【摘要】 通过对人工神经网络(ANN)的深入研究,尤其是在改进算法方面作了大量的尝试,设计出了一种FBP神经网络。在采集了大量的飞机发动机故障信息后,并结合专家的经验数据,提出了适用于民航飞机发动机,特别是波音767和波音747所装配的JT9D发动机和PW4000型发动机的故障诊断系统。使在不对发动机进行解体的情况下能早期检测到故障隐患。更多还原

【Abstract】 Through a deep exploration of artificial neural network, including experiments concerning algorithms-improvement in particular, a kind of ANN named fast back propagation(FBP ) is introduced. After collecting sufficient information on aero-engine breakdown, combining it with data provided by experienced specialists, a failure-diagnostic system is developed, which is especially applied to the JT9D and PW4000 engines of Boeing767 and Boeing747. This system can detect the possible failure in the first time without dismantling the engines.更多还原