The collapse of surrounding rock mass is affected by many factors
and the relationship between different collapse types has no distinct boundary
so the problem of recognition of collapse type is fuzzy
nonlinear
small samples and high dimensions. Support vector machine is a new machine learning technology
and there are a lot of successful application in the field of pattern recognition. This paper presents a new method based on support vector machine
and the complicated nonlinear relationship between type of collapse and its affected actors is presented well. The application of true example shows this method is feasible and precise.