ECU Simulator Matrix Scheduling for Real-Time HIL Testing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for matrix-vector multiplication in hardware-in-the-loop simulations, particularly using FPGAs, are inefficient due to the need for numerous elementary additions, leading to high computational overhead and difficulty in achieving real-time calculations for complex systems like electric drives.
Innovation Solution
The method decomposes matrix-vector multiplication into a sequence of summations by prioritizing matrix elements with the highest summation usability and reusing identical products and sums, using a sequence determination step and residual matrices to optimize the calculation process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If matrix-vector multiplication is performed using traditional elementary addition methods on FPGAs, then the calculation can be implemented with basic hardware components, but the computational overhead is high and real-time calculation is difficult to achieve
Solution Approach 1:
The patent segments the matrix-vector multiplication process into multiple parallel calculation paths. Each path processes a subset of the multiplication operations simultaneously, dividing the computational workload into manageable segments that can be executed in parallel on FPGA hardware, thereby reducing overall computation time while maintaining implementability with basic components.
Solution Approach 2:
The patent performs preliminary actions by pre-calculating and storing intermediate results of the matrix-vector multiplication. Common sub-expressions and partial products are computed in advance and cached, so that when the full multiplication is needed, the system can retrieve and combine these pre-computed values rather than recalculating them, significantly reducing real-time computational overhead.
2Measurement precision
If the mathematical environment model is calculated numerically with high accuracy, then the simulation results are reliable, but the calculation time increases and real-time simulation requirements cannot be met
Solution Approach 1:
The patent applies partial action by calculating only the essential components of the environment model with full precision, while approximating less critical components. This selective approach maintains sufficient simulation accuracy for the most important parameters while reducing the overall computational burden, enabling real-time simulation performance.
Solution Approach 2:
The patent dynamically adjusts numerical parameters such as precision levels, integration step sizes, and calculation tolerances based on the current simulation state and real-time requirements. When real-time performance is critical, parameters are adjusted to reduce computation time while maintaining acceptable accuracy, thus resolving the trade-off between precision and speed.
3Speed
If complex environment models are simulated in real-time, then the simulation meets timing requirements, but the hardware resource utilization increases and simpler calculation methods become insufficient
Solution Approach 1:
The patent implements a nested hierarchical structure where the environment model is decomposed into multiple levels of abstraction. Complex subsystems are modeled with high fidelity when needed, while simpler aggregated models are used for less critical components. This nesting allows the system to achieve real-time performance by selectively applying detailed models only where necessary, reducing overall hardware resource requirements.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Described and illustrated is a computer-implemented method (1) for testing an electronic control unit (2) with a simulator (3), wherein the simulator (3) numerically computes a mathematical environment model (4) on a computing unit, wherein the environment model (4) at least partially simulates the environment of the control unit (2), wherein the control unit (2) and the simulator (3) are coupled to each other and interact with each other via corresponding I/O interfaces (5, 6), wherein a matrix-vector multiplication is performed on the simulator (3) during the numerical computation of the environment model (4), in which a matrix (M) is multiplied by a vector (v) to form a result vector (r), wherein the matrix-vector multiplication is decomposed into a sequence of summations (b) of two summands, each summand being a product of two factors.where one factor is an element (ki) of the matrix (M) and the other factor is an element (vj) of the vector (v). Optimized planning and execution of the matrix-vector multiplication is achieved by determining, in a sequence determination step (8), the summation (b) whose summands depend on matrix elements (ki) from the highest-populated row (s) of the matrix (M), wherein the matrix elements (ki) from the highest-populated row (s) are chosen that have the highest summation usability (P), and the sequence determination step (8) is repeated with a residual matrix (M') instead of the matrix (M) until the residual matrix (M') no longer contains any non-zero matrix elements, wherein the residual matrix (M') is obtained from the matrix (M) by setting all matrix elements (Mij) in the matrix (M) to zero.that are involved in a summation (b) already planned in the sequence, that the summations (b) are carried out in the planned sequence, wherein the product operations for calculating the summands are carried out in the sequence as the summands are required for carrying out the summation (b), and that in a final summation step (9) the sums resulting from the previous summation (b) in each row of the result vector (r) are calculated by successive pairwise addition.