结果表明，支持向量机回归和预测的最大相对误差不超过6 5%。
The results show that the maximum regression and prediction relative errors are not greater than 6.5%.
经过实例检验，改进的模拟退火-灰色模型的相对误差比传统灰色模型小的多，提高了预测精度。
It is testified by instance that the relative error of stimulated annealing grey model is smaller than traditional grey model's and it has improved the prediction precision.
给出的例子表明，该模型预测主生产计划时段的参数(计划参数)与实际参数的相对误差不超过3%。
An example indicates that relative errors between forecasting parameters (planning parameters) and practical parameters are all less than 3% by applying ARMABP model.
利用BP神经网络模型实现了对造纸废水处理过程的预测，平均相对误差为19%，表明网络泛化能力不是很好。
The effluent treatment process was predicted with this BP neural network model with the average relative error of 19%, which indicates that the generalization power of the network is not so desirable.
数值实验显示，虽然策略库比较简单，但其预测的平均相对误差仅为1.73%。
The numerical experiment results show that the mean forecast relative error is 1.73% even with a simple strategies library.
预测的热负荷、热效率及温度的平均相对误差均小于10%。
The mean relative deviations of the predicted heat load, heat efficiency and temperature are less than 10%.
结果表明，相对误差较小，预测精度达到了要求。
At last the result shows that the relative error is rather small and the forecasting precision is satisfied.
利用网络预测误差的相对平均值对神经网络的泛化能力进行了定量的分析。
Making use of the relative average of network prediction uncertainty, the quantitative analysis is carried out for the ability of generalization.
并分析了相对湿度预测模型中误差产生的原因。
And discuss the reason of the error in the predicting model of the RH.
由该模型对95个聚合物的折光率进行预测，平均相对误差为0.959％。
The average prediction error by this model is 0.959% for the refractive index of 95 amorphous homopolymers.
用标准预测误差(%SEP)，平均预测误差(MPE)和平均相对误差(MRE)来评价其预测能力。
The standard error of prediction (% SEP), the mean prediction error (MPE) and the mean relative error (MRE) were utilized to evaluate the prediction ability of the BP-ANN.
结果表明：硬度预测值与实验值相对误差的绝对值的平均值为5.90%，附着力预测准确率为100%，耐冲击性预测准确率为100%。
The results show that the average absolute value of relative errors between predictive and measured values of hardness is 5.90%, the prediction accuracies of adhesion and impact resistance are 100%.
经过试验验证优化后的网络不仅收敛速度快、精度得到极大提高，而且网络预测相对误差精度都在6%以下。
Experiments prove that the optimized network converges more quickly and accurately. The relative prediction error precisions are all below 6%.
研究结果：（1）此模型预测结果的相对误差绝对值均值从PLS模型的3.92%，降低到了0.13%；
The results indicate:(1)the mean absolute value of relative error of the prediction results of this model has been reduced at 0.13% (the original is 3.92% in the PLS model);
驱油效率实际值与预测值平均相对误差8.7%，精度满足生产要求。
The relative average error between predicted oil displacement efficiency and actual value is 8.7%, the accuracy meets demand of production.
实验结果表明，模型预测结果的平均相对误差为10.316%，相对标准差为12.895%，满足工程实际要求。
Experiment shows that the average relative error of predicted results is 10.316% and the relative standard error is 12.895%, thus it satisfying requirements of the engineering.
从近年在河北省冬麦区土壤水分的监测预测结果来看，监测相对误差在10%左右，风险预测相对误差在20%左右。
The results indicate that the relative monitoring error is about 10%, and the relative risk forecasting error is about 20%.
通过运用数理统计中的回归分析方法确立采出矿石地质矿量预测数学模型，分析预测相对误差，并对2007年采出矿石地质矿量进行预测。
The model is used to analyze the relative error of forecast and to forecast the exploitable geological ore reserves of Miaogou Mine in 2007.
将此动力学模型预测固定床反应结果，计算值与实测值相对平均误差小于20%。
The model was used to predict the reaction results of fixed-bed reactor and the average deviations of the calculated values from experimental data were less than 20%.
模拟的结果显示ANN模型比线性回归模型有更好的预测能力，预测的平均相对误差：ANN模型为14.9%，线性回归模型为25.8%。
Simulation results showed that the ANN model gave better predictions than the regressive model. The average relative error of ANN was 14.9% and that of linear regression was 25.8%.
运用本文预测模型，焊缝宽度预测相对误差均在5%以下，充分验证了该预测模型的合理性及适用性。
The forecasting relative errors of weld widths were below 5%. Therefore, the proposed model was reasonable and applicable.
结果是预测结果与试验结果吻合很好，最大相对误差仅为7%。
The predicting results are in good agreement with the test results, and the maximum relative error is only 7%.
检验结果表明J9的预测模型能够把预测值的相对误差控制在5%以内，J 15的预测模型能够控制在3%以内。
The check result indicated that J9 the forecast model can control the predicted value relative error in 5%, the J15 forecast model can control in 3%.
利用GA - BP神经网络模型对气井产量进行了拟合和预测，拟合的平均相对误差为5.1%，表明新模型适用于洛带气田的产量递减预测。
GA-BP neural network model is applied in matching and predicting the production of the gas Wells with 5.1% of the average relative error. It proves th...
采用某矿区实测资料对模型进行验证，预计结果最大相对误差9%，可以满足矿山开采沉陷预测的要求。
The measured data of the mining area are used to verify the model with the expected results of the maximum relative error 9%, which can meet the requirements of mining subsidence.
算例表明，应用该法进行单井预测的相对误差只有2.07%，多井预测的相对误差小于1.5%。
The results indicate that ther elative error is only 2.07% in single well prediction, and less 1.5% in multi-we ll prediction.
模型预测值与国标法测定的酸值高度线性相关，盲样验证相对误差均小于10%。
The linear correlativity of the determination of the acid value between two methods was very well, the relative deviation of blind samples experiment's data were less than 10%.
网络检验结果表明，原丝性能预测值与实测值的相对误差不到3%，网络具有良好的拟合性。
The network was tested with the experimental data and the deviations between the measured data and the forecast were less than 3%, this means that the neural network had a good fitting.
网络检验结果表明，原丝性能预测值与实测值的相对误差不到3%，网络具有良好的拟合性。
The network was tested with the experimental data and the deviations between the measured data and the forecast were less than 3%, this means that the neural network had a good fitting.
应用推荐