Energy-Efficient Vehicle Track Generation With Route-Specific Speed Profiles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for evaluating fuel efficiency in motor vehicles do not accurately account for the specific portion of the route traveled and cannot be applied in a global fuel consumption control system with vehicles of different specifications, lacking a convenient graphical user interface for driver guidance.
Innovation Solution
A computer device generates an energy-efficient track for a motor vehicle by collecting and analyzing data from both the vehicle and the route, using a CPU and memory to perform steps that include generating a speed profile, evaluating energy efficiency, and adjusting the vehicle's operation to minimize energy consumption based on actual and estimated data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If fuel efficiency evaluation is based on similar vehicles and driving modes only, then evaluation precision is improved, but system adaptability deteriorates
Solution Approach 1:
The system segments the evaluation process into two distinct phases: an offline training phase where a neural network is trained on data from similar vehicles to achieve precise fuel efficiency evaluation, and an online evaluation phase where the trained model is applied to new vehicles. This segmentation allows the system to maintain high precision through specialized training while achieving broad adaptability through the generalizable neural network model.
Solution Approach 2:
The system performs preliminary training of the neural network model using data from multiple vehicles with different specifications before actual fuel efficiency evaluation begins. This preliminary action creates a pre-trained model that can be quickly applied to new vehicles, resolving the contradiction by preparing the evaluation tool in advance to handle diverse vehicle types while maintaining evaluation precision.
2Measurement precision
If detailed route-specific data is collected for fuel efficiency evaluation, then evaluation accuracy is improved, but data processing complexity increases
Solution Approach 1:
The neural network model serves as an intermediary between raw route-specific data and fuel efficiency evaluation results. Instead of directly processing detailed route data through complex algorithms, the system uses the trained neural network to automatically process and interpret the data, reducing processing complexity while maintaining or improving evaluation accuracy through the model's learned patterns.
3Loss of energy
If real-time feedback and control signals are provided to drivers, then energy consumption reduction is improved, but system complexity increases
Solution Approach 1:
The system implements a feedback mechanism where fuel efficiency evaluation results are provided to drivers through the user interface, enabling them to adjust their driving behavior. This feedback loop allows the system to reduce energy consumption by guiding drivers toward more efficient driving patterns without requiring complex real-time control systems, as the feedback itself empowers drivers to make optimal decisions.
Data Source
AI summary
The proposed invention relates to methods for controlling energy consumption by a motor vehicle and can be used in transportation industry. The technical problem to be solved by the claimed invention is to provide a method, a device and a system that do not possess the drawbacks of the prior art and thus make it possible to generate an accurate energy-efficient track for a motor vehicle that allows to reduce energy consumption by the motor vehicle on the specific portion of the route. The objective of the claimed invention is to overcome the drawbacks of the prior art and thus to reduce energy consumption by the motor vehicle on the specific portion of the route.