臺灣博碩士論文加值系統

近幾年政府正在推動工業4.0，而工業4.0講的就是智慧化工廠，智慧化工廠其中最重要的一點就是預測性維修，本研究提供了一個預測性維修(包含狀態監測、故障診斷、狀態預測和維修決策)建立的方法與流程，此預測性維修結合了Jiang et al. (2015) 所提到Maintenance Priority Number(MPN)的概念與支持向量回歸(Support Vector Regression)，並在最後運用 Van Horenbeek and Pintelon (2013) 所提到的衰退模型進行模擬，模擬在相同情況與時間下使用Jiang et al. (2015)的預防性維修以及本研究的預測性維修分別造成系統多少停機次數、維修次數、維修成本，並將兩結果進行比較；結果發現在模擬案例一中預測性維修的維修總成本比預防性維修的維修總成本平均少了26.7%，預測性維修在停機次數上低於預防性維修，在維修次數上兩者無太大差距；在模擬案例二中預測性維修在元件壽命改變的狀況下表現出良好的資料即時更新能力，在停機次數上少了預防性維修8次。

Government of Taiwan is promoting Industry 4.0 as its new industrial policy in recent years, which is aiming at the construction of Smart Factory. Predictive maintenance is one of the most crucial elements of Smart Factory. This study proposes a methodology and a procedure for predictive maintenance which includes Condition Monitoring, Fault Diagnostics, Prognostic Condition and Maintenance Decision-Making. This method is a combination of Support Vector Regression and the concept of Maintenance Priority Number (MPN) referred by Jiang et al. (2015). In the last part of this study, we simulate the practice of two methods of preventive maintenance, the preventive maintenance of Jiang et al. (2015) and the predictive maintenance of this study, with Degradation Modeling (Van Horenbeek and Pintelon,2013), and make a comparison of their results including the number of downtime, the number of maintenances and maintenance costs. In case one, we found that the total cost of maintenance of the predictive maintenance is 26.7% less than that of maintenance of the preventive maintenance, and that the number of downtime of predictive maintenance is fewer than the preventive maintenance. There was no significant difference in the number of maintenances. In case two, the predictive maintenance demonstrates its strong ability of data updating in the situation that the life of the component is changing. The number of downtime of the predictive maintenance is eight times fewer than that of the preventive maintenance.

摘要 I
ABSTRACT II
ACKNOWLEDGEMENT III
目錄 IV
圖目錄 VI
表目錄 VIII
第一章 緒論 1
1.1研究動機 1
1.2研究目的 2
1.3研究範圍與限制 2
1.4研究流程 2
第二章 文獻探討 4
2.1維修種類 4
2.1.1修復性維修(Corrective Maintenance) 4
2.1.2預防性維修(Preventive Maintenance) 5
2.1.3預測性維修(Predictive Maintenance) 5
2.2慣性導航系統(INERTIAL NAVIGATION SYSTEM)案例 8
2.3支持向量回歸(SUPPORT VECTOR REGRESSION) 17
第三章 研究方法 20
3.1預防性維修建立 20
3.2預測性維修建立 29
3.3資料模擬 37
第四章 案例分析 41
4.1模擬案例一 42
4.2模擬案例二 50
第五章 結論 52
5.1結論 52
5.2未來研究方向 52
參考文獻 53
附錄 57
I. 模擬衰退資料與預防性維修程式碼 57
II. 模擬衰退資料與預測性維修程式碼 67

Alaswad S., Y. Xiang, “A review on condition-based maintenance optimization models for stochastically deteriorating system,” Reliability Engineering & System Safety, 157, 54-63 (2017).
Adriaan V.H., P. Liliane, “A dynamic predictive maintenance policy for complex multi-component systems,” Reliability Engineering & System Safety, 120, 39-50 (2013).
Chalabi N., M. Dahane, B. Beldjilali, A. Neki, “Optimisation of preventive maintenance grouping strategy for multi-component series systems: Particle swarm based approach,” Computers & Industrial Engineering, 102, 440-451 (2016).
Deloux E., B. Castanier, C. Bérenguer, “Predictive maintenance policy for a gradually deteriorating system subject to stress,” Reliability Engineering & System Safety, 94 , 418–31 (2009).
Hu J., L. Zhang, W. Liang, “Opportunistic predictive maintenance for complex multi-component systems based on DBN-HAZOP model,” Process Safety and Environmental Protection, 90, 376–88 (2012).
Hsieh Y.S., F.T. Cheng, H.C. Huang, C.R. Wang, S.C. Wang, H.C. Yang, “VM-based baseline predictive maintenance scheme,” IEEE Transactions on Semiconductor Manufacturing, 26, 132–43 (2013).
Fumeo E., L. Oneto, D. Anguita, “Condition based maintenance in railway transportation systems based on big data streaming analysis,” Procedia Computer Science, 53, 437-446 (2015).

