高分求专业论文翻译05

  Entitled : "Neural Network Based coke quality prediction model," friends come to her for help and there was no time, and a professional too。

   Therefore, there is only seeking "love to ask" of the creatures they assistance。 PS1 : I have a translation, like the tagged with a。

   PS2 : Do not to the machine translation。 PS3 : I upload the two, giving further translation additional 200。 3 conclusions (1) with coal and coke coal quality between the nonlinear relationship We established a coke quality prediction of BP neural network model, select a reasonable coke quality indicators and said, as well as the training network。

   (2) Application of BP neural network model as an example, coke quality prediction and experimental results coincide, the model results showed higher accuracy, applicable to the coke quality forecasts。

   (3) coke quality of neural network prediction, the key lies in the selection of training samples, BP neural network algorithm for the sample of non-linear processing, use of the Newton gradient method, it can be accurate solution。

   (4) neural network is highly fault-tolerant, therefore, the parameters of individual differences will not affect the reliability of predictions, Moreover, as the example of the gradual rich samples, the reliability of predictions will be further enhanced。

   (5) As the traditional weighted average method and empirical formula is not suitable for the actual needs, neural network forecasting coke quality can consider all aspects of the main factors to make a judgment。

   Neural network prediction of the quality of coke value has broad prospects。 References : [1] Hao Hong Chau。 Coal quality parameters and coke [J]。

   Coal Chemical, 2001 (4) : 20。 [2] Guo 1 South, Wangling other。 Based on genetic algorithm and neural network optimization of coal mixed control [J]。

   China University of Mining Journal, rate (5) : 404 [3] Zhang Jie, LI De-jin。 Coke Quality Prediction and Application [J]。

   Industrial metrology, 2003, (1) : 39 [4] single Xiaoyun, Gao nearmodelpredictivecokesulfurresearch[J]。CoalCleaningTechnology,2004,(6)[5]-phase-Jun。

  NeuralNetworkTheoryandApplication[M]。Beijing:withthedefenseindustrialPress,1995。[6]InstituteofComputing。Neuralnetworksandapplications[M]。

  XI'AN:Xi'anJiaotongUniversityPress,1993。[7]Li-ChengJiao。NeuralNetworkTheory[M]。Xi'an:Xi'anUniversityofElectronicScienceandTechnologyPress,1990[8]YangchunChina,De-YaoShen,WuMin,etc。

  。Thecoalblendingexpertsystemdesignofthequalitativeandquantitativemethods[J]。AutomationJournal,2000,26(2):226-232[9] eindividuals。

  Dynamicblendingcoaldevelopment[J]。cleancoaltechnology,1997,3(1):18~21[10]QIN,ChenPeng。Cokingcoalblendingoptimization[J]。CleanCoalTechnology,1997,(3):46[11]Yuanwas。

  Artificialneuralnetworksandapplications[M]。Beijing:TsinghuaUniversityPress,1999:66~121。

  Entitled : "Neural Network Based coke quality prediction model," friends come to her for help and there was no time, and a professional too。

   Therefore, there is only seeking "love to ask" of the creatures they assistance。 PS1 : I have a translation, like the tagged with a。

   PS2 : Do not to the machine translation。 PS3 : I upload the two, giving further translation additional 200。 3 conclusions (1) with coal and coke coal quality between the nonlinear relationship We established a coke quality prediction of BP neural network model, select a reasonable coke quality indicators and said, as well as the training network。

   (2) Application of BP neural network model as an example, coke quality prediction and experimental results coincide, the model results showed higher accuracy, applicable to the coke quality forecasts。

   (3) coke quality of neural network prediction, the key lies in the selection of training samples, BP neural network algorithm for the sample of non-linear processing, use of the Newton gradient method, it can be accurate solution。

   (4) neural network is highly fault-tolerant, therefore, the parameters of individual differences will not affect the reliability of predictions, Moreover, as the example of the gradual rich samples, the reliability of predictions will be further enhanced。

   (5) As the traditional weighted average method and empirical formula is not suitable for the actual needs, neural network forecasting coke quality can consider all aspects of the main factors to make a judgment。

   Neural network prediction of the quality of coke value has broad prospects。 References : [1] Hao Hong Chau。 Coal quality parameters and coke [J]。

   Coal Chemical, 2001 (4) : 20。 [2] Guo 1 South, Wangling other。 Based on genetic algorithm and neural network optimization of coal mixed control [J]。

   China University of Mining Journal, rate (5) : 404 [3] Zhang Jie, LI De-jin。 Coke Quality Prediction and Application [J]。

   Industrial metrology, 2003, (1) : 39 [4] single Xiaoyun, Gao nearmodelpredictivecokesulfurresearch[J]。CoalCleaningTechnology,2004,(6)[5]-phase-Jun。

  NeuralNetworkTheoryandApplication[M]。Beijing:withthedefenseindustrialPress,1995。[6]InstituteofComputing。Neuralnetworksandapplications[M]。

  XI'AN:Xi'anJiaotongUniversityPress,1993。[7]Li-ChengJiao。NeuralNetworkTheory[M]。Xi'an:Xi'anUniversityofElectronicScienceandTechnologyPress,1990[8]YangchunChina,De-YaoShen,WuMin,etc。

  。Thecoalblendingexpertsystemdesignofthequalitativeandquantitativemethods[J]。AutomationJournal,2000,26(2):226-232[9] eindividuals。

  Dynamicblendingcoaldevelopment[J]。cleancoaltechnology,1997,3(1):18~21[10]QIN,ChenPeng。Cokingcoalblendingoptimization[J]。CleanCoalTechnology,1997,(3):46[11]Yuanwas。

  Artificialneuralnetworksandapplications[M]。Beijing:TsinghuaUniversityPress,1999:66~121。

建议你发布到专业的翻译论坛往 问问