ZJZhiyong Ji

Zhiyong Ji

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zhiyong Ji has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Frequency Division Cooperation-Based Folding Steering Control for Distributed-Drive Articulated Steering Vehicles

    by Zhiyong Ji, Zhongbin Wu, Haowen Li, Yansong Zhao, Tie Wang

    The traditional articulated steering vehicles rely on the hydraulic steering system and segmented body structure to achieve vehicle steering. The folding steering process exhibits strong hysteresis, which reduces the steering maneuverability and also impacts the autonomous driving performance. This paper proposes a novel control method of folding steering based on differential-hydraulic frequency division cooperation for the redundant drive characteristic of distributed-drive articulated steering vehicles. The main contributions of this paper are as follows: 1) By introducing the speed term into the folding angle control, a position-velocity double closed-loop structure is employed to determine the steering demand torque and achieve the variable steering ratio and accurate control of the folding angle. 2) According to the frequency-domain characteristics of the hydraulic and differential steering systems, a first-order low-pass filtering algorithm is utilized to decompose the steering demand torque into high-frequency and low-frequency components. The high-frequency torque is borne by the differential system, while the low-frequency torque is borne by the hydraulic system, thereby addressing the challenge of cooperative control of multiple actuators. 3) An experimental platform for the distributed-drive articulated steering vehicle is constructed, and the credibility of the dynamic model is experimentally validated. 4) The manipulation and path-tracking performances of the proposed folding steering control method are analyzed. The results indicate that, compared to the hydraulic steering system, the average folding angle rise time and phase delay are reduced by 19.8% and 44.4%, respectively, significantly improving the follow-up performance of folding steering. Furthermore, the average lateral position error and heading angle error in path tracking control are reduced by 38.1% and 27.5%, respectively, which contribute to the electrification and intelligent development of articulated steering vehicles.


  • Driving Condition Recognition Combined With Stochastic Prediction and Machine Learning and Its Application in Energy Management of Medium Fuel Cell Trucks

    by Zhiyong Ji, Tie Wang, Xuguang Sun, Zhongbin Wu, Jinhong Shi, Dongdong Chen, Haona Ma

    Driving condition is a key factor that affects the power demand of vehicles, and its accurate recognition helps to improve the adaptability of energy management strategy for fuel cell vehicles and thus achieve a reasonable distribution of power demand in hybrid powertrains. However, the current driving condition recognition methods suffer from severe time delay, which is not conducive to real-time control. In this study, a fusion algorithm-based driving condition recognition method is proposed to solve this problem, and efforts are made in two aspects. Firstly, a driving condition recognition model combining Markov chain prediction model and learning vector quantization neural network recognition model is established. Secondly, the key parameters affecting recognition accuracy and real-time performance are analyzed and optimized to further improve the recognition performance. Simulation and experimental results show that the real-time performance of the proposed method is significantly improved compared with the method based on historical condition data under the premise of ensuring recognition accuracy and stability. Moreover, the proposed method is applied to the energy management of a medium fuel cell truck, and simulation results highlight that the proposed method can effectively improve the adaptability of the energy management strategy. Compared with the energy management strategy without condition recognition, the fluctuation of fuel cell output power is reduced by 30.4%, and the equivalent hydrogen consumption is reduced by 1.2%, which contributes to the improvement of fuel cell lifetime and economy.


  • Open Access

    Failure Identification of Dump Truck Suspension Based on an Average Correlation Stochastic Subspace Identification Algorithm

    by Bingwen Liu, Zhiyong Ji, Tie Wang, Zhenghao Tang, Guoxing Li

    This paper proposes a fault identification method based on an improved stochastic subspace modal identification algorithm to achieve high-performance fault identification of dump truck suspension. The sensitivity of modal parameters to suspension faults is evaluated, and a fault diagnosis method based on modal energy difference is established. The feasibility of the proposed method is validated by numerical simulation and full-scale vehicle tests. The result shows that the proposed average correlation signal based stochastic subspace identification (ACS-SSI) method can identify the fluctuation of vehicle modal parameters effectively with respect to different spring stiffness and damping ratio conditions, and then fault identification of the suspension system can be realized by the variation of the modal energy difference (MED).