Parts clustering by self-organizing map neural network in a fuzzy environment

The description of the attributes or characteristics of the individual parts in a feature-based clustering system is frequently vague, and linguistic, fuzzy number or fuzzy coding is ideally suited to represent these attributes. However, due to the vagueness of the description, the resulting fuzzy membership functions are usually very approximate. Neural network learning to improve the fuzzy representation was used in this investigation to overcome these difficulties. In particular, Kohonenʹs self-organizing map network combined with fuzzy membership functions was used to classify the different parts based on their various attributes. The network can simultaneously deal with crisp attributes, interval attributes, and fuzzy attributes. Due to the fuzzy input and fuzzy weights, a revised weight updating rule was proposed. Various approaches have been proposed to define the distance or ranking of fuzzy numbers, which is essential in order to use the Kohonen map. The overall existence measurement was used in the present investigation. To illustrate the approach, parts based on two attributes were classified and discussed.