KHKun Hu

Kun Hu

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

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


Kun Hu has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Dynamic characteristics of a hybrid suspension system for flexible conveyor belts integrating deep learning and multi-body transfer matrix

    by Hao Jiang, Kun Hu, Chu Wang

    The hybrid suspension system based on flexible conveyor belts is a critical architecture for hybrid magnetic suspension conveyor systems. Traditional multi-body dynamics (MBD) methods face challenges such as computational complexity and difficulties in rapid prototyping and parametric studies. This study employs an extended transfer matrix method (TMM) method to discretize and analyze the system, proposing a hybrid multi-rigid-flexible structure combining mass-beam-damping spring elements. To address modeling errors and random disturbances, a Gated Recurrent Unit (GRU) neural network is integrated to correct the dynamic responses at suspension support points. Comparative simulations with long short-term memory (LSTM) networks demonstrate that GRU achieves lower mean, minimum, and maximum MSE values. An experimental platform for flexible conveyor belt hybrid suspension was developed, conducting interference response tests. Results show that under four-point suspension conditions, the TMM model maintains steady-state vibration response errors around 0.3[ ]mm and multifrequency disturbance response errors around 0.5[ ]mm. GRU-corrected steady-state predictions achieved minimum MSE values of 0.0114 and an average MSE of 0.021, while under multifrequency disturbances, MSE values reached 0.0757 (minimum) and 0.1127 (average). These findings validate the applicability and reliability of the GRU-TMM modeling approach in complex rigid-flexible systems.

  • Intelligent recognition of rock hardness for excavation support and anchor equipment based on feature optimization and improved sine cosine algorithm

    by Guoyong Su, Zijin Pang, Kun Hu, Hongxin Shuai, Dongyang Zhao

    To address the problem of rock hardness recognition in comprehensive excavation-face anchorage operations, a rock hardness recognition method based on feature optimization and an improved sine cosine algorithm optimised decision tree (CART) is proposed. First, the signal was reconstructed by successive variational mode decomposition (SVMD) and the waveform factor method. Second, the time–frequency matrix of the signal was calculated using short-time Fourier transform (STFT), S transform (ST), and frequency-corrected generalised S-transform (FCGST), and the dimension was reduced employing singular value decomposition (SVD). Finally, based on the improved sine cosine optimization algorithm (ISCA), the minimum leaf node size and maximum number of splits in the decision tree were optimised, and different rock hardness recognition models were established. Based on a self-developed experimental platform for the integration of excavation, support, and anchor, multiple lithologic combinations were determined. The results of drilling experiments show that by using the recognition model with SVMD, waveform factorisation method reconstruction, FCGST feature extraction, and ISCA key parameter optimization, the accuracy of rock hardness recognition was improved by 9% and 4%, respectively, and the recognition efficiency reached 97.33% compared with STFT and ST feature extraction. The effectiveness of the rock hardness identification method for drilling of excavation support and anchor equipment based on feature preference and decision tree was further verified. This study can provide technical support for the identification of rock hardness under complex working conditions of a comprehensive excavation face.


  • Open Access

    Magnetic Levitation Belt Conveyor Control System Based on Multi-Sensor Fusion

    by Kun Hu, Hao Jiang, Qinqin Zhu, Wangqian Qian, Jinhan Yang

    Belt conveyors are critical in coal transportation systems; however, they are supported by rollers, which incur high energy costs. Magnetic levitation support is adopted. The measurement of a magnetic levitation air gap is important, and a displacement sensor is usually used in real-time. To address the problems of poor linearity and low measurement stability of single displacement sensors in magnetic levitation systems, a magnetic levitation support system based on multi-sensor data fusion is proposed. First, an industrial camera sensor is used to collect images, and the suspended air gap is obtained through image processing. Second, using an extended Kalman filter, the photoelectric position sensor and industrial camera sensor are fused to the suspension air gap value in the process of suspension. The electromagnet current is controlled by the PID (proportion integration differentiation) control algorithm, and experiments are carried out. Experimental results showed that, compared with an estimation of the suspension state of two sensors before and after EKF fusion, the root mean square error is reduced by 0.0597 and 0.0081, respectively, compared with the measurement value of a single sensor. Moreover, the fusion data were more robust, thereby meeting the requirements of magnetic levitation control.


