To achieve a higher convergent speed, the forecasting model adopts Levenberg-Marquardt(LM) algorithm, and the model adopts early stop method to improve extended capacity of the model.
在预测模型中采用LM算法提高网络的收敛速度，并采用提前停止法提高网络的推广能力。
2
To reduce the influence of noise, the initial result was optimized with the Levenberg-Marquardtalgorithm.
为了降低噪声影响，使用非线性优化算法优化初值。
3
Using backpropagation neural network based on Levenberg-Marquardtalgorithm, the universal characteristics of engine were investigated.