Abstract:

The random variable fuzzy recognition model was established for the coexistence of randomness and fuzziness in cleaner production assessment. A random term obeying normal distribution was introduced to the variable fuzzy recognition model, so the randomness and fuzziness could be studied simultaneously. Four random fuzzy recognition sub-models were generated by controlling the distance parameter p and the optimization parameter α, and then according to the 3σ principle of normal distribution, after choosing a reasonable confidence, the grade was identified by the confidence interval of grade feature value. Compared with the scoring model of centesimal system, this model could cut down the effect of subjective preference on assessment results, and could improve the maneuverability and accuracy in evaluation process. The experimental results showed that the random variable fuzzy recognition model could evaluate the cleaner production level accurately, which could also provide a reference for cleaner production assessment.

Key words: random, fuzzy recognition, grade feature value, confidence interval, cleaner production assessment