Tire Tread Wear Prediction Models and Applications

Modeling and predicting tire performance and providing feedback based on summarized vehicle data to estimate tire wear, traction, and tread depth in real-time. The method involves extracting relevant features from high-frequency vehicle data using local processing, then transmitting the summarized data to a remote server for estimation. This reduces the volume of data needed for transmission and processing compared to raw data. The server estimates tire wear, traction, and tread depth based on the summarized features.

Source

Estimating tire wear based on driving patterns to provide more accurate and convenient tire wear monitoring without requiring manual tire inspections. A model learns the correlation between driving patterns and tire wear. It estimates tire wear for a specific driver based on their driving history. This allows tracking tire wear over time and notifying when replacement is needed. It also provides wear info to drivers during driving and to external services like management systems.

Source

Method for estimating tire wear and predicting tire performance using real-time vehicle data. The method involves continuously collecting vehicle and tire data, determining current tire wear status based on that data, and predicting tire performance characteristics like traction, durability, and fuel efficiency. Feedback is provided to users based on the predictions. This allows estimating tire life from periodic measurements instead of manual tread depth checks. The method uses statistical models, frequency shifts, and feature extraction from sensor data to estimate tire wear.

Source

Predicting tire wear and traction capabilities in real-time using vehicle and tire data. The method involves estimating tire wear status, predicting tire performance characteristics like traction, and providing feedback based on wear and performance. It leverages sensors, machine learning, and physics models to continuously monitor and analyze tire data to provide actionable insights. The goal is to improve tire management, reduce accidents, and optimize tire performance through real-time feedback and predictive analytics.

Source

Optimizing vehicle motion control to improve energy efficiency by considering tire parameters. The method involves estimating tire parameters like rolling resistance, wear rate, etc based on input data. A tire model is configured using these parameters to relate tire behavior to vehicle motion. This allows estimating effects like rolling resistance for different control strategies. The vehicle is then moved using the tire model to select options with lower rolling resistance for better efficiency.

Source

Predicting tire wear and traction capabilities using real-time vehicle and tire data to provide feedback to users. The method involves estimating tire wear status in real-time based on collected vehicle and tire data. Tire performance characteristics like traction are predicted using the wear status. Feedback is provided to users selectively based on the predicted wear and performance. The tire wear estimation leverages techniques like Bayesian estimation, tire wear models, and sensor data.

Source

A tire wear estimation system that accurately and reliably estimates tire wear state using easily obtained and accurate parameters, and which can operate independently of the vehicle CAN bus. The system involves mounting sensors on the tire to measure footprint length and shoulder length, as well as tire pressure and temperature. This data, along with tire identification, is used to predict tire wear using an analysis module.

Source

Quantifying tire aging and predicting tire life based on real-time monitoring of tire temperature, pressure, load, speed, and position. The method involves calculating aging units (AU) using Arrhenius reaction rate integration to quantify oxidative aging from contained air temperature and ambient temperature. The AUs accumulate over time and distance traveled. The method predicts tire life state and intervention events for each tire position on a vehicle, and across fleets. It enables real-time tire wear prediction, proactive maintenance, and tire replacement scheduling based on actual operating conditions.

Source

Predicting tire wear and load for vehicles using onboard sensors and machine learning to monitor tire health and prevent premature replacement. The method involves predicting vertical load on a vehicle tire based on measured tire temperature and known thermal characteristics for the tire-vehicle combination. A model generated from tire testing is used to predict tire temperature from input conditions like speed and inflation pressure. This predicted temperature is then used to determine the vertical load. This allows estimating tire wear and replacement needs without direct load sensors. The system can also alert when tread depth falls below thresholds.

Source

Tire wear monitoring with the capability to estimate tread wear and predict Remaining Tread Material (RTM) of tires of motor vehicles (e.g., vehicles fitted with internal combustion engines, hybrid vehicles, electric vehicles, etc.). The monitoring includes determining a calibrated Tread Wear Model (TWM) based on the measured tread-wear-related and first frictional-energy-related quantities and performing a remaining tread material prediction comprising predicting remaining tread material of the given tire of the motor vehicle by computing a remaining tread depth based on the computed tread wear value and an initial tread depth.

