Running-in real-time wear generation under vary working condition based on Gaussian process regression approximation

Nugraha, Renaldy Dwi; Chen, Shi; Yin, Nian; Wu, Tingting; Zhang, Zhinan

doi:10.1016/j.measurement.2021.109599

Cited by 9 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Derived from the Bayesian framework, GPR can quantify the prediction uncertainty in a principled way due to its probabilistic inference. In particular, the computational complexity increases in the form of cubic power in GPR, so it is regarded as more suitable for dealing with data sets with small-sized samples [33,34]. This section expounds the basic principles of GPR technique, followed by a brief description to the process of GPR model.…”

Section: Methodsmentioning

confidence: 99%

Application of cutting power in tool condition monitoring and wear prediction based on Gaussian process regression under variable cutting parameters

Qiang¹,

Shi²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Tool wear is inevitable in actual manufacturing, especially in extreme processing conditions for milling difficult-to-cut materials. With the degradation of cutting performance, the undesirable tool status could trigger instability in machining process that causes negative effect on machined surface and dimension accuracy of the precision components. Therefore, tool condition monitoring for machining process is imperative. With distinctive characteristics on easy acquisition and non-interference in machining process, the power consumption of machine tool has been proved to be a reliable indicator for reflecting the changes of cutting process in industry. Thus, the present study proposes a novel method for monitoring tool condition using net cutting power consumption. The result indicates that the developed approach performs better than traditional approach which uses original total power to predict tool wear. This can be attributed to the changes of net cutting power consumption is more relevant with tool wear evolution. Furthermore, predicting tool wear under variable cutting parameters is achieved using Gaussian process regression, because it has good generalization performance and also explains the uncertainty of prediction results in the form of probability. This study reveals that low-cost sensor like power meter, can be used as an important supplement to monitor tool condition in the industry, and also provides a research basis for predicting tool wear under different cutting conditions.

show abstract

Section: Methodsmentioning

confidence: 99%

Application of cutting power in tool condition monitoring and wear prediction based on Gaussian process regression under variable cutting parameters

Qiang¹,

Shi²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Wear particles are the transmitter of wear information, and they have recorded the local wear status and dominant operating status of friction pairs [1][2][3]. Analytical ferrography can extract comprehensive particle features, including the shape, size, and type [4], for evaluating the wear state and wear mechanism of mechanical equipment.…”

Section: Introductionmentioning

confidence: 99%

Optimized Mask-RCNN model for particle chain segmentation based on improved online ferrograph sensor

Wang,

Wan,

et al. 2023

Friction

Self Cite

View full text Add to dashboard Cite

Ferrograph-based wear debris analysis (WDA) provides significant information for wear fault analysis of mechanical equipment. After decades of offline application, this conventional technology is being driven by the online ferrograph sensor for real-time wear state monitoring. However, online ferrography has been greatly limited by the low imaging quality and segmentation accuracy of particle chains when analyzing degraded lubricant oils in practical applications. To address this issue, an integrated optimization method is developed that focuses on two aspects: the structural re-design of the online ferrograph sensor and the intelligent segmentation of particle chains. For enhancing the imaging quality of wear particles, the magnetic pole of the online ferrograph sensor is optimized to enable the imaging system directly observe wear particles without penetrating oils. Furthermore, a light source simulation model is established based on the light intensity distribution theory, and the LED installation parameters are determined for particle illumination uniformity in the online ferrograph sensor. On this basis, a Mask-RCNN-based segmentation model of particle chains is constructed by specifically establishing the region of interest (ROI) generation layer and the ROI align layer for the irregular particle morphology. With these measures, a new online ferrograph sensor is designed to enhance the image acquisition and information extraction of wear particles. For verification, the developed sensor is tested to collect particle images from different degraded oils, and the images are further handled with the Mask-RCNN-based model for particle feature extraction. Experimental results reveal that the optimized online ferrography can capture clear particle images even in highly-degraded lubricant oils, and the illumination uniformity reaches 90% in its imaging field. Most importantly, the statistical accuracy of wear particles has been improved from 67.2% to 94.1%.

show abstract

Application of cutting power consumption in tool condition monitoring and wear prediction based on Gaussian process regression under variable cutting parameters

Qiang

Shi

Liu

et al. 2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Running-in real-time wear generation under vary working condition based on Gaussian process regression approximation

Cited by 9 publications

References 26 publications

Application of cutting power in tool condition monitoring and wear prediction based on Gaussian process regression under variable cutting parameters

Application of cutting power in tool condition monitoring and wear prediction based on Gaussian process regression under variable cutting parameters

Optimized Mask-RCNN model for particle chain segmentation based on improved online ferrograph sensor

Application of cutting power consumption in tool condition monitoring and wear prediction based on Gaussian process regression under variable cutting parameters

Contact Info

Product

Resources

About