A list,

1 Overview of mine ventilation volume

As China’s basic energy, coal is widely distributed, and now the global share has exceeded 50%. China is a country with “rich coal, poor oil and little gas”, which determines that coal will play a dominant role in the production and consumption of one-time energy and will not change for a long time. In recent years, due to the energy shortage, the improvement of the coal market has also brought about problems in coal mine safety. Natural disasters such as gas and coal dust are the main causes. Mine mining is the main way of the coal industry today. Generally speaking, the higher the gas content of the mine, the worse the mining conditions, which leads to the rise of mining difficulty, and increases the risk in the mining process. Due to the complexity of national geological conditions and the limitations in mine ventilation, preventing gas, preventing no car, fire prevention and other technical aspects, resulting in gas explosion, underground fire accidents and other mining accidents occur frequently. In recent years, although the state of coal mine safety has been improving, the situation is still very grim.

For mine ventilation, prevention of gas, coal dust prevention and fire prevention, the “one and three prevention” accident. This ZhangCai with multivariate regression model is applied to the coal mine ventilation rate of the optimal prediction scheme, aimed at solving the influence factor of the coal mine ventilation is complex, and wind speed, gas, coal dust and so on various factors of gas concentration and the complex nonlinear relationship between the effect of coal dust concentration, used this method to mine the wind speed and the inherent law between factors such as gas and coal dust, Effectively prevent gas and coal dust explosion accidents.

2 regression model analysis of mine ventilation volume

Optimize mine ventilation volume design based on the collected data of mine ventilation volume, gas, coal dust, temperature and humidity. The conventional data processing is regression analysis. The ventilation volume is calculated with the collected data of gas and coal dust, mine temperature and humidity, and the output of the system is controlled through multiple regression analysis.

Regression analysis is a statistical analysis method to determine the interdependent quantitative relationship between two or more variables. Regression analysis can be divided into one variable regression analysis and multiple regression analysis according to the number of independent variables involved. According to the type of relationship between independent variable and dependent variable, it can be divided into linear regression analysis and nonlinear regression analysis. If only one independent variable and one dependent variable are included in the regression analysis, and the relationship between them can be approximated by a straight line, the regression analysis is called unary linear regression analysis. If the regression analysis includes two or more independent variables and the relationship between dependent variables and independent variables is linear, it is called multiple linear regression analysis.

Correlation analysis studies whether phenomena are correlated and the direction and degree of correlation, and generally does not distinguish independent variables or dependent variables. Regression analysis is to analyze the specific form of correlation between phenomena, determine the causal relationship, and use mathematical models to show the specific relationship. For example, we can know from correlation analysis that “quality” and “customer satisfaction” are closely related, but which of these two variables is affected by which variable, and to what extent, needs to be determined by regression analysis.

Generally speaking, regression analysis is to determine the causal relationship between variables by specifying dependent variables and independent variables, establish a regression model, and solve each parameter of the model according to the measured data, and then evaluate whether the regression model can fit the measured data well. If it can be fitted well, further prediction can be made according to independent variables.

3. Normalized processing results of working face data points

Ii. Source code

clc,clear,close all ysw1; % load data x=[v1,v3, v4]; % Wind speed y=[Pc1, Pc3,Pc4]; % coal dust figure ('color'[1 1 1])
scatter(x,y,'. ')
xlabel('wind speed (m/s));  ylabel('Coal dust concentration (g/m3)');  grid off; axis tight

p = polyfit(x,y,1) % fitting Pc=p(1)*x+p(2);
hold on
plot(x,Pc,'r*--')Modeling mapping relationship between gas concentration in air and wind speed CLC, Clear,close all YSW1; % load data x=[v1,v4]; Y = % wind speed [Pg1, Pg4]; Figure (% gas'color'[1 1 1])
scatter(x,y,'. ')
xlabel('wind speed (m/s));  ylabel('Coal dust concentration (g/m3)');  grid off; axis tight

p = polyfit(x,y,1) % fitting Pc=p(1)*x+p(2);
hold on
plot(x,Pc,'r*--')Modeling mapping relationship between temperature and humidity and wind speed in mine CLC, Clear,close all YSW1; Data = data1; n=size(data); datay=data(:,2); Datax4 =data(:,5); Datax5 =data(:,6); % as humidity input figure('Color'[1 1 1]);
subplot(121),scatter(datay,datax4,'. ')
xlabel('wind speed (m/s));   ylabel('temperature');  grid off;  axis tight
clc,clear,close all
format longysw1; N0 =size(data1); a=mean(data1); a1=std(data1);
mstdata=zscore(data1);

figure('color'[1 1 1])
X=mstdata(:,3:6);
X=[ones(n0(1.1),1),X];
Y=mstdata(:,2); 
[b,bint,r,rint,s]=regress(Y,X)
rcoplot(r,rint)

yuc = b(1)+b(2)*mstdata(:,3)+b(3)*mstdata(:,4)+b(4)*mstdata(:,5)+b(5)*mstdata(:,6);
n1=size(yuc);
for i=1:n1(1.1)
    for j=2
        yu(i,j- 1)=yuc(i,j- 1)*a1(1,j)+a(1,j); % inverse normalization operationend
end

figure('color'[1 1 1])
plot(data1(:,1),data1(:,2),'r.-'.'linewidth'.2)
hold on
plot(data1(:,1),yu,'bo-'.'linewidth'.2)
xlabel('Point in time');  ylabel('Ventilation');  grid off; axis tight
legend('Raw signal'.'Regression prediction')

error_hg= data1(:,2)-yu;
save error_hg.mat error_hg

 end
Copy the code

3. Operation results

Fourth, note

Version: 2014 a