CN103605287B - Circulating Fluidized Bed Temperature prognoses system and method - Google Patents

Abstract

The invention discloses a kind of Circulating Fluidized Bed Temperature prognoses system and method, system comprises the field intelligent instrument, database, data-interface, control station and the host computer that are connected with Circulating Fluidized Bed Boiler; Field intelligent instrument is connected with control station, database and host computer, and host computer comprises: standardization module, for gathering the training sample of key variables from database, and column criterion of going forward side by side process; Forecasting mechanism forms module, for setting up forecast model; Prediction execution module, for real-time estimate bed temperature; Model modification module; Signal acquisition module; Result display module.The present invention predicts bed temperature according to the operating condition of Circulating Fluidized Bed Boiler and performance variable, so that suggestion and guides operation, thus bed temperature is controlled at optimum range, effectively ensure the safety of Circulating Fluidized Bed Boiler, environmental protection operation, and lay the foundation for being optimized operational efficiency further.

Description

Bed temperature prediction system and method for circulating fluidized bed boiler

Technical Field

The invention relates to the field of energy engineering, in particular to a system and a method for predicting bed temperature of a circulating fluidized bed boiler.

Background

The circulating fluidized bed boiler has the advantages of less pollutant discharge, wide fuel adaptability, strong load regulation capacity and the like, and is more and more widely applied to industries such as electric power, heat supply and the like in recent years. The bed temperature of the circulating fluidized bed boiler is an important parameter which directly influences whether the boiler can safely and continuously operate, and simultaneously directly influences the desulfurization efficiency and the generation amount of nitrogen oxides in the operation of the boiler. The establishment of a prediction system of the bed temperature of the circulating fluidized bed boiler has important significance for the safe and environment-friendly operation and the operation optimization of the circulating fluidized bed boiler.

Disclosure of Invention

The invention aims to provide a system and a method for predicting heat loss of exhaust smoke of a circulating fluidized bed boiler aiming at the defects of the prior art.

The technical scheme adopted by the invention for solving the technical problems is as follows: a bed temperature prediction system of a circulating fluidized bed boiler comprises an on-site intelligent instrument, a database, a data interface, a control station and an upper computer, wherein the on-site intelligent instrument, the database, the data interface, the control station and the upper computer are connected with the circulating fluidized bed boiler; on-spot intelligent instrument and control station, database and host computer are connected, the host computer include:

a standardization processing module for collecting the operation condition variables and the historical records of the operation variables from the databaseForming a training sample matrix X of independent variables, collecting the historical records of corresponding average bed temperature signals, forming a dependent variable training sample vector Y, standardizing the training sample X, Y to ensure that the mean value of each variable is 0 and the variance is 1, and obtaining the standardized independent variable training sample matrix X^*(nxp), normalized dependent variable training sample vector Y^*(n × 1) by the following procedure:

1.1) averaging:

${\stackrel{\‾}{x}}_j=\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{x}_{\mathrm{ij}},$ （i=1,2,…,n；j=1,2,…,p）（1）

$\stackrel{\‾}{y}=\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{y}_i,$ （i=1,2,…,n）（2）

1.2) calculating the standard deviation

$s_{x,j}=\sqrt{\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(x_{\mathrm{ij}}-{\stackrel{\‾}{x}}_j)}^2},$ （i=1,2,…,n；j=1,2,…,p）（3）

$s_y=\sqrt{\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(y_i-\stackrel{\‾}{y})}^2},$ （i=1,2,…,n）（4）

1.3) normalization

$x_{\mathrm{ij}}^{*}=\frac{x_{\mathrm{ij}}-{\stackrel{\‾}{x}}_j}{s_{x,j}},$ （i=1,2,…,n；j=1,2,…,p）（5）

$y_i^{*}=\frac{y_i-\stackrel{\‾}{y}}{s_y},$ （i=1,2,…,n）（6）

Wherein x is_ij、y_iIs the original value of the training sample point, n is the number of training samples, p is the number of independent variables, is the mean of the training samples, s_x,j、s_yIn order to train the standard deviation of the sample, the normalized values of the training sample points are shown, wherein the subscripts i and j represent the ith training sample point and the jth argument, respectively.

The prediction mechanism forming module is used for establishing a prediction model and comprises the following implementation steps:

2.1) solving a prediction coefficient vector beta according to the formula (7):

β=(X^*TX^*)^-1X^*TY^*（7）

wherein, the superscript: t, -1 respectively represents the transposition of the matrix and the inverse of the matrix;

2.2) transferring and storing the prediction coefficient vector beta to a prediction execution module.

