Parameters optimization of a nano-particle wet milling process using the Taguchi method, response surface method and genetic algorithm

Figure optionsDownload as PowerPoint slideNano-particles have been successfully and widely applied in many industrial applications. The wet-type mechanical milling process is a popular method used to produce nano-particles. Therefore, it is very important to improve milling process capability and quality by setting the optimal milling parameters. In this research, the parameter design of the Taguchi method, response surface method (RSM) and genetic algorithm (GA) are integrated and applied to set the optimal parameters for a nano-particle milling process. The orthogonal array experiment is conducted to economically obtain the response measurements. Analysis of variance (ANOVA) and main effect plot are used to determine the significant parameters and set the optimal level for each parameter. The RSM is then used to build the relationship between the input parameters and output responses, and used as the fitness function to measure the fitness value of the GA approach. Finally, GA is applied to find the optimal parameters for a nano-particle milling process. The experimental results show that the integrated approach does indeed find the optimal parameters that result in very good output responses in the nano-particle wet milling process.

The wet-type bead milling machine is developed to make the TiO2 nano-particles. It can break the TiO2 nano-particles with a mean grain size of 100–200 nm. After the milling process, the SEM photography is taken to show the milling performance.