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

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...

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 It is almost impossible to conduct a risk assessment

[0003] The current prediction method for the incidence of pneumoconiosis has a good parameter setting, is simple and easy to implement, and uses a linear change model for simulation, resulting in a gap between the prediction results and the actual requirements.