The present work proposes a holonic-based mechanism for self-learning factories based on a hybrid learning approach. The self-learning factory is a manufacturing system that gains predictive capability by machine self-learning, and thus automatically anticipates the performance results during the process planning phase through learning from past experience. The system mechanism, including a modeling method, architecture, and operational procedure, is structured to agentize machines and manufacturing objects under the paradigm of Holonic Manufacturing Systems. This mechanism allows machines and manufacturing objects to acquire their data and model interconnection and to perform model-driven autonomous and collaborative behaviors. The hybrid learning approach is designed to obtain predictive modeling ability in both data-existent and even data-absent environments via accommodating machine learning (which extracts knowledge from data) and transfer learning (which extracts knowledge from existing knowledge). The present work also implements a prototype system to demonstrate automatic predictive modeling and autonomous process planning for energy reduction in milling processes. The prototype generates energy-predictive models via hybrid learning and seeks the minimum energy-using machine tool through the contract net protocol combined with energy prediction. As a result, the prototype could achieve a reduction of 9.70% with respect to energy consumption as compared with the maximum energy-using machine tool.
Abstract:In the metal cutting industry, power consumption is an important metric in the analysis of energy efficiency since it relates to energy consumption of machine tools. Much of the research has developed predictive models that correlate process planning decisions with power consumption through theoretical and/or experimental modeling approaches. These models are created by using the theory of metal cutting mechanics and Design of Experiments. However, these models may lose their ability to predict results correctly outside the required assumptions and limited experimental conditions. Thus, they cannot accurately reflect a diversity of machining configurations; i.e., selections of machine tool, workpiece, cutting tool, coolant option, and machining operation for producing a part, which a machining shop has operated. This paper proposes a predictive modeling approach based on historical data collected from machine tool operations. The proposed approach can create multiple predictive models for power consumption, which can be applicable to the diverse machining configurations. It can create fine-grained models predictable up to the level of a numerical control program. It uses standard-based data interfaces such as STEP-NC and MTConnect to implement interoperable and comprehensive data representations. This paper also presents a case study to demonstrate the feasibility and effectiveness of the proposed approach.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.