The prediction execution module is used for predicting the bed temperature according to the running working condition of the circulating fluidized bed boiler and the set operation variable, and the implementation steps are as follows:

3.1) processing the input independent variable signal according to the formula (8):

$x{\left(t\right)}_j^{*}=\frac{x{\left(t\right)}_j-{\stackrel{\‾}{x}}_j}{s_{x,j}},$ （j=1,2,…,p）（8）

wherein, x (t)_jFor the jth original value of the independent variable at the time t,is the mean, s, of the jth independent variable training sample_x,jFor the standard deviation of the jth independent variable training sample,is the jth independent variable dimensionless value at the t moment, and t represents time and unit is second;

3.2) the dimensionless predicted value of the bed temperature is determined according to the following formula:

$\hat{y}{\left(t\right)}^{*}=\left(\begin{array}{cccc}x{\left(t\right)}_1^{*}& x{\left(t\right)}_2^{*}& ...& x{\left(t\right)}_p^{*}\end{array}\right)\mathrm{\β}---\left(9\right)$

wherein,a dimensionless predicted value of the bed temperature at the moment t is obtained;

3.3) solving the original dimensional forecast value of the bed temperature according to the following formula:

$\hat{y}\left(t\right)=\hat{y}{\left(t\right)}^{*}{\·s}_y+\stackrel{\‾}{y}---\left(10\right)$

wherein,is the original dimensional forecast value of the bed temperature at the time t.

As a preferred solution: the host computer still include: and the model updating module is used for comparing the actual bed temperature with the predicted value according to a set time interval, adding new data into training sample data if the relative error is more than 10%, and executing the standardization processing module and the prediction mechanism forming module again.

Further, the host computer still include:

and the signal acquisition module is used for acquiring real-time data from the field intelligent instrument according to a set sampling time interval and acquiring historical data from the database.

And the result display module is used for reading the setting parameters from the control station, transmitting the predicted bed temperature value to the control station for display and giving an operation suggestion: under the current working condition, how to adjust the operation variables is most beneficial to controlling the bed temperature in the optimal range, so that the control station workers can adjust the operation conditions in time according to the predicted value of the bed temperature and the operation suggestion to control the bed temperature in the optimal range, and the safe and environment-friendly operation of the circulating fluidized bed boiler is effectively ensured. How to adjust the operation variables is most beneficial to controlling the bed temperature in the optimal range, and a simple method is to substitute various combination values of the operation variables into a bed temperature prediction system to obtain corresponding bed temperature prediction values, so that the bed temperature prediction values can be obtained visually by comparing the sizes of the operation variables.

As another preferred solution: the independent variables include: the operation condition variables are as follows: main steam flow, environment temperature, water supply temperature, hearth negative pressure, bed pressure, coal moisture, coal volatile matter, coal ash and coal sulfur; the operation variables are as follows: the total air volume of the primary air and the total air volume of the secondary air.

A bed temperature prediction method of a circulating fluidized bed boiler comprises the following steps:

1) collecting historical records of operation condition variables and operation variables from a database to form a training sample matrix X of independent variables, collecting the historical records of corresponding average bed temperature signals to form a dependent variable training sample vector Y, standardizing training samples X, Y to ensure that the mean value of each variable is 0 and the variance is 1, and obtaining the standardized independent variable training sample matrix X^*(nxp), normalized dependent variable training sample vector Y^*(n × 1) by the following procedure:

1.1) averaging:

${\stackrel{\‾}{x}}_j=\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{x}_{\mathrm{ij}},$ （i=1,2,…,n；j=1,2,…,p）（1）

$\stackrel{\‾}{y}=\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{y}_i,$ （i=1,2,…,n）（2）

1.2) calculating the standard deviation

$s_{x,j}=\sqrt{\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(x_{\mathrm{ij}}-{\stackrel{\‾}{x}}_j)}^2},$ （i=1,2,…,n；j=1,2,…,p）（3）

$s_y=\sqrt{\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(y_i-\stackrel{\‾}{y})}^2},$ （i=1,2,…,n）（4）

1.3) normalization

$x_{\mathrm{ij}}^{*}=\frac{x_{\mathrm{ij}}-{\stackrel{\‾}{x}}_j}{s_{x,j}},$ （i=1,2,…,n；j=1,2,…,p）（5）

$y_i^{*}=\frac{y_i-\stackrel{\‾}{y}}{s_y},$ （i=1,2,…,n）（6）

Wherein x is_ij、y_iIs the original value of the training sample point, n is the number of training samples, p is the number of independent variables, is the mean of the training samples, s_x,j、s_yIn order to train the standard deviation of the sample, the normalized values of the training sample points are shown, wherein the subscripts i and j represent the ith training sample point and the jth argument, respectively.

