would alter the interpretation of the test findings. In this study, we suggest combining multi-feature extraction and a convolutional neural network (CNN) to increase accuracy in pile defect recognition for layered soil conditions and traditional deep learning flaws. First, numerical simulations are run to create velocity–time curves for foundation piles under layered soil conditions. Then, the data are extracted from three dimensions: time domain, frequency domain, and time-frequency domain, respectively, and fused into a set of feature vectors. Finally, a foundation pile defect identification model combining multi-scale features and CNN is established. The findings demonstrate that the CNN model has 97.8% accuracy while the PNN has 28.6% accuracy, demonstrating that the approach is very reliable.https://www.mdpi.com/2076-3417/12/19/9840layered soilmulti-features extractiondefect recognitionnumerical simulationconvolutional neural network (CNN) |
spellingShingle | Chuan-Sheng Wu Tian-Qi Hao Ling-Ling Qi De-Bing Zhuo Zhen-Yang Feng Jian-Qiang Zhang Yang-Xia Peng Multi-Feature Extraction-Based Defect Recognition of Foundation Pile under Layered Soil Condition Using Convolutional Neural Network Applied Sciences layered soil multi-features extraction defect recognition numerical simulation convolutional neural network (CNN) |
title | Multi-Feature Extraction-Based Defect Recognition of Foundation Pile under Layered Soil Condition Using Convolutional Neural Network |
title_full | Multi-Feature Extraction-Based Defect Recognition of Foundation Pile under Layered Soil Condition Using Convolutional Neural Network |
title_fullStr | Multi-Feature Extraction-Based Defect Recognition of Foundation Pile under Layered Soil Condition Using Convolutional Neural Network |
title_full_unstemmed | Multi-Feature Extraction-Based Defect Recognition of Foundation Pile under Layered Soil Condition Using Convolutional Neural Network |
title_short | Multi-Feature Extraction-Based Defect Recognition of Foundation Pile under Layered Soil Condition Using Convolutional Neural Network |
title_sort | multi feature extraction based defect recognition of foundation pile under layered soil condition using convolutional neural network |
topic | layered soil multi-features extraction defect recognition numerical simulation convolutional neural network (CNN) |
url | https://www.mdpi.com/2076-3417/12/19/9840 |
work_keys_str_mv | AT chuanshengwu multifeatureextractionbaseddefectrecognitionoffoundationpileunderlayeredsoilconditionusingconvolutionalneuralnetwork AT tianqihao multifeatureextractionbaseddefectrecognitionoffoundationpileunderlayeredsoilconditionusingconvolutionalneuralnetwork AT linglingqi multifeatureextractionbaseddefectrecognitionoffoundationpileunderlayeredsoilconditionusingconvolutionalneuralnetwork AT debingzhuo multifeatureextractionbaseddefectrecognitionoffoundationpileunderlayeredsoilconditionusingconvolutionalneuralnetwork AT zhenyangfeng multifeatureextractionbaseddefectrecognitionoffoundationpileunderlayeredsoilconditionusingconvolutionalneuralnetwork AT jianqiangzhang multifeatureextractionbaseddefectrecognitionoffoundationpileunderlayeredsoilconditionusingconvolutionalneuralnetwork AT yangxiapeng multifeatureextractionbaseddefectrecognitionoffoundationpileunderlayeredsoilconditionusingconvolutionalneuralnetwork |