IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v12y2024i21p3414-d1511392.html
   My bibliography  Save this article

Explaining the Anomaly Detection in Additive Manufacturing via Boosting Models and Frequency Analysis

Author

Listed:
  • Mario Vozza

    (Department of Control and Computer Engineering (DAUIN), Polytechnic University of Turin, 10129 Turin, Italy
    DAIMON Lab, CNR-ISMN, 40129 Bologna, Italy)

  • Joseph Polden

    (School of Mechanical Materials Mechatronic and Biomedical Engineering, University of Wollongong, Wollongong, NSW 2500, Australia)

  • Giulio Mattera

    (Department of Chemical, Materials and Production Engineering, University of Naples Federico II, 80126 Naples, Italy)

  • Gianfranco Piscopo

    (Department of Mathematics and Applications “R. Caccioppoli”, University of Naples Federico II, 80126 Naples, Italy)

  • Silvestro Vespoli

    (Department of Chemical, Materials and Production Engineering, University of Naples Federico II, 80126 Naples, Italy)

  • Luigi Nele

    (Department of Chemical, Materials and Production Engineering, University of Naples Federico II, 80126 Naples, Italy)

Abstract

Anomaly detection is an important feature in modern additive manufacturing (AM) systems to ensure quality of the produced components. Although this topic is well discussed in the literature, current methods rely on black-box approaches, limiting our understanding of why anomalies occur, making complex the root cause identification and the consequent decision support about the action to take to mitigate them. This work addresses these limitations by proposing a structured workflow designed to enhance the explainability of anomaly detection models. Using the wire arc additive manufacturing (WAAM) process as a case study, we examined 14 wall structures printed with INVAR36 alloy under varying process parameters, producing both defect-free and defective parts. These parts were classified based on surface appearance and welding camera images. We collected welding current and voltage data at a 5 kHz sampling rate and extracted features from both time and frequency domains using a knowledge-based approach. Isolation Forest, k-Nearest Neighbor, Artificial Neural Network, XGBoost, and LGBM models were trained on these features, and the results shown best performance of boosting models, achieving F1 scores of 0.927 and 0.945, respectively. These models presented higher performance compared to other models like k-Nearest Neighbor, whereas Isolation Forest and Artificial Neural Network posses lower performance due to overfitting, with an F1 score of 0.507 and 0.56, respectively. Then, by leveraging the feature importance capabilities of these models, we identified key signal characteristics that distinguish between normal and anomalous behavior, improving the explainability of the detection process and in general about the process physics.

