A novel intelligent reasoning system to estimate energy consumption and optimize cutting parameters toward sustainable machining

Abstract

As it is hard to estimate the energy consumption and to optimize the cutting parameters in different tool wear status, this paper presents a novel intelligent reasoning system for the milling process. The system consists of three parts including the improved case based reasoning (ICBR), the adaptive neural fuzzy inference system (ANFIS) and the vibration particle swarm optimization (VPSO) algorithm. The ICBR is used for providing accurate estimation of cutting power. The inputs of ICBR are cutting parameters and tool wear status, and the output is cutting power. In ICBR, the similar cases to the inputs are retrieved using K-nearest neighbor and artificial neural network (ANN) methods in the case retrieval stage. In the case reuse stage, the Gaussian fuzzy grey correlation model is proposed to estimate the cutting power based on the retrieved similar cases. The VPSO algorithm is proposed to establish ANN and ANFIS models. With the aid of ANFIS-VPSO method, the optimal cutting parameters can be obtained under different machining conditions. The experimental results have confirmed that the VPSO algorithm has better global optimization ability than PSO and DE algorithms. The cutting speed has the greatest influence on the cutting power and cutting vibration. The estimation accuracy of ICBR is up to 91.7%, which are better than that of standard CBR and other intelligent models. The optimal cutting parameters are verified with an optimization error less than 13.5% by experiment results. The intelligent reasoning system can reduce energy consumption, maintain machine tool stability and improve machining efficiency. As an important platform, this system can realize clean and intelligent production.