内圆切入磨削不同砂轮磨削性能在线监测模型研究

Research on Online Monitoring Model of Grinding Performance of Different Grinding Wheels in Internal Plunge Grinding

摘要: 针对不同砂轮磨削性能对内圆切入磨削加工质量具有重要影响，为了实现在线监测内圆磨削加工过程中不同砂轮在相同实验参数条件下进行磨削时的磨削性能，提出了一种基于粒子群优化BP神经网络的不同砂轮磨削性能监测模型。首先，对采集的声发射信号、功率信号、振动信号、位移信号以及电流信号的特征参数进行特征提取；然后，根据各传感器的特征值数据样本及粒子群优化算法对BP神经网络的全局寻优功能，采用粒子群算法优化BP神经网络初始权值和阈值，建立了POS-BP在线监测模型对不同砂轮磨削性能进行精准监测；最后，结合实验数据将BP神经网络模型与POS-BP模型进行分析对比，表明了POS-BP监测模型比BP神经网络模型监测精度更高，能够有效监测不同砂轮的磨削性能状态。

Abstract: According to different grinding wheel grinding performance internal circle cut into the grinding quality has an important influence, in order to realize on-line monitoring of the grinding perfor-mance of different grinding wheels when they are grinding under the condition of the same exper-imental parameters in the process of internal circular cutting grinding, a method based on Particle swarm optimization BP neural network for monitoring the grinding performance of different grinding wheels is proposed. Firstly, the feature parameters of acoustic emission signal, power sig-nal, vibration signal, displacement signal and current signal are extracted. Then, according to the eigenvalue data samples of each sensor and the global optimization function of BP neural network by particle swarm optimization algorithm, the initial weights and thresholds of BP neural network were optimized by particle swarm optimization algorithm, and the POS-BP online monitoring model was established to accurately monitor the grinding performance of different grinding wheels. Final-ly, combined with the experimental data, BP neural network model and POS-BP model were ana-lyzed and compared, indicating that the monitoring accuracy of POS-BP model is higher than that of BP neural network model, and it can effectively monitor the grinding performance of different grinding wheels.