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

Mechanical equipment operating state monitoring method and system used for edge calculation side

A technology of mechanical equipment and edge computing, applied in the direction of comprehensive factory control, comprehensive factory control, electrical program control, etc., can solve the problems of trend change analysis, can not reflect the details of equipment operating status changes, etc., to achieve the effect of improving the level of intelligence

Active Publication Date: 2019-06-18
北京大通惠德科技有限公司
View PDF17 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The Chinese patent with the publication number CN102243140 discloses a method for monitoring the state of mechanical equipment based on sub-band signal analysis, and specifically discloses the use of multi-stage filters to process the state signals of mechanical equipment operation, which can decompose the measured signals into a group of Narrowband sub-band signals, and then extract the status information of mechanical equipment from the sub-band signals. Although the main features of the collected data are extracted by signal processing methods, and the extracted features are used for equipment status analysis, the extracted main features are not analyzed. For trend change analysis, the results obtained can only reflect the main changes in the operating state of the equipment, but not the detailed changes in the operating state of the equipment, especially the early failure of the equipment body and the influence relationship between the equipment body and external process parameters, etc.

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
  • Mechanical equipment operating state monitoring method and system used for edge calculation side
  • Mechanical equipment operating state monitoring method and system used for edge calculation side
  • Mechanical equipment operating state monitoring method and system used for edge calculation side

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] A method for monitoring the operating status of mechanical equipment on the edge computing side, such as figure 1 As shown, the method includes the following steps:

[0049] (1) Design the sensor layout plan, select the required type of sensors, arrange the sensors for the mechanical equipment according to the plan, and record the corresponding information in the configuration file; use various types of sensors (including temperature sensors and acceleration sensors, etc.) to collect the operating condition data of the mechanical equipment Including vibration type data and non-vibration type data; wherein, the eigenvalues ​​corresponding to vibration type data include effective value, peak value, rotational frequency and its multiplier, bearing characteristic frequency and blade passing frequency; non-vibration type data include rotational speed and temperature;

[0050] (2) Then, the above-mentioned working condition data signals are subjected to signal conditioning (d...

Embodiment 2

[0060] A method for fault diagnosis of mechanical equipment, such as figure 2 As shown, the method includes the following steps:

[0061] (1) Model training

[0062] a) Obtain historical operation data of mechanical equipment from the data center;

[0063] b) Perform data processing and feature extraction, and determine the training sample set in combination with the equipment operating status corresponding to each data;

[0064] c) Determine the parameters of the BP neural network, including the number of input layer nodes, the number of hidden layer nodes, and the number of output layer nodes, train the BP neural network according to the training sample set, obtain the neural network weight matrix, and establish a fault diagnosis model;

[0065] (2) Real-time diagnosis

[0066] a) Collect real-time operation data of mechanical equipment;

[0067] b) carry out data processing and feature extraction, and use the extracted features to carry out alarm discrimination, wherei...

Embodiment 3

[0071] A method for discriminating alarms of mechanical equipment, said method comprising the following steps:

[0072] (1) For non-vibration type data, including temperature, rotational speed, etc., directly compare with the set threshold value, if the threshold value is exceeded continuously for 3 times in normal state, then set this type of physical quantity as an alarm state, for example, temperature alarm, Speed ​​alarm, etc.; if the threshold value is not exceeded for 3 consecutive times in the alarm state, the physical quantity of this type will be released from the alarm and return to the normal state;

[0073] (2) For the vibration type data, a feature extraction is completed for the first time, and the extracted feature value is compared with the set threshold value. If it exceeds the threshold value for 3 times in a normal state, the feature value is set as an alarm state; if If the threshold value is not exceeded for 3 consecutive times in the alarm state, the char...

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 discloses a mechanical equipment operating state monitoring method and system used for an edge calculation side. Equipment operation condition data is collected, which includes vibrationtype and non-vibration type data. According to a unit component type, characteristic extraction is performed on vibration data, which includes one extraction of a corresponding characteristic value of the vibration type data, and also includes secondary extraction of the corresponding characteristic value of the vibration type data and the non-vibration type data. Threshold judgment of the data is possessed, and a data change trend can be acquired, which includes a change slope, a magnitude of jump, and the magnitude of the change. Whether there are slow rise, slow decline, and sudden changeconditions in mechanical settings can be accurately determined. Data types are enriched and data monitoring quality is improved. Online real-time condition monitoring of equipment and automatic earlywarning of an operating condition are realized, and effective and real-time data is provided for a subsequent system.

Description

technical field [0001] The present invention relates to the technical field of mechanical equipment status monitoring, in particular to a method and system for monitoring the running status of mechanical equipment on the edge computing side. Background technique [0002] Mechanical equipment is the core of an enterprise's operation, and its operational reliability not only involves the economic benefits of the enterprise itself, but also affects the safety and continuous production of other related enterprises. Therefore, ensuring the safe operation of equipment, reducing maintenance costs and improving equipment availability is becoming more and more important. be valued. Therefore, in order to reduce equipment downtime, reduce life cycle costs, improve equipment availability, and reduce safety risks, how to conduct real-time online condition monitoring and fast and accurate fault diagnosis of equipment has become one of the research hotspots in intelligent maintenance of e...

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): G05B19/418
CPCY02P90/02
Inventor 陈睿金玮
Owner 北京大通惠德科技有限公司
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