基于SAGA优化BP神经网络的木材含水率预测

Prediction of Wood Moisture Content Based on BP Neural Network Optimized by SAGA

针对木材干燥过程中含水率的检测问题,提出了一种基于SAGA优化BP神经网络的木材含水率预测方法,即采用遗传算法与模拟退火算法相结合的学习策略,利用SAGA的全局寻优能力优化BP网络的权值和阈值。仿真试验表明,优化后的BP网络表现出良好的预测性能,缩短了训练时间,避免了BP算法陷入局部小,具有很高的预测精度。

According to the problem of the wood moisture content detection for drying process, this paper proposes a BP neural network method based on SAGA optimization algorithm for predicting wood moisture content. It combines genetic algorithm and simulated annealing algorithm, using the global optimization ability of the SAGA to optimize BP network weights and threshold value. The simulation results show that the optimized BP network has good prediction performance, reduces the training time, avoids the BP algorithm into local minimum value, has a very high prediction accuracy.