【摘要】 采用MATLAB的BP人工神经网络,以铝青铜的化学成分作为输入参数,其抗拉强度σb、屈服强度σ0.2和伸长率δ作为输出,建立了高强度船用螺旋桨铝青铜的力学性能预测模型。计算结果表明,三项输出的预测值与实测数据接近,其相对误差基本在±2%～±7%,因此,该模型对高强度船用螺旋桨铝青铜的生产具有一定的指导意义。更多还原

【Abstract】 A mechanical property predicting model is set up for marine propeller aluminum bronze by back-propagation (BP) artificial neural network in MATLAB toolbox. The calculation results show that the tensile strength, yield strength and elongation of the alloy predicted by the model are approximate to real value and the relative errors are respectively from ±2% to ±7%, so that the model can be used in the production of the marine propeller aluminum bronze.更多还原