研究生: |
吳建瑋 Chien-Wei Wu |
---|---|
論文名稱: |
基於剩餘使用壽命預測之波焊錫爐清理預警系統 A Cleaning Warning System for Wave Soldering Tin Stove Based on Remaining Useful Life Prediction |
指導教授: |
林淵翔
Yuan-Hsiang Lin |
口試委員: |
黃文正
阮聖彰 Shanq-Jang Ruan 吳晉賢 Chin-Hsien Wu |
學位類別: |
碩士 Master |
系所名稱: |
電資學院 - 電子工程系 Department of Electronic and Computer Engineering |
論文出版年: | 2019 |
畢業學年度: | 107 |
語文別: | 中文 |
論文頁數: | 156 |
中文關鍵詞: | 波焊錫爐清理 、預防性維護 、剩餘使用壽命 、健康指標 、資料融合 、自動迴歸移動平均模型 |
外文關鍵詞: | wave soldering cleaning, predictive maintenance, remaining useful life, health indicator, data fusion, autoregressive moving average model |
相關次數: | 點閱:355 下載:0 |
分享至: |
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 |
預防性維護為工業4.0時代中重要的發展項目之一,而剩餘使用壽命預測即為預防性維護方法的一種,可以有效降低設備故障所造成之損失。在電子代工廠中常見的波焊錫爐需要定時清除錫渣,以防止錫渣過多造成焊接品質下降或機台停止運轉的狀況發生。若固定時間定期清理,可能增加人力資源消耗外,或無法在焊接品質已下降的情況下,提前進行錫渣之清理。因此,若能透過預測波焊錫爐錫渣清理之剩餘使用壽命,將可降低人力資源與提升焊接品質。
本論文使用溫度、電流與高度感測器配合資料擷取器做為感測與量測裝置,進行波焊錫爐從開始運轉到泵浦馬達停止轉動時的資料收集。在感測器經過濾波去雜訊與變化量計算後,本論文使用健康指標化與感測器資料融合兩種方法將三種感測器的資料融合成一可做為評估波焊錫爐健康狀況之實際健康指標,並用實際健康指標套入自動迴歸移動平均模型進行剩餘使用壽命預測,在平均使用時間長度六小時的測試資料中,預估的平均誤差為20分鐘。
本論文已開發一套基於剩餘使用壽命預測之波焊錫爐清理預警系統,希望可以降低人力資源使用與提升波焊錫爐焊接品質。
Predictive maintenance is one of the most significant developing projects in industry 4.0. Remaining useful life prediction is one of the predictive maintenance methods, which can effectively reduce the losses caused by equipment failure. Wave soldering tin stoves commonly found in the electronic factories require regular cleaning of tin dross in prevention of motor clogging, which will cause quality decrease in soldering or cause the tin stoves to stop running. However, regular cleaning may increase the consumption of human resources, and the tin dross may not be cleaned on time while the soldering quality had become low. Therefore, if we can predict the tin dross cleaning time by using remaining useful life prediction, then we can decrease the consumption of human resources and increase the soldering quality.
We use temperature, current, and height sensors for data measuring with the data acquisition box in this thesis. Data is collected as the tin stove starts running till the motor stops running. After processing the data, we construct a health indicator and use data fusion to mix three different kinds of sensor’s data into one real health indicator, which can evaluate tin stove’s real health condition. After that, we use the real health indicator’s data and autoregressive moving average model to make the remaining useful life prediction. In the average testing time of 360 minutes, the average error of the tin stove’s cleaning prediction is 20 minutes.
In this thesis we have developed a pre-warning system of the wave soldering cleaning based on the prediction of remaining useful life to decrease the consumption of human resources and increase the soldering quality.
[1] M. Lorenz, M. Rüßmann, R. Strack, K. Lueth, and M. Bolle, "Man and Machine in Industry 4.0," Sep. 2015. [Online]. Available:https://www.bcg.com/publications/2015/technology-business-transformation-engineered-products-infrastructure-man-machine-industry-4.aspx [Accessed on 16 Dec. 2018].
[2] "Wave Soldering Troubleshooting Guide - Alpha Assembly Solutions," Oct. 2011. [Online]. Available:https://alphaassembly.com/~/media/Files/.../wave_trouble_10_06.pdf [Accessed on 21 Nov. 2018].
