Ultrasonic Tire Type Detection Using AI and Vehicle Speed Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automotive sensor technologies face challenges in accurately determining tire types, such as summer or winter tires, which is crucial for improved control and regulation in autonomously driving vehicles, especially when environmental factors like weather and road conditions are considered.
Innovation Solution
A computer-implemented method for training an AI module using ultrasound data from existing sensors, such as ultrasonic sensors, to differentiate tire types by generating a training data set that includes ultrasound and speed data, and correlating these with tire type information, allowing for improved detection accuracy and reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing sensors are used to detect tire types, then hardware cost is reduced, but measurement precision is insufficient
Solution Approach 1:
The patent applies multi-functionality by enabling existing ultrasonic sensors to serve dual purposes: their original function for distance measurement and a new function for tire type classification. The sensor system processes ultrasonic signals to extract features that indicate tire type (summer, winter, all-season) without requiring dedicated tire detection hardware, thus reducing device complexity while improving measurement precision through AI-based analysis
Solution Approach 2:
The patent changes the parameter analysis approach by transforming raw ultrasonic sensor data into feature vectors that capture tire-specific characteristics. The AI module learns to recognize patterns in ultrasonic signal parameters (amplitude, frequency, time-of-flight variations) that correlate with different tire types, enabling accurate classification using existing sensor capabilities
2Measurement precision
If AI module is trained with comprehensive data, then detection accuracy improves, but training time and computational resources increase
Solution Approach 1:
The patent applies preliminary action by pre-processing ultrasonic sensor data into structured feature vectors before feeding them to the AI module. The training data is prepared in advance with extracted features that capture essential tire characteristics, allowing the AI model to learn more efficiently from pre-organized information rather than raw sensor streams, thus reducing training time while maintaining high detection accuracy
Solution Approach 2:
The patent segments the training process by dividing the dataset into distinct categories (summer tires, winter tires, all-season tires) and processing them separately during training. This segmentation allows the AI module to learn specific patterns for each tire type more efficiently, improving convergence speed and reducing overall training time while achieving high accuracy across all categories
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The method achieves a high detection accuracy of at least 95% for tire types, even in varying conditions, using existing sensors without the need for additional hardware, enhancing the reliability and efficiency of autonomous vehicle control.
Implementation Method 1
the ultrasonic data describe at least one ultrasonic wave which was generated by a tire of the motor vehicle rolling
Data Source
Figure 1~2
Figure 3~4
AI summary
The invention relates to a computer-implemented method (100) for training an artificial intelligence (AI) module (204) to determine a tyre type of a motor vehicle (300), comprising the steps of: - providing (S1) a measured value dataset on a data carrier, wherein the measured value dataset contains at least one data entry regarding ultrasound data, speed data and tyre data, wherein the ultrasound data describe at least one ultrasonic wave that was produced by rolling of a tyre (302) of the motor vehicle (300), wherein the speed data describe a speed of the motor vehicle (300), wherein the tyre data describe a tyre type of the motor vehicle (300), - generating (S2) a modified training dataset based on the measured value dataset, wherein generating the modified training dataset comprises the steps of: - forming an input dataset (S2a) based on the ultrasound data and the speed data of the measured value dataset, - forming an output dataset (S2b) based on the tyre data of the measured value dataset, - training (S3) the AI module (204) based on the modified training dataset.