Proceedings of the
9th International Conference of Asian Society for Precision Engineering and Nanotechnology (ASPEN2022)
15 – 18 November 2022, Singapore
doi:10.3850/978-981-18-6021-8_OR-08-0271
Development of artificial intelligence for assessing microprocess plans and metadata models based on ISO 14649 using the Unified HMI platform
1Department of System Engineering, Kyung Hee University, 1732 Deokyeong-daero, Giheung-gu, Yongin-si, Gyeonggi-do, Korea
2Digital Transformation R&D Department, Korea Institute of Industrial Technology, 143 Hanggaulro, Sangrok-gu, Ansan-si, Gyeonggi-do, Korea
ABSTRACT
The primary element raising the competitiveness of the manufacturing systems is the machine tool industry, which is the backbone of the industrial sector. To compete in a global competitive society, it is necessary to the smart control system covering with the digital thread from machine control until process planning and data analysis based on the Cyber-Physical System. To implement advanced, or smart, features, an open platform of machine tools that can incorporate with intelligent functions such as data integration, intelligent data processing, and anomaly detection. This paper, based on the unified platform, implements a neutral metadata model required for artificial intelligence data analysis via ISO 14649, as well as an artificial intelligence algorithm that automatically identifies process information-NC data by integrating real-time data of numerical controller and sensor data. The intelligent data processing provides automated data classification and data compressing using deep neural network. Based on the actual processing situation, a metadata model was built from the CAM data, and the processing status, process type, and sensor profile were predicted by applying it to the actual processing real-time data. Chattering detection was implemented through the proposed platform as the proof-of-concept.
Keywords: Unified HMI Platform, STEP-NC, CNC
1Department of System Engineering, Kyung Hee University, 1732 Deokyeong-daero, Giheung-gu, Yongin-si, Gyeonggi-do, Korea
2Digital Transformation R&D Department, Korea Institute of Industrial Technology, 143 Hanggaulro, Sangrok-gu, Ansan-si, Gyeonggi-do, Korea
ABSTRACT
The primary element raising the competitiveness of the manufacturing systems is the machine tool industry, which is the backbone of the industrial sector. To compete in a global competitive society, it is necessary to the smart control system covering with the digital thread from machine control until process planning and data analysis based on the Cyber-Physical System. To implement advanced, or smart, features, an open platform of machine tools that can incorporate with intelligent functions such as data integration, intelligent data processing, and anomaly detection. This paper, based on the unified platform, implements a neutral metadata model required for artificial intelligence data analysis via ISO 14649, as well as an artificial intelligence algorithm that automatically identifies process information-NC data by integrating real-time data of numerical controller and sensor data. The intelligent data processing provides automated data classification and data compressing using deep neural network. Based on the actual processing situation, a metadata model was built from the CAM data, and the processing status, process type, and sensor profile were predicted by applying it to the actual processing real-time data. Chattering detection was implemented through the proposed platform as the proof-of-concept.
Keywords: Unified HMI Platform, STEP-NC, CNC
