The assessed results show that the prediction effect of artificial neutral networks model is better than that of multivariate nonlinear regression model , as well as the forecast effect of subsection model for water content of crude oil is better than that of united model 評價(jià)結(jié)果表明:神經(jīng)網(wǎng)絡(luò)模型預(yù)測效果優(yōu)于多元非線性回歸模型,原油含水率分段預(yù)測模型效果優(yōu)于統(tǒng)一模型。
Then on the base of the prerequisite hypothesis , the author establishes three rural - urban land conversion models , from which the plural linear regression equation is hers best choice through careful case studies of three different regional cities in china 然后,在提出模型假設(shè)前提的基礎(chǔ)上,構(gòu)思了三種農(nóng)地城市流轉(zhuǎn)模型,通過對三個(gè)區(qū)域的實(shí)證分析,確定多元非線性回歸方程為最佳農(nóng)地城市流轉(zhuǎn)模型。
The pattern recognition method of pipe mfl signals is put forward , the features of signals are extracted from the recorded flux leakage response and characterizing definition is introduced as well ; the main - part analysis , nonlinear regression , statistical methods are studied and used to establish characterization and compensation algorithms , the quantitative estimation of defect geometry and the result accuracy are accepted 引入了缺陷漏磁信號的模式識別方法,提出了缺陷漏磁場及缺陷外形尺寸的特征量;實(shí)現(xiàn)了用主成分分析、多元非線性回歸和統(tǒng)計(jì)識別分析等方法對缺陷漏磁信號波形進(jìn)行特征提取和定量識別,精度在誤差準(zhǔn)許范圍內(nèi)。
Using multi - sensor technology , some parameters affecting the measurement of water content of crude oil are measured , and prediction models of water content of crude oil based on the methods of multivariate nonlinear regression and artificial neutral networks are presented , and then being improved by subsection modeling 摘要通過多傳感器技術(shù)對原油含水率測量有影響的多個(gè)參量進(jìn)行測定,提出基于多元非線性回歸和神經(jīng)網(wǎng)絡(luò)融合處理兩種方法建立原油含水率預(yù)測模型,并采用分段建模的方法分別進(jìn)行改進(jìn)。