EV Battery Consumption Prediction via Multi-Source Data Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing battery consumption prediction systems for electric vehicles fail to accurately estimate battery usage due to neglecting factors such as driver behavior, external environment conditions, and vehicle state, leading to inaccurate distance and time estimates.
Innovation Solution
A device and method that collects and processes information on the vehicle's state and external environment, including drive mode, weather, and traffic, to predict battery consumption, with a learning module that adjusts reliability based on actual vs. predicted consumption differences, providing a consumption table with reliability feedback.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If battery consumption is predicted based only on voltage or current measurements, then the prediction method is simple, but the prediction accuracy is low because factors like driving pattern, weather, and traffic conditions are not considered
Solution Approach 1:
The prediction system is segmented into multiple independent modules: a collection module that gathers data from multiple sources (voltage, current, driving pattern, weather, traffic), a prediction module that processes this data, and a learning module that improves accuracy over time. This segmentation allows the system to consider comprehensive factors while maintaining manageable complexity through modular design.
Solution Approach 2:
The prediction system is designed to handle multiple types of input data (electrical parameters, environmental conditions, driving behaviors) through a unified prediction framework. The learning module serves multiple functions by both training the prediction model and providing feedback mechanisms, making the system multi-functional and adaptable to various prediction scenarios.
2Reliability
If multiple factors including driving pattern, weather, and traffic are considered in prediction, then prediction accuracy improves, but the system complexity increases
Solution Approach 1:
The system incorporates a learning module that receives feedback from the difference between predicted and actual battery consumption. This feedback mechanism continuously trains the prediction model, improving reliability over time. The feedback loop allows the system to adapt to varying conditions and refine its predictions based on real-world performance.
Solution Approach 2:
The collection module proactively gathers all necessary data (voltage, current, driving pattern, weather, traffic) before the prediction is made. This preliminary data collection ensures that when prediction is performed, all relevant factors are already available, improving reliability without requiring complex real-time processing during the prediction moment.
3Measurement precision
If the system collects and processes multiple types of information (vehicle state, external environment), then the prediction becomes more accurate, but the data processing complexity increases
Solution Approach 1:
Data collection is segmented into distinct categories (vehicle electrical parameters, driving pattern data, environmental conditions, traffic information) handled by the collection module. Each data type is processed independently through specific algorithms, reducing the overall complexity compared to handling all data uniformly. This segmentation makes the system more manageable and easier to implement.
Solution Approach 2:
The learning module acts as an intermediary between the diverse data sources and the prediction algorithm. It standardizes and preprocesses the multi-source data, transforming various types of inputs into a unified format suitable for prediction processing, thereby reducing the difficulty of handling heterogeneous data.
Data Source
AI summary
A system and a method for predicting a battery consumption of an electric vehicle are disclosed. The battery consumption prediction system of the electric vehicle predicts the battery consumption considering an overall state of the electric vehicle and an external environment of the electric vehicle. The battery consumption prediction system of the electric vehicle may be associated with an artificial intelligence module, a robot, an augmented reality (AR) device, a virtual reality (VR) device, devices related to 5G services, and the like.