  • Refined plate elements for the analysis of composite plate using Carrera unified formulation

    by Teng Wenxiang, Liu Pengyu, Shen Gang, Hu Kun, He Jipeng, Wang Cheng


  • Shape selection recognition and scattering distribution prediction of adhesion targets in multi-scale dual-energy X-ray images of coal and gangue

    by Lei He, Shuang Wang, Yongcun Guo, Kun Hu, Gang Cheng

    Identifying and predicting the distribution of scattered coal and gangue is the premise of locating them. By analyzing the shape of multi-scale coal and gangue, an approach for shape selection and recognition is provided. The issues of independent and adhesion target recognition, adhesion type recognition, and distribution prediction have been resolved. The binary target, circumscribed convex hull, and concave defect images are used to extract a total of 27 shape features. The ReliefF algorithm is employed to select features. The shape recognition model 1 shows the highest adhesion and independent recognition rates of 98.54%. For adhesion kinds, shape recognition model 2 gets the highest recognition accuracy of 92%. According to the experimental findings, the difference between predicted and actual results for the parameters describing the dispersed distribution of targets, such as target number, distribution overlap rate, and distribution density, is less than 4.1%, which is acceptable for use in real-world scenarios.


  • Open Access

    Aging and tribological behavior of styrene butadiene rubber conveyor belts under combined seawater dry-wet conditions

    by Kun Hu, Jinhan Yang

    In this study, the aging and tribological behaviors of styrene butadiene rubber (SBR) conveyor belts exposed to seawater dry–wet cycles were investigated. Using hardness as a measure of the aging performance, the worst seawater dry-wet (W-SDW ) cycle conditions were selected using an orthogonal design method, the study was conducted based on such conditions. The changes in SBR surface properties and tribological properties with aging time before and after aging and the degree were investigated by using a hardness tester, SEM, EDS, etc. The performance degradation, microscopic morphological changes of wear surface, and evolutionary behavior of wear mechanism of styrene-butadiene rubber conveyor belt after aging by dry and wet cycles of seawater were discussed. The results show that the most severe combination of wet-dry cycles of seawater for the aging of SBR conveyor belts comprised a soak temperature of 45 °C, soak time of 12 h, drying temperature of 100 °C, and drying time of 9 h. The total surface discoloration of the conveyor belt increases as the number of W-SDW cycles increases, along with the hardness. The friction coefficient of the belt increases with increasing load and decreases with the increasing number of W-SDW cycles. The mass loss increases gradually with the number of W-SDW cycles and load. The wear mechanism gradually changes from fatigue wear to the damage mechanism of coexistence of adhesive wear and fatigue.


  • A modified butterfly optimization algorithm: An adaptive algorithm for global optimization and the support vector machine

    by Kun Hu, Hao Jiang, Chen‐Guang Ji, Ze Pan

    A modified adaptive butterfly optimization algorithm is established with the aim of addressing the “early search blindness” and the relatively poor adaptability of the sensory modality. A normal‐distribution‐based model and a Weibull‐distribution‐based adaptive model of sensory modalities are respectively proposed for the global search process and iteration process. Among them, the Weibull‐distribution‐based adaptive model of sensory modalities is mainly manifested as the c value, that is, the adaptive change trend based on the Weibull model. The performance of the modified butterfly optimization algorithm is validated using a 14‐benchmark test function and compared with performances of some latest algorithms. The experimental results indicate that the modified algorithm performs competitively in terms of accuracy and stability. Following the experiment, the modified algorithm is further tested by running a support‐vector‐machine prediction model based on engineering data of a pipe belt conveyor's flat‐pipe/pipe‐flat transition segment. The results of the modified algorithm are then compared with test‐run outcomes of the back‐propagation prediction model and KCV‐SVM model. The results show that the prediction error is well within 10%, demonstrating the method's competence as a reliable reference for future designs of pipe belt conveyors.