應用生存分析結合 SHAP 解析產品製程參數在製造過程中導致設備異常之原因以及預測研究

簡易檢索 / 詳目顯示

回結果列表

研究生：	簡維扁 WEI-PIEN CHIEN
論文名稱：	應用生存分析結合 SHAP 解析產品製程參數在製造過程中導致設備異常之原因以及預測研究 A Study Using Survival Analysis and SHAP to Interpret the Causes of Equipment Failures from Product Process Parameters and to Perform Failure Prediction in Manufacturing
指導教授：	葉英傑 YING-CHIEH YEH
口試委員:
學位類別：	碩士 Master
系所名稱：	管理學院 - 工業管理研究所 Graduate Institute of Industrial Management
論文出版年：	2025
畢業學年度：	113
語文別：	中文
論文頁數：	50
中文關鍵詞：	機器學習、生存分析、SHAP 、SurvSHAP(t)
外文關鍵詞：	machine learning, survival analysis, SHAP, SurvSHAP(t)
相關次數：	點閱：147 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

本研究旨在結合生存分析與 SHAP 解釋技術，探討製造過程中不同產品製
程參數對機器異常風險的影響，並建立具可解釋性的預測模型。資料採用網路
上公開之預測型維護資料集以及 A 公司所提供之塗佈機資料集。研究首先比較
Cox 比例風險模型、隨機生存森林（Random Survival Forest, RSF）、XGBoost
Cox 與 DeepSurv 等四種生存分析方法，並以 C-Index 與整合 Brier 分數
（IBS）評估模型效能，最終選擇表現最佳的隨機生存森林作為核心模型。
模型建構後，進一步應用 SHAP 與其時間依賴版本 SurvSHAP(t)，量化各
產品製程參數對異常發生風險的影響以及生存機率變化的影響與其隨時間的變
動趨勢，辨識出加速機器劣化的關鍵製程參數。在此基礎上，透過隨機生存森
林預測之生存機率門檻進行產品製程風險分類，對未來在生產製造維護策略上
可提供須優先維護觀察之產品，以降低產品在生產製造上發生異常的可能性。
結果顯示，本方法不僅能有效預測產品生產時的生存機率，亦能針對關鍵
製程參數與高風險時點提供具體解釋，協助工程師優化維護策略與製程設定。
相較於傳統僅預測是否故障的分類型預測方法，本研究所提出之方法可同時考
量風險隨時間變化的動態特性，並具備透明度與實務應用價值。

This study aims to integrate survival analysis with SHAP interpretability
techniques to investigate how different product process parameters influence the risk
of machine failure during manufacturing. The analysis utilizes both a publicly
available predictive maintenance dataset and a coating machine dataset provided by
Company A. Four survival analysis methods are compared—Cox Proportional
Hazards Model, Random Survival Forest (RSF), XGBoost Cox, and DeepSurv—
using the C-index and Integrated Brier Score (IBS) to evaluate model performance.
The Random Survival Forest, which demonstrated the best performance, is selected as
the core model.
After model construction, SHAP and its time-dependent extension SurvSHAP(t)
are applied to quantify the impact of each process parameter on failure risk and
survival probability over time, identifying key factors that accelerate machine
degradation. Based on these insights, process risk classification is performed using
survival probability thresholds predicted by RSF. This allows for the identification of
high-risk products that require prioritized monitoring and maintenance, thereby
reducing the likelihood of anomalies during production.
Results show that the proposed approach not only accurately predicts the
survival probability of products during manufacturing but also provides concrete
explanations for key parameters and high-risk time points. This supports engineers in
optimizing maintenance strategies and process settings. Compared to traditional
classification models that only predict whether failure will occur, the proposed
method captures the dynamic nature of risk over time while offering greater
transparency and practical value.

