Tire Temperature Prediction Using Segmented Load and Speed Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing tire temperature prediction systems for loading vehicles face high computational loads due to the use of time-sequential data, particularly when predicting temperatures for multiple vehicles, which is a challenge for external devices like operation management servers.
Innovation Solution
A tire temperature prediction system that divides time-sequential load and speed data into unit periods, calculates representative values, and predicts tire temperatures based on these values, reducing computational load and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all time-sequential load data and speed data are used for tire temperature prediction, then prediction accuracy is improved, but computational load increases enormously
Solution Approach 1:
The patent divides time-sequential data into unit periods based on load changes. Instead of processing all continuous data, the system segments the data into discrete units where each unit represents a period with relatively stable load conditions. This segmentation reduces the total number of data points while preserving the essential thermal characteristics of tire operation under different load conditions.
Solution Approach 2:
The patent dynamically adjusts the unit period length based on the magnitude of load changes. When load changes exceed a predetermined threshold, the system shortens the unit period to capture the thermal transition more accurately. This dynamic adjustment allows the system to maintain prediction accuracy during critical load transitions while using longer periods during stable operation to reduce computational load.
2Power
If time-sequential data is divided into unit periods and representative values are calculated, then computational load is reduced, but data processing complexity increases
Solution Approach 1:
The patent extracts only the essential representative values (such as average load, average speed, and maximum load) from each unit period data set. By taking out only these critical parameters rather than processing the entire time-sequential data, the system significantly reduces computational load while maintaining the information necessary for accurate temperature prediction.
Solution Approach 2:
The patent transforms continuous time-sequential data into discrete representative parameters for each unit period. This parameter transformation converts a large volume of continuous data into a manageable set of discrete values that can be efficiently processed by the prediction algorithm, reducing computational complexity while preserving the essential thermal behavior characteristics.
Data Source
AI summary
The present invention is provided with a time-sequential load data acquisition unit that acquires data on a load of a predetermined loaded item in a time-sequential manner regarding a loading vehicle capable of loading the predetermined loaded item; a unit period setting unit that sets predetermined unit periods of which it is possible to change lengths according to a change in the load; a data division unit that divides time-sequential load data on the load of the loaded item by separating the time-sequential load data according to the unit periods; a representative value calculation unit that calculates respective representative values for each piece of divided data of the time-sequential load data divided by the data division unit; and a tire temperature prediction unit that predicts a temperature of tires mounted on the loading vehicle, at a specific time point, based on the respective representative values.