from the conferences organized by TANGER Ltd.
The work concerns an idea of the expert system for predicting the life of forging tools used in die forging processes, for which the knowledge representation and processing were based on Adaptive Neuro-Fuzzy Inference System (ANFIS). Using the results of extensive investigations and analysis, a knowledge base was developed for the three representative industrial hot forging processes (forging of front wheel, casing of constant velocity joint body, and fastener construction). The knowledge base contains elements of both theoretical knowledge about destructive phenomena and empirical knowledge gained from the experience of the authors and industry experts (forge employees) and also from the acquired values of selected forging parameters. The parameters, including the number of forgings, the billet and tool temperature, tool loading, contact time, path of friction and lubrication, were compiled in the form of knowledge vectors in respective tables. The task of the developed system is to quantify the amount of wear, which is a geometric loss suffered by the die cavity during successive operations of the industrial hot forging process, after entering some technological parameters as inputs for this process. It is an original approach, as, so far, the thematic literature has not provided any examples of the use of ANFIS to solve the problem faced by the system. Differences between the results obtained from the ANFIS- based system and empirical data derived from the study of worn tools are in the range of 0-10 %.
Keywords: durability of forging tool, wear, expert system, ANFIS© This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.