Changfu Liu

Dr. Changfu Liu

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 January 2017 in The International Journal of Advanced Manufacturing Technology
Verified
Journal Article
Closed access
PDF file
Changfu LiuChangfu Liu
Changfu Liu
LZLida Zhu
Lida Zhu
CNChenbing Ni
Chenbing Ni

3 January 2023 in The International Journal of Advanced Manufacturing Technology
Verified
Journal Article
Open access
PDF file
Bo LiuBo Liu
Bo Liu
Changfu LiuChangfu Liu
Changfu Liu
YZYang Zhou
Yang Zhou
DWDaohai Wang
Daohai Wang
In metal cutting processing, especially in the processing of low-rigidity workpieces, chatter is a crucial factor affecting many aspects such as surface quality, processing efficiency, and tool life. In this paper, a novel online chatter detection method for milling processes is proposed. In this method, firstly, periodic signal and noise parts are filtered by a comb filter and empirical mode decomposition (EMD), respectively. Then, signal reconstruction is performed on the intrinsic mode functions (IMFs) based on the Pearson correlation coefficient. GWO is applied to reconstruct the signal to obtain optimized parameters. Subsequently, the reconstructed signal is decomposed by VMD with the optimal parameters. To obtain rich chatter information frequency bands, the energy entropy characteristics of each order IMF are calculated, and the two-order IMFs with larger energy entropy are selected for reconstruction. Finally, the multi-scale permutation entropy (MPE) and multi-scale fuzzy entropy (MFE) of the reconstructed signal are calculated. According to the value range of entropy in each processing state, the optimal scale feature is selected. The analysis results show that the proposed method can effectively detect the milling processing state based on the optimal scale.

7 March 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
YQYu Quan
Yu Quan
Changfu LiuChangfu Liu
Changfu Liu
ZYZhuang Yuan
Zhuang Yuan
BYBoling Yan
Boling Yan
Deep learning has been widely applied in fault diagnosis and monitoring, but obtaining labeled data under abnormal conditions is challenging. This limitation makes the best current deep learning methods seem powerless as they require a large amount of labeled data for training. When the training dataset is small, overfitting is highly likely to occur, leading to performance degradation of deep neural networks. To address this issue, this paper proposes a hybrid data augmentation mechanism (HDAM) that utilizes a multi-category generative adversarial network (MCGAN) model and similarity-based selection criteria to generate high-quality data in few-shot scenarios. The selected samples are mixed with augmented samples that undergo image flipping, rotation, and noise addition to form the training set, enhancing the generalization capability of the recognition model after training. To validate the effectiveness of the proposed method, experiments are conducted on the PHM2010 dataset and the TC4 titanium alloy dataset. The experimental results demonstrate a significant improvement in the recognition accuracy of tool wear states in few-shot scenarios.

1 February 2025 in Machines
Verified
Journal Article
Open access
PDF file
XSXiaoning Sun
Xiaoning Sun
ZYZhifeng Yang
Zhifeng Yang
MXMaojin Xia
Maojin Xia
Min XiaMin Xia
Min Xia
Changfu LiuChangfu Liu
Changfu Liu
YGYuquan Guo
Yuquan Guo
Cutting tools are executive components in metal processing, and tool wear directly affects the quality of the workpiece and processing efficiency; monitoring the change in its state is crucial to avoid accidents and ensure the safety of workers. The traditional monitoring model cannot compress a large amount of cutting data effectively, failing to obtain reliable feature data, and there are some defects in generalization ability and monitoring accuracy. For this purpose, this article takes milling cutters as the research object, and it integrates signals from force sensors, vibration sensors, and acoustic emission sensors, combining the advantages of the denoising autoencoder (DAE) model in data compression and the high monitoring accuracy of the support vector regression (SVR) model, to establish a tool wear monitoring model based on DAE–SVR. The results show that compared with traditional DAE and SVR models in multiple datasets, the maximum improvement in monitoring performance (MAE) is 43.58%.

30 September 2016 in Journal of Vibroengineering
Verified
Journal Article
Open access
PDF file
LZLida Zhu
Lida Zhu
YDYang Ding
Yang Ding
Changfu LiuChangfu Liu
Changfu Liu
ZXZhiwei Xu
Zhiwei Xu
High-speed milling of thin-walled part is a common application for aerospace industry, automotive, computer hardware and bioengineering industries. Aiming at the small-stiffness frequency response characteristics of thin-walled parts, the dynamic model and critical condition of stability was proposed by the relative transfer functions between cutter subsystem and thin-walled part subsystem in this paper. The stability critical domain was predicted by semi-discretization (SD) method based on the dynamic behavior of the multi-DOF system. It can be shown that the chatter condition in high-speed milling is closely related to both cutter speed and depth of cut, besides cutter geometry, engagement conditions, relative frequency response function, material property of thin-walled part and so on. This conclusion provides a theoretical foundation and reference for the milling mechanism research.

29 April 2024 in International Journal on Interactive Design and Manufacturing (IJIDeM)
Verified
Journal Article
Closed access
PDF file
JLJianping Liu
Jianping Liu
Changfu LiuChangfu Liu
Changfu Liu
HTHao Tong
Hao Tong
DWDaohai Wang
Daohai Wang