摘要
基于铣削加工过程中的电流、振动、声发射等信号,建立了基于皮尔逊相关系数(PCC)和长短期记忆人工神经网络(LSTM)的刀具磨损预测模型。模型充分利用PCC的降维优势以及LSTM的时间序列预测优势,实现刀具磨损预测精度与预测效率的协调统一。实验结果表明,该模型可以实现刀具磨损状态的快速、精确预测,对铣削加工质量的提升具有重要意义。
A tool wear prediction model based on Pearson correlation coefficient(PCC)and long-and short-term memory artificial neural network(LSTM)is established based on current,vibration and acoustic emission signals in milling process.The model makes full use of the advantages of dimension reduction of PCC and time series prediction of LSTM to achieve the coordination and unification of tool wear prediction accuracy and prediction efficiency.The experimental results show that this model can realize the rapid and accurate prediction of tool wear state,which is of great significance for the improvement of milling quality.
作者
李阳光
冯都忠
季海晨
赵君怡
Li Yangguang;Feng Duzhong;Ji Haichen;Zhao Junyi(College of Mechanical and Electrical Engineering,Hohai University,Jiangsu Changzhou,213002,China)
出处
《机械设计与制造工程》
2023年第3期73-77,共5页
Machine Design and Manufacturing Engineering
关键词
刀具磨损
磨损状态监测
磨损量预测
皮尔逊相关系数
长短期记忆人工神经网络
tool wear
wear condition monitoring
wear prediction
Pearson correlation coefficient
long and short term memory artificial neural network
