空心钻磨削砂轮状态智能监测方法

• Format: Patent
• Language: Chinese
• Published: 31.03.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIRCHEMICAL OR PHYSICAL PROPERTIES; MEASURING; PHYSICS; TESTING

本发明涉及一种空心钻磨削砂轮状态智能监测方法，首先，传感器安装及信号监测，监测磨削过程中的声发射信号、功率信号和振动信号，再进行信号特征参数提取，提取声发射信号和功率信号的时域参数以及振动信号的高频特征信息作为特征参数，然后对这些特征参数进行归一化处理并提取主要成分作为SA-SVM模型的输入样本，然后，运用模拟退火算法优化支持向量机参数的选择，并对样本进行训练学习；最后，采用SA-SVM模型智能预测，将系统分析结果与砂轮实际磨削状态做对比，判断模型的预测性能。 The invention relates to an intelligent monitoring method for the state of a hollow drill grinding wheel. Firstly, sensors are installed and signals are monitored; an acoustic emission signal, a powersignal and a vibration signal in the grinding process are monitored; signal characteristic parameter extraction is carried out; time domain parameters of the acoustic emission signal and the power signal and high-frequency characteristic information of the vibration signal are extracted as characteristic parameters; the characteristic parameters are normalized, main components are extracted as input samples of an SA-SVM model, selection of support vector machine parameters is optimized by using a simulated annealing algorithm, and training learning is performed on the samples; and fin