ML-Driven Predictive Modeling for Tire Performance
22 patents in this list
Updated:
Tire performance is crucial for safety, efficiency, and comfort in vehicles, demanding precise monitoring and prediction. Traditional methods often fall short in capturing the complex interplay of factors affecting tire behavior. Machine learning offers a way to analyze vast datasets, revealing patterns and insights that were previously hidden. This approach is essential for addressing the dynamic challenges of tire wear, pressure, and overall performance.
Professionals in the automotive industry face the challenge of integrating diverse data sources—such as tire pressure, vehicle speed, and temperature—into cohesive models. The variability in driving conditions and tire materials further complicates accurate predictions. Ensuring that these models remain adaptable and reliable under different scenarios is a constant hurdle.
This page explores a range of machine learning-driven solutions that improve tire performance prediction. These include models for predicting tire wear using incremental data optimization, estimating tire forces from dynamic driving data, and analyzing sensor data for real-time condition monitoring. By implementing these strategies, professionals can enhance tire reliability and optimize vehicle dynamics.
1. Machine Learning-Based Tire Wear Prediction Model with Incremental Data Optimization and Multi-Factor Analysis
GREE ELECTRIC APPLIANCES INC OF ZHUHAI, GREE ELECTRIC APPLIANCES INC.OF ZHUHAI, ZHUHAI LEAYUN TECH CO LTD, 2024
A tire wear prediction method using machine learning to accurately predict tire wear and improve driving safety by finding excessive wear or aging conditions in time. The method involves collecting tire wear data under varying road conditions, vehicle loads, and tire types. This data is used to train a tire wear prediction model that can analyze road factors like quality and curves, as well as vehicle factors like load, to comprehensively predict tire wear. The model can also optimize itself incrementally as new data is added.
2. Machine Learning-Based Method for Predicting Tire Ride Comfort and Handling from Measured Properties
SUMITOMO RUBBER IND LTD, 2024
A method for evaluating tire performance that uses machine learning to predict ride comfort and handling based on measured tire properties. The method involves acquiring tire measurements, inputting them into a predictive model, and deriving an output that allows the driver to evaluate ride comfort and handling. This output corresponds to the driver's sensory evaluation of a vehicle equipped with that tire compared to a reference tire. The model is trained using measured tire properties and sensory evaluations.
3. Machine Learning-Based Indirect Tire Pressure Estimation System Using Wheel Speed and Temperature Inputs
ZF COMMERCIAL VEHICLE SYSTEMS CO LTD, ZF COMMERCIAL VEHICLE SYSTEMS QINGDAO CO LTD, 2024
Improving tire pressure monitoring accuracy in vehicles using machine learning. Instead of installing pressure sensors in each tire, the method determines tire pressure indirectly based on wheel speed and temperature. A tire pressure prediction model trained using historical tire data is used. The model takes wheel speed and temperature as inputs and outputs predicted tire pressure. The model can be updated over time as actual tire pressure readings are received. This allows improving model accuracy based on the specific vehicle's tires.
4. End-to-End Tire Performance Margin Identification Model Using Vehicle Data for AI-Based Prediction
JILIN UNIVERSITY, UNIV JILIN, 2024
Modeling an end-to-end tire performance margin identification model using vehicle data to accurately estimate tire condition without direct sensor measurements. The method involves obtaining tire performance margins from vehicle data, segmenting the labeled data, and training an AI model on the segmented data to predict tire performance margins from new vehicle data.
5. Stacked Denoising Self-Encoder Model with Attention for Predicting Tire Lateral Force from Production Parameters
Hefei University of Technology, HEFEI UNIVERSITY OF TECHNOLOGY, 2023
Detecting tire lateral force using deep learning to enable tire uniformity quality control without relying on expensive equipment. The method involves training a stacked denoising self-encoder model with attention using tire production process parameters. The trained model can then predict tire lateral force from the process parameters, allowing in-line tire uniformity detection using data that is already being collected during production. This provides real-time tire quality monitoring at lower cost compared to traditional equipment-based lateral force measurement.
6. Machine Learning-Based System for Estimating Tire Health Variables Using Iteratively Refined Models
BRIDGESTONE AMERICAS TIRE OPERATIONS LLC, 2023
Digital tire health estimation for predicting tire wear, fatigue, and damage using machine learning models. The method involves generating tire health models based on input variables like tire type, load, pressure, speed, temperature, etc. These models are iteratively refined over time using historical data. When a tire's input values are measured, the appropriate model is selected and tire health variables like tread depth, carcass health, and ply crack growth are estimated. An output signal indicates the tire's overall health. The method allows predicting tire wear, fatigue, and damage for proactive maintenance and tire management.
