Bo Qin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Bo Qin has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Kuo Liu
School of Mechanical Engineering, Dalian University of Technology, Dalian, China
4 shared publications - Yongqing Wang
State Key Laboratory of High-Performance Precision Manufacturing, Dalian University of Technology, Dalian 116024, China
4 shared publications Mengmeng Niu
School of Mechanical Engineering, Dalian University of Technology, Dalian, China
3 shared publications- Mingrui Shen
School of Mechanical Engineering, Dalian University of Technology, Dalian, China
3 shared publications - Lingsheng Han
School of Mechanical Engineering, Dalian University of Technology, No. 2 Linggong Road, Ganjingzi District, Dalian City 116024, Liaoning Province, China
2 shared publications - Haibo Liu
State Key Laboratory of High-Performance Precision Manufacturing, Dalian University of Technology, Dalian 116024, China
1 shared publication
Latest Publications
- 7 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 34 (10) , 7024-7033
A Novel Data Augmentation Method Based on CoralGAN for Prediction of Part Surface Roughness
Deep learning networks can be applied to the field of intelligent prediction of part surface roughness. However, the surface roughness samples of parts have the problems of high collection cost, unbalanced categories, and complicated data distribution, which inevitably limit the application of deep learning network models in the field of intelligent prediction of part surface roughness. To solve these problems, this article proposes a novel data augmentation method based on CoralGAN for prediction of part surface roughness, which introduces the domain adaptive method deep coral function to help optimize the network parameters of the generator of generative adversarial network (GAN). Specifically, the vibration signal collected during processing is converted into frequency spectrum data and input into CoralGAN. The training of the generator is guided by coral loss, that is, the distance between the covariances of the real samples and generated samples features, not just the statistical consistency of the traditional GAN. Experiments have been carried out on the three-axis vertical machining center. Research shows that the proposed method can improve the prediction accuracy of part surface roughness to 95.5%.
- 7 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 34 (10) , 7024-7033
A Novel Data Augmentation Method Based on CoralGAN for Prediction of Part Surface Roughness
Deep learning networks can be applied to the field of intelligent prediction of part surface roughness. However, the surface roughness samples of parts have the problems of high collection cost, unbalanced categories, and complicated data distribution, which inevitably limit the application of deep learning network models in the field of intelligent prediction of part surface roughness. To solve these problems, this article proposes a novel data augmentation method based on CoralGAN for prediction of part surface roughness, which introduces the domain adaptive method deep coral function to help optimize the network parameters of the generator of generative adversarial network (GAN). Specifically, the vibration signal collected during processing is converted into frequency spectrum data and input into CoralGAN. The training of the generator is guided by coral loss, that is, the distance between the covariances of the real samples and generated samples features, not just the statistical consistency of the traditional GAN. Experiments have been carried out on the three-axis vertical machining center. Research shows that the proposed method can improve the prediction accuracy of part surface roughness to 95.5%.
- 21 June 2021
- Published by ASME International
Tool Condition Monitoring Method Based on Generative Adversarial Network for Data Augmentation
In the process of parts processing, due to the real working conditions and data acquisition equipment, the collected working data of tools are actually limited. Meanwhile, the tool usually works in the normal state, so it is prone to cause the problem of unbalanced data set, which restricts the accuracy of tool condition monitoring. Aiming at this problem, this paper proposes a tool condition monitoring method based on generative adversarial network (GAN) for data augmentation. Specifically, first collect original samples data during processing in different tool conditions, then the collected sample data is input into GAN, and the generator of GAN can generate new samples which has similar distribution with original samples from tool condition signals data, finally the real samples and generated samples are combined to train deep learning network to predict tool conditions. Experimental results show that the proposed method can significantly improve the accuracy of tool condition monitoring. This paper compares and visualizes the impact of the training data set on the classification ability of the deep learning network model. In addition, some traditional methods are used for comparison, and F1 measure is introduced to evaluate the quality of the results. The results show that this method is better than the Adaptive Synthetic Sampling (Adasyn), add-noise, and resampling.
- 21 June 2021
- Published by ASME International
Tool Condition Monitoring Method Based on Generative Adversarial Network for Data Augmentation
In the process of parts processing, due to the real working conditions and data acquisition equipment, the collected working data of tools are actually limited. Meanwhile, the tool usually works in the normal state, so it is prone to cause the problem of unbalanced data set, which restricts the accuracy of tool condition monitoring. Aiming at this problem, this paper proposes a tool condition monitoring method based on generative adversarial network (GAN) for data augmentation. Specifically, first collect original samples data during processing in different tool conditions, then the collected sample data is input into GAN, and the generator of GAN can generate new samples which has similar distribution with original samples from tool condition signals data, finally the real samples and generated samples are combined to train deep learning network to predict tool conditions. Experimental results show that the proposed method can significantly improve the accuracy of tool condition monitoring. This paper compares and visualizes the impact of the training data set on the classification ability of the deep learning network model. In addition, some traditional methods are used for comparison, and F1 measure is introduced to evaluate the quality of the results. The results show that this method is better than the Adaptive Synthetic Sampling (Adasyn), add-noise, and resampling.
