ALUMINUM PLATE DEFECT DETECTION BASED ON MULTILEVEL LSTM

Zhang Fengyi; Wang Lihua; Ye Wenjing

doi:10.6052/0459-1879-23-193

Volume 55 Issue 11

Nov. 2023

Turn off MathJax

Article Contents

Abstract

References

Chinese Journal of Theoretical and Applied Mechanics > 2023 > 55(11): 2566-2576. > DOI: 10.6052/0459-1879-23-193 CSTR: 32045.14.0459-1879-23-193

Zhang Fengyi, Wang Lihua, Ye Wenjing. Aluminum plate defect detection based on multilevel LSTM. Chinese Journal of Theoretical and Applied Mechanics, 2023, 55(11): 2566-2576. DOI: 10.6052/0459-1879-23-193

Citation:

PDF (3360 KB)

ALUMINUM PLATE DEFECT DETECTION BASED ON MULTILEVEL LSTM

School of Aerospace Engineering and Applied Mechanics, Tongji University, Shanghai 200092, China

Received Date: May 18, 2023
Accepted Date: July 23, 2023
Available Online: July 26, 2023

Graphical Abstract

Abstract

Abstract

Aluminum plates are widely used in fields such as aviation, aerospace, and construction due to their excellent fatigue resistance and ductility. However, during the production process, various defects can occur due to external environmental factors, operating processes and so on. These defects can affect the mechanical properties of aluminum plates, such as reducing their strength, ductility, and toughness, which leads to a shortened service life. This article proposes a method of using a multilevel long short-term memory (LSTM) neural network for assisting the detection of inclusions (void defects) in aluminum plates under the condition of single transmission and reception of ultrasonic waves. The propagation of ultrasonic waves in an aluminum plate containing inclusion defects is simulated using the finite element software COMSOL Multiphysics. Waveform data containing defect information is then derived. By training the waveform data, a neural network model reflecting the relationship between waveform data and the size and location of inclusions is obtained. In addition, we adopt a hard voting method to alleviate the problem of complex parameter adjustment during network training and improve the reliability of the detection results. The results show that the accuracy of radius detection for inclusion defects exceeds 98%, the accuracy of depth detection for inclusion defects reaches 1, and the accuracy of horizontal position detection for inclusion defects exceeds 95%. It provides reference for the application of LSTM neural network in ultrasonic non-destructive testing.
- multilevel LSTM,
- aluminum inclusion defect,
- ultrasound,
- finite element analysis

FullText(HTML)

References (33)

