基于数据挖掘的非能动系统功能可靠性评估方法研究

针对多维不确定性参数及小概率的功能失效问题,提出一种基于数据挖掘的功能可靠性分析方法。该方法将自举抽样响应面拟合模型及最优化线抽样技术相结合,进而高效获得非能动系统的功能可靠性。以西安脉冲堆为例,结合中破口失水事故,考虑输入参数及模型的不确定性,对其进行功能可靠性评价。结果表明,该自举抽样响应面模型具有较高的拟合度;最优化线性抽样技术具有很高的计算效率,同时又能保证很好的计算精度。因此,本研究的评价方法对非能动系统隐式非线性的功能失效分析具有很强的适应性。

Research of Functional Reliability Evaluation Method for Passive Systems Based on Data Mining Technology

In order to solve the problem of multi-dimensional uncertainty parameters and small probability of functional failure, an innovative functional reliability estimation method named Data Mining Technology was presented. In the presented method, with the combination of the bootstrap response surface model and optimization line sampling design, the functional failure probability can be evaluated with high efficiency. This method was applied in the natural circulation cooling in Xi’an Pulsed Reactor (XAPR). Combined with Medium Break Loss of Coolant Accident (MLOCA), the uncertainties related to the input parameters and the model were considered. And then the probability of functional failure was estimated with the presented method. The numerical results show that the bootstrap response surface model has a high degree of fitting, and the optimized line sampling technique has a high computational efficiency and an excellent computational accuracy. In addition, the evaluation method in this paper has strong adaptability to the implicit nonlinear functional failure analysis of the passive systems.