USING BACK-PROPAGATION NEURAL NETWORK TO PREDICT TIME-TO-FAILURE OF AIRCRAFT COMPONENTS–A CASE STUDY ON ELECTRICAL CONTROL UNIT OF T700-GE-401 ENGINE

• Main Authors: Tung-keng Yang, 楊東耿
• Other Authors: Tian-syung Lan
• Format: Others
• Language: zh-TW
• Published: 2015
• Online Access: http://ndltd.ncl.edu.tw/handle/a6y48z

碩士 === 大同大學 === 工程管理碩士在職專班 === 103 === The attack helicopters of Taiwan Army play an extremely important role in all anti-landing and littoral assaults operation, when unexpected malfunctions of critical components during operations occurred, to aboard mission and return for further repairs will become inevitable, therefore, to establish the time-to-failure predicting system against components, also apply appropriate actions prior to failures, operational readiness rate will be enhanced and unexpected malfunctions will be effectively reduced. This study was focused on the Electrical Control Unit which installed on the T700-GE-401 engine of a random Taiwan Army attack helicopter. The Modified Delphi Method was applied when conducting initial questionnaires to collect critical influencing factors of Electrical Control Unit time-to-failure, secondary questionnaires were sent out along with establishing Likert Scale and total 7 critical factors were identified：Individual to Time Since New and ohmic resistance of Thermocouple Assembly, Hydromechanical Control Unit Linear Variable Displacement Transducer, Power Turbine Rotor Speed Sensor, Torque and Overspeed Sensor, Overspeed and Drain Valve Solenoid and Hydromechanical Control Unit Torque Motor, the abovementioned patterns are key influential factors of post-examine time to failure of Electronic Control Unit. Testing data of Electronic Control Unit between 2011 to 2013 were collected, then loaded with Back-Propagation Neural Network software Alyuda NeuroIntelligence to test the interactions between input and output, to establish the prediction mode and to assess with the parameters and conditions generated：1 hidden layer with 12 neurons, learning rate at 0.2 and iteration at 2,000, to effectively predict time-to-failure of Electronic Control Unit using Back-Propagation Neural Network. The result of the study revealed that the Correlation and R-squared reached 0.999 and 0.997 respectively with Alyuda NeuroIntelligence educational training applied, the accuracy of prediction was 92.45% and the high precision accuracy proves its value of implementation, the study result also shown that Back-Propagation Neural Network can be an standardization of predicting time-to-failure against aircraft critical components. With the predicting capability of Back-Propagation Neural Network being applied, the preventative maintenance management for Taiwan Army can be optimized; also introducing this method to other components of domestic military and civilian aircrafts is also beneficial to the operational readiness of components and parts, and lower the aviation safety risks caused by unpredicted malfunctions.