Faria H.D., J.G.S. Costa, J.L.M. Olivas, “A review of monitoring methods for predictive maintenance of electric power transformers based on dissolved gas analysis,” Renewable and Sustainable EnergyAs, 46, 201–209 (2015).
Gustavsson E., M. Patriksson, A.B. Strmberg, A. Wojciechowski, M. Önnheim, “Preventive maintenance scheduling of multi-component systems with interval costs,” Computers & Industrial Engineering, 76, 390–400 (2014).
Huynh K.T., A. Barros, C. Bérenguer, I.T. Castro, “A periodic inspection and replacement policy for systems subject to competing failure modes due to degradation and traumatic events,” Reliability Engineering & System Safety, 96, 497–508 (2011).
Jiang X, F. Duan, H. Tian, X. Wei, “Optimization of reliability centered predictive maintenance scheme for inertial navigation system,” Reliability Engineering & System Safety, 140, 208–17 (2015).
Lin J., J. Pulido, M. Asplund, “Reliability analysis for preventive maintenance based on classical and Bayesian semi-parametric degradation approaches using locomotive wheel-sets as a case study,” Reliability Engineering & System Safety, 134, 143-156 (2015).
Michele C., Z. Enrico, “Risk sensitive particle filtering in support of predictive maintenance,” Chemical Engineering Transactions, 33, 307–12 (2013).
Moura M. d. C., E. Zio, I. D. Lins, E. Droguett, “Failure and reliability prediction by support vector machines regression of time series data,” Reliability Engineering & System Safety, 96, 1527-1534 (2011).
Neves M.L., L.P. Santiago, C.C. Maia, “A condition-based maintenance policy and input parameters estimation for deteriorating systems under periodic inspection,” Computers & Industrial Engineering, 61, 503–11 (2011).
Potočnik P., E. Govekar, “Semi-supervised vibration-based classification and condition monitoring of compressors,” Mechanical Systems and Signal Processing, 93, 51-65 (2017).
Stephens M. A., “EDF Statistics for goodness of fit and some comparisons,” American Statistical Association, 69, 730-737 (1974).
Stephens M. A., “Asymptotic results for goodness-of-fit statistics with unknown parameters,” Annals of Statistics, 4, 357-369 (1976).
Stephens M. A., “Goodness of Fit for the Extreme Value Distribution,” Biometrika, 64, 583-588 (1977).
Stephens M. A., “Tests of Fit for the Logistic Distribution Based on the Empirical Distribution Function,” Biometrika, 66, 591-595 (1979).
Shafiee M. and M. Finkelstein, “An optimal age-based group maintenance policy for multi-unit degrading systems,” Reliability Engineering & System Safety, 134, 230-238 (2015).
Sheikhalishahi M., A. Azadeh, and L. Pintelon, “Dynamic maintenance planning approach by considering grouping strategy and human factors,” Process Safety and Environmental Protection, 107, 289-298 (2017).
Scheibelhofer P., D. Gleispach, G. Hayderer, E. Stadlober, “A methodology for Predictive Maintenance in Semiconductor Manufacturing,” Austrlan Journal of Statistic, 41, 161–173 (2012).
Tinga T., “Predictive maintenance of military systems based on physical failure models,” Chemical Engineering Transactions, 33, 295–300 (2013).
Tian Z.G., B.R. Wu, M.Y. Chen, “Condition-based maintenance optimization considering improving prediction accuracy,” Journal of the Operational Research Society, 65, 1412–22 (2014).
Van Horenbeek A., Pintelon L., “A dynamic predictive maintenance policy for complex multi-component systems,” Reliability Engineering & System Safety, 120, 39–50 (2013).
Wei Z., T. Tao,D. ZhuoShu, and E. Zio, “A dynamic particle filter-support vector regression method for reliability prediction,” Reliability Engineering & System Safety, 119, 109-116 (2013).
Yang Y., Y. Liao, G. Meng, and J. Lee, “A hybrid feature selection scheme for unsupervised learning and its application in bearing fault diagnosis,” Expert Systems with Applications, 38, 11311-11320 (2011).