Object Process Methodology to Turning Focused System Architecture Design for Manufacturing

Monitoring and predicting tool wear and surface roughness are considered crucial factors of automation and maximization of the manufacturing process like turning operations. However, nonlinearity and stochasticity in the formation and variation of tool wear contribute to considering turning as a complex system, making it difficult to design a precise prediction model to optimize machining parameters for maximum quality and production. Therefore, it is required to apply a systematic approach to identify the entities and relationships from a system design perspective and learn about the emergents like tool wear, surface roughness, force, etc., derived from the interaction of 'form' and 'function' during the turning operation. The representation of the instruments (machining parameters) of the process and their impacts on the operand (workpiece) could be worthwhile to explore for the sources of stochasticity. Object Process Methodology (OPM) has been established as an effective and integrated model that can incorporate the form, function, entities, and their relationship into a single model. Through the OPM, the objects, processes, and their relationships for the turning-focused complex system architecture are represented in this research. In consequence, nonlinear theoretical equations have been used to generate synthetic data using Monte Carlo Simulation (MCS) in the system. Finally, a Long Short-Term Memory (LSTM)-based Recurrent Neural Network (RNN) is considered to design a predictive model for the emergent properties. This proposed design of the turning-focused complex system architecture could be useful for the development of system pipelines concerning automation, digital twin technology, and Industry 4.0.