基于置信规则库的应急方案调整方法

Emergency Alternative Adaptation Method based on Belief Rule-base

针对运用案例推理生成应急方案的问题,提出了一种基于置信规则库的方案调整方法.依据案例检索方法得到与目标案例最相似的历史案例,计算案例库中其他案例与最相似历史案例的问题差值,并转换为评价等级置信度形式;再利用历史案例信息及学习模型确定案例规则库的参数.在此基础上,将目标案例与最相似案例的问题差值转换为评价等级置信度形式,通过置信规则库的推理规则得到目标案例的方案.最后,通过一个环境突发事件的救援算例来说明该方法的可行性和有效性.

We propose an alternative adaptation method based on belief rule-base to solve the problem of applying the case-based reasoning to generate the emergency alternative. First,the most similar historical case with the target case is obtained according to the retrieval method,after which the problem difference values between the historical cases and the most similar case are computed. Second,the problem difference values are transformed into the belief degree form of evaluation grade. Next,the information of historical cases and the learning model are then used to determine the parameter of the belief rule-base. Furthermore,the problem value difference between the target case and the most similar case is transformed into the belief degree form of evaluation grade. On the basis of this finding,the alternative of the target case is gained through the inference rules of the belief rule-base. Finally,an illustrative example of environmental emergency rescue is provided to demonstrate the feasibility and validity of the proposed method.