首页|基于改进LSTM-AdaBoost的铣刀磨损量预测

基于改进LSTM-AdaBoost的铣刀磨损量预测

扫码查看
原文链接
  • 万方数据
  • 维普
针对铣刀磨损量预测时精度低的问题，提出一种基于黑寡妇算法(BWO)优化的长短期记忆神经网络(LSTM)与AdaBoost集成学习算法相结合的铣刀磨损量预测方法。在铣刀磨损振动信号中提取时域、频域以及时频域多域特征。通过BWO算法优化LSTM的核心参数，并将优化后的LSTM网络与AdaBoost算法进行结合，构建铣刀磨损量预测模型。最后用PHM Society 2010铣刀全寿命周期的振动数据进行实验。研究结果表明:所提方法能够有效地预测出铣刀磨损量变化值，优化后模型的平均绝对误差百分比为3。436％、均方根误差为6。471、决定系数R2为0。935。该方法能够获得准确率更高的铣刀磨损量预测值，预测效率更高。
Improved LSTM-AdaBoost Based Milling Tool Wear Prediction
Aiming at the problem of low accuracy when predicting milling tool wear,a milling tool wear prediction method was pro-posed based on a long short-term memory neural network(LSTM)optimized by the black widow algorithm(BWO)combined with the AdaBoost integrated learning algorithm.The time domain,frequency domain and time-frequency domain multi-domain features were ex-tracted from the milling tool wear vibration signal.The core parameters of the LSTM were optimized by the BWO algorithm,and the opti-mized LSTM network was combined with the AdaBoost algorithm to build a milling tool wear prediction model.Finally,experiments were conducted with the whole life cycle vibration data of the milling tool of PHM Society 2010.The results show that the proposed method can effectively predict the variation of milling tool wear,and the mean absolute percentage error of the optimized model is 3.436％,root mean squared error is 6.471 and R2 is 0.935 when compared with the pre-optimized model.This method can obtain the prediction value of milling cutter wear with higher accuracy and higher prediction efficiency.

milling cutter wearwear volume predictionblack widow optimization algorithmlong short-term memory(LSTM)AdaBoost algorithm

赵小惠、杨文彬、胡胜、郇凯旋、谭琦

展开 >

西安工程大学机电工程学院,陕西西安 710048

铣刀磨损 磨损量预测 黑寡妇算法 长短期记忆神经网络 AdaBoost算法

国家自然科学基金青年科学基金项目陕西省科技计划项目陕西省教育厅专项科研计划项目陕西省社科联重大项目

720011662022JQ-72118JK032420ZD195-95

2024

10.3969/j.issn.1001-3881.2024.10.003

机床与液压
中国机械工程学会 广州机械科学研究院有限公司

机床与液压

CSTPCD北大核心
影响因子：0.32
ISSN：1001-3881
年,卷(期)：2024.52(10)