Xiaoning Sun

Mr. Xiaoning Sun


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
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%.

1 March 2026 in Lubricants
Verified
Journal Article
Open access
PDF file
Changfu LiuChangfu Liu
Changfu Liu
YLYubai Liu
Yubai Liu
XSXiaoning Sun
Xiaoning Sun
MWMeng Wang
Meng Wang
SFSiqi Feng
Siqi Feng
JGJingjing Gao
Jingjing Gao
Excessive tool wear can compromise machining precision and increase costs, rendering accurate tool remaining useful life (RUL) prediction imperative in intelligent manufacturing. Traditional methods exhibit intrinsic limitations in cross-modal modeling accuracy and capturing temporal dependencies, failing to meet practical requirements. To transcend these bottlenecks, this study proposes a robust tool RUL prediction framework that combines a multi-channel CNN and a Cross-Modal Transformer. The CNN performs convolution operations to extract local features from wear signals, while the Transformer adaptively synchronizes heterogeneous features (cutting force, vibration, and acoustic emission) to capture long-term degradation trends. Empirical evaluations conducted on the PHM2010 dataset demonstrate the model’s robustness and generalization capability: under the random shuffle–split protocol, the proposed method achieves an R2 of up to 0.99, with the RMSE and MAE reaching 2.51 and 1.98, respectively. To further evaluate the framework’s extrapolation ability under domain shifts, a cross-cutter validation protocol was implemented. Under this condition, the experimental results yield an R2 of 0.961, an RMSE of 6.92, and an MAE of 6.09. Additionally, the correlation between modality-specific attention weights and their corresponding physical interpretations is systematically investigated. These results confirm the model’s potential for cross-cutter life cycle management in smart manufacturing, providing stable and physically consistent wear estimation and remaining useful life prediction in noise-intensive environments.

27 July 2025 in Journal of Measurements in Engineering
Verified
Journal Article
Open access
PDF file
NZNa Zhao
Na Zhao
XSXiaoning Sun
Xiaoning Sun
HTHao Tong
Hao Tong
SFSiqi Feng
Siqi Feng
High-speed cutting of titanium alloy has the advantages of high processing efficiency, reducing tool wear, and obtaining good surface quality, but there is a lack of research on the influence of chip shape on machining parameter selection mechanism in the cutting process, which hinders the development of high-speed milling quality of titanium alloy. In this paper, the shape of titanium alloy (Ti6Al4V) chips at different speeds and different temperatures were simulated. With the increase of cutting speed, the tool squeezes the workpiece material, causing it to undergo elastic deformation and thereby forming a cutting layer. As the cutting process progresses, the chip gradually takes on a serrated shape, the degree of sawtooth sharpening of chips was analyzed. The formation mechanism of chips and the formation process of sawtooth chips during right-angle cutting were analyzed. The locust optimization algorithm was used to optimize the multi-objective parameters, and it was found that high performance machining effect could be achieved by using large feed speed, radial cutting depth and spindle speed.