A fuzzy set is fully defined by its membership functions. For most control applications, the sets that have to be defined are easily identifiable. However, for other applications they have to be determined by knowledge acquisition from an expert or group of experts. Once the fuzzy sets have been established, one must consider their associated membership functions. How best to determine the membership function is the first question that has to be tackled. In this paper, a new method presented to evaluate the membership function by using experimental data