| ZHANG Hang,BAO Jiusheng,YIN Yan,CAO Ting,HU Deping,SU Wensheng,ZHU Chenzhong,CAO Jingyu,GU Yonghua.Frictional Braking Temperature Rise Characteristics and Intelligent Prediction Model of Heavy-duty Mining Trucks in Open-pit Mines[J],54(11):83-99, 172 |
| Frictional Braking Temperature Rise Characteristics and Intelligent Prediction Model of Heavy-duty Mining Trucks in Open-pit Mines |
| Received:October 08, 2024 Revised:March 21, 2025 |
| View Full Text View/Add Comment Download reader |
| DOI：10.16490/j.cnki.issn.1001-3660.2025.11.007 |
| KeyWord:heavy-duty mining truck temperature rise characteristics thermal-mechanical coupling prediction model |
| Author | Institution |
| ZHANG Hang |
School of Mechanical and Electrical Engineering, China University of Mining and Technology, Jiangsu Xuzhou , China |
| BAO Jiusheng |
School of Mechanical and Electrical Engineering, China University of Mining and Technology, Jiangsu Xuzhou , China |
| YIN Yan |
School of Mechanical and Electrical Engineering, China University of Mining and Technology, Jiangsu Xuzhou , China |
| CAO Ting |
School of Mechanical and Electrical Engineering, China University of Mining and Technology, Jiangsu Xuzhou , China |
| HU Deping |
Xuzhou XCMG Heavy Vehicle Co., Ltd., Jiangsu Xuzhou , China |
| SU Wensheng |
Jiangsu Institute of Special Equipment Safety Supervision and Inspection, Nanjing , China |
| ZHU Chenzhong |
Xuzhou XCMG Heavy Vehicle Co., Ltd., Jiangsu Xuzhou , China |
| CAO Jingyu |
School of Mechanical and Electrical Engineering, China University of Mining and Technology, Jiangsu Xuzhou , China |
| GU Yonghua |
Jiangsu Institute of Special Equipment Safety Supervision and Inspection, Nanjing , China |
|
| Hits: |
| Download times: |
| Abstract: |
| This research focuses on the frictional braking temperature rise characteristics and intelligent prediction model of heavy-duty mining trucks in open-pit mines, aiming to address the potential safety risks resulting from unpredictable braking- induced temperature increase. The study is centered around the XG105 three-bridge rigid mining truck of XCMG Group. Initially, the three main braking modes including emergency braking, continuous braking, and cyclic multiple braking are thoroughly analyzed. A thermal- mechanical coupling model of the drum brake is then developed with the direct coupling method. In this process, the vehicle mass is equivalently distributed onto the brake drum to simplify the complex vehicle dynamics model. During braking, the energy conversion occurs, and a significant portion of the mechanical energy of the vehicle is transformed into heat in the braking system. A correction coefficient of 0.9 is adopted, signifying that approximately 90% of the mechanical energy is converted into heat absorbed by the brakes. This coefficient is crucial as it more accurately reflects the actual heat-generating situation in the braking process. Subsequently, a simulation test system for the brake temperature rise of mining trucks is established in the laboratory. In accordance with relevant standards, parameters such as load, longitudinal slope gradient, and initial braking speed are precisely set. The load conditions include no-load (35 t), full-load (105 t), and 30% over-load (126 t), while the longitudinal slope gradient values are set at 6%, 7%, and 8%. These parameter settings cover a wide range of actual operating conditions in open-pit mines. Under continuous braking and cyclic multiple braking modes, 27 sets of orthogonal experiments are conducted, generating a total of 8 876 sample data. This large-scale data collection is essential for comprehensively understanding the temperature rise characteristics under different braking conditions. Finally, an intelligent prediction model for brake temperature rise is constructed based on the CNN-LSTM-Attention algorithm. By means of Pearson correlation analysis, input features with a correlation coefficient exceeding 0.8 with the maximum braking temperature are carefully selected. These features, such as travel time, longitudinal slope gradient, initial braking speed, total quality, and braking frequency, are highly relevant to the temperature rise phenomenon. After a series of data preprocessing steps, including data cleaning, division, normalization, and transformation, the model is trained. The trained model shows remarkable prediction accuracy. In the continuous braking mode, under three new working conditions, the average prediction error is 5.2 ℃, and the relative error of the percentage does not exceed 7%. In the cyclic multiple braking mode, under three new working conditions, the average prediction error is 4.79 ℃, and the relative error of the percentage is within 5%. In summary, the thermal-mechanical coupling model effectively simulates different braking scenarios, providing a reliable way for analyzing the temperature rise process. The intelligent prediction model based on the CNN-LSTM-Attention algorithm can accurately forecast the maximum braking temperature rise. However, there are areas for improvement. Future research should concentrate on optimizing the friction coefficient and refining simulation parameters to make the model more adaptable to the complex and variable real-world conditions in open-pit mines. This study offers a solid theoretical basis for enhancing the driving safety of mining trucks and paves the way for further research in this field. |
| Close |
|
|
|