Tire force online estimation method based on neural network
A neural network and tire force technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve the problems of inconsistent wheel model changes, high prices, and inability to change the model.
Active Publication Date: 2020-09-25
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF6 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002]
Traditional vehicle status information, especially tire longitudinal and lateral force, is measured by sensors or calculated through a large number of experimental modeling and other information of the vehicle. Sensors are not only susceptible to external environmental interference, but also expensive; experimental modeling methods It is time-consuming, labor-intensive and costly to obtain the force on the wheel, and once the model is established, it cannot be changed, which does not conform to the characteristics that the wheel model will change during the actual vehicle operation, and the real-time performance is poor
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0042] Embodiments of the invention are described in detail below, examples of which are illustrated in the accompanying drawings. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.
[0043] Such as figure 1 Shown is the flowchart of the tire force online estimation method based on neural network of the present invention, and its input is the vertical load F of each tire zfr_le , F zfr_ri , Fzre_le , F zre_ri , wheel slip angle α fr 、α re , longitudinal slip rate s fr_le , s fr_ri , s re_le , s re_ri and the front and rear wheel angles δ fr ,δ re , fr represents the front axle front, re represents the rear axle rear, le represents the left side of the wheel, ri represents the right side of the wheel, and the corresponding label of each set of input data is the longitudinal acceleration of the body state information a x , Lateral acceleratio...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a tire force online estimation method based on a neural network. The input is the vertical load, the wheel slip angle, the longitudinal slip rate and the front and rear wheel rotation angles of each tire; the label of each group of corresponding input data is vehicle body state information longitudinal acceleration, lateral acceleration and yaw angle acceleration, the output signal is each wheel longitudinal force and lateral force estimated by an algorithm, and four neural network parallel structures and a gradient descent algorithm are adopted to achieve online estimation of each wheel tire force. According to the method designed by the invention, the real-time monitoring of the wheel stress is achieved, the use of expensive wheel sensors is avoided, the complex test required for obtaining a wheel model is also avoided, the designed algorithm result is accurate and effective, and the method plays a positive role in promoting the active safety of the vehicle.
Description
technical field [0001] The invention relates to an online tire force estimation method based on a neural network, which belongs to the technical field of vehicle state estimation. Background technique [0002] Traditional vehicle state information, especially tire longitudinal and lateral force, is measured by sensors or calculated through a large number of experimental modeling and other information of the vehicle. Sensors are not only susceptible to external environmental interference, but also expensive; experimental modeling methods It is time-consuming, labor-intensive and costly to obtain the force on the wheel, and once the model is established, it cannot be changed, which does not conform to the characteristics that the wheel model will change during the actual vehicle operation, and the real-time performance is poor. Contents of the invention [0003] The technical problem to be solved by the present invention is to provide an online tire force estimation method b...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06F17/13G06F17/16G06N3/04G06N3/08B60W40/10
CPCG06F17/13G06F17/16G06N3/08B60W40/10B60W2520/105B60W2520/125G06N3/045Y02T90/00
Inventor 王秋伟赵又群张陈曦张桂玉
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS