A Reevaluable Property Lattice-Based Knowledge Representation for Proposing and Assessing Computational Tools in Manufacturing

This study explores a learning knowledge representation, using an iteratively reevaluated lattice of equivalence-classified properties. The proposed methodology is based on the evaluation feedback between the maximal and minimal elements of the compatibility lattice. The simplified example shows how the expert evaluations of conventional and advanced Artificial Intelligence/Machine Learning (AI/ML) computational tools contribute to generating novel solutions for manufacturing industries. The knowledge base is initialized with heuristically established equivalence classes and pairwise compatibility relations between classified properties. The learning process begins with a heuristically determined, initially evaluated subset of maximal elements (complete combinations), followed by the implementation of a theoretically established iterative learning algorithm, driven by evaluation feedback. Utilizing the normalized real-valued assessments of the complete combinations, the knowledge base undergoes reevaluation, leading to uncertain assessments of the binary compatibility relations. This evolving knowledge base then facilitates the algorithmic generation of new, tendentiously more effective complete combinations. Findings indicate that through these iterative learning steps, the uncertainty due to ‘lack of knowledge’ significantly decreases, while the uncertainty associated with accumulated knowledge increases. The overall summarized uncertainty initially reaches a minimum before gradually rising again. Further analysis of the knowledge base after several learning iterations reveals the contribution of individual binary relations to the valuation of newly proposed combinations, as well as contains lessons for the optional refinement of the initial compatibility lattice.