自動變速箱油壓控制系統之參數辨識與故障診斷之研究

Study on Parameters Identification and Fault Diagnosis of Hydraulic Control Systems for Automatic Transmissions

戴主修(Chu-Hsiu Tai)

指導教授 ： 鄒忠全

崑山科技大學/工程學院/機械工程研究所/碩士(2004年)

https://doi.org/10.6828/KSU.2004.00002

摘要

汽車自動變速箱之油壓控制系統構造精密又複雜，發生故障時，有時會呈現模糊性、間歇性和相關聯性，故很難用單一的判斷方式將故障很明確分門別類。過去從事故障診斷時，一般皆是靠專家們的豐富經驗與「錯誤嘗試法」借助試探性拆卸來診斷油壓控制系統故障，浪費許多寶貴工時、材料和金錢。
本文依據先前所建立的油壓控制系統的數學模式，使用MATLAB模擬程式，配合實驗設計法(Experimental Design Method)中之反應曲面法(Response Surface Methodology) 及多目標最佳值搜尋，調整參數使模擬結果和實際實驗之結果趨勢吻合，且經過電腦模擬與實驗驗證後，只需修改參數即可應用在不同的自動變速箱之故障診斷，可節省釵h時間。並使用油壓控制系統之模擬程式產生故障樣本，提供倒傳遞類神經網路之故障診斷程式學習，然後進行自動變速箱的故障診斷模擬。

關鍵字

故障診斷 ； 參數辨識 ； 類神經倒傳遞網路 ； 自動變速箱

並列摘要

Due to its sophisticated and complex construction, it is hard to diagnose the failure of the hydraulic control systems of the automatic transmissions for automotives. In the past, experts diagnose the AT faults counting on accumulated experiences and try-and-error methods. It wastes working hours, materials and money.
Applying the Model-Based Diagnostics, this paper would develop a mathematic model of the hydraulic control system of AT. The parameters of this model will be obtained by experiments on the test rig in Vehicle Control Lab. The advantages of Model-Based approach are timesaving. By deriving the mathematic model, running computer simulation, and validating by experiments, this Model-Based Diagnostics approach would make easy adjustments with new parameters for different AT. At the same time, the Back-Propagation method of Neural Network will be used to diagnose the faults occurred on the hydraulic control system of AT.

並列關鍵字

Back-Propagation of Neural Network ； Fault Diagnosis ； Automatic Transmission ； Parameters Identification

參考文獻

[28]羅華強，類神經網路-MATLAB的應用，清蔚科技股份有限公司，2001初版。

[1]K. Usuki, K. Fujita, and K. Hatta, “ The INVESINVECS-II Electronically Controlled Automatic Transaxles for FWD Passenger Cars, ” SAE Paper No.960429, 1996, pp.87-99.

[2]Herbert E . Merritt , Hydraulic Control Systems, John Wiley & Sons, Inc., New York, 1967.

[3]Q. Zheng, K. Srinivasan, and G. Rizzoni, “ Dynamic Modeling and Characterization of Transmission Response for Controller Design , ” SAE Paper No.981094, 1998, pp.207-217.

[4]B. H. Cho, G. H. Jung , J. W. Hur and K. l. Lee, “ Modeling of Proportional Control Solenoid Valve for Automatic Transmission Using System Identification Theory, ” SAE Paper No.1999-01-1061, 1999, pp.291-297.