Improving generalisation and accuracy of on-line milling chatter detection via a novel hybrid deep convolutional neural network

Zhang, Pengfei; Gao, Dong; Hong, Dongbo; Lü, Yong; Wu, Qian; Zan, Shusong; Liao, Zhirong

doi:10.1016/j.ymssp.2023.110241

Cited by 18 publications

(2 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The stability of the method may be improved by setting up two base classifier banks: Memory bank MS and recall bank ES to keep valuable base classifiers, where MS saves all the base classifiers with weak present classification effect but strong history classification effect; In order to The MAE algorithm's learning process still has the following issues, though: For instance, the majority of the high-performance computing node status data acquired is data from nodes operating normally; failure data only makes up a minor portion of this data. To put it another way, a base classifier learned with this kind of data block will perform poorly for subsequent fault prediction because the state data of high-performance computer nodes used for fault prediction has a class imbalance phenomenon that may cause the current learning data block to contain only normal state data and no upcoming failure data [33][34][35].…”

Section: Experiments and Analysis Data Flow Classification Is Basical...mentioning

confidence: 99%

Computer Hardware Fault Detection based on Machine Learning

2023

SCPE

View full text Add to dashboard Cite

In order to solve the computer fault detection problem of machine learning, the author proposes a computer hardware fault detection problem based on machine learning. The method combines mutual information and class separability to analyze their relationship, which improves classification accuracy. This study presents an adaptive machine learning technique for the adaptive fusion of data from multiple sources. In addition, the mCRC algorithm seeks for the optimal feature subset using the enhanced forward floating search method, thereby overcoming the limitation that the mRMR algorithm does not specify how to determine the final feature subset. The classification accuracy of the mCRC algorithm is approximately 1% better than that of the mRMR algorithm, and the size of the final feature subset of the mCRC algorithm is 22% smaller than that of the final subset of the mRMR algorithm. Conclusion: the ReMAE algorithm has a higher rate of accurate failure prediction.

show abstract

Section: Experiments and Analysis Data Flow Classification Is Basical...mentioning

confidence: 99%

Computer Hardware Fault Detection based on Machine Learning

2023

SCPE

View full text Add to dashboard Cite

show abstract

“…This approach has recently started gaining traction in manufacturing, predominantly in CNC milling. Zhang et al [ 41 ] employed CNNs with 1D-adapted inception modules and residual blocks for chatter identification based on raw cutting force signals. Lu et al [ 42 ] developed vibration-based 1D CNN models to predict chatter during milling of thin- walled parts.…”

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Networks for Raw Signal Classification in CNC Turning Process Monitoring

Stathatos,

Tzimas,

Benardos

et al. 2024

Sensors

View full text Add to dashboard Cite

This study addresses the need for advanced machine learning-based process monitoring in smart manufacturing. A methodology is developed for near-real-time part quality prediction based on process-related data obtained from a CNC turning center. Instead of the manual feature extraction methods typically employed in signal processing, a novel one-dimensional convolutional architecture allows the trained model to autonomously extract pertinent features directly from the raw signals. Several signal channels are utilized, including vibrations, motor speeds, and motor torques. Three quality indicators—average roughness, peak-to-valley roughness, and diameter deviation—are monitored using a single model, resulting in a compact and efficient classifier. Training data are obtained via a small number of experiments designed to induce variability in the quality metrics by varying feed, cutting speed, and depth of cut. A sliding window technique augments the dataset and allows the model to seamlessly operate over the entire process. This is further facilitated by the model’s ability to distinguish between cutting and non-cutting phases. The base model is evaluated via k-fold cross validation and achieves average F1 scores above 0.97 for all outputs. Consistent performance is exhibited by additional instances trained under various combinations of design parameters, validating the robustness of the proposed methodology.

show abstract