An Expert System for Hot Forging Process Monitoring and Guidance

Date

2025-3

Author

Uluyurt, Aslı Gülbike

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

69
views

72
downloads

Cite This

Increasing productivity of forging companies is critical for their competitiveness. Digital Transformation technologies provide opportunity for the forging companies to increase productivity and quality by reducing defective parts and increasing equipment life. In this Ph.D. thesis study, a novel smart forging process software, which is an expert software system, has been developed and named as “SmartForge”. SmartForge monitors by recording sensors data in real time during forging production in the shopfloor for process parameters, evaluates them, diagnoses the out of limits cases, and provides guidance. According to evaluation, warning messages are sent to the related personnel and SmartForge generates reports after completion of the production of the related production lot. Reports help them for solving problems encountered during the mass production and/or prevent from manufacturing of defective forging part, damage of the forging dies and damage of forging press, etc. SmartForge has flexibility to be customized for any hot forging company. In this study, the images captured by preparing different setups in forging shopfloor, have also been analyzed in forging industry and one of the applications has been integrated to SmartForge. SmartForge has been successfully tested both by the real time data in real forging production environment, and by synthetic data. Since it is not possible to observe the out-of-limit cases for all the process parameters in forging companies, synthetic sensors data has been generated to test the capabilities of SmartForge. Use of SmartForge provides positive impact on sustainability and decrease in cost.

Subject Keywords

Hot Forging, Digital Transformation, Artificial Intelligence, Expert Software System, Image Processing

URI

https://hdl.handle.net/11511/114008

Collections

Graduate School of Natural and Applied Sciences, Thesis