基于非线性测度函数的改进属性识别模型在水质综合评价中的应用

Application of improved attribute recognition model based on non-linear measure function to comprehensive assessment on river water quality

线性测度函数的传统属性识别模型,对水质评价标准随机抽样的评价结果存在较大误差。为增加其对实测样本评价的可信度,提出了基于非线性属性测度函数的改进属性识别模型。均匀随机和正交设计两种抽样的评价试验显示,改进属性识别模型评价结果准确度明显好于传统模型,说明指标的属性测度函数对属性识别模型的综合评价结果有重要影响。太原市地下水水质的综合评价实例说明,由于非线性测度函数比线性测度函数能更好地描述评价指标的实际隶属度,故改进的属性识别模型具有更高的评价可信度,在水质综合评价中具有更广泛的适用性。

Misjudgements occurred when the general attribute recognition model based on linear measure function（LMF-ARM） is used to make assessment on the virtual samples drawn randomly from the criterion of water quality. This leads to the downward reliability of the result while LMF-ARM is applied to the actual water samples. Therefore, the improved attribute recognition model based on non-linear measure function （NLMF-ARM） is proposed here. The results given by the later model are much better than the former, according to the tests of the virtual samples selected by both the random method and the orthogonal design. It indicates that the measure function can play an important role during the process of utilizing attribute recognition model to make comprehensive assessment. So the conclusion can be draw from the case on a city groundwater quality assessment, that non-linear measure function, compared with the linear, has better abilities to describe the natural attribute degree of assessment indexes. Because of the higher reliability than LMF-ARM, NLMF-ARM has wider applicability in the comprehensive assessment of water quality.