- 8 June 2021
- Published by ASME International in Journal of Tribology
- Vol. 144 (3)
Theoretical Leakage Equations Towards Liquid-Phase Flow in the Straight-Through Labyrinth Seal
Labyrinth seals are widely applied in turbomachinery for gas and liquid sealing. A series of labyrinth seal leakage equations so far have been proposed for compressible gas and few equations for incompressible liquid. Based on the flow conserving governing equations, this paper originally presents semi-empirical analytic equations of the leakage flow rate and tooth-clearance pressure for liquid-phase flow in the straight-through labyrinth seal. The equations indicate that the leakage and pressure are closely related to the inlet pressure, outlet pressure, seal geometrical parameters, and four empirical coefficients, while no relation to the temperature and compressibility effects compared to the common gas equations. The empirical coefficients include the velocity compensation coefficient, friction coefficient, jet contraction coefficient, and resistance coefficient. Particularly, the velocity compensation coefficient is determined through an optimization by the genetic algorithm, while others are referred from previous research. Ultimately, taking the sealing of deeply subcooled liquid nitrogen within the spindle of the cryogenic cooling machine tool as a case, the accuracy of proposed equations is evaluated under various pressure ratios and geometry conditions using the numerical approach, whose numerical model has been validated by the experimental data in the literature. The results show that errors between calculation and simulation are generally within the limit of ±5%, except for the pressure values at the first two teeth. This work provides a theoretical basis for further studies on the liquid leakage equations in other labyrinth seal types.
- 8 June 2021
- Published by ASME International in Journal of Tribology
- Vol. 144 (3)
Theoretical Leakage Equations Towards Liquid-Phase Flow in the Straight-Through Labyrinth Seal
Labyrinth seals are widely applied in turbomachinery for gas and liquid sealing. A series of labyrinth seal leakage equations so far have been proposed for compressible gas and few equations for incompressible liquid. Based on the flow conserving governing equations, this paper originally presents semi-empirical analytic equations of the leakage flow rate and tooth-clearance pressure for liquid-phase flow in the straight-through labyrinth seal. The equations indicate that the leakage and pressure are closely related to the inlet pressure, outlet pressure, seal geometrical parameters, and four empirical coefficients, while no relation to the temperature and compressibility effects compared to the common gas equations. The empirical coefficients include the velocity compensation coefficient, friction coefficient, jet contraction coefficient, and resistance coefficient. Particularly, the velocity compensation coefficient is determined through an optimization by the genetic algorithm, while others are referred from previous research. Ultimately, taking the sealing of deeply subcooled liquid nitrogen within the spindle of the cryogenic cooling machine tool as a case, the accuracy of proposed equations is evaluated under various pressure ratios and geometry conditions using the numerical approach, whose numerical model has been validated by the experimental data in the literature. The results show that errors between calculation and simulation are generally within the limit of ±5%, except for the pressure values at the first two teeth. This work provides a theoretical basis for further studies on the liquid leakage equations in other labyrinth seal types.
- 24 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 17 (9) , 6023-6033
A New Multitask Learning Method for Tool Wear Condition and Part Surface Quality Prediction
Deep learning has been gradually used in the field of machining condition monitoring. However, at present only single-task prediction can be performed, which results in increased experimental costs, wasted datasets, and repetitive work. In this article, a new multitask learning method based on a deep belief network (DBN) is proposed, which can be used to predict the tool wear condition and part surface quality. The single-task data transmission of the last few hidden layers of the DBN network is improved to multitask parallel data transmission so that the improved DBN can realize multitask learning. The loss function of the multitask learning model is defined as the weighted sum of all single-task loss functions. According to the loss of different tasks in the iteration process, the weight of corresponding tasks can be adjusted automatically. Furthermore, the multitask deep learning method can realize information sharing, suppress overfitting, improve prediction accuracy, and require less computing time. Combined with the abovementioned improvements, a multitask model for tool wear and part surface quality was developed. Experimental verification was performed on a KVC850M three-axis vertical machining center. The results show that the accuracy of the proposed multitask prediction model is 99% for the tool wear prediction and 92.86% for part surface quality prediction.
- 24 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 17 (9) , 6023-6033
A New Multitask Learning Method for Tool Wear Condition and Part Surface Quality Prediction
Deep learning has been gradually used in the field of machining condition monitoring. However, at present only single-task prediction can be performed, which results in increased experimental costs, wasted datasets, and repetitive work. In this article, a new multitask learning method based on a deep belief network (DBN) is proposed, which can be used to predict the tool wear condition and part surface quality. The single-task data transmission of the last few hidden layers of the DBN network is improved to multitask parallel data transmission so that the improved DBN can realize multitask learning. The loss function of the multitask learning model is defined as the weighted sum of all single-task loss functions. According to the loss of different tasks in the iteration process, the weight of corresponding tasks can be adjusted automatically. Furthermore, the multitask deep learning method can realize information sharing, suppress overfitting, improve prediction accuracy, and require less computing time. Combined with the abovementioned improvements, a multitask model for tool wear and part surface quality was developed. Experimental verification was performed on a KVC850M three-axis vertical machining center. The results show that the accuracy of the proposed multitask prediction model is 99% for the tool wear prediction and 92.86% for part surface quality prediction.
- 16 May 2014
- Published by Springer Nature in Acta Mechanica Sinica
- Vol. 30 (3) , 361-369
Experimental investigation of the effect of Reynolds number on flow structures in the wake of a circular parachute canopy
- 16 May 2014
- Published by Springer Nature in Acta Mechanica Sinica
- Vol. 30 (3) , 361-369
Experimental investigation of the effect of Reynolds number on flow structures in the wake of a circular parachute canopy