CAJ | 학술논문

在进行非Markov系统的可靠性仿真时,为获得准确的状态转移时间抽样,提出剩余分布的近似抽样(ASRD)方法,利用多个均匀分布拟合一般形式的剩余分布,通过拟合参数d调整抽样精度和抽样效率.在此基础上,提出基于强制转移(FT)策略的ASRD(FT-ASRD)仿真方法.多个算例结果表明,当5≤d≤10时,FT-ASRD相对于常规仿真方法具有更高的效率,而且仿真结果的相对误差较小.
재진행비Markov계통적가고성방진시,위획득준학적상태전이시간추양,제출잉여분포적근사추양(ASRD)방법,이용다개균균분포의합일반형식적잉여분포,통과의합삼수d조정추양정도화추양효솔.재차기출상,제출기우강제전이(FT)책략적ASRD(FT-ASRD)방진방법.다개산례결과표명,당5≤d≤10시,FT-ASRD상대우상규방진방법구유경고적효솔,이차방진결과적상대오차교소.
In order to sample precisely the state transition time when simulating non-Markovian system, a new sampling method named Approximate Sampling for Residual Distribution(ASRD) method is put forward, in which several uniform distributions are used to approach general residual life distributions. The approach-coefficient d is used to adjust sampling precision and efficiency. Another method named Forced Transitions(FT) based ASRD(FT-ASRD) simulation method is brought forward to simulate high-reliable non-Markovian systems. FT-ASRD uses FT strategy to get the unreliability parameter. Several examples show that, when 5≤d≤10, FT-ASRD is more efficient and has lower relative error compared with crude simulation methods.