To converse membership degrees from indexes to objective is the core step in the safety reliability evaluation of mine ventilation system based on information fusion technology; but the existing converse algorithms of membership degrees are questionable because redundant data of membership degrees of indexes, which are useless to objective classification, are involved in calculation of membership degrees of the objective. In fact, to converse membership degrees is information fusion technology, the key steps of which is to find the information in index membership about object classification. For this case, distinguishable weight, effective value and comparable value are designed through the analysis of contribution of index to sample classification, which eliminates the redundant data and extract the effective values. In this way, the safety reliability model of mine ventilation system based on information fusion technology, was proposed.