7. Machine Learning-Based Feature Extraction System for Tire Sensor Data Analysis
TOYO TIRE CORP, 2023
Estimating tire wear more accurately by extracting features from tire sensor data using machine learning models. The system involves installing a sensor on the tire to measure physical quantities related to deformation. A learning-based model extracts features from the sensor data and estimates the tire wear index. This improves wear estimation accuracy compared to directly using the raw sensor data. The extracted features are more representative of tire condition compared to raw sensor values.
8. Convolutional Neural Network-Based Tire Force and Parameter Estimation System with Feature Extraction and Normalization
TOYO TIRE CORP, 2023
A tire physical information estimation system that accurately estimates tire forces and other parameters using a deep learning model. The system has a convolutional neural network (CNN) with input layers, feature extraction layers, and output layers. The CNN takes tire motion data as input, extracts features, and outputs estimated tire forces and other physical parameters. The CNN uses convolution operations and normalization to process the tire motion data and extract relevant features. This allows accurate estimation of directional tire forces using a learning-based approach.
9. Two-Stage Machine Learning System for Predicting Vehicle Attributes from Tire Design and Dynamics Data
GEELY HOLDING GROUP CO LTD, NINGBO GEELY AUTOMOBILE RES & DEVELOPMENT CO LTD, NINGBO GEELY AUTOMOBILE RESEARCH & DEVELOPMENT CO LTD, 2022
Predicting real vehicle attributes like load and handling stability using machine learning models trained on tire design and dynamics databases. The method involves two prediction models. A first model predicts tire external characteristics like hysteresis loss based on tire design parameters. A second model predicts vehicle attributes like stability based on the tire external characteristic predictions. This two-stage approach improves real vehicle attribute prediction accuracy compared to directly predicting vehicle attributes from tire design.
10. Machine Learning-Driven Tire Wear Prediction and Vehicle Dynamics Adjustment System
HYUNDAI MOTOR CO, HYUNDAI MOTOR CO LTD, KIA CORP, 2022
Artificial intelligence-based tire wear prediction method for autonomous vehicles that can predict tire wear life and optimize tire durability through active control of vehicle dynamics. The method uses machine learning to analyze tire wear factors from real-world testing and predicts tire wear life for each tread groove. This wear data is then used to optimize vehicle parameters like braking, suspension, steering, and turning to maximize tire life. The wear predictions are provided to the vehicle's electronics for active control.
11. Neural Network-Based System for Real-Time Estimation of Tire Force and Friction Coefficient Using Sensor Data
TOYO TIRE CORP, 2022
Real-time estimation of physical tire properties like tire force and friction coefficient using a neural network model. The model takes input data from sensors to estimate tire-specific metrics related to tire contact forces and friction. The neural network has an arithmetic model with an input layer, output layer, and a feature extraction layer that applies convolution operations to extract features from the input data. This allows real-time estimation of physical tire properties without relying on vehicle dynamics and accelerometers.
12. AI-Based Real-Time Tire Condition Simulation and Monitoring System for Unmanned Vehicles
ZHANG YITING, 2022
An unmanned vehicle tire monitoring method using AI to predict tire conditions and prevent failures. The method involves monitoring tire temperature and pressure in real-time, and using AI models to simulate future tire conditions based on historical data. By comparing the simulated conditions to the current readings, it can detect if the tire is at risk of overheating or overpressure. This allows early warning and intervention to prevent internal cracks or bursts. The AI models are trained using historical tire data from multiple vehicles to account for variation in tire wear and loading.
13. Machine Learning-Based Tire Force Prediction Model Using Dynamic Driving Data
JIANGSU SCIENCE AND TECHNOLOGY UNIV, JIANGSU SCIENCE AND TECHNOLOGY UNIVERSITY, 2022
Data-driven tire modeling method for accurate and efficient tire force prediction in vehicle dynamics. The method involves capturing tire force data during dynamic driving conditions and using machine learning techniques to build a tire model that can predict tire forces based on vehicle and road inputs. This allows more accurate and dynamic tire force prediction compared to traditional tire models built using static testing and mechanical theory. The method involves collecting tire force data during dynamic driving conditions, feature engineering to extract relevant variables, and training a machine learning model using this data to predict tire forces for different vehicle and road inputs. This provides a more accurate and dynamic tire model for vehicle dynamics applications compared to traditional steady-state tire models built using static testing and mechanical theory.
