Holonic Manufacturing Systems (HMSs) are regarded as a foundation of cyber-physical production systems as they enable computers to conduct intelligent process planning, scheduling, and control by endowing manufacturing components with autonomy and collaboration. In an HMS, autonomy is realized by specifying holons that represent virtual agents of manufacturing components, while collaboration is facilitated through a communication mechanism that enables data exchange and decision making throughout a holarchy of holons without human intervention. This study presents the development of a virtualized holon model and a predictive process planning procedure using the Asset Administration Shell (AAS), i.e., a standardized model that can identify digital representation of manufacturing components to ensure interoperability. Specifically, an AAS-based information model was proposed to define operator, machine, product, and order holons. In addition, a predictive process planning procedure based on the Contract Net Protocol was developed to automatically allocate tasks while predicting task execution times. This study can contribute to the designing of an AAS- domain specific information model for HMS to increase interoperability in the holon holarchy, exhibiting the feasibility of AAS applications in predictive process planning on HMS.

Cyber-Physical Production Systems (CPPS), which pursue the implementation of machine intelligence in manufacturing systems, receive much attention as an advanced technology in Smart Factories. CPPS significantly necessitates the selflearning capability because this capability enables manufacturing objects to foresee performance results during their process planning activities and thus to make data-driven autonomous and collaborative decisions. The present work designs and implements a self-learning factory mechanism, which performs predictive process planning for energy reduction in metal cutting industries based on a hybrid-learning approach. The hybrid-learning approach is designed to accommodate traditional machine-learning and transfer-learning, thereby providing the ability of predictive modeling in both data sufficient and insufficient environments. Those manufacturing objects are agentized under the paradigm of Holonic Manufacturing Systems to determine the best energy-efficient machine tool through their self-decisions and interactions without the intervention of humans’ decisions. For such purpose, this paper includes: the proposition of the hybrid-learning approach, the design of system architecture and operational procedure for the self-learning factory, and the implementation of a prototype system.

In the metal-cutting industry, energy prediction is important for environmentally-conscious manufacturing because it enables a numerical anticipation of the energy consumption from the input of the process parameters, and therefore it contributes to the increasing of the energy-efficiency of the machine-tool operations. This paper proposes an energy-prediction modeling approach for numerical-control programs based on historical machine-monitoring data that have been collected from machine-tool operations. The proposed approach can create accurate energy-prediction models that forecast the energy that is consumed by the execution of a numerical-control program. Also, it can create machine-specific energy-prediction models that accommodate the variety of shop-floor machining contexts. For this purpose, it uses MTConnect to represent the machine-monitoring data to embody an interoperable data-collection environment regarding the shop floor. This paper also presents a case study to show the feasibility and practicability of the proposed approach.