Original document(12 pages)  中文版
    A method for data processing and optimisation of a neural network for application in the determination of physical property data of hydrocarbon products from measured (Near) I.R. spectral absorbances, characterized by the steps of: a) measuring the I.R. spectra of a large set of hydrocarbon product samples from a wide range of sources; b) selecting a harmonic region; c) converting a number of the said wavelengths to absorption data and using said absorption data as an input to a neural network; d) training the neural network to correlate the absorbance values with said relevant physical property; e) generating a set of values of the interconnection weights and biases of the network; and f) applying these adjusted values, utilizing the neural network algorithm to (near-)infrared spectra.
Application Number
申请号
94191022 Application Date
申请日
1994.01.26
Title 名称 Method for prediction of physical property data of hydrocarbon products
Publication Number
公开号
1116878 Publication Date
公开日
1996.02.14
Approval Pub. Date Granted Pub. Date
International Classification 分类号 G01N21/35;G01N33/28
Applicant(s) Name
申请人
Shell Internationale Research Maatschappij B.V.
Address 地址
Inventor(s) Name 发明人 John Michael Tolchard;Andrew Boyd
Attorney & Agent 代理人 DU RIXIN

  
Compounds having crth2 antagonist activity
Fluid flow meter
Solid fuel burner
Continuously-variable-ratio transmission
Clutch module having a thick-edged pressure plate
Clutch module with integrated securing screws
Hydraulic pump controller
Electromagnetic valve
Electromagnetic valve
Fuel injection pump
Google
Note:All patent data come from State Intellectual Property Office of the People's Republic of China. If there were discrepancies between here and the State Intellectual Property office, the later is more accurate. The patent data is only for public exchange and learning purposes. We are not responsible for the adverse consequences with unverified use of the data.