基于投影寻踪模型和加速遗传算法的石羊河流域水资源承载力综合评价

Application of PPC Model and RAGA for Comprehensive Evaluation of Water Resource Carrying Capacity in Shiyang River Basin

针对区域水资源承载力状况,采用高维降维技术——投影寻踪分类模型(PPC),利用基于实数编码的加速遗传算法(RAGA)优化其投影方向,将多维数据指标(样本评价指标)转换到低维子空间,根据投影函数值的大小评价出样本的优劣,从而做出评价,最大限度避免了灰色关联法评判中权重矩阵取值的人为干扰,为区域水资源承载力状况评价及其它评判问题提供一条新的方法与思路。

Through applying PPC model based on RAGA in the evaluation of regional water resource carrying capacity, the authors turn multi--dimension data into low dimension space. So the optimum projection direction can stand for the best influence to the collectivity. Thus, the value of projection function can evaluate each item. The PPC model can avoid jamming of weight matrix in the method of grey relation, and obtain better result. It provides a new method and thought for comprehensive evaluation of water resource carrying capacity and other relative study.