EV Route Selection Using Expert Systems and Fuzzy Logic
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for managing electric vehicle (EV) routing lack efficient algorithms that consider multiple factors such as battery charging station locations, travel time, roadway conditions, traffic congestion, and energy usage, leading to suboptimal route selection and increased range anxiety.
Innovation Solution
The implementation of artificial intelligence expert systems with battery energy management and navigation route control, utilizing propositional logic and fuzzy logic calculations to evaluate and select routes based on real-time data, including vehicle specifications, energy requirements, and environmental factors, to optimize EV travel and charging routes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional routing systems are used for EVs, then route selection is simple, but energy efficiency and travel time optimization are insufficient
Solution Approach 1:
The routing system is segmented into multiple independent modules: energy consumption calculator, route evaluator, charging station locator, and traffic condition analyzer. Each module handles a specific aspect of route optimization, allowing the system to process multiple factors simultaneously without becoming unmanageably complex.
Solution Approach 2:
The system performs preliminary calculations of energy consumption for each potential route segment before final route selection. By pre-evaluating energy requirements, charging needs, and traffic conditions for all possible routes, the system can quickly select the optimal route without complex real-time computations during travel.
2Reliability
If multiple factors are considered in route selection, then routing optimization improves, but system complexity increases
Solution Approach 1:
The evaluation system divides multiple routing factors into separate calculation modules: energy consumption, travel time, charging requirements, and traffic conditions. Each factor is evaluated independently by its dedicated module, then results are integrated to select the optimal route, maintaining system reliability without overwhelming complexity.
Solution Approach 2:
The system evaluates more route factors than traditionally necessary (including energy consumption, charging needs, traffic, and time), but implements this through a modular architecture where only relevant modules are activated based on current vehicle state and route options, preventing complexity from becoming unmanageable.
3Measurement precision
If real-time data processing is implemented, then routing accuracy improves, but computational requirements increase
Solution Approach 1:
The system pre-calculates energy consumption values for each route segment based on historical data and vehicle specifications before real-time travel begins. During actual route selection, only minor adjustments are made based on real-time traffic and charging station availability, significantly reducing the computational power needed during active navigation.
Solution Approach 2:
The system processes real-time data selectively rather than continuously - updating route evaluations only when significant changes occur in traffic conditions, battery state, or charging station availability. This partial real-time processing maintains high precision while minimizing computational power consumption during normal operation.
Data Source
AI summary
The present invention provides specific systems, methods and algorithms based on artificial intelligence expert system technology for determination of preferred routes of travel for electric vehicles (EVs). The systems, methods and algorithms provide such route guidance for battery-operated EVs in-route to a desired destination, but lacking sufficient battery energy to reach the destination from the current location of the EV. The systems and methods of the present invention disclose use of one or more specifically programmed computer machines with artificial intelligence expert system battery energy management and navigation route control. Such specifically programmed computer machines may be located in the EV and/or cloud-based or remote computer/data processing systems for the determination of preferred routes of travel, including intermediate stops at designated battery charging or replenishing stations. Expert system algorithms operating on combinations of expert defined parameter subsets for route selection are disclosed. Specific fuzzy logic methods are also disclosed based on defined potential route parameters with fuzzy logic determination of crisp numerical values for multiple potential routes and comparison of those crisp numerical values for selection of a particular route. Application of the present invention systems and methods to autonomous or driver-less EVs is also disclosed.