Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for verifying and selecting model for state monitoring of machine

A model and machine technology, applied in the field of verification and selection of models used for state monitoring of machines, can solve problems such as lack of abnormal states

Pending Publication Date: 2021-09-07
ROBERT BOSCH GMBH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the lack of data on abnormal states, training on these abnormal states was not performed

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
  • Method for verifying and selecting model for state monitoring of machine
  • Method for verifying and selecting model for state monitoring of machine
  • Method for verifying and selecting model for state monitoring of machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] In the following, according to Figure 1A and 1B An exemplary embodiment of a method according to the invention for validating and selecting a model for machine monitoring will be described. exist Figure 1A The corresponding block diagram is shown in , while in Figure 1B The associated flowchart is shown in .

[0030] This verification and selection is performed according to a (first) model set comprising at least one model, preferably a plurality of models. exist Figure 1A Two models are symbolically depicted in . Models are characterized by defining parameter configurations 2 of these models. Here, a parameter configuration of a model means a specification about the structure, the value of a particular parameter, the training parameters (such as the learning rate or the number of iterations in an iterative learning process), the error measure of the algorithm on which the model is based, etc., when the algorithm has This parameterization leads to the thus deter...

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 verifying at least one model for monitoring a state of a machine and selecting at least one model for monitoring a state of a machine from a first set model set, the model being an algorithm trained by means of machine learning, wherein the model is trained by means of a reference data record of operating parameters and is characterized by different parameter configurations for different models, the method comprising: generating one or more test data records from the reference data record, wherein at least one value of the operating parameters in the reference data record is replaced by a corresponding inadmissible operating parameter value; for each model in the model set: applying the model to each of the one or more test data records in order to determine an error value for the model with respect to each test data record, and determining a distance value for the model based on the error value for the model; selecting one or more models based on the magnitude of the distance values.

Description

technical field [0001] The invention relates to a method for validating and selecting at least one model for monitoring the state of a machine from a first set of models. In particular, the invention relates to validating a model suitable for machine monitoring and selecting a model suitable for machine monitoring from one or more models. Background technique [0002] Mathematical models based on machine learning can be used within the scope of the predictive maintenance concept in order to classify the operating states of machines in industrial installations and in particular to identify abnormal operating states which indicate a malfunction of the machines. In order to train these mathematical models or algorithms, it is possible to use as training data samples or reference data which are recorded during the operation of the machine. During training, the model learns to recognize the operating state of the machine as represented by the training data. After training, conc...

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
IPC IPC(8): G06F11/30G06F11/34G06N20/00
CPCG06F11/3055G06F11/3058G06F11/3447G06N20/00G05B23/024G05B23/0256G05B17/02G06N3/088G06N3/045
Inventor T·托里卡
Owner ROBERT BOSCH GMBH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com