基于物理信息神经网络的燃烧化学微分方程求解

王意存,邢江宽,罗坤,王海鸥,樊建人

Solving combustion chemical differential equations via physics-informed neural network

Yi-cun WANG,Jiang-kuan XING,Kun LUO,Hai-ou WANG,Jian-ren FAN

表 2 顺序的PINNs结构

Tab.2 Structure of sequential PINNs model

层类型 激活函数 输出类型 ROBER问题 混合分数PDE Input — (None, 1): t (None, 2): x, y Dense tanh (None, 100) (None, 200) Dense tanh (None, 100) (None, 200) Dense tanh (None, 100) (None, 200) Dense tanh (None, 100) (None, 200) Output # (None, 3): y1, y2, y3 (None, 1): Z