XFXin Fan

Xin Fan

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xin Fan has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • PC-CIL: a physical consistency class-incremental learning framework for fault diagnosis of rotating machinery under variable operating conditions

    by Xin Fan, Wenbin Liu, Quan Chen, Shaoyi Bei, Jiangyi Han, Zixu Liu, Yuanjiang Li

    When rotating machinery encounters a continuous flow of new fault categories under variable operating conditions, traditional deep learning-based diagnostic methods fail to handle feature distribution shifts and suffer from catastrophic forgetting, significantly compromising long-term monitoring reliability. To address this problem, we propose a physical consistency class-incremental learning (PC-CIL) framework. Physical consistency representation learning serves as the model backbone, incorporating universal physical statistical features as prior constraints to bridge the gap between data-driven models and physical laws. We then introduce a pseudo-sample generation mechanism based on prototype boundary sampling and confidence filtering to tackle data isolation in incremental scenarios. The generated pseudo-samples enable a hybrid replay strategy to dynamically update decision boundaries while suppressing negative transfer with low computational overhead. To mitigate catastrophic forgetting, we implemented a topology-preserving relational knowledge distillation approach, thus facilitating the structural consistency of the feature space. Experimental results on two publicly available benchmark datasets, namely the HUST and CWRU bearing datasets, as well as a self-built bearing dataset, demonstrate that PC-CIL consistently maintains high diagnostic accuracy while effectively mitigating catastrophic forgetting during sequential fault-category expansion. The consistent improvements across different bearing types, test rigs, sampling systems, and operating conditions further verify the robustness and generalization capability of the proposed framework.

  • Open Access

    ISequoiaOA: A hybrid multi-strategy improved sequoia optimization algorithm for engineering optimization

    by Xin Fan, Yanchen Li, Yuanjiang Li, Shaoyi Bei, Jiangyi Han, Zixu Liu

    Heuristic intelligent optimization algorithms have been widely applied to complex engineering design, parameter optimization, and control-system optimization because of their strong global search capabilities and adaptability. To address the problems of uneven initial population distribution, insufficient search guidance, and a tendency to become trapped in local optima at later stages when the standard Sequoia Optimization Algorithm is applied to high-dimensional, multimodal, and complex constrained problems, this paper proposes an improved Sequoia Optimization Algorithm, termed ISequoiaOA. The algorithm is improved in three aspects. First, a Piecewise-map segmented chaotic mapping strategy is employed to generate the initial population, thereby enhancing population uniformity, ergodicity, and diversity, and improving global exploration capability in the early stage. Second, a differential mutation perturbation strategy is introduced and combined with an adaptive scaling factor and a greedy selection mechanism to strengthen the directional search capability of individual updating while preventing degradation of population quality. Finally, an adaptive Gaussian local search strategy is designed to dynamically adjust the perturbation step size according to the iteration process and the scale of the search space, thereby improving late-stage local exploitation accuracy and the ability to escape local optima. In the CEC-2017 and CEC-2022 benchmark tests, ISequoiaOA is compared with 14 state-of-the-art algorithms and achieves the best overall ranking. Further applications to two types of engineering design optimization problems and the parameter optimization of a ship fin stabilizer controller demonstrate that the proposed algorithm has clear advantages in solution accuracy, stability, and engineering applicability.

  • Open Access

    LQR Trajectory Tracking Control of Unmanned Wheeled Tractor Based on Improved Quantum Genetic Algorithm

