BEV Power Consumption Forecasting for Refrigerated Delivery Range
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Battery Electrical Vehicles (BEVs) have limited autonomy compared to thermal engines, and there is a need to accurately forecast energy consumption for refrigeration units to optimize daily operations, including distance traveled and battery pack cooling autonomy.
Innovation Solution
A method and system that utilize real-time vehicle data, including state of charge, load conditions, and weather forecasts, to estimate energy consumption and display the impact on remaining kilometers, incorporating a machine learning model to analyze user driving patterns and adjust calculations for temperature differences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If real-time data collection and machine learning models are implemented to forecast energy consumption, then measurement precision and reliability are improved, but device complexity increases
Solution Approach 1:
The electronic control unit performs multiple functions including data collection, machine learning model execution, energy consumption forecasting, and user interface management within a single integrated component, reducing the need for separate dedicated systems for each function
Solution Approach 2:
The system uses the vehicle's existing sensors, processors, and communication infrastructure to power and execute the forecasting system, rather than requiring entirely separate dedicated hardware, thereby leveraging existing resources to minimize added complexity
2Loss of information
If comprehensive real-time vehicle data and weather forecasts are processed to calculate distance estimates, then information completeness is improved, but loss of time increases
Solution Approach 1:
The machine learning model is pre-trained with historical data and weather patterns, allowing it to rapidly process current inputs and generate forecasts without requiring extensive real-time computation, thus reducing calculation time while maintaining information completeness
Solution Approach 2:
The system continuously monitors actual energy consumption against forecasts and adjusts model parameters in real-time, enabling faster convergence to accurate predictions by leveraging ongoing feedback rather than requiring complete initial data processing
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for managing power consumption in a BEV (100) includes obtaining real time vehicle data via an ECU (111) of the BEV and receiving information regarding deliveries that are planned by a user for a specific day based on a user input or data acquisition from a remote database (119). The method further includes determining consumption of energy for completion of the deliveries on the specific day based on the obtained real time vehicle data and the received information and then calculating a distance that can be traveled by the BEV based on the determined consumption of energy. The method further includes determining a temperature difference between an internal temperature of a TRU (101) of the BEV and an external temperature outside the TRU in real time, estimating an impact of the determined temperature difference on the determined consumption of energy, and thereafter displaying the results of the estimation on an HMI (117).