Machine-Learning-Assisted Composition Design of High-Entropy CaBi4Ti4O15-Based Piezoceramics with Ultrahigh
Yangyang Zhou1,2, Chun Guo1,2, Zhiyong Zhou1
1State Key Laboratory of High Performance Ceramics, Shanghai Institute of Ceramics, Chinese Academy of Sciences, 588 Heshuo Road, Jiading District, Shanghai 201899, China.
None:
High-entropy strategy presents a promising approach for enhancing the piezoelectric properties of bismuth layer-structured ferroelectrics, yet the vast compositional space poses significant challenges for traditional trial-and-error methods. In this work, a machine learning (ML)-assisted design strategy is proposed to accelerate the discovery of high-performance, high-entropy CaBi4Ti4O15 ceramics. Based on a small data set containing 114 compositions, seven key elements closely related to the piezoelectric coefficient (d33) were identified through feature engineering. Using the eXtreme Gradient Boosting regression model, the d33 values of 22500 candidate compositions were predicted, thereby guiding the synthesis of Ca1-x(Na1/6Bi1/6Li1/6Ce1/6K1/6Bi1/6)xBi4Ti3.9(Nb1/2Mn1/2)0.1O15 ceramics. The optimal composition (x = 0.3) achieved a record-high d33 of 28.1 pC/N, along with outstanding temperature stability (93% retention after 500 °C annealing). Structural characterization indicates that the high-entropy-induced chemical disorder promotes the formation and switching of nanodomains. On the other hand, the significant lattice distortion it induces enhances the spontaneous polarization, with both aspects synergistically improving the piezoelectric performance. This work demonstrates the effectiveness of ML in navigating complex composition-performance relationships in high-entropy piezoceramics and provides a viable route for designing piezoelectric materials with superior integrated performance for high-temperature applications.
