CAJ | 학술논문

以凝胶注模法制备多孔氮化硅陶瓷正交试验结果作为样本,建立3层Back Pmpagation(BP)神经网络,并进行训练以预测陶瓷性能.通过附加试验值对建立的神经网络预测能力进行验证,证明该BP神经网络模型是有效的,能准确预测多孔氮化硅陶瓷性能.通过BP神经网络模型研究多孔氮化硅陶瓷性能的结果表明,随着固含量的增加,气孔率单调下降;固含量存在一优化值,此时陶瓷抗弯强度最大;单体含量越大,气孔率越大,而抗弯强度降低.
이응효주모법제비다공담화규도자정교시험결과작위양본,건립3층Back Pmpagation(BP)신경망락,병진행훈련이예측도자성능.통과부가시험치대건립적신경망락예측능력진행험증,증명해BP신경망락모형시유효적,능준학예측다공담화규도자성능.통과BP신경망락모형연구다공담화규도자성능적결과표명,수착고함량적증가,기공솔단조하강;고함량존재일우화치,차시도자항만강도최대;단체함량월대,기공솔월대,이항만강도강저.
Based on orthogonal experimental results of porous SigN4 ceramics by gel casting preparation, a three-layer back propagation (BP) artificial neural network (BP ANN) was developed for prediction of the flexnral strength and porosity. The BP ANN is composed of three neurons in the input layer, two neurons in the output layer and six neurons the hidden layer. This study demonstrates that the proposed neural network approach can predict the performances of porous Si_3N_4 ceramics by gel casting preparation to a high degree of accuracy, and the neural network is a very useful and accurate tool for performances analysis of porous Si_3N_4 ceramics. By the proposed neural network prediction and analysis, the results suggest that the porosity monotonically decreases with the increase of solid loading, flexural strength is low when solid loading was too low or too high, and flexural strength has an optimum value.