References

[1]	Ismail PK, Erdal E. Deep learning-based detection of aluminum casting defects and their types. Engineering Applications of Artificial Intelligence, 2023, 118: 105636 doi: 10.1016/j.engappai.2022.105636
[2]	Mugica GW, Tovio DO, Cuyas JC, et al. Effect of porosity on the tensile properties of low ductility aluminum alloys. Materials Research, 2004, 7(2): 221-229 doi: 10.1590/S1516-14392004000200002
[3]	Ardika RD, Triyono T, Muhayat N. A review porosity in aluminum welding. Procedia Structural Integrity, 2021, 33: 171-180 doi: 10.1016/j.prostr.2021.10.021
[4]	Sui D, Han Q. Ultrasound-assisted cast-on method: Obtaining high-quality metallurgical bonds between a bare steel insert and A354 aluminum alloy within a composite casting. Journal of Materials Processing Technology, 2023, 311: 117783 doi: 10.1016/j.jmatprotec.2022.117783
[5]	Mirmahdi E. Analysis and examination of aluminum sheets suitable for automotion body: ultrasonic testing, signal processing, simulation. Russian Journal of Nondestructive Testing, 2021, 57(2): 135-144 doi: 10.1134/S1061830921020108
[6]	任会兰, 宁建国, 宋水舟等. 基于声发射矩张量分析混凝土破坏的裂纹运动. 力学学报, 2019, 51(6): 1830-1840 (Ren Huilan, Ning Jianguo, Song Shuizhou, et al. Investigation on crack growth in concrete by moment tensor analysis of acoustic emission. Chinese Journal of Theoretical and Applied Mechanics, 2019, 51(6): 1830-1840 (in Chinese) doi: 10.6052/0459-1879-19-170 Ren Huilan, Ning Jianguo, Song Shuizhou, et al. Investigation on crack growth in concrete by moment tensor analysis of acoustic emission. Chinese Journal of Theoretical and Applied Mechanics, 2019, 51(6): 1830-1840 (in Chinese) doi: 10.6052/0459-1879-19-170
[7]	Wan Q, Zhao H, Zou C. Effect of micro-porosities on fatigue behavior in aluminum die castings by 3D X-ray tomography inspection. ISIJ International, 2014, 54(3): 511-515 doi: 10.2355/isijinternational.54.511
[8]	Palanisamy S. Ultrasonic inspection of gas porosity defects in aluminium die castings. [PhD Thesis]. Swinburne University of Technology, Industrial Research Institute Swinburne, 2006
[9]	Cho H, Lissenden CJ. Structural health monitoring of fatigue crack growth in plate structures with ultrasonic guided waves. Structural Health Monitoring, 2012, 11(4): 393-404 doi: 10.1177/1475921711430439
[10]	Junping C, Hang J, Shaohua W, et al. Research of non-destructive testing for aluminium sheaths of HV cables using ultrasonic-guided waves. The Journal of Engineering, 2019, 2019(16): 2078-2083 doi: 10.1049/joe.2018.8738
[11]	Tiwari KA, Raisutis R, Tumsys O, et al. Defect estimation in non-destructive testing of composites by ultrasonic guided waves and image processing. Electronics, 2019, 8(3): 315-330 doi: 10.3390/electronics8030315
[12]	Hasiotis T, Badogiannis E, Tsouvalis NG. Application of ultrasonic C-scan techniques for tracing defects in laminated composite materials. Strojniški Vestnik-Journal of Mechanical Engineering, 2011, 57(3): 192-203
[13]	Xu X, Zhao M, Shi P, et al. Crack detection and comparison study based on faster R-CNN and mask R-CNN. Sensors, 2022, 22(3): 1215-1231 doi: 10.3390/s22031215
[14]	Dung CV. Autonomous concrete crack detection using deep fully convolutional neural network. Automation in Construction, 2019, 99: 52-58 doi: 10.1016/j.autcon.2018.11.028
[15]	Xu H, Su X, Wang Y, et al. Automatic bridge crack detection using a convolutional neural network. Applied Sciences, 2019, 9(14): 2867-2880 doi: 10.3390/app9142867
[16]	仇静博, 燕雪峰, 汪俊等. 基于全卷积神经网络的单幅隧道图像裂纹提取算法. 计算机工程与科学, 2022, 44(5): 845-854 (Chou Jingbo, Yan Xuefeng, Wang Jun, et al. Crack extraction algorithm for single tunnel image based on fully convolutional neural network. Computer Engineering and Science, 2022, 44(5): 845-854 (in Chinese) doi: 10.3969/j.issn.1007-130X.2022.05.010 Chou Jingbo, Yan Xuefeng, Wang Jun, et al. Crack extraction algorithm for single tunnel image based on fully convolutional neural network. Computer Engineering and Science, 2022, 44(05): 845-854 (in Chinese) doi: 10.3969/j.issn.1007-130X.2022.05.010
[17]	Ali R, Chuah JH, Talip MSA, et al. Structural crack detection using deep convolutional neural networks. Automation in Construction, 2022, 133: 103989 doi: 10.1016/j.autcon.2021.103989
[18]	马栋梁, 王德禹. 基于加速度和卷积神经网络的船体板裂纹损伤检测. 船舶力学, 2022, 26(8): 1180-1188 (Ma Dongliang, Wang Deyu. Ship hull plate crack damage detection based on acceleration and convolutional neural network. Journal of Ship Mechanics, 2022, 26(8): 1180-1188 (in Chinese) doi: 10.3969/j.issn.1007-7294.2022.08.008 Ma Dongliang, Wang Deyu. Ship hull plate crack damage detection based on acceleration and convolutional neural network. Journal of Ship Mechanics, 2022, 26(08): 1180-1188 (in Chinese) doi: 10.3969/j.issn.1007-7294.2022.08.008
