CAJ | 학술논문

以某汽车发动机的HT150气缸套激光表面硬化正交实验得到的实验数据为基础,利用Mat-lab人工神经网络工具箱中的BP网络强大的数据预测功能,建立了该HT150气缸套激光表面硬化指标(表面硬度和硬化层深度)的神经网络预测模型,通过对网络隐含层神经元个数的调整,使收敛速度加快,提高了硬化指标的预测精度.
이모기차발동궤적HT150기항투격광표면경화정교실험득도적실험수거위기출,이용Mat-lab인공신경망락공구상중적BP망락강대적수거예측공능,건립료해HT150기항투격광표면경화지표(표면경도화경화층심도)적신경망락예측모형,통과대망락은함층신경원개수적조정,사수렴속도가쾌,제고료경화지표적예측정도.
Based on the data obtained from the perpendicular experiment of laser surface hardening on HT150 cylinder liner of a certain motor engine, and with BP neural network's powerful function in numeric forecast, a neural network forecast model of laser surface hardening index about HT150 cylinder liner is established. The convergence speed is accelerated and the prediction accuracy of the hardening index is improved by adjusting the number of hiddenlayer neurons in the network.