Prediction of Energy Storage Performance in Polymer Composites Using High‐Throughput Stochastic Breakdown Simulation and Machine Learning

Abstract

Polymer dielectric capacitors are widely utilized in pulse power devices owing to their high power density. Because of the low dielectric constants of pure polymers, inorganic fillers are needed to improve their properties. The size and dielectric properties of fillers will affect the dielectric breakdown of polymer‐based composites. However, the effect of fillers on breakdown strength cannot be completely obtained through experiments alone. In this paper, three of the most important variables affecting the breakdown strength of polymer‐based composites are considered: the filler dielectric constants, filler sizes, and filler contents. High‐throughput stochastic breakdown simulation is performed on 504 groups of data, and the simulation results are used as the machine learning database to obtain the breakdown strength prediction of polymer‐based composites. Combined with the classical dielectric prediction formula, the energy storage density prediction of polymer‐based composites is obtained. The accuracy of the prediction is verified by the directional experiments, including dielectric constant and breakdown strength. This work provides insight into the design and fabrication of polymer‐based composites with high energy density for capacitive energy storage applications.

Enhanced Energy Storage Performance of PVDF-Based Composites Using BN@PDA Sheets and Titania Nanosheets

“…The F(β) of all samples are shown in Figure 3d. Both series of composites possessed increased values of F(β), which indicates that the fillers with rich −OH on the surface could induce α-β phase transformation [30]. The PVDF/BN@PDA−STNSs ternary composites possessed higher F(β) compared with PVDF/BN@PDA composites, which could be ascribed to the presence of more interfaces introduced by STNSs in ternary composites.…”

Machine Learning for Harnessing Thermal Energy: From Materials Discovery to System Optimization

“…By taking the structure−properties relationships from experiments and/or rigorous numerical calculations, multiple algorithms have been applied to learn the thermal conductivity of composites, such as support vector regression, Gaussian regression, and neural networks. 45,46 In addition, ML methods have also been applied to design functional composites for thermal cloaking, 147 energy storage, 148,149 and additive manufacturing. 150 ■ THERMOPHYSICAL PROPERTIES OF MATERIALS…”

“…However, the rigorous numerical calculations based on finite element analysis, lattice Boltzmann method, or others usually take too much time for material design, which undoubtedly can benefit from the ML approach to speed up the computations for composites. By taking the structure–properties relationships from experiments and/or rigorous numerical calculations, multiple algorithms have been applied to learn the thermal conductivity of composites, such as support vector regression, Gaussian regression, and neural networks. , In addition, ML methods have also been applied to design functional composites for thermal cloaking, energy storage, , and additive manufacturing …”

Polyimide-Based Composite Films with Largely Enhanced Energy Storage Performances toward High-Temperature Electrostatic Capacitor Applications

“…Polymer-based dielectrics, characterized by their outstanding electrical dielectric strength, relatively low dielectric loss, fast charge–discharge capability, and mechanical flexibility, have become a research hotspot in current work and are widely applied in energy storage devices. − Typically, discharge energy density ( U d ) and charge/discharge efficiency (η) are the basic performance parameters for evaluating capacitors, and researchers have made substantial efforts to improve the U d and η values of capacitors at room temperature (RT) in the past decades. − Nowadays, owing to electric power system installation close to the motor and the ever-increasing requirement of high-power applications (which are always exposed to elevated temperatures), capacitors, the fundamental component of power inverters, are required to function efficiently at temperatures above 140 °C. , Nevertheless, the poor thermal stability of polymers and the inevitable conduction loss caused by the fundamental issue of thermally and electrically assisted charge injection, excitation, and transport will lead to the drastically deteriorated capacitive properties of polymer-based dielectrics at high temperature, which severely hampers their usage in extreme environments. − …”