Rong Zhiming, Li Yuxiong, Wu Li, Zhang Chong, Li Jialin
Applied Technology College, Dalian Ocean University, Dalian 116023, China.
School of Mechanical Engineering, Dalian Jiaotong University, Dalian 116028, China.
Sensors (Basel). 2024 May 24;24(11):3394. doi: 10.3390/s24113394.
Tool wear prediction is of great significance in industrial production. Current tool wear prediction methods mainly rely on the indirect estimation of machine learning, which focuses more on estimating the current tool wear state and lacks effective quantification of random uncertainty factors. To overcome these shortcomings, this paper proposes a novel method for predicting cutting tool wear. In the offline phase, the multiple degradation features were modeled using the Brownian motion stochastic process and a SVR model was trained for mapping the features and the tool wear values. In the online phase, the Bayesian inference was used to update the random parameters of the feature degradation model, and the future trend of the features was estimated using simulation samples. The estimation results were input into the SVR model to achieve in-advance prediction of the cutting tool wear in the form of distribution densities. An experimental tool wear dataset was used to verify the effectiveness of the proposed method. The results demonstrate that the method shows superiority in prediction accuracy and stability.
刀具磨损预测在工业生产中具有重要意义。当前的刀具磨损预测方法主要依赖于机器学习的间接估计，这种方法更多地侧重于估计当前刀具的磨损状态，而缺乏对随机不确定性因素的有效量化。为克服这些缺点，本文提出了一种预测切削刀具磨损的新方法。在离线阶段，使用布朗运动随机过程对多个退化特征进行建模，并训练一个支持向量回归（SVR）模型来映射特征与刀具磨损值。在在线阶段，利用贝叶斯推理更新特征退化模型的随机参数，并使用模拟样本估计特征的未来趋势。将估计结果输入到SVR模型中，以分布密度的形式实现对切削刀具磨损的提前预测。使用一个实验刀具磨损数据集验证了所提方法的有效性。结果表明，该方法在预测精度和稳定性方面表现出优越性。
