針對(duì)火電廠汽輪發(fā)電機(jī)組經(jīng)濟(jì)性監(jiān)測(cè)系統(tǒng)中參數(shù)失效的問題,提出了利用徑向基函數(shù)神經(jīng)網(wǎng)絡(luò)的仿真手段作為虛擬傳感器。分析了徑向基函數(shù)神經(jīng)網(wǎng)絡(luò)的原理與特點(diǎn),總結(jié)了求解各層權(quán)值和閾值的數(shù)學(xué)公式,闡述了參數(shù)學(xué)習(xí)和仿真的方法與過(guò)程。
關(guān)鍵詞:徑向基;神經(jīng)網(wǎng)絡(luò);汽輪發(fā)電機(jī)組;經(jīng)濟(jì)性監(jiān)測(cè);仿真;虛擬傳感器
Abstract :In order to solve the problem of failure measure parameter in the economic monitoring system of steam turbine unit , a method employing radial basis function neural network (RBFN) to simulate the parameter is proposed. The principle and charac2 teristics of RBFN are analyzed , the mathematics method to evaluate the network weights and biases of each layer is summarized , and the training and simulation methods and processes are expounded. Besides , a more convenient method that can use MATLAB to training the network off2line was proposed.
Key words :radial basis; neural network; steam turbine unit ; economic monitoring; simulation; virtual sensor