Coal worker disease incidence rate prediction method based on radial primary function neural network combination model

A technology that combines models and prediction methods, applied in biological neural network models, neural learning methods, data processing applications, etc., can solve problems such as the gap between prediction results and actual requirements, and achieve clear algorithm derivation, accurate prediction results, and learning accuracy high effect

Inactive Publication Date: 2017-11-17
HARBIN UNIV OF SCI & TECH
View PDF2 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At this stage, most of the research on pneumoconiosis is in the way of theoretical exploration, monitoring and numerical simulation. However, pneumoconiosis in the region is a small sample event. To predict the potential occupational hazards of dust, a reasonable statistical model should be given in advance I

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

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0020] The method for predicting the morbidity of coal workers based on the radial basis function neural network combination model of the present embodiment, the described method is realized through the following steps:

[0021] Step 1. Collect and preprocess the data on the pathogenic factors of pneumoconiosis. The pathogenic factors include: dust type E related to dust toxicity, dust concentration in the working environment C, and dust exposure time T. The relationship between the three pathogenic factors is: P =F(E,C,T);

[0022] Step 2, modeling the BP neural network, determining the number of layers of the input and output layers, hidden layers and output layers, and adjusting thresholds and weights;

[0023] Step 3, using the genetic algorithm to optimize the BP neural network to obtain the optimal network initial weight and network threshold;

[0024] Step 4: Carry out result prediction and optimize the prediction result;

[0025] Step five, forming a prediction resul...

specific Embodiment approach 2

[0031] The difference from the specific embodiment 1 is that the method for predicting the morbidity of coal workers based on the radial basis function neural network combination model in this embodiment, the process of collecting the data of the pathogenic factors of pneumoconiosis described in step 1 is that the experiment and field investigation are used Data required by the mobile phone.

specific Embodiment approach 3

[0032] The difference from the specific embodiment 1 or 2 is that the method for predicting the morbidity of coal workers based on the radial basis function neural network combination model of this embodiment, the BP neural network described in step 2 is modeled, and the entry and exit layers, hidden Including layers and the number of layers of the output layer, in the process of adjusting the threshold and weight, the involved

[0033] (1) Modeling the BP neural network is specifically:

[0034] Suppose the actual measured value of the predicted incidence probability of coal worker pneumoconiosis is X=(x 1 , x 2 , x 3 ... x n ), there are m different models for prediction, and m≥2, the weights in the combined model are vector w=(w 1 ,w 2 ......w m ), the prediction value of the jth prediction model is Then the predicted value of period t in the combined forecasting model is In the formula, t=1, 2, 3, 4...n, the actual observation value of the tth period is X t , th...

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 coal worker disease incidence rate prediction method based on a radial primary function neural network combination model and solves a problem of difference between the prediction result and an actual requirement caused by good parameter setting, easy and simple realization and simulation through utilizing a linear changing model existing in a dust phthisis disease incidence rate prediction method in the prior art. The method comprises steps that disease factors including dust kinds, working environment dust concentration and the dust reception time are collected through an experiment and solid investigation method, and the BP neural network and a support vector machine algorithm are employed to predict a dust phthisis disease incidence rate. The method is advantaged in that the dust phthisis disease incidence rate can be predicted, and the dust phthisis disease incidence rate prediction result in small-sample coal mine enterprises can be accurately predicted.

Description

Technical field: [0001] The invention relates to a method for predicting the incidence of coal workers based on a radial basis function neural network combined model. Background technique: [0002] my country's coal production enterprises include large state-owned coal enterprises, joint-stock coal enterprises and many small coal kilns. In the production process of coal enterprises, there are not only occupational toxic and harmful factors, but also problems such as overtime, high-intensity labor, and new occupational disease hazards brought about by new processes and new materials. Every year, more than 12,000 people die from pneumoconiosis in my country's coal industry, causing hundreds of millions of direct economic losses, which shows that the degree of occupational hazards is quite serious. According to the survey and statistics of 16,792 coal mining enterprises in 23 provinces and cities by the State Coal Mine Safety Supervision Bureau, as of 2014, the cumulative numb...

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
IPC IPC(8): G06Q10/06G06Q50/02G06F19/00G06N3/08
CPCG06N3/084G06Q10/0635G06Q50/02
Inventor 蒋永清李明王晓婷孙超王博任锁张秋楠李瀚斌
Owner HARBIN UNIV OF SCI & 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