A stethoscope-guided interpretable deep learning framework for powder flow diagnosis in cold spray additive manufacturing

被引：1

作者：

Lee, Jiho ^{[1
]}

Akin, Semih ^{[2
]}

Sim, Yuseop ^{[1
]}

Lee, Hojun ^{[1
]}

Kim, Eunseob ^{[1
]}

Nam, Jungsoo ^{[3
]}

Song, Kyeongeun ^{[3
]}

Jun, Martin B.G. ^{[1
]}

机构：

[1] School of Mechanical Engineering, Purdue University, West Lafayette

[2] Department of Mechanical, Aerospace and Nuclear Engineering, Rensselaer Polytechnic Institute, Troy

[3] Smart Manufacturing System R&D Department, Korea Institute of Industrial Technology (KITECH), Cheonan

来源：

Manufacturing Letters | 2024年 / 41卷

关键词：

Additive manufacturing; Cold spray; Interpretable deep learning; Multi-stage model; Powder flow monitoring; Stethoscope sound sensor;

D O I：

10.1016/j.mfglet.2024.09.178

中图分类号：

学科分类号：

摘要：

Cold spray (CS) particle deposition, also known as cold spray additive manufacturing, has garnered great attention as an advanced additive manufacturing (AM) and surface deposition technology, facilitating rapid and scalable production of functional parts and surfaces in a solid-state manner. In CS, consistent and precise feeding of functional feedstock powders is crucial for achieving effective particle deposition. However, vibratory-based powder feeders often face challenges associated with powder delivery and powder segregation. This underscores the critical need for a precise diagnostic framework to effectively control powder flow during cold spraying. To this end, the present study proposes a powder flow monitoring framework for the CS process using a stethoscope sound-guided interpretable deep learning (IDL) model. Internal sound data from the vibrated powder feeder is collected through a stethoscope sensor to train a two-stage model. In the first stage, a convolutional autoencoder (CAE) is trained to build an unsupervised learning-based anomaly detector, which identifies classification thresholds based on the receiver operation characteristic curve. In the second stage, a convolutional neural network (CNN) model is trained as the powder flow diagnostic tool by considering process anomalies, namely (i) no powder flow; (ii) feeder clogging; and (iii) no gas flow. The results reveal that the stethoscope sound-guided model achieves a classification accuracy of 95% on the test set, significantly outperforming benchmark utilizing typical external-sound recording microphones in diagnosing CS powder flow. Furthermore, the model is visualized and interpreted by employing t-distribution stochastic neighbor embedding and integrated gradients techniques to enhance reliability of CS powder flow diagnosis. This research highlights the effectiveness of the stethoscope sound-guided IDL model for in situ powder flow monitoring and process diagnosis in the domain of cold spray additive manufacturing, contributing to effective particle deposition. © 2024 The Author(s)

引用

页码：1515 / 1525

页数：10

共 29 条

[21]

Por E., Van Kooten M., Sarkovic V., Nyquist-Shannon sampling theorem. Leiden University, 1, (2019)

[22]

(2021)

[23]

Afshari A.A., Et al., Development of a thermal spray coating aerosol generator and inhalation exposure system, Toxicol Rep, 9, pp. 126-135, (2022)

[24]

Li J., Et al., A comparison of deep learning methods for environmental sound detection, ICASSP IEEE, pp. 126-130, (2017)

[25]

Meng H., Et al., Speech emotion recognition from 3D log-mel spectrograms with deep learning network, IEEE Access, 7, pp. 125868-125881, (2019)

[26]

Jeong K.-J., Et al., Two-stage deep anomaly detection with heterogeneous time series data, IEEE Access, 10, pp. 13704-13714, (2022)

[27]

Liu J., Yang Z., Song Y., A two-stage anomaly detection framework: Towards low omission rate in industrial vision applications, Adv Eng Inform, 55, (2023)

[28]

Van der maaten L., Hinton G., Visualizing data using t-SNE, JMLR, 9, 11, (2008)

[29]

Sundararajan M., Taly A., Yan Q., Axiomatic attribution for deep networks, ICML PMLR, pp. 3319-3328, (2017)

← 1 2 3 →