论文部分内容阅读
为实现ADS-B系统运行可靠性的综合评价,提出了一种基于T-S模糊神经网络的方法。以平均首次故障时间、平均故障间隔时间、平均维修时间、平均可用度和维修时间率5项可靠性评价指标作为输入向量。利用T-S模糊系统构建可靠性综合评价的非线性映射关系,经神经网络的自适应训练,调整模糊规则和隶属度函数,建立ADS-B系统运行可靠性的综合评价模型。实验仿真与应用情况表明,该方法可行、有效,并具有较高的计算稳定性、精确性和良好的泛化能力,且评价结果客观、准确可靠,可作为提高ADS-B系统运行可靠性的决策依据。
In order to achieve a comprehensive evaluation of the operational reliability of ADS-B system, a method based on T-S fuzzy neural network is proposed. Five reliability evaluation indexes such as mean time to first failure, mean time between failures, average maintenance time, average availability and maintenance time rate are taken as input vectors. The T-S fuzzy system is used to construct the non-linear mapping relationship of reliability comprehensive evaluation. The neural network adaptive training is used to adjust the fuzzy rules and membership functions to establish the comprehensive evaluation model of ADS-B system reliability. The experimental simulation and application shows that this method is feasible and effective, and has high computational stability, accuracy and good generalization ability. The evaluation results are objective, accurate and reliable, and can be used as an effective method to improve the reliability of ADS-B system Decision-making basis.