【摘要】 关于用内燃机油模拟实验数据预测其台架实验结果的经验知识,在内燃机油配方的开发过程中有着重要的作用。但是,由于内燃机油在模拟实验和台架试验中分别处在非常不同的条件下发生物理化学变化,影响因素复杂,因而很难用数学模型准确地描述这些结果间的关系。近年来,由于人工智能的发展,为知识的获取和利用提供了更为有力的工具。本文介绍用人工神经网络的方法,根据内燃机油模拟实验数据预测其台架评定结果的知识。更多还原

【Abstract】 The knowledge used to predict the results of engine test from the data of bench test of engine oil plays an important role in the development of new engine oil formula. As different physical and chemical changes take place under very different conditions for an engine oil during engine test and bench test, it is different to describe accurately the relationship between the data of bench test and the results of engine test by using mathematical models. This paper presents an artificial neural network based method for manipulating this kind of knowledge.更多还原