润滑与密封
潤滑與密封
윤활여밀봉
LUBRICATION ENGINEERING
2014年
11期
14-18,54
,共6页
薛继斌%吕亚非%齐士成%江盛玲%张孝阿%员荣平
薛繼斌%呂亞非%齊士成%江盛玲%張孝阿%員榮平
설계빈%려아비%제사성%강성령%장효아%원영평
人工神经网络%摩擦材料%性能预测%摩擦因数
人工神經網絡%摩抆材料%性能預測%摩抆因數
인공신경망락%마찰재료%성능예측%마찰인수
artificial neural network(ANN)%brake friction material%performance prediction%friction coefficient
基于3种典型的人工神经网络,即Elman (反馈)、BP (前馈)和RBF (径向),分别建立3种制动摩擦材料摩擦性能的评价预测模型,采用[240,8]的数据样本对3种模型进行训练,同时采用贝叶斯正则化训练函数进一步优化。结果表明,Elman网络预测实验数据的精度最高,能较为准确地预测摩擦材料的升温摩擦因数和降温摩擦因数,尤其适用于磨料含量较低的情况。
基于3種典型的人工神經網絡,即Elman (反饋)、BP (前饋)和RBF (徑嚮),分彆建立3種製動摩抆材料摩抆性能的評價預測模型,採用[240,8]的數據樣本對3種模型進行訓練,同時採用貝葉斯正則化訓練函數進一步優化。結果錶明,Elman網絡預測實驗數據的精度最高,能較為準確地預測摩抆材料的升溫摩抆因數和降溫摩抆因數,尤其適用于磨料含量較低的情況。
기우3충전형적인공신경망락,즉Elman (반궤)、BP (전궤)화RBF (경향),분별건립3충제동마찰재료마찰성능적평개예측모형,채용[240,8]적수거양본대3충모형진행훈련,동시채용패협사정칙화훈련함수진일보우화。결과표명,Elman망락예측실험수거적정도최고,능교위준학지예측마찰재료적승온마찰인수화강온마찰인수,우기괄용우마료함량교저적정황。
Three different evaluation models on tribolocical performances of brake friction composites were established based on three types of typical artificial neural networks (ANN),including Elman,BP and RBF. All three models were trained and optimized with a Bayesian Regulation algorithm,and were applied to predict the friction coefficient of friction materials in both heating and cooling processes. The research results show that the Elman model is the best one in accurate-ly predicting the friction coefficient of friction materials,especially for the formulations with a low usage of abrasives.