FCHEV Energy Control With Sensor Fault Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing control and energy management systems for fuel cell hybrid electric vehicles (FCHEVs) face challenges such as slow dynamic response, limited robustness against parametric uncertainties, and a lack of effective mechanisms to handle sensor faults, leading to performance degradation and instability under dynamic driving conditions.
Innovation Solution
A fault-tolerant control system integrating fractional-order sliding mode control with Radial Basis Function Neural Networks (RBFNNs) for rapid convergence and sensor fault compensation, utilizing a minimum learning parameter scheme to enhance robustness and accuracy, and maintain DC-bus voltage stability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Stability of the object's composition
If conventional control algorithms are used for FCHEV energy management, then the system achieves asymptotic stability, but the convergence rate is slow under varying load conditions
Solution Approach 1:
The patent applies finite-time stability theory to change the convergence characteristics of the control system. By designing the control law with finite-time stability parameters, the system transitions from asymptotic convergence to finite-time convergence, significantly improving the convergence rate while maintaining stability under varying load conditions
2Ease of operation
If conventional control algorithms are used, then the system operates under fault-free assumptions, but the system performance degrades when sensor faults occur
Solution Approach 1:
The patent introduces an intermediary fault estimation mechanism that acts between the sensor and the controller. This intermediary component estimates sensor faults in real-time and provides compensated measurements to the controller, enabling the system to maintain reliability and performance even when sensor faults occur, without significantly increasing control complexity
3Device complexity
If integer-order calculus is used for control, then the control algorithm is simpler, but the robustness and adaptability are limited
Solution Approach 1:
The patent changes the mathematical order parameter from integer-order to fractional-order calculus in the control algorithm. This parameter change enhances the system's robustness and adaptability by providing additional degrees of freedom in control design, allowing better handling of uncertainties and varying operating conditions while maintaining reasonable algorithm complexity
4Stability of the object's composition
If asymptotic convergence is targeted, then the system achieves stability as time approaches infinity, but the current tracking accuracy is insufficient for dynamic driving conditions
Solution Approach 1:
The patent changes the convergence time parameter from infinite (asymptotic) to finite by designing a finite-time stable control law. This ensures that the current tracking error converges to zero within a predetermined finite time, providing both stability and high tracking accuracy for dynamic driving conditions
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
The system ensures rapid current tracking with finite-time stability, improved robustness to sensor faults and parametric uncertainties, and efficient energy management across varying driving conditions, enhancing the FCHEV's performance and reliability.
Implementation Method 1
a sensor fault is detected and estimated in at least one of the plurality of current measurements using a radial basis function neural network (RBFNN)
Implementation Method 2
using a fractional-order sliding mode control strategy with finite-time stability to compensate for the estimated sensor fault
Implementation Method 3
Fuel cells generate electricity through electrochemical reactions with water and oxygen as byproducts
Implementation Method 4
The electric vehicle with multiple energy sources is commonly referred to as a fuel-cell hybrid electric vehicle (FCHEV)
Implementation Method 5
batteries and/or ultracapacitors together with the fuel cells to power the drivetrain of the electric vehicle
Data Source
AI summary
A method for controlling a fuel cell hybrid electric vehicle (FCHEV) with sensor fault tolerance includes receiving current measurements of a fuel cell, a battery, an ultracapacitor, and a voltage measurement of a DC-bus from sensors; detecting and estimating a sensor fault in at least one of the current measurements using a radial basis function neural network (RBFNN); calculating a new value for a single parameter of the RBFNN according to a minimum learning parameter scheme; calculating a duty cycle value for each power converter; and applying the calculated duty cycle value to power converters that connect the fuel cell, the battery, and the ultracapacitor to the DC-bus, to maintain a current distribution despite the sensor fault.