Liqing Fang

Liqing Fang


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
XGXie Gaoyang
Xie Gaoyang
LFLiqing Fang
Liqing Fang
XSXujun Su
Xujun Su
DGDeqing Guo
Deqing Guo
ZQZiyuan Qi
Ziyuan Qi
JCJinli Che
Jinli Che
Path planning for an unmanned vehicle in an off-road uncertain environment is important for navigation safety and efficiency. Regarding this, a global improved A* algorithm is presented. Firstly, based on remote sensing images, the artificial potential field method is used to describe the distribution of risk in the uncertain environment, and all types of ground conditions are converted into travel time costs. Additionally, the improvements of the A* algorithm include a multi-directional node search algorithm, and a new line-of-sight algorithm is designed which can search sub-nodes more accurately, while the risk factor and the passing-time cost factor are added to the cost function. Finally, three kinds of paths can be calculated, including the shortest path, the path of less risk, and the path of less time-cost. The results of the simulation show that the improved A* algorithm is suitable for the path planning of unmanned vehicles in a complex and uncertain environment. The effectiveness of the algorithm is verified by the comparison between the simulation and the actual condition verification.

9 February 2025 in Drones
Verified
Journal Article
Open access
PDF file
XGXie Gaoyang
Xie Gaoyang
LFLiqing Fang
Liqing Fang
XSXujun Su
Xujun Su
DGDeqing Guo
Deqing Guo
ZQZiyuan Qi
Ziyuan Qi
JCJinli Che
Jinli Che
In the process of autonomous driving, the identification and avoidance of risk points is of great significance for the safe and efficient navigation of unmanned vehicles. To solve this problem, a new strategy combining a Bezier curve and the genetic algorithm is proposed in this paper. Firstly, in order to make the curvature of the path continuous, the design uses two symmetric Bezier curves as the path curves. Then, in order to describe the influence range of risk points more accurately, the artificial potential field model is used to describe the risk points, and the integral of the curve path in the potential field is calculated. Finally, an improved genetic algorithm is designed. The limit of the path and the risk value of the path are added to the fitness function, and the selection operator and the mutation operator are improved. It can be seen from the results of simulation and real vehicle experiments that this new strategy can provide an effective path planning method to avoid risk points.

20 November 2025 in Entropy
Verified
Journal Article
Open access
PDF file
JCJinli Che
Jinli Che
LFLiqing Fang
Liqing Fang
QMQiao Ma
Qiao Ma
GYGuibo Yu
Guibo Yu
XSXiaoting Sun
Xiaoting Sun
XZXiujie Zhu
Xiujie Zhu
Aiming to tackle the challenge of feature transfer in cross-domain fault diagnosis for rolling bearings, an enhanced domain adaptation-based intelligent fault diagnosis method is proposed. This method systematically combines multi-layer multi-core MMD with adversarial domain classification. Specifically, we will extend alignment to multiple network layers, while previous work typically applied MMD to fewer layers or used single core variants. Initially, a one-dimensional convolutional neural network (1D-CNN) is utilized to extract features from both the source and target domains, thereby enhancing the diagnostic model’s cross-domain adaptability through shared feature learning. Subsequently, to address the distribution differences in feature extraction, the multi-layer multi-kernel maximum mean discrepancy (ML-MK MMD) method is employed to quantify the distribution disparity between the source and target domain features, with the objective of extracting domain-invariant features. Moreover, to further mitigate domain shift, a novel loss function is developed by integrating ML-MK MMD with a domain classifier loss, which optimizes the alignment of feature distributions between the two domains. Ultimately, testing on target domain samples demonstrates that the proposed method effectively extracts domain-invariant features, significantly reduces the distribution gap between the source and target domains, and thereby enhances cross-domain diagnostic performance.