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

Method and system for fault diagnosis, training method of model and medium

A training method and model technology, applied in general control systems, control/regulation systems, instruments, etc., can solve problems such as deep learning models that are difficult to instrument, difficult to clean data in different formats, etc.

Inactive Publication Date: 2020-06-02
SIEMENS AG
View PDF12 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If raw data is collected from one type of meter, it is difficult to obtain enough data to train a deep learning model for a specific type of meter; if raw data is collected from multiple types of meters, it is difficult to clean data with different formats

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 and system for fault diagnosis, training method of model and medium
  • Method and system for fault diagnosis, training method of model and medium
  • Method and system for fault diagnosis, training method of model and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] The subject matter described herein will now be discussed with reference to example implementations. It should be understood that the discussion of these implementations is only to enable those skilled in the art to better understand and realize the subject matter described herein, and is not intended to limit the protection scope, applicability or examples set forth in the claims. Changes may be made in the function and arrangement of elements discussed without departing from the scope of the disclosure. Various examples may omit, substitute, or add various procedures or components as needed. For example, the methods described may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with respect to some examples may also be combined in other examples.

[0072] As used herein, the term "comprising" and its variants represent open terms meaning "including but not limited to". The...

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 disclosure relates to a method and system for fault diagnosis, a training method of a model and a medium. The training method of a fault prediction model comprises the steps that: sensor units ofat least two intelligent instruments collect multiple pieces of measurement data of at least one physical quantity of to-be-tested equipment respectively, and the measurement data are sent to transmitter units of the intelligent instruments respectively; the transmitter units convert the received measurement data into a unified format, and upload the measurement data in the unified format and diagnosis data which are stored in the transmitter units and are related to the measurement data to a cloud server; and the cloud server uses the measurement data in the unified format and the diagnosis data related to the measurement data as a training data set, and uses supervised deep learning for training to obtain a fault prediction model of the to-be-tested equipment.

Description

technical field [0001] The present disclosure generally relates to the field of process control, and more particularly, to methods and systems for fault diagnosis, methods for training models, and media Background technique [0002] For meters and sensors, it is often desirable to be able to report diagnostic information earlier. In order to realize this function, it is very important to efficiently analyze not only the instantaneous measurement data, but also the historical values. Currently, the measurement data is first sent to a higher layer, such as an industrial computer or the cloud, but this communication process of the measurement data delays the diagnosis of critical faults. [0003] Currently, deep learning experts apply deep learning artificial intelligence (AI) techniques to sensors to analyze raw data locally. But in the process industry, the format of raw data from different types of instruments varies. If raw data is collected from one type of meter, it is...

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): G05B13/04
CPCG05B13/042G05B13/027
Inventor 余浪张猛王青岗王岩周林飞
Owner SIEMENS AG