错误评价及其消错优化研究

现实中决策者往往希望将评价对象的特征值与期望值之间的偏差控制在可接受范围之内,而且偏差越小越好.基于消错学对错误的界定,利用错误函数对评价对象的特征指标值与评价标准之间的偏差进行了度量,并遵循"区分主次、明确底线、综合集成"的思路,通过建立消错规划模型实施消错优化,从而在保证各特征指标不突破临界错误值的情况下,做到评价对象的整体错误值最小化.最后通过算例分析,演示了消错优化的过程,验证了消错优化模型的合理性和可操作性.

Error Evaluation and Optimization of Error-eliminating

In reality,decision makers often hope that the deviations between the actual values and the expected values of indexes describing the characteristics of an evaluation object can be controlled within an acceptable range,and the deviations as small as possible.Based on the error definition of the theory of error-eliminating,the deviations between the actual values of indexes and their evaluation criterials are measured by use of different error functions,and then according to the basic thoughts of distinguishing between primary and secondary factors,clearing bottom lines of each index and comprehensive integration,a programming model is established to optimize error-eliminating which can not only ensure the error of every index not to exceed the threshold error value but also realize the minimization of the overall error.Finally,a numerical example is used to demonstrate the optimization process of error-eliminating,and verifies the model is reasonable and practical.