论文部分内容阅读
为了提高数控机床故障预测的能力,针对BP神经网络在数控机床故障预测中出现的收敛速度慢和训练容易陷入局部极值问题,提出了一种基于萤火虫算法优化BP神经网络的数据机床故障诊断算法。文章详细介绍了常见的数控机床故障类型和分类,在萤火虫优化算法和BP神经网络的基础上,建立了萤火虫算法优化BP神经网络的数控机床故障诊断模型,并提出了基于该模型的算法。该模型和算法采用萤火虫算法优化BP神经网络的初始权值和阈值,优化后的BP神经网络能对测试集进行更好的预测。实验结果表明,萤火虫算法优化BP神经网络的预测误差明显小于GRNN和PNN算法。该模型和算法具有很好的预测能力,可以快速、准确地完成数控机床故障诊断研究。
In order to improve the ability of NC machine tool fault prediction, aiming at the problems of slow convergence speed and easy trapping of local boundary value in fault prediction of NC machine tool, a new fault diagnosis algorithm for machine tool based on firefly algorithm is proposed . Based on the firefly optimization algorithm and the BP neural network, the article has established the firefly algorithm optimization BP neural network fault diagnosis model of the CNC machine tool, and put forward the algorithm based on the model. The model and algorithm use firefly algorithm to optimize the initial weight and threshold of BP neural network. The optimized BP neural network can predict the test set better. Experimental results show that the prediction error of firefly algorithm optimization BP neural network is significantly less than that of GRNN and PNN algorithm. The model and algorithm have good predictive ability, and can quickly and accurately complete the NC machine tool fault diagnosis research.