Hard-wired RBF Model Calculation Unit for Real-time Engine Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data-based models, such as Gaussian process models, require high computing capacity to achieve sufficient accuracy and struggle to meet real-time calculation requirements in control units for complex systems like internal combustion engines, due to their high number of nodes.
Innovation Solution
A hard-wired model calculation unit is designed for a processor core to efficiently calculate Radial Basis Function (RBF) models using fixed processing algorithms and local length scales, reducing processing load and enabling real-time calculations by implementing an RBF model in hardware, which can be used in control units for motor vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data-based models with high number of nodes are used to achieve sufficient modeling accuracy, then modeling precision is improved, but computing capacity requirements increase and real-time calculation becomes difficult
Solution Approach 1:
The model calculation unit is divided into multiple functional blocks (exponential function calculation block, distance calculation block, multiplication block, accumulation block) that process different parts of the RBF model calculation independently and in parallel, enabling high-accuracy computation with improved speed
Solution Approach 2:
The patent replaces software-based model calculation with a hard-wired hardware circuit implementation, substituting the mechanical/software system with an electronic hardware system that performs RBF model calculations in real-time with high precision
2Ease of operation
If data-based functional models are calculated in software-controlled microprocessors, then ease of operation is maintained, but processing load increases and real-time calculation is not achieved
Solution Approach 1:
The patent merges the microprocessor control unit with a dedicated hard-wired model calculation unit into a single integrated control device, combining the advantages of software controllability with hardware acceleration for real-time RBF model calculation
Solution Approach 2:
The hard-wired model calculation unit acts as an intermediary between the microprocessor and the RBF model calculation, offloading the computationally intensive tasks from the software-controlled microprocessor to the hardware circuit while maintaining software controllability
3Measurement precision
If Gaussian process models with high number of nodes are used, then modeling accuracy is improved, but device complexity and computing capacity requirements increase
Solution Approach 1:
The patent changes the mathematical parameters and structure by using RBF model with local length scales instead of Gaussian process models, achieving comparable or superior modeling accuracy with fewer nodes and reduced device complexity through the hardware-accelerated calculation architecture
Data Source
AI summary
A model calculation unit for calculating an RBF model is described, including a hard-wired processor core designed as hardware for calculating a fixedly predefined processing algorithm in coupled functional blocks, the processor core being designed to calculate an output variable for an RBF model as a function of one or multiple input variable(s) of nodes V[j,k], of length scales (L[j,k]), of weighting parameters p3[j,k] predefined for each node, the output variable being formed as a sum of a value calculated for each node V[j,k], the value resulting from a product of a weighting parameter p3[j,k] assigned to the particular node V[j,k], and a result of an exponential function of a value resulting from the input variable vector as a function of a square distance of the particular node (V[j,k]), weighted by the length scales (L[j,k]), the length scales (L[j,k]) being provided separately for each of the nodes as local length scales.