故障树分析(Fault Tree Analysis,FTA)是对系统进行可靠性分析的一种有效方法。而在现在所有的故障树分析中,二元决策图(Binary Decision Diagram,BDD)又是其中最有效的方法之一。由于BDD的节点数在很大程度上依赖于输入的底事件的排列...故障树分析(Fault Tree Analysis,FTA)是对系统进行可靠性分析的一种有效方法。而在现在所有的故障树分析中,二元决策图(Binary Decision Diagram,BDD)又是其中最有效的方法之一。由于BDD的节点数在很大程度上依赖于输入的底事件的排列次序,所以从故障树到BDD的转换过程中,需要先对底事件进行排序。而如何对底事件进行有效的排序则成为一个重要且未完全解决的课题。本文提出了一种新的底事件排序法——相邻底事件优先法。其基本思想是利用故障树的相邻关系来给其赋予不同的排序优先级。该排序方法所具备的特点包括:其底事件排序过程是静态的,但在BDD的构造过程中,能动态地对已经排序的底事件进行筛选,同时它还支持在BDD的不同分支采用不同的底事件排序方法。实验证明,与现有的最优方法相比,相邻底事件优先法可有效提高75%的故障树的BDD转化效率。展开更多
Quantified constraint satisfaction problems (QCSPs) are an extension to constraint satisfaction problems (CSPs) with both universal quantifiers and existential quantifiers. In this paper we apply variable ordering...Quantified constraint satisfaction problems (QCSPs) are an extension to constraint satisfaction problems (CSPs) with both universal quantifiers and existential quantifiers. In this paper we apply variable ordering heuristics and integrate standard dependency schemes in QCSP solvers. The technique can help to decide the next variable to be assigned in QCSP solving. We also introduce a new factor into the variable ordering heuristics: a variable's dep is the number of variables depending on it. This factor represents the probability of getting more candidates for the next variable to be assigned. Experimental results show that variable ordering heuristics with standard dependency schemes and the new factor dep can improve the performance of QCSP solvers.展开更多
文摘故障树分析(Fault Tree Analysis,FTA)是对系统进行可靠性分析的一种有效方法。而在现在所有的故障树分析中,二元决策图(Binary Decision Diagram,BDD)又是其中最有效的方法之一。由于BDD的节点数在很大程度上依赖于输入的底事件的排列次序,所以从故障树到BDD的转换过程中,需要先对底事件进行排序。而如何对底事件进行有效的排序则成为一个重要且未完全解决的课题。本文提出了一种新的底事件排序法——相邻底事件优先法。其基本思想是利用故障树的相邻关系来给其赋予不同的排序优先级。该排序方法所具备的特点包括:其底事件排序过程是静态的,但在BDD的构造过程中,能动态地对已经排序的底事件进行筛选,同时它还支持在BDD的不同分支采用不同的底事件排序方法。实验证明,与现有的最优方法相比,相邻底事件优先法可有效提高75%的故障树的BDD转化效率。
基金supported in part by the National Natural Science Foundation of China under Grant No. 61070039
文摘Quantified constraint satisfaction problems (QCSPs) are an extension to constraint satisfaction problems (CSPs) with both universal quantifiers and existential quantifiers. In this paper we apply variable ordering heuristics and integrate standard dependency schemes in QCSP solvers. The technique can help to decide the next variable to be assigned in QCSP solving. We also introduce a new factor into the variable ordering heuristics: a variable's dep is the number of variables depending on it. This factor represents the probability of getting more candidates for the next variable to be assigned. Experimental results show that variable ordering heuristics with standard dependency schemes and the new factor dep can improve the performance of QCSP solvers.