Application of Machine Learning in Optimization of High-permittivity Energy-storage Ba(Ti_1-xHf_x)O₃ Ceramic

In order to accelerate the design process of high dielectric permittivity materials, the machine learning optimization iterating with fabrication and experiment characterization method was employed in designing the high dielectric permittivity tricritical point Ba(Ti_1-xHf_x)O₃ ceramic. During the process, the optimization machine learning model was built to accelerate the searching for high-permittivity tricritical point, and several possible algorithms' efficiency and convergence rate have been compared and discussed. The results show that the largest relative permittivity is found to be 4.5×10⁴ at the composition of x=11%, which is much higher than that of normal ceramics (about 1 000); and the efficiency has been improved by 37.5%. This finding may provide a new method for designing high permittivity and energy density ceramics dielectrics.