This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Kalman Filter Slope Measurement Method Based on Improved Genetic Algorithm-Back Propagation
ISSN: 0148-7191, e-ISSN: 2688-3627
To be published on April 14, 2020 by SAE International in United States
This content contains downloadable datasetsAnnotation ability available
How to improve the measurement accuracy of road gradient is the key content of the research on the speed warning of commercial vehicles in mountainous roads. The large error of the measurement causes a significant effect of the vehicle speed threshold, which causes a risk to the vehicle's safety. Conventional measuring instruments such as accelerometers and gyroscopes generally have noise fluctuation interference or time accumulation error, resulting in large measurement errors. To solve this problem, the Kalman filter method is used to reduce the interference of unwanted signals, thereby improving the accuracy of the slope measurement. However, the Kalman filtering method is limited by the estimation error of various parameters, and the filtering effect is difficult to meet the project research requirements. In this paper, the acceleration of vehicle gravity, driving speed and acceleration of parallel slope are utilied as auxiliary measurement parameters to improve the measurement method. Based on the Kalman model, GA (genetic algorithm) and BP (Back Propagation) neural network are employed to carry out the innovation, covariance matrix and the last Kalman numerical value optimization, improve the filtering effect. Matlab simulation and real vehicle experiment are used to verify this improved algorithm, and the average absolute error can be within 0.2%, to meet the accuracy requirements of the slope required for the speed warning of commercial vehicles during mountainous roads. This confirms the accuracy and reliability of the method presented. In addition, the improved filtering method also has wide application in the fields of navigation, detection, target tracking and other fields.
- Haoyu Wang - Wuhan University of Technology
- Donghua Guo - Wuhan University of Technology
- Gangfeng Tan - Wuhan University of Technology
- Zhenyu Wang - Wuhan University of Technology
- Ming Li - Wuhan University of Technology
- Yifeng Jiang - Wuhan University of Technology
- Meng Ye - Wuhan University of Technology
- Kailang Chen - Wuhan University of Technology
CitationWang, H., Guo, D., Tan, G., Wang, Z. et al., "Kalman Filter Slope Measurement Method Based on Improved Genetic Algorithm-Back Propagation," SAE Technical Paper 2020-01-0897, 2020.
Data Sets - Support Documents
|[Unnamed Dataset 1]|
- Ge, M. , “Study on Calculation Model of Running Speed of Downhill Section,”Hunan University, Hunan, 2011.
- Qian, K., Tan, G., Zhou, R., Mei, B. et al. , “Vehicle-GIS Assistant Driving System for Real-Time Safety Speed Warning on Mountain Roads,” SAE Technical Paper 2017-01-1400, 2017, https://doi.org/10.4271/2017-01-1400.
- Shang, L., Liu, G., and Zhang, R. , “Autonomous Orbit Determination Adaptive Kalman Filtering Algorithm Based on BP Neural Network,” Journal of Astronautics 34(7):926-931, 2013.
- Yong, W., Guan, X., and Wang, B. , “Longitudinal Slope Recognition Algorithm Based on Multi-Sensor Data Fusion Filtering,” Journal of Mechanical Engineering 54(14):116-124, 2018.
- Ran, X., Li, L., Zhao, X., Song, J. et al. , “Real-time Recognition Algorithm of Longitudinal Road Slope Based on Vehicle Dynamics and Acceleration Sensor Information,” Journal of Mechanical Engineering 52(18):98-104, 2016.
- Kichun, J., Keonyup, C., and Sunwoo, M. , “Interacting Multiple Model Filter-Based Sensor Fusion of GPS With In-Vehicle Sensors for Real-Time Vehicle Positioning”, IEEE Transactions on Intelligent Transportation Systems 13:329-343, (2012).
- Hao, S., Luo, P., and Xi, J. , “Vehicle Quality and Road Slope Estimation Based on Steady-State Kalman Filter,” Automotive Engineering, 2018, 40(9): 1062-1067, 1075.
- Pan, D., Liu, H., and Li, Y. , “Optimization Model of Wind Farm Wind Speed Prediction Based on Time Series Analysis and Kalman Filter Algorithm,” Power Grid Technology 32(7):82-86, 2008.
- Yang, S., and Huang, L. , “A Financial Early Warning Model of Listed Companies Based on BP Neural Network,” Systems Engineering -Theory & Practice, 2005, 25(1): 12-18, 26.
- Li, L., Zhao, L., and Tang, X. , “Gyro Error Compensation Algorithm Based on Improved Kalman Filter,” Journal of Transduction Technology, 2018, 31(4): 538-544, 550.
- Peng, J., Lv, W., and Xing, H. , “Temperature Compensation of Humidity Sensor Based on Improved GA-BP Neural Network,” Chinese Journal of Scientific Instrument 34(1):153-160, 2013.
- Zhai, Y., Li, H., and Liu, H. , “A Method for Optimizing Initial Weight of Neural Network by Genetic Algorithm,” Journal of Jilin University: Engineering Science 33(2):45-50, 2003.