A Fault Monitoring Method Based on Hierarchical Density Peak Clustering and Most Similar Modes

A technology for fault monitoring and density peaks, applied in electrical testing/monitoring and other directions, which can solve problems such as multi-modal fault monitoring methods relying on prior modal information

Active Publication Date: 2020-08-07
SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of the prior art, the present invention provides a fault monitoring method based on hierarchical density peak clustering and most similar modes, which considers the multi-modality and multi-modal dynamics and uncertainty of complex industrial processes, and overcomes the Problems of Existing Multimodal Fault Monitoring Methods Relying on Prior Modal Information

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
  • A Fault Monitoring Method Based on Hierarchical Density Peak Clustering and Most Similar Modes
  • A Fault Monitoring Method Based on Hierarchical Density Peak Clustering and Most Similar Modes
  • A Fault Monitoring Method Based on Hierarchical Density Peak Clustering and Most Similar Modes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0067] Such as figure 1 Shown is the flow chart of the method of the present invention.

[0068] Based on the fault monitoring method of hierarchical density peak clustering and the most similar mode, the industrial process data is collected, and after obtaining the hierarchical mode information, the independent element analysis and the most similar mode are used for fault monitoring.

[0069] Concrete steps of the present invention are as follows:

[0070] Step 1: Collect historical normal data of penicillin fermentation process, including ventilation rate, agitator power, substrate feeding speed, heat generated by reaction, medium volume, carbon dioxide concentration, pH value, temperature, dissolved oxygen saturation, and conduct Standardized processing, the mean value of each variable of the processed data is 0, and the variance is 1;

...

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 fault monitoring method based on hierarchical density peak clustering and the most similar mode. The historical normal data of an industrial process are modally divided to acquire hierarchical modal information. The hierarchical modal information is used to establish a fault monitoring model for the historical normal data of the industrial process. The most similar modeof the industrial process data to be monitored is acquired and input into the fault monitoring model for fault monitoring. According to the invention, existing industrial data resources are used; multimodality and multimodal dynamics and uncertainty of a complex industrial process are considered; the limitations of relying on priori modal information and using fixed modal dividing and models of the existing multimodal fault monitoring method are overcome; and the method is important for timely detecting abnormal conditions in the industrial process, ensuring production safety and improving product quality.

Description

technical field [0001] The invention relates to the technical field of fault monitoring and diagnosis, in particular to a fault monitoring method based on hierarchical density peak clustering and most similar modes. Background technique [0002] The purpose of fault monitoring is to discover abnormal working conditions of industrial processes in time, ensure production safety, and improve product quality. The operating conditions of industrial processes are usually changed due to changes in raw materials, manufacturing parameters, product specifications, etc., resulting in multiple operating modes. The different modes have similar, each specific characteristics and durations. A mode is defined as a process with similar statistical properties and a certain duration. In addition, there may be a gradual transition process between two adjacent modes. Therefore, it is of great significance to study effective and feasible multi-mode process fault monitoring methods. [0003] M...

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 Patents(China)
IPC IPC(8): G05B23/02
Inventor 李帅周晓锋史海波潘福成李歆张宜驰
Owner SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products