论文部分内容阅读
激光加工过程中,切割切口大小与工艺条件之间是一种非线性变换关系,为了提高激光切割切口精度,针对传统神经网络参数优化存在的缺陷,提出一种改进神经网络算法的激光切割切口大小预测模型。首先收集激光切割切口大小与工艺条件数据,并对其进行归一化处理,然后采用训练样本对神经网络进行训练,通过量子粒子群优化算法解决传统神经网络参数优化问题,建立激光切割切口大小的预测模型,最后采用测试样本对预测模型进行验证。结果表明,本文模型可以很好拟合工艺条件与切割切口大小间的关系,能够有效预测切口大小,为提高激光切割质量提供了理论依据。
In the process of laser processing, the size of the cutting notch is a nonlinear transformation relationship with the processing conditions. In order to improve the precision of the laser cutting, aiming at the defects of traditional neural network parameters optimization, an improved laser cutting notch size Predictive model. Firstly, the laser cutting incision size and process condition data were collected and normalized. Then the training samples were used to train the neural network. The quantum particle swarm optimization algorithm was used to solve the traditional neural network parameter optimization problem. The laser cutting incision size Prediction model, and finally use the test sample to verify the prediction model. The results show that the model can well fit the relationship between the process conditions and the size of the incision, which can effectively predict the incision size and provide a theoretical basis for improving the quality of laser cutting.