精度比

• The weight changeable combination forecasting model and the weight unchangeable combination forecasting model are attempted to forecast the annual rainfall . because combination forecasting model can synthetically use the information that is provided by every single model , the shortage of every single model can be avoided . generally speaking , the result of combination forecasting model is balanced , and the precision of it is better than that of every single model
  而且，本文还尝试采用不变权重和变权重两种组合预测模型来进行年降雨的预测，因为组合预测模型可以综合利用各个单项预测模型所提供的信息，避免了单项预测模型预测结果的“时好时坏”性，所做出的预测结果较为平稳，而且，预测结果也说明组合预测模型预测精度比单项预测模型的高。
• It is very important to estimate the basic parameters in helicopter preliminary design . neural network ( nn ) has the advantages in estimating accuracy and generalization over traditional methods . however , there are some difficulties in using nn , e . g . , how to select a proper network structure and the number of hidden layers . in this paper , structure and connection weight of a three - layer nn are optimized by genetic algorithm , and the optimized network is applied to helicopter sizing . the proposed method can not only give an optimal nn structure and connection weight , but also reduce the prediction error and has the capability of self - learning when the latest data are available . furthermore , this method can be easily applied to helicopter design systems
  在直升机初步设计阶段估算其基本参数是很重要的.神经网络的通用性和精度比传统的估算方法有更多的优势,但是在应用神经网络时存在如何选择合适的网络结构和隐层节点数目等一些困难.应用遗传算法优化三层神经网络结构和连接权重,并将优化得到的网络应用于直升机参数选择中.该方法不但可以给出一个最优的神经网络结构和连接权重,而且降低了估算误差,具有及时应用最新数据学习的能力.此外,该方法易于在直升机设计系统中得到应用
• The paper describes a capacity predicting method : combining the open circuit voltage prediction with the fuzzy prediction of the " storage batteries health " . and the method does not only increase the prediction speed but also improve the prediction precision , so it can offer credible data to charging management . 8
  提出了在独立光伏系统中采用开路电压预测和基于蓄电池“健康状态”的模糊预测相结合的容量预测方法，使容量预测速度和精度比传统的预测方法都得到提高，为充电管理提供可靠的充电依据。
• Ycm ann works under the principle of vcm , in which ann targets to adjust the faint knowledge of vcm and keeps the knowledge among the connections of ann crunodes in ftart arm network . the thesis has testified that vcm ann method is more precise than tf idf ig , can conquer part of what the latter can not deal with , and has less work to compute
  我们通过实验证明了人工神经方法的计算精度比改进的信息增益方法高，能够有效地克服信息增益方法不能克服的精确性问题，计算的复杂性也比信息增益方法低，这说明人工神经元网络方法虽然捕捉的是模糊信息，却能够较为精确的捕捉到文档中词条项与文档的类别之间的模糊关系。
• Experimental results on butane and butane - plant oil flames indicated that , measurement precision by the multi - wavelength method is strengthened by taking radiation information on multiple wavelength units into consideration , and moreover , the radiation calibration procedure is simplified , in that a halogen light source is used instead of in situ flame radiation . in section 2 , fluctuation and averaging analyses are carried out on optical transmission signals by particles passed through laser beams to derive particle size and concentration in measuring area , furthermore , correlation calculations are conducted on two adjacent laser beam signals to obtain flowing velocity of particle
  对丁烷气体火焰及丁烷-植物油混合燃料火焰的测量结果表明，多波长分析方法优于传统的双色法，表现在两个方面：一、由于综合考虑多个波长单元上的火焰辐射信息，多波长方法的测量精度比双色法有较大的提高；二、在多波长分析方法中，采用标准卤素灯进行相对辐射强度标定，简化了双色法中的火焰绝对辐射强度的标定。
• Abstract : it is very important to estimate the basic parameters in helicopter preliminary design . neural network ( nn ) has the advantages in estimating accuracy and generalization over traditional methods . however , there are some difficulties in using nn , e . g . , how to select a proper network structure and the number of hidden layers . in this paper , structure and connection weight of a three - layer nn are optimized by genetic algorithm , and the optimized network is applied to helicopter sizing . the proposed method can not only give an optimal nn structure and connection weight , but also reduce the prediction error and has the capability of self - learning when the latest data are available . furthermore , this method can be easily applied to helicopter design systems
  文摘:在直升机初步设计阶段估算其基本参数是很重要的.神经网络的通用性和精度比传统的估算方法有更多的优势,但是在应用神经网络时存在如何选择合适的网络结构和隐层节点数目等一些困难.应用遗传算法优化三层神经网络结构和连接权重,并将优化得到的网络应用于直升机参数选择中.该方法不但可以给出一个最优的神经网络结构和连接权重,而且降低了估算误差,具有及时应用最新数据学习的能力.此外,该方法易于在直升机设计系统中得到应用