Road Surface Determination Spaces for Noisy Tire Waveforms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Time-varying waveforms of tire vibrations during running include noise from elements other than road surface state, making it difficult to accurately determine the road surface state.
Innovation Solution
Classifying output waveform data into groups based on running conditions such as speed and tire wear, and using machine learning to create determination spaces for each group, with normalization and extraction of important waveform data to isolate road surface state effects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If time-varying waveforms of tire vibrations are used to determine road surface state, then road surface state can be determined, but noise from elements other than road surface state reduces determination accuracy
Solution Approach 1:
The patent segments the determination process by creating multiple determination spaces corresponding to different running conditions (speed, tire wear level). Each determination space is specialized for specific conditions, allowing accurate determination by selecting the appropriate space based on current running conditions, thereby isolating the signal from noise.
Solution Approach 2:
The patent applies local quality by normalizing waveform data within each determination space and extracting important parts of the waveform that are most indicative of road surface state. This focuses the analysis on locally relevant features rather than processing the entire waveform uniformly, improving signal-to-noise ratio.
2Measurement precision
If waveform data is processed without classification, then processing is simpler, but determination accuracy decreases due to varying running conditions
Solution Approach 1:
The patent implements a dynamic determination system where the appropriate determination space is selected based on current running conditions (speed and tire wear level). This dynamic adaptation allows the system to maintain high accuracy across varying conditions without requiring a completely complex reconfiguration, as the selection logic is based on readily available sensor data.
3Measurement precision
If machine learning is performed on all waveform data, then comprehensive analysis is achieved, but computation time and resources increase
Solution Approach 1:
The patent extracts only the important parts of the waveform data that are most relevant for road surface state determination. By identifying and focusing on these critical features rather than processing the entire waveform, the machine learning computation is significantly reduced while maintaining determination accuracy.
Solution Approach 2:
The patent applies partial action by performing machine learning only on extracted important waveform features rather than the complete waveform data. This selective processing reduces computational burden while still capturing the essential information needed for accurate road surface state determination.
Data Source
AI summary
A method creates determination spaces for determining a road surface state of a road surface on which a vehicle is running from output waveform data obtained by measuring changes in a physical quantity of a tire of the vehicle during the running using information regarding road surfaces and the output waveform data. The method includes obtaining the output waveform data in a plurality of different road surface states and a running condition at times of measurement of the output waveform data, classifying the output waveform data into a plurality of groups on a basis of the running condition, performing, for each group, machine learning using training data where the output waveform data is associated with information regarding the road surface states, and creating the determination space corresponding to the group.