Automated process parameters tuning for an injection moulding machine with soft computing

Abstract

In injection moulding production, the tuning of the process parameters is a challenging job, which relies heavily on the experience of skilled operators. In this paper, taking into consideration operator assessment during moulding trials, a novel intel- ligent model for automated tuning of process parameters is proposed. This consists of case based reasoning (CBR), empirical model (EM), and fuzzy logic (FL) methods. CBR and EM are used to imitate recall and intuitive thoughts of skilled operators, respectively, while FL is adopted to simulate the skilled operator optimization thoughts. First, CBR is used to set up the initial process parameters. If CBR fails, EM is employed to calculate the initial parameters. Next, a moulding trial is performed using the initial parameters. Then FL is adopted to optimize these parameters and correct defects repeatedly until the moulded part is found to be satisfactory. Based on the above methodologies, intelligent software was developed and embedded in the controller of an injection moulding machine. Experimental results show that the intelligent software can be effectively used in practical produc- tion, and it greatly reduces the dependence on the experience of the operators.