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

TE Process Fault Diagnosis Method Based on Parameter Optimization Deep Belief Network Model

A deep belief network and fault diagnosis technology, which is applied in the direction of instruments, test/monitoring control systems, control/regulation systems, etc., can solve the problems of reducing network generalization ability, large network scale, and difficulty in convergence, so as to avoid easy to fall into local The effect of minimum value, fast convergence speed, and strong global convergence ability

Active Publication Date: 2022-07-01
重庆仲澜科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the above method has improved the accuracy rate, due to the large network size, difficulty in convergence, and longer training time, the generalization ability of the network is reduced, and the diagnosis result cannot be obtained quickly.

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
  • TE Process Fault Diagnosis Method Based on Parameter Optimization Deep Belief Network Model
  • TE Process Fault Diagnosis Method Based on Parameter Optimization Deep Belief Network Model
  • TE Process Fault Diagnosis Method Based on Parameter Optimization Deep Belief Network Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0073] The specific embodiments and working principles of the present invention will be further described in detail below with reference to the accompanying drawings.

[0074] from figure 1 It can be seen that a TE process fault diagnosis method based on a parameter-optimized deep belief network model is performed according to the following steps:

[0075] Step 1: Carry out experimental simulation with the TE process as the research object, obtain simulation data, and divide the simulation data into training set data samples and test set data samples;

[0076] The specific content of the test simulation in step 1 is:

[0077] From all the observed variables of the TE process, randomly select a gc observed variables as output variables, A-a gc An observed variable is used as a control variable;

[0078] In this embodiment, software environment: Matlab2016a, Windows7 operating system; hardware environment: CPU 2.20GHz, memory 8GB, 750G hard disk.

[0079] In this embodiment...

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 TE process fault diagnosis method based on a parameter-optimized deep belief network model. and test set data samples; based on quantum particle swarm algorithm, the deep belief network is optimized to obtain the optimized deep belief network; the training set data samples are brought into the optimized deep belief network for training, and the TE process deep belief network fault diagnosis model is obtained; The test set data samples are brought into the TE process deep belief network fault diagnosis model to diagnose the faults of the TE process, and the test set fault data samples are obtained; according to the test set fault data samples, the fault diagnosis results are evaluated. Beneficial effects: the convergence speed is faster, the global convergence ability is stronger, and the DBN algorithm is easy to fall into the local minimum value, insufficient training and premature phenomenon.

Description

technical field [0001] The invention relates to the technical field of TE process fault diagnosis, in particular to a TE process fault diagnosis method based on a parameter-optimized deep belief network model. Background technique [0002] Modern chemical production processes are becoming larger, more integrated and more refined. When a certain link of the system fails, if it is not dealt with in time, it may cause the failure to expand and lead to the occurrence of major accidents. Therefore, establishing an efficient and accurate real-time fault detection and diagnosis system, eliminating hidden faults, eliminating faults in time, and ensuring safe, stable and high-quality production have become the key to the entire production process. [0003] For example: TE process is a simulation simulation of an actual chemical process proposed by J.J.Downs and E.F.Vogel of the process control group of Tennessee Eastman Chemical Company in the United States, which is widely used in ...

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
CPCG05B23/0256
Inventor 黄迪张卫黄家华
Owner 重庆仲澜科技有限公司
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