Source

Predicting tire wear in an apparatus mounted in a vehicle by facilitating the development of a virtual vehicle through early prediction and analysis of tire wear performance when evaluating tire wear before practical driving. The prediction includes importing a tire wear database generated based on basic data, generating a dataset by preprocessing the basic data, classifying the dataset for each vehicle driving method, optimizing a hyper parameter for machine learning based on the classified dataset, and predicting a tire wear lifespan of the vehicle by performing the machine learning on the optimized hyper parameter.

Source

Predicting progression in vehicle tire wear. The prediction includes collecting vehicle data for a vehicle and/or tire data for at least one tire associated with the vehicle, determining a current tire wear status in real-time for the at least one tire, based at least in part on the collected data, one or more tire performance characteristics are predicted, based at least in part on the determined tire wear status and the collected data, real-time feedback is selectively provided, based on the predicted one or more tire performance characteristics and/or determined current tire wear status.

Source

Tire tread wear monitoring system that estimates remaining tread depth more accurately by accounting for irregular tread wear. The system uses machine learning and tire testing to build a model that factors in uneven wear patterns. It involves simulating driving routes on a tire wear test machine, measuring the tread profile, and training an artificial neural network (ANN) to correlate wear with tread shapes. The ANN is then used to estimate remaining tread depth based on real-world tread profiles.

Source

Tire wear prediction using histograms and machine learning to reduce the amount of data needed for tire wear prognostics compared to using raw sensor data. Instead of transmitting detailed tire wear sensor data, the tire wear is summarized into histograms representing distribution of power levels across variables like velocity, steering angle, and temperature. These histograms are sent to a cloud server where machine learning models trained on historical tire wear data are used to translate the histograms into estimates of physical tire wear.

Source

Smart driveline system for vehicles that uses tire telemetry to predict tire wear and optimize maintenance. The system monitors factors like slip distance, road conditions, braking, loads, and speed to predict when tire tread will fall below a minimum depth. This allows proactive planning of tire replacement instead of reactive repair. Real-time tire wear data is transmitted to enable remote monitoring and diagnostics. It also provides real-time quotes for tire maintenance to help owners find the best deals.

Source

Computer-implemented method and system for accurately estimating wear of each axial zone of a tire tread under arbitrary running conditions. The method involves calculating average wear energies for each circumferential zone based on rolling simulations. Wear estimates are made by weighting the average energies using occurrence frequencies for each zone type. This allows accurate estimation of uneven wear like crown, shoulder, and railway wear.

Source

Predicting tire abrasion using a dynamic model that calculates sliding amount based on tire parameters derived from measured forces and angles. This allows precise prediction of tire abrasion for a given slip ratio by calculating the sliding region on the contact patch. The model uses tire dynamic parameters derived from force and angle curves to accurately replicate the curves. This allows calculating the sliding amount at a specific slip ratio. By combining the sliding amount with rubber abrasion properties, tire abrasion can be predicted for different slip ratios.

Source

Monitoring vehicle tires to predict tire wear and deterioration, detect unsafe conditions, and estimate remaining tire life. It involves calculating tire-specific diagnostic models using vehicle operating parameters like load and steering angle, tire-specific models using adjustment parameters like camber, and environmental models using temperature and sunlight. These models are combined into interaction and reliability maps. By detecting operating, adjustment, and environmental parameters, the tire maps can be populated and tire health assessed.

Source

A method for predicting tire wear using vehicle and tire parameters to provide accurate and timely wear estimates. The method involves tracking wheel forces, speeds, camber, and slip during vehicle motion. These wheel characteristics are treated with tire parameters to predict tread contact forces and wear. Cumulative wear is calculated over time. The predictions are compared to actual wear measurements to refine future predictions. This allows accurate wear estimation without needing continuous measurement devices.

Source