Fleet Tire Wear Prediction Using Driver and Vehicle Coefficients
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to accurately predict tire wear in a fleet of vehicles, which affects fuel consumption and maintenance costs, necessitating a more precise method for tire wear prediction.
Innovation Solution
A tire wear prediction system and method using a 3-stage least-squares model to calculate coefficients based on driver and vehicle attributes, incorporating data from TPMS, weather, and operational variables to predict tire wear and fuel consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional demand forecasting systems are used to predict tire wear, then maintenance costs can be reduced, but prediction accuracy is insufficient to optimize fuel consumption
Solution Approach 1:
The patent segments the tire wear prediction into multiple independent modules: TPMS data acquisition module, weather data acquisition module, operational variable acquisition module, and 3-stage least-squares calculation module. Each module handles specific data types and processing tasks, allowing the system to achieve high prediction accuracy through specialized processing while maintaining manageable system complexity through modular architecture.
Solution Approach 2:
The patent introduces multiple new dimensions to the prediction system beyond conventional methods. It incorporates TPMS data (pressure and temperature dimensions), weather conditions (environmental dimension), and detailed operational variables (routing, loading, driver behavior dimensions). The 3-stage least-squares model adds a mathematical rigor dimension by calculating specific coefficients for each variable, transforming the prediction from a single-dimensional estimate to a multi-dimensional analytical model.
2Measurement precision
If multiple variables including driver attributes and vehicle attributes are incorporated into the prediction model, then prediction accuracy improves, but data processing complexity increases
Solution Approach 1:
The patent creates a universal data collection framework that handles multiple data types through standardized interfaces. The system universally processes TPMS data, weather data, operational variables, driver attributes, and vehicle attributes through a common 3-stage least-squares calculation engine. This multi-functional approach allows diverse data sources to be integrated seamlessly, improving prediction accuracy while managing data processing complexity through standardized handling procedures.
Solution Approach 2:
The system implements feedback mechanisms where predicted tire wear results are used to refine the model coefficients through the 3-stage least-squares calculation. The system continuously receives feedback from actual tire wear measurements and operational data, adjusting the coefficients for driver attributes, vehicle attributes, and operational variables to improve prediction accuracy over time while streamlining data processing through learned patterns.
3Use of energy by moving object
If TPMS data, weather data, and operational variables are integrated into the prediction system, then fuel consumption optimization improves, but system complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-calculating the coefficients for each variable (tire pressure coefficient, tire temperature coefficient, weather coefficient, operational variable coefficients) using the 3-stage least-squares method before actual prediction needs arise. This pre-processing of data relationships allows the system to quickly optimize fuel consumption during operation without requiring complex real-time calculations, thus improving energy efficiency while managing system complexity through advance preparation.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A tire wear prediction system predicts the wear of tires mounted on a vehicle comprising a fleet. The tire wear prediction system sets a driver-related coefficient to be applied to the driver-related explanatory variable and a vehicle-related coefficient to be applied to the vehicle-related explanatory variable based on the actual values of the driver-related explanatory variables and the vehicle-related explanatory variables, and calculates the wear as an objective variable by using the driver-related explanatory variables and the vehicle related explanatory variables. The tire wear prediction system recalculates a predicted value of the wear when at least one of the attribute of the driver and the attribute of the vehicle is changed by using the driver-related coefficient and the vehicle-related coefficient.