Neural Vehicle State Estimation for Suspension Damping Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle state estimation techniques lack accuracy in estimating relative velocity and vehicle body velocity, which are crucial for effective damping force control in suspension systems.
Innovation Solution
A vehicle state quantity estimation device employing a data acquisition unit and a neural network to estimate relative velocity and vehicle body velocity using wheel speed, yaw rate, current value, steering angle, and acceleration data, improving estimation accuracy through machine learning-based models like LSTM.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional techniques are used to estimate vehicle state, then the system structure is simple, but the estimation accuracy of relative velocity and vehicle body velocity is insufficient
Solution Approach 1:
The patent replaces conventional mechanical estimation methods with a neural network-based estimation system. The neural network learns complex nonlinear relationships between wheel speed data and vehicle state parameters (relative velocity, vehicle body velocity), achieving superior estimation accuracy without requiring direct mechanical sensors for these parameters.
Solution Approach 2:
The patent transforms the estimation approach by changing from direct measurement to data-driven prediction. Multiple input parameters (wheel speed, steering angle, brake pedal position) are processed through a neural network to generate accurate estimates of target parameters (relative velocity, vehicle body velocity), leveraging parameter transformations and nonlinear mappings.
2Measurement precision
If multiple types of data are input to the neural network, then the estimation accuracy is improved, but the data processing complexity increases
Solution Approach 1:
The neural network is designed as a universal processing unit that handles multiple input data types (wheel speed, steering angle, brake pedal position, vehicle acceleration) and produces multiple output estimates (relative velocity, vehicle body velocity). This multi-functional architecture consolidates complex data processing into a single integrated system.
Solution Approach 2:
The patent segments the data processing into distinct input and output components. Input data from various sensors are separately acquired and pre-processed, then fed into the neural network which performs the complex integration and transformation, finally outputting the estimated vehicle state parameters. This segmentation simplifies the overall system architecture.
Data Source
AI summary
A vehicle state quantity estimation device according to an embodiment includes a data acquisition unit and a vehicle state estimation unit. The data acquisition unit acquires first data that is data about a velocity of a vehicle. The vehicle state estimation unit estimates either or both of a relative velocity and a vehicle body velocity according to the first data acquired by the data acquisition unit by using a neural network trained to estimate either or both of the relative velocity and the vehicle body velocity according to input of the first data, the relative velocity being a relative velocity of a tire-wheel assembly with respect to a vehicle body of the vehicle in a vertical direction of the vehicle, and the vehicle body velocity being a velocity of the vehicle body in the vertical direction.