[19]	骆撷冬, 马栋梁, 张松林等. 基于门控循环单元神经网络的箱型梁结构裂纹损伤检测方法. 中国舰船研究, 2022, 17(4): 194-203 (Luo Xiedong, Ma Dongliang, Zhang Songlin, et al. Crack damage detection method for box-beam structures based on gated recurrent unit neural network. Chinese Journal of Ship Research, 2022, 17(4): 194-203 (in Chinese) Luo Xiedong, Ma Dongliang, Zhang Songlin, et al. Crack damage detection method for box-beam structures based on gated recurrent unit neural network. Chinese Journal of Ship Research, 2022, 17(04): 194-203 (in Chinese)
[20]	Barry TJ, Kesharaju M, Nagarajah CR, et al. Defect characterisation in laminar composite structures using ultrasonic techniques and artificial neural networks. Journal of Composite Materials, 2016, 50(7): 861-871 doi: 10.1177/0021998315584651
[21]	钱金花, 郑文娟, 吴文彬等. 基于小波去噪和循环神经网络-k重-整合移动平均自回归模型转炉煤气柜位预测. 冶金自动化, 2023, 47(3): 21-34 (Qian Jinhua, Zheng Wenjuan, Wu Wenbing, et al. Prediction of converter gas location based on wavelet denoising and cyclic neural network-k-weight integrated moving average autoregressive model. Metallurgical Industry Automation, 2023, 47(3): 21-34 (in Chinese) Qian Jinhua, Zheng Wenjuan, Wu Wenbing, et al. Prediction of converter gas location based on wavelet denoising and cyclic neural network-K-weight integrated moving average autoregressive model. Metallurgical Industry Automation, 2023, 47(03): 21-34 (in Chinese)
[22]	李华旭. 基于RNN和Transformer模型的自然语言处理研究综述. 信息记录材料, 2021, 22(12): 7-9 (Li Huaxu. A review of natural language processing based on RNN and Transformer model. Information Recording Material, 2021, 22(12): 7-9 (in Chinese) doi: 10.3969/j.issn.1009-5624.2021.12.xxjlcl202112004 Li Huaxu. A review of natural language processing based on RNN and Transformer model. Information Recording Material, 2021, 22(12): 7-9 (in Chinese) doi: 10.3969/j.issn.1009-5624.2021.12.xxjlcl202112004
[23]	郭家兴, 韩纪庆. 一种RNN-T与BERT相结合的端到端语音识别模型. 智能计算机与应用, 2021, 11(2): 169-173 (Guo Jiaxing, Han Jiqing. An end-to-end speech recognition model combining RNN-T and BERT. Intelligent Computers and Applications, 2021, 11(2): 169-173 (in Chinese) doi: 10.3969/j.issn.2095-2163.2021.02.037 Guo Jiaxing, Han Jiqing. An end-to-end speech recognition model combining RNN-T and BERT. Intelligent Computers and Applications, 2021, 11(02): 169-173 (in Chinese) doi: 10.3969/j.issn.2095-2163.2021.02.037
[24]	白瑞芳. 基于RNN编码器的交互式机器翻译平台控制技术. 计算机测量与控制, 2019, 27(7): 89-92 (Bai Ruifang. Control technology of interactive machine translation platform based on RNN encoder. Computer Measurement & Control, 2019, 27(7): 89-92 (in Chinese) doi: 10.16526/j.cnki.11-4762/tp.2019.07.019 Bai Ruifang. Control technology of interactive machine translation platform based on RNN encoder. Computer Measurement & Control, 2019, 27(07): 89-92 (in Chinese) doi: 10.16526/j.cnki.11-4762/tp.2019.07.019
[25]	孙承爱, 张馨俸, 田刚. 基于奖励值RNN和A2C模型的音乐生成. 软件, 2019, 40(7): 96-99 (Sun Chengai, Zhang Xinfeng, Tian Gang. Music generation based on reward value RNN and A2C model. Software, 2019, 40(7): 96-99 (in Chinese) doi: 10.3969/j.issn.1003-6970.2019.07.017 Sun Chengai, Zhang Xinfeng, Tian Gang. Music generation based on reward value RNN and A2 C model. Software, 2019, 40(07): 96-99 (in Chinese) doi: 10.3969/j.issn.1003-6970.2019.07.017
[26]	Wang L, Ye W, Zhu Y, et al. Optimal parameters selection of back propagation algorithm in the feedforward neural network. Engineering Analysis with Boundary Elements, 2023, 151: 575-596 doi: 10.1016/j.enganabound.2023.03.033
[27]	Ye W, Zhang F, Wang L, et al. Shale crack identification based on acoustic emission experiment and wavenet data recovery. International Journal of Applied Mechanics, 2022, 14(10): 2250073 doi: 10.1142/S1758825122500739
[28]	叶文静, 王莉华. 基于反向传播神经网络的疲劳裂纹扩展分析. 力学季刊, 2021, 42(4): 613-632 (Ye Wenjing, Wang Lihua. Fatigue crack growth analysis based on backpropagation neural network. Chinese Quarterly of Mechanics, 2021, 42(4): 613-632 (in Chinese) doi: 10.15959/j.cnki.0254-0053.2021.04.013 Ye Wenjing, Wang Lihua. Fatigue crack growth analysis based on backpropagation neural network. Chinese Quarterly of Mechanics, 2021, 42(4): 613-632 (in Chinese) doi: 10.15959/j.cnki.0254-0053.2021.04.013
[29]	Liu G, Guo J. Bidirectional LSTM with attention mechanism and convolutional layer for text classification. Neurocomputing, 2019, 337: 325-338 doi: 10.1016/j.neucom.2019.01.078
[30]	Ahmadzadeh E, Kim H, Jeong O, et al. A deep bidirectional LSTM-GRU network model for automated ciphertext classification. IEEE Access, 2022, 10: 3228-3237 doi: 10.1109/ACCESS.2022.3140342
[31]	Mao K, Zhang W, Wang DB, et al. Prediction of depression severity based on the prosodic and semantic features with bidirectional LSTM and time distributed CNN. IEEE Transactions on Affective Computing, 2022, in press
[32]	Wang Q, Feng C, Xu Y, et al. A novel privacy-preserving speech recognition framework using bidirectional LSTM. Journal of Cloud Computing, 2020, 9(36): 1-13
[33]	Mutasa S, Sun S, Ha R. Understanding artificial intelligence based radiology studies: What is overfitting? Clinical Imaging, 2020, 65: 96-99

