An End-to-End Deep Learning Model to Predict Surface Roughness

Lv, Jintao; Huang, Xi-ning; Zhu, Junjiang; Zhaojie, Zhang

doi:10.1007/978-981-16-7213-2_58

Cited by 4 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For model input, spindle current, vibration, and acoustic emission signals were selected as process signals considering the aspects of grinding wheel rotation, workpiece supporting, and material removal. Similarly, Lv et al [21] suggested an end-to-end deep learning prediction model for improving surface roughness prediction using acceleration sensors arranged on spindles, fixtures, and metal blocks to obtain vibration signals. First, the 1D-CNN model was used to automatically extract the vibration signal features and train the data; second, an LSTM model suitable for time-series-sensitive signal training was used for the 1D-CNN training data and continued training; and finally, the fully connected classification performed predictive analysis.…”

Section: Related Workmentioning

confidence: 99%

Surface Roughness Prediction in Ultra-Precision Milling: An Extreme Learning Machine Method with Data Fusion

Shang,

Wang,

Liang

et al. 2023

Micromachines

View full text Add to dashboard Cite

This paper pioneers the use of the extreme learning machine (ELM) approach for surface roughness prediction in ultra-precision milling, leveraging the excellent fitting ability with small datasets and the fast learning speed of the extreme learning machine method. By providing abundant machining information, the machining parameters and force signal data are fused on the feature level to further improve ELM prediction accuracy. An ultra-precision milling experiment was designed and conducted to verify our proposed data-fusion-based ELM method. The results show that the ELM with data fusion outperforms other state-of-art methods in surface roughness prediction. It achieves an impressively low mean absolute percentage error of 1.6% while requiring a mere 18 s for model training.

show abstract

Section: Related Workmentioning

confidence: 99%

Surface Roughness Prediction in Ultra-Precision Milling: An Extreme Learning Machine Method with Data Fusion

Shang,

Wang,

Liang

et al. 2023

Micromachines

View full text Add to dashboard Cite

show abstract

“…Along with the variant of resnet [27] known as resnet18, resnet34, and res-net50, other commonly used CNN models include Vgg16 [28] and Xception [29]. CNN is an end-to-end network [30] that learns multi-scale feature information of images by stacking input, convolutional, pooling, fully connected, and output layers together to transform the features of the images into millions or even tens of millions of parameters. The input image is continuously convolved with these parameters, in which the multi-scale feature information of the image is continuously extracted and summarized, and the result is finally output after the output layer.…”

Section: Cnn-based Roughness Measurement Technologymentioning

confidence: 99%

Automatic non-contact grinding surface roughness measurement based on multi-focused sequence images and CNN

Shi,

Li,

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Microscopic images of surfaces can be used for non-contact roughness measurement by visual methods. However, the images are usually acquired manually and need to be as sharp as possible, which limits the general application of the method. This manuscript provides an automatic roughness measurement method that can apply to automatic industrial sites. This method first automatically acquires the sharpest image and then feeds the image into a convolutional neural network (CNN) model for roughness measurement. In this method, the weighted window enhanced sharpness evaluation algorithm based on the sharpness evaluation function is proposed to automatically extract the sharpest image. Then, a CNN model, CFEN, suitable for the roughness measurement task was designed and pre-trained. The results demonstrate that the measurement accuracy of the method reaches 91.25% and the time is within a few seconds. It is proved that the method has high accuracy and efficiency and is feasible in practical applications.

show abstract

“…Guo et al (2021) propose a hybrid feature selection method that selects features based on their correlation to surface roughness, as well as hardware and time costs. Lv et al (2021) propose an end-to-end deep learning prediction model using a sequential deep learning framework and a LSTM network. Cooper et al (2023) developed a conditional generative adversarial network (CGAN) to synthesize power signals associated with different combinations of process parameters, and the synthesized signal is then used to enhance the measurement signal and develop CNNs to predict machined surface roughness.…”

Section: Introductionmentioning

confidence: 99%

Prediction of surface roughness using deep learning and data augmentation

Guo,

Wei,

Han

et al. 2024

JIMSE

View full text Add to dashboard Cite

PurposeSurface roughness has a serious impact on the fatigue strength, wear resistance and life of mechanical products. Realizing the evolution of surface quality through theoretical modeling takes a lot of effort. To predict the surface roughness of milling processing, this paper aims to construct a neural network based on deep learning and data augmentation.Design/methodology/approachThis study proposes a method consisting of three steps. Firstly, the machine tool multisource data acquisition platform is established, which combines sensor monitoring with machine tool communication to collect processing signals. Secondly, the feature parameters are extracted to reduce the interference and improve the model generalization ability. Thirdly, for different expectations, the parameters of the deep belief network (DBN) model are optimized by the tent-SSA algorithm to achieve more accurate roughness classification and regression prediction.FindingsThe adaptive synthetic sampling (ADASYN) algorithm can improve the classification prediction accuracy of DBN from 80.67% to 94.23%. After the DBN parameters were optimized by Tent-SSA, the roughness prediction accuracy was significantly improved. For the classification model, the prediction accuracy is improved by 5.77% based on ADASYN optimization. For regression models, different objective functions can be set according to production requirements, such as root-mean-square error (RMSE) or MaxAE, and the error is reduced by more than 40% compared to the original model.Originality/valueA roughness prediction model based on multiple monitoring signals is proposed, which reduces the dependence on the acquisition of environmental variables and enhances the model's applicability. Furthermore, with the ADASYN algorithm, the Tent-SSA intelligent optimization algorithm is introduced to optimize the hyperparameters of the DBN model and improve the optimization performance.

show abstract

An End-to-End Deep Learning Model to Predict Surface Roughness

Cited by 4 publications

References 17 publications

Surface Roughness Prediction in Ultra-Precision Milling: An Extreme Learning Machine Method with Data Fusion

Surface Roughness Prediction in Ultra-Precision Milling: An Extreme Learning Machine Method with Data Fusion

Automatic non-contact grinding surface roughness measurement based on multi-focused sequence images and CNN

Prediction of surface roughness using deep learning and data augmentation

Contact Info

Product

Resources

About