[3] G. A. Susto, A. Beghi, and C. D. Luca, "A Predictive Maintenance System for Epitaxy Processes Based on Filtering and Prediction Techniques," IEEE Transactions on Semiconductor Manufacturing, vol. 25, no. 4, pp. 638-649, Nov. 2012.
[4] G. A. Susto, A. Schirru, S. Pampuri, S. McLoone, and A. Beghi, "Machine Learning for Predictive Maintenance: A Multiple Classifier Approach," IEEE Transactions on Industrial Informatics, vol. 11, no. 3, pp. 812-820, Jun. 2015.
[5] M. Rigamonti, P. Baraldi, E. Zio, D. Astigarraga, and A. Galarza, "Particle Filter-Based Prognostics for an Electrolytic Capacitor Working in Variable Operating Conditions," IEEE Transactions on Power Electronics, vol. 31, no. 2, pp. 1567-1575, Feb. 2016.
[6] A. E. Mejdoubi, H. Chaoui, J. Sabor, and H. Gualous, "Remaining Useful Life Prognosis of Supercapacitors Under Temperature and Voltage Aging Conditions," IEEE Transactions on Industrial Electronics, vol. 65, no. 5, pp. 4357-4367, May 2018.
[7] V. Mathew, T. Toby, V. Singh, B. M. Rao, and M. G. Kumar, "Prediction of Remaining Useful Lifetime (RUL) of Turbofan Engine using Machine Learning," IEEE International Conference on Circuits and Systems (ICCS), pp. 306-311, Dec. 2017.
[8] F. Cheng, L. Qu, and W. Qiao, "Fault Prognosis and Remaining Useful Life Prediction of Wind Turbine Gearboxes Using Current Signal Analysis," IEEE Transactions on Sustainable Energy, vol. 9, no. 1, pp. 157-167, Jan. 2018.
[9] D. Wang, K. L. Tsui, and Q. Miao, "Prognostics and Health Management: A Review of Vibration Based Bearing and Gear Health Indicators," IEEE Access, vol. 6, pp. 665-676, Nov. 2017.
[10] X. Fang, S. Lin, X. Huang, F. Lin, Z. Yang, and S. Igarashi, "A Review of Data-Driven Prognostic for IGBT Remaining Useful Life," Chinese Journal of Electrical Engineering, vol. 4, no. 3, pp. 73-79, Sep. 2018.
[11] L. Zhang, Z. Mu and, C. Sun, "Remaining Useful Life Prediction for Lithium-Ion Batteries Based on Exponential Model and Particle Filter," IEEE Access, vol. 6, pp. 17729-17740, Mar. 2018.
[12] Y. Long, H. Luo, Y. Zhi, and X. Wang, "Remaining Useful Life Estimation of Solder joints using an ARMA Model Optimized by Genetic Algorithm," International Conference on Electronic Packaging Technology (ICEPT), pp. 1108-1111, Aug.2018.
[13] M. B. Jamshidi and N. Alibeigi, "Neuro-Fuzzy System Identification for Remaining Useful Life of Electrolytic Capacitors," International Conference on System Reliability and Safety (ICSRS), pp. 227-231, Dec. 2017.
[14] J. Xue, L. Wang, X. Wei, and S. Yang, "Remaining Useful Life Prediction of Aluminum Electrolytic Capacitors Used in Wind Turbines," International Conference Sustainable and Renewable Energy Engineering (ICSREE), pp. 121-124, May 2017.
[15] X. Ni, X. Zhang, F. Sun, J. Zhao, and J. Zhao, "An Adaptive State-Space Model for Predicting Remaining Useful Life of Planetary Gearbox," Prognostics and System Health Management Conference (PHM-Chengdu), pp. 1-6, Oct. 2016.
[16] H. Zhang, C. Maoyin, and D. Zhou, "Remaining useful life prediction for a nonlinear multi-degradation system with public noise," Journal of Systems Engineering and Electronics, vol. 29, no. 2, pp. 429-435, Apr. 2018.
[17] NDT Education, "Introduction to Nondestructive Testing," [Online]. Available: https://www.nde-ed.org/GeneralResources/IntroToNDT/Intro_to_NDT.ppt. [Accessed on 3 Jan. 2019].
