Unlock instant, AI-driven research and patent intelligence for your innovation.

Generating simplified models for XiL systems

A technology for simplifying models and models, applied in general control systems, biological neural network models, control/regulation systems, etc., can solve problems such as unusable models

Pending Publication Date: 2022-04-22
FORD GLOBAL TECH LLC
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Accordingly, correspondingly complex models cannot be used in such cases

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Generating simplified models for XiL systems
  • Generating simplified models for XiL systems
  • Generating simplified models for XiL systems

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The following is based on figure 1 The method for generating a simplified model for use in the XiL system according to the present invention is explained in more detail. In a first step 1 , at least one specified parameter that quantitatively characterizes the complexity of the model is determined for at least one starting model. In this case, the parameters may be specified during the course of the method or may have been specified and predefined. It is also possible to determine a plurality of prescribed parameters for the activation model that quantitatively characterize the complexity of the activation model.

[0038] In a next step 2, input data and output data of at least one starting model are generated. In step 3, using the generated training set of input data and output data of the at least one priming model to train the neural network to generate or develop a simplified model, wherein the simplified model has a lower complexity than the complexity of the at ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a method for generating a simplified model for use in a XiL system, comprising the following steps: determining specified parameters (1) for starting the model, which quantitatively characterize the complexity of the model; generating input data and output data of the starting model (2); training the neural network using a training set of the generated input data and output data of the start-up model in order to generate a simplified model having a lower complexity than the complexity of the start-up model and in which a prescribed lower threshold of parameters that quantitatively characterize the reliability of the model is exceeded (3); using the trained neural network to generate a simplified model (4); determining a parameter (5) for simplifying the characterization complexity of the model; if the determined complexity of the generated simplified model is lower than the complexity of the starting model (6), testing the generated simplified model using a test set of the generated input and output data of the at least one starting model, the test set being different from the training set, and determining parameters of the generated simplified model characterizing the reliability (7); if the determined reliability of the simplified model exceeds a specified threshold value (8), the simplified model (9) is output.

Description

technical field [0001] The present invention relates to a method for generating simplified models for use in XiL systems. The invention also relates to a data processing device, a computer program, a device for performing XiL tests on components of a motor vehicle, in particular an autonomous motor vehicle, a method for performing a XiL test, a A computer readable storage medium, and a data carrier signal. Background technique [0002] Self-driving motor vehicles (also sometimes referred to as autonomous land vehicles) are motor vehicles that can drive, steer, and park without the influence of a human driver (highly automated driving or autonomous driving). The term robot car is also used if no manual control by the driver is required. The driver's seat may remain unoccupied; there may be no steering wheel, no brake pedal, and no gas pedal. Autonomous motor vehicles can capture their environment with the help of different sensors and can determine their position as well a...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/15G06F30/27G06N3/04G06N3/08
CPCG06F30/15G06F30/27G06N3/08G06N3/045G05B17/02G05B13/027G06N3/082G06N3/044
Inventor 图尔加伊·伊斯克·阿斯兰德里
Owner FORD GLOBAL TECH LLC