【摘要】 当某次评价不达标,选取怎样的方案使系统整改后达标是评价后续决策问题。从经济角度研究模糊综合评价的后续决策问题,即如何以最少花费达到评价阈值要求。首先建立指标得分成本、单位成本及改善代价等模型。在此基础上,将各指标得分编码为一条遗传信息,应用遗传算法迭代求取既满足模糊评价得分阈值要求,又能使总改善代价最优的各指标得分。最后分析迭代过程及结果,建立指标改变先后度模型。在经济预算紧张或系统运转困难时,可用该模型确定指标改变的轻重缓急次序。本文实例经2 000次迭代使系统达标并确定了各指标的改变先后顺序。该方法切实可行,可用于灰色评价、可拓学评价以及集对分析等常规评价。更多还原

【Abstract】 If a system is not up to the standard in an evaluation,what solution should be selected to amend the system is a subsequent decision problem after evaluation. The subsequent decision for fuzzy comprehensive evaluation is studied from the perspective of economics,namely,the evaluation threshold requirements are met at the least cost. Firstly,the models of score cost,score unit cost,and improved cost are established. Based on the three models,each index score is encoded as a genetic information.The genetic algorithm is used to iteratively calculate an index score,which could meet the requirements of fuzzy evaluation score threshold with the least improved cost. Finally,the iteration process and results are analyzed,an an index modification priority model is established. When the budget is tight or the system is difficult to be operated,the model could be used to decide the priority for modifying the indexes. The system reaches a set standard and the modification sequence of the indexes through 2 000 iterative calculations The proposed method can be used for the conventional evaluation,such as gray evaluation,extenics assessment and set pair analysis.更多还原