第一章 緒論...............................................................................................1
1 研究背景與動機..............................................................................................1
2 研究挑戰..........................................................................................................1
3 研究目的..........................................................................................................2
4 研究方法..........................................................................................................3
第二章 文獻探討 ......................................................................................4
1 設備壽命預測與剩餘壽命（RUL）分析方法..............................................4
2 生存分析..........................................................................................................5
2.1 生存分析方法的發展...................................................................................5
2.2 生存分析的跨領域應用：由醫療走向組織管理與智慧製造...................6
3 機器學習模型的可解釋性..............................................................................7
3.1 SurvSHAP(t).................................................................................................8
第三章 研究方法 ......................................................................................9
1 研究架構..........................................................................................................9
2 資料介紹..........................................................................................................9
2.1 AI4I 2020 Predictive Maintenance Dataset ................................................10
2.2 塗佈機設備資料.........................................................................................10
3 生存分析模型................................................................................................12
3.1 Cox 比例風險 (Cox proportional hazards model).....................................12
3.2 隨機生存森林 (Random Survival Forest).................................................13
3.3 XGBoost Cox..............................................................................................15
3.4 DeepSurv.....................................................................................................16
4 模型能力評估指標........................................................................................17
4.1 C-index........................................................................................................17
4.2 Integrated Brier Score .................................................................................17
5 模型可解釋性................................................................................................18
5.1 SHAP ..........................................................................................................18
iv
5.2 SurvSHAP(t)...............................................................................................19
第四章 實驗與結果 ................................................................................21
1 實驗環境與開發工具....................................................................................21
2 資料前處理....................................................................................................21
3 模型參數設置以及效能比較........................................................................22
3.1 Cox 比例風險 (Cox proportional hazards model).....................................22
3.2 隨機生存森林 (Random Survival Forest).................................................23
3.3 XGBoost Cox..............................................................................................23
3.4 DeepSurv.....................................................................................................24
4 製程參數對異常風險影響............................................................................25
4.1 SHAP 全局模型結果 .................................................................................26
4.2 SHAP & SurvSHAP(t)局部模型結果........................................................28
第五章 討論與結論 ................................................................................35
1 預防性維護策略討論....................................................................................35
2 結論................................................................................................................36
參考文獻...................................................................................................38
                                

Adeoye, J., Hui, L., Koohi-Moghadam, M., Tan, J. Y., Choi, S. W., & Thomson, P.
(2022). Comparison of time-to-event machine learning models in predicting
oral cavity cancer prognosis. International journal of medical
informatics, 157, 104635.
Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system.
In Proceedings of the 22nd acm sigkdd international conference on knowledge
discovery and data mining (pp. 785-794).
Cox, D. R. (1972). Regression models and life‐tables. Journal of the Royal Statistical
Society: Series B (Methodological), 34(2), 187-202.
Huang, C. G., Huang, H. Z., & Li, Y. F. (2019). A bidirectional LSTM prognostics
method under multiple operational conditions. IEEE Transactions on
Industrial Electronics, 66(11), 8792-8802.
Ishwaran, H., Kogalur, U. B., Blackstone, E. H., & Lauer, M. S. (2008). Random
survival forests.
Jin, Z., Shang, J., Zhu, Q., Ling, C., Xie, W., & Qiang, B. (2020, October). RFRSF:
Employee turnover prediction based on random forests and survival analysis.
In International Conference on Web Information Systems Engineering (pp.
503-515). Cham: Springer International Publishing.
Kaplan, E. L., & Meier, P. (1958). Nonparametric estimation from incomplete
observations. Journal of the American statistical association, 53(282), 457-
481.
Katzman, J. L., Shaham, U., Cloninger, A., Bates, J., Jiang, T., & Kluger, Y. (2018).
DeepSurv: personalized treatment recommender system using a Cox
proportional hazards deep neural network. BMC medical research
methodology, 18(1), 24.
Kraus, M., & Feuerriegel, S. (2019). Forecasting remaining useful life: Interpretable
deep learning approach via variational Bayesian inferences. Decision Support
Systems, 125, 113100.
Krzyziński, M., Spytek, M., Baniecki, H., & Biecek, P. (2023). SurvSHAP (t): timedependent explanations of machine learning survival models. KnowledgeBased Systems, 262, 110234.
Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model
predictions. Advances in neural information processing systems, 30.
Matzka, S. (2020, September). Explainable artificial intelligence for predictive
maintenance applications. In 2020 third international conference on artificial
intelligence for industries (ai4i) (pp. 69-74). IEEE.
Parii, D., Janssen, E., Tang, G., Kouzinopoulos, C., & Pietrasik, M. (2025). Predicting
the Lifespan of Industrial Printheads with Survival Analysis. arXiv preprint
arXiv:2504.07638.
Su, X., Liu, H., Tao, L., Lu, C., & Suo, M. (2021). An end-to-end framework for
remaining useful life prediction of rolling bearing based on feature preextraction mechanism and deep adaptive transformer model. Computers &
Industrial Engineering, 161, 107531.
Tobon-Mejia, D. A., Medjaher, K., Zerhouni, N., & Tripot, G. (2011, May). Hidden
Markov models for failure diagnostic and prognostic. In 2011 Prognostics and
System Health Managment Confernece (pp. 1-8). IEEE
Wang, K., Tian, J., Zheng, C., Yang, H., Ren, J., Liu, Y., ... & Zhang, Y. (2021).
Interpretable prediction of 3-year all-cause mortality in patients with heart
failure caused by coronary heart disease based on machine learning and
SHAP. Computers in biology and medicine, 137, 104813.
Wei, L. J. (1992). The accelerated failure time model: a useful alternative to the Cox
regression model in survival analysis. Statistics in medicine, 11(14‐15), 1871-
1879.

簡易檢索 / 詳目顯示

相關論文