A data-driven electric vehicle attachment stability recognition method and device

Abstract

The invention relates to an identification method and device for estimating the adhesion stability of an electric drive vehicle based on direct measurement parameters such as driving force, acceleration, and road surface identification type. The motor driving torque is measured by a motor driving torque acquisition unit, and the vehicle is measured along the vehicle body by an acceleration acquisition unit. For the acceleration of the vertical axis, the road surface type parameter is identified by the road surface type parameter acquisition unit, and the trained recognizer is input based on the above three types of signals to obtain the vehicle adhesion stability parameter, and the vehicle stability state is judged according to the obtained adhesion stability state. The whole technical solution does not need to estimate or calculate signals that are difficult to estimate or measure accurately, and has the advantages of simplicity, reliability, fast response, and good practicability.

Description

technical field [0001] The invention belongs to the technical field of vehicle control, and in particular relates to the monitoring of vehicle adhesion stability, in particular to a method for identifying vehicle adhesion stability and a device for implementing the method. Background technique [0002] The identification of vehicle stability on low-adhesion road conditions is the key to ensure safe driving of the vehicle. When the vehicle is running on low-adhesion roads, such as rain, snow, ice, and muddy roads, it is easy to enter the state of unstable adhesion, and then the driving wheels will slip or lock. Instructions attached figure 1 It shows the stable state of vehicle adhesion on different road surfaces. The abscissa in the figure is the slip rate, and the ordinate is the adhesion coefficient. The slip rate is the proportion of the sliding component in the wheel motion. It can be seen that whether it is the dry asphalt road in the upper part of the figure or the r...

AI Technical Summary

Problems solved by technology

However, since the measurement accuracy and bandwidth of adhesion coefficient and slip rate are not high, and they are susceptible to noise interference, the calculation of their differential signals will introduce high-frequency noise, so the practicability of the above-mentioned discrimination method is very poor.

[0008] In order to overcome this problem, the patent ZL201410783813.2 uses the driving force, wheel speed and estimated adhesion to determine whether the vehicle is stable under traction. Difficulties in practical application due to interference

However, this method still needs to estimate the adhesion, which increases the computational complexity on the one hand, and on the other hand, the accuracy of the adhesion estimation is also easily affected by the wheel speed measurement signal, making it difficult to guarantee the accuracy.

[0009] Therefore, in the prior art of vehicle adhesion stability identification, it is generally necessary to measure parameters such as slip ratio, optimal slip ratio, adhesion coefficient, wheel speed, etc. or to estimate signals based on these parameters, and the measurement bandwidth of these signals is low. , the measurement or estimation accuracy is not high, and the overall scheme also has the disadvantages of high computational complexity, so it is easy to cause the existing attachment stability identification technology scheme to be ineffective in practical applications.

Images