[1]	Wang Yirui, Li Mingtao, Zhou Binghong. IMPULSIVE TRAJECTORY OPTIMIZATION OF KINETIC IMPACTOR MISSIONS FOR ASTEROID DEFLECTION BASED ON AN APPROXIMATION DEFLECTION MODEL[J]. Chinese Journal of Theoretical and Applied Mechanics, 2021, 53(3): 912-928. DOI: 10.6052/0459-1879-20-210
[2]	Du Xiangnan, Yang Zhen. AN ALGORITHM FOR SOLVING SPACECRAFT REACHABLE DOMAIN WITH SINGLE-IMPULSE MANEUVERING[J]. Chinese Journal of Theoretical and Applied Mechanics, 2020, 52(6): 1621-1631. DOI: 10.6052/0459-1879-20-111
[3]	Li Xueyan, Zhang Huimin. STUDY OF DAMAGE IDENFICATION METHOD BASED ON THE COVARIANCE OF STRAIN IMPULSE RESPONSE FUNCTION[J]. Chinese Journal of Theoretical and Applied Mechanics, 2017, 49(5): 1081-1090. DOI: 10.6052/0459-1879-17-039
[4]	Jia Jianhua, Lü Jing, Wang Qi. POWERED GRAVITY ASSIST IN THREE DIMENSIONS[J]. Chinese Journal of Theoretical and Applied Mechanics, 2016, 48(2): 437-446. DOI: 10.6052/0459-1879-15-218
[5]	Wang Wei, Yuan Jianping, Luo Jianjun. OPTIMAL SINGLE IMPULSE MANEUVER FOR SPACECRAFT CLUSTER FLIGHT[J]. Chinese Journal of Theoretical and Applied Mechanics, 2015, 47(5): 799-806. DOI: 10.6052/0459-1879-14-386
[6]	Liu Song Cai Guoping Dong Xingjian. Time-domain dynamic modeling and active control of offshore platform[J]. Chinese Journal of Theoretical and Applied Mechanics, 2011, 43(4): 737-745. DOI: 10.6052/0459-1879-2011-4-lxxb2010-373
[7]	Xu Han, Jie Liu, Weijie Li. A computational inverse technique for reconstruction of multisource loads in time domain[J]. Chinese Journal of Theoretical and Applied Mechanics, 2009, 41(4): 595-602. DOI: 10.6052/0459-1879-2009-4-2008-038
[8]	Chunning Ji, Yuanzhan Wang, Jianfeng Wang. Application of the fictitious domain method in fluid- structure interaction[J]. Chinese Journal of Theoretical and Applied Mechanics, 2009, 41(1): 49-59. DOI: 10.6052/0459-1879-2009-1-2007-549
[9]	A TIME DOMAIN BOUNDARY ELEMENT METHOD FOR SYSTEMS WITH DAMPING[J]. Chinese Journal of Theoretical and Applied Mechanics, 1997, 29(5): 627-630. DOI: 10.6052/0459-1879-1997-5-1995-276
[10]	THE DRIFT INSTABILITY OF LOCAL TRANSMITTING BOUNDARY IN TIME DOMAIN[J]. Chinese Journal of Theoretical and Applied Mechanics, 1996, 28(5): 627-632. DOI: 10.6052/0459-1879-1996-5-1995-379

Cited By

Get Citation

PDF

XML

Article Metrics

Article views (568) PDF downloads (74)

ALUMINUM PLATE DEFECT DETECTION BASED ON MULTILEVEL LSTM

Abstract

References

Related Articles

Catalog

Article Metrics

Related

Download Center

Author Center

ALUMINUM PLATE DEFECT DETECTION BASED ON MULTILEVEL LSTM

Abstract

References

Related Articles

Catalog

Article Metrics

Related

Download Center

Author Center

Export File

Citation

Format

Content