Moment-independence global sensitivity analysis for the system with fuzzy failure state and its Kriging method

For the system with the fuzzy failure state, the effects of the input random variables and the fuzzy failure state on the fuzzy probability of failure for the structural system are studied, and the moment-independence global sensitivity analysis（GSA） model is proposed to quantitatively measure these effects. According to the fuzzy random theory, the fuzzy failure state is transformed into an equivalent new random variable for the system, and the complementary function of the membership function of the fuzzy failure state is defined as the cumulative distribution function（CDF） of the new random variable. After introducing the new random variable, the equivalent performance function of the original problem is built. The difference between the unconditional fuzzy probability of failure and conditional fuzzy probability of failure is defined as the moment-independent GSA index. In order to solve the proposed GSA index efficiently, the Kriging-based algorithm is developed to estimate the defined moment-independence GSA index. Two engineering examples are employed to verify the feasibility and rationality of the presented GSA model, and the advantages of the developed Kriging method are also illustrated.

An Evolution Strategy for the Induction of Fuzzy Finite-State Automata

This paper presents an evolution strategy to induce fuzzy finite-state automata from examples of fuzzy languages. The coding, fitness function of a generated automaton and corresponding mutation operators are given respectively. The application example given at last shows the effectiveness of the proposed evolution strategy for automata induction.

Minimization of Fuzzy Finite Generalized Automata

Some concepts in Fuzzy Generalized Automata （FGA） are established. Then an important new algorithm which would calculate the minimal FGA is given. The new algorithm is composed of two parts： the first is called E-reduction which contracts equivalent states, and the second is called RE-reduction which removes retrievable states. Finally an example is given to illuminate the algorithm of minimization.

Achieving of Fuzzy Automata for Processing Fuzzy Logic

At present, there has been an increasing interest in neuron-fuzzy systems, the combinations of artificial neural networks with fuzzy logic. In this paper, a definition of fuzzy finite state automata （FFA） is introduced and fuzzy knowledge equivalence representations between neural networks, fuzzy systems and models of automata are discussed. Once the network has been trained, we develop a method to extract a representation of the FFA encoded in the recurrent neural network that recognizes the training rules.

基于灰色模糊综合评判的高压断路器状态评估

针对高压断路器状态评估因素具有模糊性和灰色性的特点,将灰色模糊理论应用到高压断路器的状态评估中。基于试点工程,建立考虑高压断路器运行机理的递阶层次评估模型;采用层次分析法计算各层次评估因素权重集的模部,结合信息充裕程度及专家经验,确定相应评估因素权重集的灰部;综合定性分析与定量分析,以隶属度描述评估因素与状态等级间的模糊关系,并引入点灰度描述模糊关系的不可信程度,建立灰色模糊判别矩阵,进而对高压断路器运行状态进行综合评估。实际算例表明,所提模型能够客观有效地评估高压断路器的状态。