【摘要】 提出一种从RBF神经网络隐含层的输出信息出发,通过PLS快速剪枝法,一次性剪去多余节点,生成最优规模的数学解析模型的方法。并用该方法建立了某化工企业精对苯二甲酸(PTA)晶体平均粒径的软测量模型,针对实际对象进行仿真研究,结果表明,该方法计算速度快,建立的模型精度高,适合实际工程应用的需求。更多还原

【Abstract】 A soft sensor modeling algorithm which can prune away the redundant nodes of the RBF neural network at one time by analyzing the output information of its hidden nodes with PLS-Pruning algorithm is presented,the corresponding optimized mathematic analytical model can be obtained.The obtained method is applied to build a soft sensor model for the average diameter of an industrial purified terephthalic acid (PTA) crystal.Simulation results demonstrate that the new algorithm is fast in computation and accurate in prediction,it is suitable to practical application.更多还原