[18] National Instruments, "溫度感測器概述:量測原理、種類與規格、特性概述," Jan. 2017. [Online]. Available: http://www.ni.com/white-paper/4218/zht/#toc2.[Accessed on 18 Dec. 2018].
[19] National Instrument, "Temperature Sensor Basics," National Instrument, Jun 2016. [Online]. Available:http://www.ni.com/white-paper/53184/en/?fbclid=IwAR0Bfm0FJPbjpztGU9UbOh_4gd7SQKP3rByowe2XzeI6p3-MyOveMbs8GPw#thermocouples.[Accessed on 12 Aug. 2018].
[20] G. Lee, "熱電偶的基本原理與設計要點," EE Times Taiwan 電子工程專輯網, Dec 2016. [Online]. Available:https://www.eettaiwan.com/news/article/20161222TA31-Thermocouples-Basic-principles-and-design-essentials. [Accessed on 18 Dec. 2018].
[21] NIST Technology, "Rational function curve fits of NIST ITS-90 thermocouple data produce," [Online]. Available: http://www.mosaic-industries.com/embedded-systems/_media/microcontroller-projects/temperature-measurement/thermoc
ouple/thermocouple-equations-from-nist-data.xls. [Accessed on 3 Jan. 2019].
[22] C. Okoh, R. Roy, J. Mehnen, and L. Redding, "Overview of Remaining Useful Life Prediction Techniques in Through-Life Engineering Services," Conference on Industrial Product-Service Systems (CIRP), vol. 16, pp. 158-163, 2014.
[23] "Feature Fusion and Multiple Linear Regression Analysis," [Online]. Available: http://shodhganga.inflibnet.ac.in/bitstream/10603/203183/11/11_chapter3.pdf. [Accessed on 3 Jan. 2019].
[24] MBAlib, "多元線性回歸分析預測法," [Online]. Available: https://wiki.mbalib.com/zh-tw/%E5%A4%9A%E5%85%83%E7%BA%BF%E6%80%A7%E5%9B%9E%E5%BD%92%E5%88%86%E6%9E%90%E9%A2%84%E6%B5%8B%E6%B3%95. [Accessed on 3 Jan. 2019].
[25] Math Works, "Autoregressive Model," [Online]. Available: https://www.mathworks.com/help/econ/autoregressive-model.html.[Accessed on 3 Jan. 2019].
[26] Math Works, "Moving Average Model," [Online]. Available: https://www.mathworks.com/help/econ/moving-average-model.html[Accessed on 3 Jan. 2019].
[27] Math Works, "Autoregressive Moving Average Model," MathWorks, [Online]. Available: https://www.mathworks.com/help/econ/arma-model.html.[Accessed on 3 Jan. 2019].
[28] Math Works, "ARMAX," [Online]. Available: https://www.mathworks.com/help/ident/ref/armax.html.[Accessed on 3 Jan. 2019].
[29] Analog Devies, "AD8495," [Online].Available:https://www.analog.com/en/products/ad8495.html#product-overview[Accessed on 6 Jan. 2019].
[30] Analog Device, "Precision Thermocouple Amplifiers with Cold Junction Compensation," [Online]. Available:https://www.analog.com/media/en/technical-documentation/data-sheets/ad8494_8495_8496_8497.pdf. [Accessed on 6 Jan. 2019].
[31] MICRO-EPSILON, "Eddy Current Sensor," [Online]. Available: https://www.micro-epsilon.co.uk/download/applications/app100_en-Measuring-solder-wave-height-wave-soldering-machines.pdf. [Accessed on 6 Jan. 2019].
[32] National Instrument, "NI-9215 Datasheet - National Instrument," Mar. 2016. [Online].Available:http://www.ni.com/pdf/manuals/373779a_02.pdf. [Accessed on 6 Jan. 2019].
[33] National Instrument, "NI-9246 Datasheet - National Instrument," May 2015. [Online]. Available: http://www.ni.com/pdf/manuals/376372a.pdf. [Accessed on 6 Jan. 2019].
[34] National Instruments, "Specifications NI cDAQ-9174," May 2013. [Online]. Available: http://www.ni.com/pdf/manuals/374045a.pdf. [Accessed on 6 Jan. 2019].
[35] National Instruments, "CompactDAQ," [Online]. Available:http://www.ni.com/zh-tw/shop/select/compactdaq-chassis?modelId=125698. [Accessed on 3 Jan. 2019].