Suggested Citation

  • Mario Vozza & Joseph Polden & Giulio Mattera & Gianfranco Piscopo & Silvestro Vespoli & Luigi Nele, 2024. "Explaining the Anomaly Detection in Additive Manufacturing via Boosting Models and Frequency Analysis," Mathematics, MDPI, vol. 12(21), pages 1-17, October.
  • Handle: RePEc:gam:jmathe:v:12:y:2024:i:21:p:3414-:d:1511392
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/12/21/3414/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/12/21/3414/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Andrew Kusiak, 2017. "Smart manufacturing must embrace big data," Nature, Nature, vol. 544(7648), pages 23-25, April.
    2. H. K. Nigam & H. M. Srivastava, 2023. "Filtering of Audio Signals Using Discrete Wavelet Transforms," Mathematics, MDPI, vol. 11(19), pages 1-12, September.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Zhao, Guanjia & Cui, Zhipeng & Xu, Jing & Liu, Wenhao & Ma, Suxia, 2022. "Hybrid modeling-based digital twin for performance optimization with flexible operation in the direct air-cooling power unit," Energy, Elsevier, vol. 254(PC).
    2. Maximilian Zarte & Agnes Pechmann & Isabel L. Nunes, 2022. "Problems, Needs, and Challenges of a Sustainability-Based Production Planning," Sustainability, MDPI, vol. 14(7), pages 1-19, March.
    3. Lu, Shixiang & Xu, Qifa & Jiang, Cuixia & Liu, Yezheng & Kusiak, Andrew, 2022. "Probabilistic load forecasting with a non-crossing sparse-group Lasso-quantile regression deep neural network," Energy, Elsevier, vol. 242(C).
    4. Wang, Di & He, Bin & Hu, Zhimu, 2024. "Financial technology and firm productivity: Evidence from Chinese listed enterprises," Finance Research Letters, Elsevier, vol. 63(C).
    5. Wang, Linhui & Chen, Qi & Dong, Zhiqing & Cheng, Lu, 2024. "The role of industrial intelligence in peaking carbon emissions in China," Technological Forecasting and Social Change, Elsevier, vol. 199(C).
    6. Guo, Daqiang & Li, Mingxing & Lyu, Zhongyuan & Kang, Kai & Wu, Wei & Zhong, Ray Y. & Huang, George Q., 2021. "Synchroperation in industry 4.0 manufacturing," International Journal of Production Economics, Elsevier, vol. 238(C).
    7. Shiguang Li & Yixiang Tian, 2023. "How Does Digital Transformation Affect Total Factor Productivity: Firm-Level Evidence from China," Sustainability, MDPI, vol. 15(12), pages 1-17, June.
    8. Wei Fang & Lianyu Zheng, 2020. "Shop floor data-driven spatial–temporal verification for manual assembly planning," Journal of Intelligent Manufacturing, Springer, vol. 31(4), pages 1003-1018, April.
    9. Mingxing Li & Ray Y. Zhong & Ting Qu & George Q. Huang, 2022. "Spatial–temporal out-of-order execution for advanced planning and scheduling in cyber-physical factories," Journal of Intelligent Manufacturing, Springer, vol. 33(5), pages 1355-1372, June.
    10. Zhe Li & Yi Wang & Kesheng Wang, 2020. "A data-driven method based on deep belief networks for backlash error prediction in machining centers," Journal of Intelligent Manufacturing, Springer, vol. 31(7), pages 1693-1705, October.
    11. Chaohong Na & Xue Chen & Xiaojun Li & Yuting Li & Xiaolan Wang, 2022. "Digital Transformation of Value Chains and CSR Performance," Sustainability, MDPI, vol. 14(16), pages 1-24, August.
    12. Xifan Yao & Nanfeng Ma & Jianming Zhang & Kesai Wang & Erfu Yang & Maurizio Faccio, 2024. "Enhancing wisdom manufacturing as industrial metaverse for industry and society 5.0," Journal of Intelligent Manufacturing, Springer, vol. 35(1), pages 235-255, January.
    13. Li, Mingxing & Huang, George Q., 2021. "Production-intralogistics synchronization of industry 4.0 flexible assembly lines under graduation intelligent manufacturing system," International Journal of Production Economics, Elsevier, vol. 241(C).
    14. Andrew Kusiak, 2019. "Editorial: Intelligent manufacturing: bridging two centuries," Journal of Intelligent Manufacturing, Springer, vol. 30(1), pages 1-2, January.
    15. Yixiao Zhao & Yihai He & Fengdi Liu & Xiao Han & Anqi Zhang & Di Zhou & Yao Li, 2020. "Operational risk modeling based on operational data fusion for multi-state manufacturing systems," Journal of Risk and Reliability, , vol. 234(2), pages 407-421, April.
    16. Wei Ji & Shubin Yin & Lihui Wang, 2019. "A big data analytics based machining optimisation approach," Journal of Intelligent Manufacturing, Springer, vol. 30(3), pages 1483-1495, March.
    17. Zeng, Huixiang & Ran, Hangxin & Zhou, Qiong & Jin, Youliang & Cheng, Xu, 2022. "The financial effect of firm digitalization: Evidence from China," Technological Forecasting and Social Change, Elsevier, vol. 183(C).
    18. Yanning Sun & Wei Qin & Zilong Zhuang & Hongwei Xu, 2021. "An adaptive fault detection and root-cause analysis scheme for complex industrial processes using moving window KPCA and information geometric causal inference," Journal of Intelligent Manufacturing, Springer, vol. 32(7), pages 2007-2021, October.
    19. Zhang, Yunqi & Zhang, Xiaoyu, 2024. "Regulation-induced digitalization," China Economic Review, Elsevier, vol. 88(C).
    20. Shanhe Lou & Yixiong Feng & Hao Zheng & Yicong Gao & Jianrong Tan, 2020. "Data-driven customer requirements discernment in the product lifecycle management via intuitionistic fuzzy sets and electroencephalogram," Journal of Intelligent Manufacturing, Springer, vol. 31(7), pages 1721-1736, October.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jmathe:v:12:y:2024:i:21:p:3414-:d:1511392. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.