Online stability boundary drifting prediction in milling process: An incremental learning approach

Yu, Yu-Yue; Zhang, Dong; Zhang, Xiaoming; Peng, Xiaobo; Ding, Han

doi:10.1016/j.ymssp.2022.109062

Cited by 12 publications

(2 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concept drift can happen over time when the definition of an activity class previously learned might change in the future data streams when the newer models are trained from the streaming data. In the manufacturing setting, maintaining and improving machining efficiency is directly related to the quality of manufacturing end products [116]. Yu et al studied process prediction in the aspect of milling stability and the effect of damping caused by tool wear in the manufacturing setting.…”

Section: Process Prediction and Operator Trainingmentioning

confidence: 99%

A Survey of Incremental Deep Learning for Defect Detection in Manufacturing

Mohandas,

Southern,

O’Connell

et al. 2024

BDCC

View full text Add to dashboard Cite

Deep learning based visual cognition has greatly improved the accuracy of defect detection, reducing processing times and increasing product throughput across a variety of manufacturing use cases. There is however a continuing need for rigorous procedures to dynamically update model-based detection methods that use sequential streaming during the training phase. This paper reviews how new process, training or validation information is rigorously incorporated in real time when detection exceptions arise during inspection. In particular, consideration is given to how new tasks, classes or decision pathways are added to existing models or datasets in a controlled fashion. An analysis of studies from the incremental learning literature is presented, where the emphasis is on the mitigation of process complexity challenges such as, catastrophic forgetting. Further, practical implementation issues that are known to affect the complexity of deep learning model architecture, including memory allocation for incoming sequential data or incremental learning accuracy, is considered. The paper highlights case study results and methods that have been used to successfully mitigate such real-time manufacturing challenges.

show abstract

Section: Process Prediction and Operator Trainingmentioning

confidence: 99%

A Survey of Incremental Deep Learning for Defect Detection in Manufacturing

Mohandas,

Southern,

O’Connell

et al. 2024

BDCC

View full text Add to dashboard Cite

show abstract

“…However, machining chatter and dimensional error caused by the problem of low rigidity occur in the milling of a thin-walled workpiece, which can affect the surface quality, machining productivity, and tool life [ 4 , 5 , 6 ]. In the milling of thin-walled workpieces, the methods of milling stability prediction are extensively investigated for avoiding chatter [ 7 , 8 , 9 ]. Generally, accurate stability lobe diagrams calculated by solving a time period delay differential equation are critical for milling stability [ 10 , 11 , 12 ].…”

Section: Introductionmentioning

confidence: 99%

Output-Only Time-Varying Modal Parameter Identification Method Based on the TARMAX Model for the Milling of a Thin-Walled Workpiece

Yan

et al. 2022

Micromachines

View full text Add to dashboard Cite

The process parameters chosen for high-performance machining in the milling of a thin-walled workpiece are determined by a stability prediction model, which needs accurate modal parameters of the machining system. However, the in-process modal parameters are different from the offline modal parameters and are difficult to precisely obtain due to material removal. To address this problem, an accurate time-dependent autoregressive moving average with an exogenous input (TARMAX) method is proposed for the identification of the modal parameters in the milling of a thin-walled workpiece. In this process, a TARMAX model considering external force excitation is constructed to characterize the actual condition in the milling of a thin-walled workpiece. Then, recursive method and sliding window recursive method are used to identify TARMAX model parameters under time-varying cutting conditions. Subsequently, a three-degree of freedom (3-DOF) time-varying structure numerical model under theoretical milling forces and white-noise excitation is established, and the computational results show that the predicted natural frequencies using the proposed method are in close agreement with the simulated values. Finally, several experiments are designed and carried out to validate the effectiveness of the proposed method. The experimental results show that the predicted accuracy of the proposed method using actual cutting forces is 95.68%. Good agreement has been drawn in the numerical simulation and machining experiments. Our further research objectives will focus on the prediction of the damping ratios, modal stiffness, and modal mass.

show abstract

Incremental learning of LSTM-autoencoder anomaly detection in three-axis CNC machines

Li,

Bedi

et al. 2023

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Online stability boundary drifting prediction in milling process: An incremental learning approach

Cited by 12 publications

References 50 publications

A Survey of Incremental Deep Learning for Defect Detection in Manufacturing

A Survey of Incremental Deep Learning for Defect Detection in Manufacturing

Output-Only Time-Varying Modal Parameter Identification Method Based on the TARMAX Model for the Milling of a Thin-Walled Workpiece

Incremental learning of LSTM-autoencoder anomaly detection in three-axis CNC machines

Contact Info

Product

Resources

About