A Novel Tool (Single-Flute) Condition Monitoring Method for End Milling Process Based on Intelligent Processing of Milling Force Data by Machine Learning Algorithms

Yang, Yan; Hao, Bijun; Hao, Xiaohong; Li, Liang; Chen, Ni; Xu, Tao; Aqib, Khan M.; He, Ning

doi:10.1007/s12541-020-00388-8

Cited by 23 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the basis of the literature review, the physical phenomena that are most often used as the source of diagnostic signals were distinguished. They are: temperature [26], vibrations [27], forces [28][29][30] and acoustic emission (AE) [31][32] or audible energy sound [33]. These are the values that indirectly an indicate the condition of the machining processes.…”

Section: Introductionmentioning

confidence: 99%

Selected aspects of diagnosing material removal machining processes state

et al. 2021

View full text Add to dashboard Cite

The article presents the results of works on the analysis of the possibility of using force measurements to determine the state of the machining process, both in relation to the phenomena occurring during machining and the workpiece itself compared to acoustic emission signal (AE). The research and analyzes were carried out for the commonly used material removal processes of objects; turning, milling, grinding and drilling. Various materials were processed - metal alloy Hardox 400 as well as fiber composite materials (GFRP - Glass Fiber Reinforced Polymer) and polymer construction material RenShape® BM5035 with various structures. As a result of the conducted analyzes, it was determined that the forces generated in the machine tool-holder-workpiece-tool layout can constitute a good diagnostic signal, on the basis of which it is possible to conclude about the state of the process.

show abstract

Section: Introductionmentioning

confidence: 99%

Selected aspects of diagnosing material removal machining processes state

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The regularization parameter C determines the trade-off between training error and testing error, with high values of C favouring complex models to avoid underfitting, while low values support simpler models to avoid overfitting [31]. On the other hand, the hyperparameter gamma controls the width of the Gaussian kernel, with small values leading to wider kernel functions and smoother decision boundaries, and large values resulting in narrower kernel functions and more complex decision boundaries [32].…”

Section: 𝜎 = √ 1 (2𝛾)mentioning

confidence: 99%

Classification of Acceleration Signal in Machining Process for Surface Roughness Identification using Tuned Support Vector Mechanics

Jamil,

Rosyidi,

Yusoff

2023

Preprint

View full text Add to dashboard Cite

In industrial applications, accurate surface roughness identification and characterization are essential for ensuring product quality, dependability, and performance. The suggested technique efficiently processes and examines the acceleration data of a cutting operation for surface quality detection using customized Support Vector Mechanics (SVM). The suggested method extracts pertinent data from the acceleration signals using a number of feature extraction approaches. Incorporating the collected features, the improved SVM model creates a strong classification framework that is capable of precisely recognizing various degrees of surface roughness. An extensive dataset made up of acceleration signals from various machining operations and surface roughness conditions is used to assess the performance of the proposed approach. Using this dataset, the hyper-tuning of the SVM model is trained and tested to determine its classification precision and generalizability. The experimental findings show that, when compared to conventional classification methods, the customized SVM model performs better. The suggested method regularly demonstrates durability and reliability while achieving excellent classification accuracy across a range of surface roughness levels. The suggested method provides a workable and effective solution for automating surface roughness identification, enabling in-process quality control and real-time monitoring.

show abstract

“…Linear algorithms transform a high-dimensional feature space into a lower dimensional feature space with a linear combination of the original dimensions. Principal component analysis (PCA) [ 61 , 194 , 195 ], singular value decomposition (SVD) [ 196 ], linear discriminant analysis (LDA) [ 197 ], Fisher discriminant analysis (FDA) [ 198 ], Fisher discriminant ratio (FDR) [ 199 ], factor analysis (FA) [ 200 ], and independent component analysis (ICA) [ 201 ] are examples of linear feature transformation algorithms. On the other hand, nonlinear algorithms, such as kernel PCA (KPCA) [ 202 , 203 ], probabilistic kernel FA (PKFA) [ 200 ], kernel Fisher discriminant analysis FDA (KFDA) [ 204 ], and isometric mapping (ISOMAP) [ 205 ], nonlinearly transform a high-dimensional feature space into a lower space.…”

Section: Signal Processing Techniquesmentioning

confidence: 99%

Tool Condition Monitoring for High-Performance Machining Systems—A Review

Mohamed

Hassan

M’Saoubi³

et al. 2022

Sensors

View full text Add to dashboard Cite

In the era of the “Industry 4.0” revolution, self-adjusting and unmanned machining systems have gained considerable interest in high-value manufacturing industries to cope with the growing demand for high productivity, standardized part quality, and reduced cost. Tool condition monitoring (TCM) systems pave the way for automated machining through monitoring the state of the cutting tool, including the occurrences of wear, cracks, chipping, and breakage, with the aim of improving the efficiency and economics of the machining process. This article reviews the state-of-the-art TCM system components, namely, means of sensing, data acquisition, signal conditioning and processing, and monitoring models, found in the recent open literature. Special attention is given to analyzing the advantages and limitations of current practices in developing wireless tool-embedded sensor nodes, which enable seamless implementation and Industrial Internet of Things (IIOT) readiness of TCM systems. Additionally, a comprehensive review of the selection of dimensionality reduction techniques is provided due to the lack of clear recommendations and shortcomings of various techniques developed in the literature. Recent attempts for TCM systems’ generalization and enhancement are discussed, along with recommendations for possible future research avenues to improve TCM systems accuracy, reliability, functionality, and integration.

show abstract

A Novel Tool (Single-Flute) Condition Monitoring Method for End Milling Process Based on Intelligent Processing of Milling Force Data by Machine Learning Algorithms

Cited by 23 publications

References 22 publications

Selected aspects of diagnosing material removal machining processes state

Selected aspects of diagnosing material removal machining processes state

Classification of Acceleration Signal in Machining Process for Surface Roughness Identification using Tuned Support Vector Mechanics

Tool Condition Monitoring for High-Performance Machining Systems—A Review

Contact Info

Product

Resources

About