14. Machine Learning-Based System for Predicting Tire Contact Patch Dimensions and Configurations
SUBRAMANIAN CHIDAMBARAM, VOLVO TRUCK CORP, 2022
Optimizing tire contact patches using machine learning to find the best tire configuration for a vehicle based on vehicle parameters, road conditions, and driver preferences. The method involves two machine learning models. The first model takes vehicle data like velocity, tire pressure, load, road surface, and center of gravity motion to predict optimal tire contact patch dimensions. The second model takes the predicted patch dimensions, vehicle data, and driver preferences to determine the optimal tire pressure and suspension adjustment for the load. This iterative process of predicting and adjusting tire configurations using machine learning allows finding optimal tire setups for specific driving conditions and preferences.
15. Machine Learning-Based System for Weighted Factor Analysis in Tire Durability Prediction
SPRINGCLOUD INC, 2022
Using machine learning to accurately predict tire durability in various conditions beyond just laboratory tests. The method involves assigning weights to factors like temperature, road conditions, and load, scoring them based on a formula, and training a machine learning model on the scored data. This allows quantitative analysis of environmental and vehicle effects on tire durability. The model is then used to predict tire longevity based on input conditions.
16. BP Neural Network-Based Tire Wear Life Estimation Method and Device Incorporating Tire Pressure, Vehicle Speed, Load, and Modal Frequency Data
JIANGSU UNIVERSITY OF TECHNOLOGY, UNIV JIANGSU TECHNOLOGY, 2021
Intelligent tire wear life estimation method and device based on BP neural networks for accurately predicting tire wear life using a neural network trained on factors like tire pressure, vehicle speed, load, and modal frequencies. The method involves acquiring tire data, splitting into training, validation, and test sets, creating a BP neural network, training it on the first sets, and estimating wear life using the trained network on the test set.
17. Real-Time Tire Behavior Modeling System Using Neural Network-Based Vehicle Data Analysis
AUDI AG, VOLKSWAGEN AG, VOLKSWAGEN AKTIENGESELLSCHAFT, 2021
Enhancing vehicle performance by dynamically modeling tire behavior in real-time to improve traction and cornering. The method involves using vehicle data like acceleration, steering, and thrust to predict tire performance factors like cornering limits. This allows adjusting the vehicle's lateral guidance profile based on real-time tire behavior instead of fixed conservative limits. The tire performance predictions are made using a trained neural network analyzing historical vehicle data.
18. Method for Extracting Changes in Tire Characteristics Using Historical Sensor Data
GOODYEAR TIRE & RUBBER, THE GOODYEAR TIRE & RUBBER CO, 2021
A method to improve the accuracy of tire condition estimation systems by extracting changes in tire characteristics over the life of the tire. The method involves using historical sensor data to model the relationship between specific tire characteristics and tire conditions. By isolating and analyzing the underlying trend in the characteristic of interest, like tread depth, while accounting for external factors, it provides more accurate predictions of tire wear state and load compared to direct measurement techniques.
19. Artificial Neural Network-Based System for Analyzing Time-Varying Tire Sensor Data to Detect Anomalies
MICRON TECHNOLOGY INC, 2021
Predictive maintenance for vehicle tires using artificial neural networks to analyze sensor data over time to identify issues and recommend maintenance before failures. The technique involves measuring tire parameters with sensors, feeding the time-varying data into an ANN to analyze for issues, and generating maintenance recommendations based on the ANN results. This allows proactive tire maintenance instead of relying on fixed schedules. The ANN can learn to detect tire problems and predict maintenance needs based on historical data.
20. Onboard Sensor-Based Real-Time Tire Pressure Prediction System Utilizing Machine Learning Classification Model
New H3C Technologies Co., Ltd., H3C HOLDING LTD, 2020
Monitoring vehicle tire pressure in real-time while driving using onboard sensors and machine learning. The method involves acquiring vehicle driving data like video, speed, and position. This data is input into a pre-trained classification model to predict the tire pressure. By periodically checking tire pressure using the model, the actual tire pressure can be monitored without physical sensors. The model is trained on sample driving data with known tire pressures.
Request the PDF report with complete details of all 22 patents for offline reading.