The solution is realized by generalized regression neural network, and is proved by experiment 利用廣義回歸神經(jīng)網(wǎng)絡(luò)來實(shí)現(xiàn),并做了相關(guān)實(shí)驗(yàn)。
The correlation model between main chemical compositions and sensory qualities of flue-cured tobaccos was constructed by generalized regression neural network ( grnn ) 摘要采用廣義回歸神經(jīng)網(wǎng)絡(luò)分別對烤煙的主要化學(xué)成分與香氣質(zhì)、香氣量、雜氣、刺激、馀味、勁頭和煙氣濃度等感官質(zhì)量進(jìn)行建模。
This paper presented a kind of nn modeling method named generalized regression neural network ( grnn ), through which the physical, mechanical properties of chinese fir could be obtained from its internal structure parameters 摘要給出由木材內(nèi)部結(jié)構(gòu)參數(shù)確定其物理力學(xué)特徵的神經(jīng)網(wǎng)絡(luò)設(shè)計(jì)與實(shí)現(xiàn)的方法廣義回歸神經(jīng)網(wǎng)絡(luò)(grnn)模型。
In chapter five, algorithm of load identification is discussed in detail . levenberg ? marquardt algorithm and generalized regression neural network are used to identify the position and degree of the one load on the surface of the airfoil, correlation analysis algorithm of multi-load identification is also proposed in the paper 第五章重點(diǎn)論述了系統(tǒng)設(shè)計(jì)中的載荷識別算法,采用人工神經(jīng)網(wǎng)絡(luò)lm-bp算法及廣義回歸網(wǎng)絡(luò)對單個(gè)載荷大小、位置進(jìn)行了判定,提出了基于相關(guān)分析的多載荷識別算法。
Ann methods are feasible for the verification measurements in nuclear safeguards . experimental data sets have been used to study the performance of neural networks involving radial basis function neural network and generalized regression neural network ( grnn ) . the optimization of the parameter spreads have been given and the analysis error of grnn no more than 0.2 % 分析結(jié)果表明,使用泛化能力較高的混合訓(xùn)練集訓(xùn)練神經(jīng)網(wǎng)絡(luò),網(wǎng)絡(luò)給出的富集度值與標(biāo)準(zhǔn)樣品的標(biāo)稱值之間的相對差異小于13%;使用泛化能力相對較弱的分組訓(xùn)練集訓(xùn)練神經(jīng)網(wǎng)絡(luò),網(wǎng)絡(luò)給出的分析結(jié)果的不確定度小于2%;使用分組訓(xùn)練集和廣義回歸神經(jīng)網(wǎng)絡(luò),網(wǎng)絡(luò)給出的分析結(jié)果的不確定度小于0
Abstract : on the basis of the experimental data of microstructure and strength for gray cast iron with high carbon equivalent, the adapted fuzzy neural network model of relationship between microstructure and strength for predicting the strength of gray cast iron has been developed by using adaptive neural-fuzzy inference method . comparing with the models based on multiple statistic analysis, fuzzy regression or generalized regression neural network, it shows better learning precision and generalization 文摘:以高碳當(dāng)量灰鑄鐵組織-強(qiáng)度實(shí)驗(yàn)數(shù)據(jù)為基礎(chǔ),用自適應(yīng)模糊推理方法,建立了灰鑄鐵強(qiáng)度自適應(yīng)模糊神經(jīng)網(wǎng)絡(luò)預(yù)測模型,與多元線性回歸、模糊回歸和廣義回歸神經(jīng)網(wǎng)絡(luò)模型相比,該模型學(xué)習(xí)精度高且具有較好的泛化性。