Manufacturing Engineering
突变理论指导的混合建模
Catastrophe Theory-Informed Hybrid ModelingA framework combining a random forest classifier with a fully connected neural network to predict chip-splitting states and specific cutting force in thread turning using domain-adversarial training and cusp catastrophe equilibrium surface geometry as a regularizer. / 一种结合随机森林分类器和全连接神经网络，利用域对抗训练和尖点突变平衡面几何作为正则化项，预测车削中断屑状态和比切削力的框架。
- Knowledge type
- 工艺技术
- First proposed or discovered
- 2026
- Proposer
- Liangshan Xiong, Peng Wu, Mingxian Xu, Shaonan Zhang, Baoyi Zhu
- Creator
- 农场主
- Last updated
- 2026-10-30 19:06:23
Sub-knowledge points
Random Forest ClassifierFully Connected Neural NetworkDomain-Adversarial TrainingCusp Catastrophe Geometry
Higher-order knowledge points
No connected node yet
Main parameters and performance indicators
Cusp catastrophe equilibrium surface: Used as a regularizerStratified train/test split: 1001/251MAPE: Mean Absolute Percentage ErrorR2: Coefficient of determinationNormalized RMSE: Root Mean Square Error
Open problems
No unresolved problem recorded yet
Related literature
ranked by community starsCatastrophe Theory-Informed Hybrid Modeling for Chip Splitting State and Specific Cutting Force Prediction in Thread TurningOpen source
Related products and links
No item recorded yet
Creation and modification trail
1 recordsRecord title: Catastrophe Theory-Informed Hybrid Modeling.
Node update feedback
review required