Milling chatter detection by multi-feature fusion and Adaboost-SVM

Wan, Shaoke; Li, Xiaohu; Yin, Yanjing; Hong, Jun

doi:10.1016/j.ymssp.2021.107671

Cited by 75 publications

(20 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al 100 adopted the Multi Class Support Vector Machine (MC-SVM) model, which made up for the poor classification accuracy of LSVM. Wan et al 101 integrated multiple SVM weak classifiers through the Adaboost algorithm to form Adaboost-SVM, a strong classifier with better performance, avoids the problem of falling chatter classification accuracy due to sample label errors. The input vector of identifies the machining state.…”

Section: Chatter Identificationmentioning

confidence: 99%

Prediction, detection, and suppression of regenerative chatter in milling

Liang

Liu

et al. 2022

Advances in Mechanical Engineering

View full text Add to dashboard Cite

In metal cutting processing, especially in the processing of low-rigidity workpieces, chatter is a key factor affecting many aspects such as surface quality, processing efficiency and tool life. The academic research on chatter mainly focuses on three directions: chatter prediction, real-time detecting, and chatter suppression. With the continuous development of machining toward intelligence, the hot spots and trends of chatter research are also constantly changing. Therefore, an in-depth and systematic summary of the current situation of chatter research is urgently needed. On this basis, it is of great significance to realize the prediction of the hot spots and trends of chatter research. This article summarizes the research status from three aspects of chatter prediction, detecting and suppression, and points out the advantages and limitations of current chatter research. After in-depth discussion, this article also looks forward to the trend of chatter research. The hot spots of chatter research will focus on the following points: (1) Chatter research methods and means based on data-driven. (2) Integrated data collection, processing and decision-making methods. (3) Chatter detecting unit and chatter suppression unit are integrated in the smart spindle. (4) The chatter mechanism and detecting research of robot milling.

show abstract

Section: Chatter Identificationmentioning

confidence: 99%

Prediction, detection, and suppression of regenerative chatter in milling

Liang

Liu

et al. 2022

Advances in Mechanical Engineering

View full text Add to dashboard Cite

show abstract

“…SVM (Peng et al, 2015;Wan et al, 2021) is a supervised machine learning method that is used largely for classification, but also prediction. Like ANNs, SVMs infer a function from labeled training data consisting of a set of training examples of paired inputs and outputs.…”

Section: Support Vector Machine (Svm)mentioning

confidence: 99%

Stability modeling for chatter avoidance in self-aware machining: an application of physics-guided machine learning

Greis

Nogueira²,

Bhattacharya³

et al. 2022

J Intell Manuf

View full text Add to dashboard Cite

Physics-guided machine learning (PGML) offers a new approach to stability modeling during machining that leverages experimental data generated during the machining process while incorporating decades of theoretical process modeling efforts. This approach addresses specific limitations of machine learning models and physics-based models individually. Data-driven machine learning models are typically black box models that do not provide deep insight into the underlying physics and do not reflect physical constraints for the modeled system, sometimes yielding solutions that violate physical laws or operational constraints. In addition, acquiring the large amounts of manufacturing data needed for machine learning modeling can be costly. On the other hand, many physical processes are not completely understood by domain experts and have a high degree of uncertainty. Physics-based models must make simplifying assumptions that can compromise prediction accuracy. This research explores whether data generated by an uncertain physics-based milling stability model that is used to train a physics-guided machine learning stability model, and then updated with measured data, domain knowledge, and theory-based knowledge provides a useful approximation to the unknown true stability model for a specific set of factory operating conditions. Four novel strategies for updating the machine learning model with experimental data are explored. These updating strategies differ in their assumptions about and implementation of the type of physics-based knowledge included in the PGML model. Using a simulation experiment, these strategies achieve useful approximations of the underlying true stability model while reducing the number of experimental measurements required for model update.

show abstract

“…And force sensor and displacement sensor might be costly and difficult for installation. In order to extract more chatter feathers, Wan et al [12] extracted manually selected 8 features in time domain and frequency domain and 8 features automatically extracted by features extracted by stacked-denoising autoencoder, highly improving the accuracy and reliability of milling chatter identification based on Adaboost-SVM.…”

Section: Introductionmentioning

confidence: 99%

Chatter detection in milling process based on the combination of wavelet packet transform and PSO-SVM

Zheng

Chen

Jiao

2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Chatter has become the mainly limiting factor in the development of rapid and stable machining of machine tools, which seriously impacts on surface quality and dimensional accuracy of the finished workpiece. In this paper, a novel method of chatter recognition was proposed based on the combination of wavelet packet transform (WPT) and PSO-SVM in milling. The collected vibration signal was pre-processed by wavelet packet transform (WPT), and the wavelet packets with rich chatter information were selected and reconstructed. The selected wavelet packets can reduce the redundant noise and useless information. a combination of 10 time-domain and 4 frequency-domain feature parameters were obtained through calculating the reconstructed vibration signals. Compared to three methods of k-fold cross validation (k-CV), genetic algorithm (GA) and particle swarm optimization (PSO) to optimize the input parameters of SVM, the experiment results were shown that the PSO algorithm has is characterized by high accuracy. The proposed approach can recognize the stable, chatter and transition states more accurately than the other traditional approaches.

show abstract

Milling chatter detection by multi-feature fusion and Adaboost-SVM

Cited by 75 publications

References 42 publications

Prediction, detection, and suppression of regenerative chatter in milling

Prediction, detection, and suppression of regenerative chatter in milling

Stability modeling for chatter avoidance in self-aware machining: an application of physics-guided machine learning

Chatter detection in milling process based on the combination of wavelet packet transform and PSO-SVM

Contact Info

Product

Resources

About