The retrieval method of KMS knowledge meshes by complexity analysis

Abstract

Knowledgeable manufacturing system (KMS) transforms all types of advanced manufacturing modes into corresponding knowledge meshes (KMs) and selects the best combination of KMs to satisfy enterprise requirements. Efficiently retrieving and reconfiguring KMs can reduce the complexity of new KMs gained by self-reconfiguration operations and enhance its practicability. This paper presents the method for measuring the KM complexity based on entropy and that for fuzzily classifying and retrieving for KMs based on granularity. Utilising the intrinsic information of KM, knowledge capacity function based on entropy is introduced to measure the KM complexity, and proved to be a monotone function of the number, measure, coefficient and weight of elements in KM. Properties of the KM operations are kept. Taking quality, quantity and complexity into account, the similarity function is defined. As revealed by our analysis, this function is of similarity both in the sense of matching, and in the mode of gaining KM. Then, the KMs in the KM base are fuzzily clustered. The number of classes is not fixed in advance, but can be dynamically adjusted. Each clustering centre is the best state corresponding to certain demands and has the minimum complexity degree. KM features are quantised in importance using the weight vectors. The search space is determined by centring at the clustering, which converts the problem from fine-grained space to coarse-grained space. Our tests and software package developed have proved the method to be quite effective.