最后在模拟测试之下，利用最大概似估计法求得各参数的误差、均方根误差、参数之上下界限以及涵盖。
Simulation results show that the maximum likelihood estimates perform well in most cases in terms of the mean bias, errors in the root mean square and the coverage rate.
除了用单行数值比较法外，还计算了重组和数学模型之间的归一化均方根偏差、归一化平均偏差和最大偏差。
Besides a comparison of the characteristic line, the normalized mean square root error, the normalized mean error, and the maximum deviation are calculated and discussed.
对SVM多元非线性回归泛化性能进行测试，其均方根相对误差为1.06%，平均绝对相对误差为0.96%，最大绝对相对误差为1.16%。
The root mean square relative error, mean absolute relative error and maximize absolute relative error of SVM model generalization performance are 1.06%, 0.96% and 1.16%, respectively.
文章对其几何尺寸与平衡参数进行了优化设计，证实该机型曲柄轴的均方根扭矩比异相型减少了31.2％，最大扭矩减少了35.3％，平衡效果显著。
The geometric dimensions and balance parameters of the beam pumping units are optimized. As a result, Me is re- duced 31.2% and Mnmax is reduced 35.3% than phased balance.
文章对其几何尺寸与平衡参数进行了优化设计，证实该机型曲柄轴的均方根扭矩比异相型减少了31.2％，最大扭矩减少了35.3％，平衡效果显著。
The geometric dimensions and balance parameters of the beam pumping units are optimized. As a result, Me is re- duced 31.2% and Mnmax is reduced 35.3% than phased balance.
应用推荐