    by Xin Fan, Junyan Wang, Haifeng Wang, Lin Yang, Changgao Xia

    In the process of trajectory tracking using the linear quadratic regulator (LQR) for driverless wheeled tractors, a weighting matrix optimization method based on an improved quantum genetic algorithm (IQGA) is proposed to solve the problem of weight selection. Firstly, the kinematic model of the wheeled tractor is established according to the Ackermann steering model, and the established model is linearized and discretized. Then, the quantum gate rotation angle adaptive strategy is optimized to adjust the rotation angle required for individual evolution to ensure a timely jumping out of the local optimum. Secondly, the populations were perturbed by the chaotic perturbation strategy and Hadamard gate variation according to their dispersion degree in order to increase their diversity and search accuracy, respectively. Thirdly, the state weighting matrix Q and the control weighting matrix R in LQR were optimized using IQGA to obtain control increments for the trajectory tracking control of the driverless wheeled tractor with circular and double-shifted orbits. Finally, the tracking simulation of circular and double-shifted orbits based on the combination of Carsim and Matlab was carried out to compare the performance of LQR optimized by five algorithms, including traditional LQR, genetic algorithm (GA), particle swarm algorithm (PSO), quantum genetic algorithm (QGA), and IQGA. The simulation results show that the proposed IQGA speeds up the algorithm’s convergence, increases the population’s diversity, improves the global search ability, preserves the excellent information of the population, and has substantial advantages over other algorithms in terms of performance. When the tractor tracked the circular trajectory at 5 m/s, the root mean square error (RMSE) of four parameters, including speed, lateral displacement, longitudinal displacement, and heading angle, was reduced by about 30%, 1%, 55%, and 3%, respectively. When the tractor tracked the double-shifted trajectory at 5 m/s, the RMSE of the four parameters, such as speed, lateral displacement error, longitudinal displacement error, and heading angle, was reduced by about 32%, 25%, 37%, and 1%, respectively.


  • Open Access

    Contrast-Controllable Image Enhancement Based on Limited Histogram

    by Xin Fan, Junyan Wang, Haifeng Wang, Changgao Xia

    To address the technical shortcomings of conventional histogram equalization (HE), such as over-enhancement and artifacts, we propose a histogram-constrained and contrast-tunable HE technique for digital image enhancement. Firstly, the input image histogram is partitioned into two parts, the main histogram and the constrained histogram, by a cumulative probability density threshold; second, the main histogram is redistributed equally in the whole grayscale range; and finally, the nonlinearity of the constrained histogram is mapped to the main histogram. The experimental averages show that the values of the two metrics, information entropy and MS-SSIM, processed by the algorithms in this paper, are more accurate compared to the other six excellent algorithms.


  • Open Access

    Research on the Influence of Tractor Parameters on Shift Quality, Based on Uniform Design

    by Junyan Wang, Changgao Xia, Xin Fan, Junyu Cai

    This paper mainly studies the influence of tractor parameters on shift quality. The kinetic theoretical model of the powertrain system was deduced, and then the simulation model was established by using AMESim simulation software. The acceptable jerk and shift time were selected as the evaluation indexes of shift quality. The influence of engine speed, the tractive resistance of the tractor, the clutch oil pressure and the orifice diameter on the above evaluation indexes were quantitatively studied. The simulation test, under the influence of a single parameter, was carried out using the parameter analysis method. After this, the uniform design experimentation method was used to carry out the simulation test, under the influence of combined parameters. The results showed that in order to improve the shift quality, it is necessary to focus on the selection of clutch oil pressure and orifice diameter.


  • Open Access

    Research on Transmission Characteristics of Hydromechanical Continuously Variable Transmission of Tractor

    by Junyan Wang, Changgao Xia, Xin Fan, Junyu Cai

    This paper proposes a new transmission scheme of hydromechanical continuously variable transmission (HMCVT) for tractors. The HMCVT has 4 working ranges in each of the front and rear directions. The speed characteristic and the torque characteristic of HMCVT are theoretically derived. On the basis of HMCVT power flow direction, the KpeHec formula is used to calculate the transmission efficiency. Then, the image analysis method is used to study the influence of parameters on the transmission efficiency of HMCVT, and the main influencing factors are found. The results of theoretical derivation demonstrate that, by coordinating control of the HST displacement ratio and the engagement conditions of shifting clutches, the stepless speed regulation of HMCVT at the tractor speed of 0-50 km/h can be realized. The proposed HMCVT has the ability to continuously transmit and change torque over all working ranges. The overall transmission efficiency of HMCVT is at a high level. To verify the theoretical derivation, Amesim simulation software is used for the modeling and simulation of HMCVT. The simulation results are consistent with the theoretical analysis results. Therefore, the HMCVT proposed in this paper has the advantages of compact structure and high transmission efficiency, and it is suitable for matching tractors.