Ship unloader association rule fault prediction model method based on deep belief network

A deep belief network and fault prediction technology, applied in biological neural network models, neural learning methods, loading/unloading, etc., can solve problems affecting machine functions, economic losses, accidents, etc., to enhance intelligence and solve high-dimensional problems Disaster and the effects of dealing with nonlinear data, removing complexity and ambiguity

Active Publication Date: 2019-11-15
ZHEJIANG UNIV OF TECH
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Failure of the trolley running system will affect the function of the whole machine, which may cause serious accidents and economic losses

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
  • Ship unloader association rule fault prediction model method based on deep belief network
  • Ship unloader association rule fault prediction model method based on deep belief network
  • Ship unloader association rule fault prediction model method based on deep belief network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The present invention will be further described below in conjunction with the accompanying drawings.

[0059] refer to Figure 1 to Figure 21 , a kind of ship unloader association rule fault prediction model method based on depth belief network, described prediction method comprises the following steps:

[0060] (1) The time series of the status monitoring of the trolley system of the bridge grab ship unloader is used as the model input, and the associated internal feature information and fault categories of the trolley system are obtained as the model output by sampling;

[0061] (2) Preprocess the original monitoring data, normalize the data, generate data sets and group them to obtain training sets and test sets;

[0062] (3) Reconstruct the phase space of the acquired time series T, convert it into a matrix form and construct the input and output y t ={x t}Map relationship f:R m → R;

[0063] (4) Train the deep belief network prediction model composed of RBM ...

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

A ship unloader association rule fault prediction model method based on a deep belief network comprises the following steps: (1) taking a time sequence of state monitoring of a bridge type grab ship unloader trolley system as model input, and obtaining associated internal feature information and fault categories of the trolley system through sampling and taking the associated internal feature information and fault categories as model output; (2) preprocessing the original monitoring data; (3) carrying out phase space reconstruction on the obtained time sequence, converting the time sequence into a matrix form, and constructing an input and output mapping relationship; (4) training a deep belief network prediction model formed by RBM stacking and a regression layer, and obtaining a future residual error sequence prediction value of which the vibration intensity of each related monitoring point is a time sequence; (5) constructing a fault type and corresponding monitoring point residualerror sequence characteristic constraint function model by utilizing an association rule; and (6) inputting a data set, and predicting by using the trained model. The method is high in precision, simple in calculation and high in engineering practicability.

Description

technical field [0001] The present invention designs a fault prediction method for the trolley system of a bridge-type grab ship unloader, especially a fault prediction model method for a ship unloader association rule based on a deep belief network. Background technique [0002] As the main working system of the bridge grab ship unloader, the trolley operation system undertakes key functions such as lifting and opening and closing of the grab and trolley walking during the normal operation of the ship unloader, and occupies a very important position in its actual production. Failure of the trolley running system will affect the function of the whole machine, which may cause serious accidents and economic losses. Therefore, it is necessary to monitor, analyze and predict the health status of the trolley operation system to ensure the safe and stable operation of the ship unloader, early warning, reduce economic losses caused by sudden failures, and avoid major accidents such...

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): G06F17/50G06N3/08G06N3/04B65G67/60
CPCG06N3/08B65G67/606G06N3/045Y02T90/00
Inventor 叶永伟程毅飞赖剑人任设东
Owner ZHEJIANG UNIV OF TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap