模型分解是减小系统复杂程度、降低仿真运行代价的有效手段．当前许多定性仿真理论，由于仿真代价过高等原因而难以处理大规模系统．针对这种状况，文中对定性理论中常见的因果关系有向图形式表示的结构模型，给出一种模型分解方法，通过实例给出了具体的分解过程，并与定性理论中别的方法作了简要比较 Model decomposition is to reduce system complexity and reduce the cost of simulation and effective means. At present, many qualitative simulation theories are difficult to deal with large-scale systems because of the high simulation cost. In view of this situation, this paper gives a structural decomposition model of the causal relationship in the qualitative theory, and gives a decomposition method of the model. The specific decomposition process is given and compared with the other methods of qualitative theory A brief comparison