模糊层次分析法和人工神经网络模型在电梯风险评估中的应用  

The application of fuzzy analytic hierarchy process and artificial neural network in elevator risk assessment

作　　者：张广明[1] 邱春玲[1] 钱夏夷[2] 黄水霞[1] 

机构地区：[1]南京工业大学自动化与电气工程学院,江苏南京210009 [2]江苏省特种设备安全监督检验研究院,江苏南京210009

出　　处：《控制理论与应用》2009年第8期931-933,共3页Control Theory & Applications

基　　金：江苏省社会发展计划项目(BS2007083)

摘　　要：针对特种设备风险评估模型中的人工神经网络(ANN)技术一般采用定量加权平均法.由于其权值是以专家经验为依据,导致评估所需时间太长.针对这个缺点,建议将模糊层次分析法(F-AHP)和ANN相结合,用于对电梯的风险评估中.实验证明用此方法进行评估所用的时间比ANN方法要少,且评估的准确性没有降低.The method of weighted averaging is commonly special equipment. Because the selection of weights depends employed in the ANN model for the risk- assessment of on the expert experience, the process of the assessment generally takes a long time to complete. To deal with this problem, we propose a new risk-assessment model based on F- AHP and ANN. This model is applied to the risk-assessment of elevators. Results show that the assessment time is shorter and the accuracy is not lower, in comparison with that from the ANN model.

关 键 词：模糊层次分析法 人工神经网络 风险评估 电梯 

分 类 号：TU857[建筑科学] TP183[自动化与计算机技术—控制理论与控制工程]