Vehicle Vibration Control Using ML Prediction and Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for suppressing vibrations in vehicles are static and do not fully utilize modern sensory systems, primarily focusing on material improvements and static dampers, which fail to adapt to dynamic driving conditions and external factors effectively.
Innovation Solution
An electronic system utilizing a machine learning-based approach that integrates data from various sensors, including LiDAR, RADAR, cameras, and IMUs, to predict and counteract vibrations through actuators, optimizing vibration cancellation across multiple areas of interest within a vehicle.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional static dampers and material improvements are used, then vibration suppression is achieved, but the system cannot adapt to dynamic driving conditions and external factors
Solution Approach 1:
The patent transforms the static vibration suppression system into a dynamic one by implementing real-time sensor data acquisition and machine learning-based prediction. The system continuously monitors road conditions, vehicle movements, and vibration patterns, then dynamically adjusts actuator responses to counteract vibrations adaptively, resolving the contradiction between adaptability and reliability.
Solution Approach 2:
The system performs preliminary action by using machine learning models to predict upcoming vibrations based on sensor data from LiDAR, RADAR, cameras, and IMUs. The actuators are activated in advance to counteract predicted vibrations before they occur, enabling proactive adaptation to dynamic conditions while maintaining reliable vibration suppression.
2Adaptability or versatility
If modern sensory systems are fully utilized for vibration prediction, then adaptability improves, but system complexity increases
Solution Approach 1:
The patent merges multiple sensor systems (LiDAR, RADAR, cameras, IMUs) and integrates them with machine learning algorithms into a unified vibration prediction and control system. This consolidation approach enables comprehensive real-time prediction capability while managing system complexity through integrated architecture rather than separate independent systems.
Solution Approach 2:
The system replaces traditional mechanical vibration suppression approaches with intelligent software-based machine learning models that process sensor data and generate actuator control signals. This substitution reduces mechanical complexity while enhancing adaptability through computational intelligence.
3Measurement precision
If multiple sensors and machine learning systems are integrated, then vibration control precision improves, but computational requirements and processing time increase
Solution Approach 1:
The system implements continuous vibration monitoring and control through real-time sensor data acquisition and continuous machine learning inference. The actuators provide continuous counter-vibration output, ensuring uninterrupted vibration suppression with high precision while maintaining real-time responsiveness through ongoing computational processing.
Solution Approach 2:
The system incorporates feedback loops where sensor measurements of actual vibrations are continuously fed back to the machine learning model, which adjusts actuator control signals in real-time. This feedback mechanism enhances measurement precision through iterative optimization while managing processing time through efficient closed-loop control algorithms.
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
This solution significantly reduces passenger discomfort and fatigue by dynamically adapting to changing road conditions and external factors, providing real-time vibration control and improving overall vehicle stability.
Implementation Method 1
convert, by means of a machine learning system, the input data into actuator settings
Implementation Method 2
generating the same frequency and amplitude at 180° out of phase and then adding it to the original frequency
Data Source
Figure 1
Figure 2a~2c
Figure 3a~3c
AI summary
An electronic system for controlling vibrations and/or inertial forces occurring at a plurality of areas of interest within an operating vehicle, the electronic device comprising circuitry configured to: receive input data comprising sensor data from one or more environment sensors (12) and/or one or more internal sensors (14); convert, by means of a machine learning system (18), the input data into actuator settings; and transmit the actuator settings to one or more actuators (20) to control vibrations and/or inertial forces occurring at each of the plurality of areas of interest within the vehicle.