2) And establishing a prediction model by the obtained standardized training sample through the following processes:

2.1) solving a prediction coefficient vector beta according to the formula (7):

β=(X^*TX^*)^-1X^*TY^*（7）

wherein, the superscript: t, -1 respectively represents the transposition of the matrix and the inverse of the matrix;

2.2) saving the obtained prediction coefficient vector beta.

3) The method comprises the following steps of taking operating condition variables and set operating variables of the circulating fluidized bed boiler as input signals, and predicting the bed temperature according to a prediction coefficient vector, wherein the method comprises the following steps:

3.1) processing the input independent variable signal according to the formula (8):

$x{\left(t\right)}_j^{*}=\frac{x{\left(t\right)}_j-{\stackrel{\‾}{x}}_j}{s_{x,j}},$ （j=1,2,…,p）（8）

wherein, x (t)_jFor the jth original value of the independent variable at the time t,is the mean, s, of the jth independent variable training sample_x,jFor the standard deviation of the jth independent variable training sample,is the jth independent variable dimensionless value at the t moment, and t represents time and unit is second;

3.2) the dimensionless predicted value of the bed temperature is determined according to the following formula:

$\hat{y}{\left(t\right)}^{*}=\left(\begin{array}{cccc}x{\left(t\right)}_1^{*}& x{\left(t\right)}_2^{*}& ...& x{\left(t\right)}_p^{*}\end{array}\right)\mathrm{\β}---\left(9\right)$

wherein,a dimensionless predicted value of the bed temperature at the moment t is obtained;

3.3) solving the original dimensional forecast value of the bed temperature according to the following formula:

$\hat{y}\left(t\right)=\hat{y}{\left(t\right)}^{*}\·s_y+\stackrel{\‾}{y}---\left(10\right)$

wherein,is the original dimensional forecast value of the bed temperature at the time t.

As a preferred solution: the method further comprises the following steps: 4) and (3) acquiring field intelligent instrument signals according to a set sampling time interval, comparing the obtained actual bed temperature with a predicted value, adding new data into training sample data if the relative error is more than 10%, and re-executing the steps 1) and 2) to update the prediction model.

Further, in the step 3), reading the setting parameters from the control station, transmitting the predicted bed temperature value to the control station for display, and giving an operation suggestion: under the current working condition, how to adjust the operation variables is most beneficial to controlling the bed temperature in the optimal range, so that the control station workers can adjust the operation conditions in time according to the predicted value of the bed temperature and the operation suggestion to control the bed temperature in the optimal range, and the safe and environment-friendly operation of the circulating fluidized bed boiler is effectively ensured. How to adjust the operation variables is most beneficial to controlling the bed temperature in the optimal range, and a simple method is to substitute various combination values of the operation variables into a bed temperature prediction system to obtain corresponding bed temperature prediction values, so that the bed temperature prediction values can be obtained visually by comparing the sizes of the operation variables.

As another preferred solution: the independent variables include: the operation condition variables are as follows: main steam flow, environment temperature, water supply temperature, hearth negative pressure, bed pressure, coal moisture, coal volatile matter, coal ash and coal sulfur; the operation variables are as follows: the total air volume of the primary air and the total air volume of the secondary air.

The invention has the following beneficial effects: the bed temperature of the circulating fluidized bed boiler is predicted, production operation is recommended and guided, the bed temperature is controlled in an optimal range, and safe and environment-friendly operation of the circulating fluidized bed boiler is effectively guaranteed.

Drawings

Fig. 1 is a hardware configuration diagram of the system proposed by the present invention.

FIG. 2 is a functional block diagram of the upper computer of the present invention.

Detailed Description

The invention is further illustrated by the following figures and examples.

Example 1

Referring to fig. 1 and 2, a bed temperature prediction system of a circulating fluidized bed boiler comprises a field intelligent instrument 2, a data interface 3, a database 4, a control station 5 and an upper computer 6 which are connected with the circulating fluidized bed boiler 1, wherein the field intelligent instrument 2 is connected with a field bus, the data bus is connected with the data interface 3, the data interface 3 is connected with the database 4, the control station 5 and the upper computer 6, and the upper computer 6 comprises:

a standardization processing module 7, configured to collect historical records of operating condition variables and operating variables from the database, form a training sample matrix X of independent variables, collect historical records of corresponding average bed temperature signals, form a dependent variable training sample vector Y, standardize the training sample X, Y to make the mean value of each variable 0 and the variance 1, and obtain a standardized independent variable training sample matrix X^*(nxp), normalized dependent variable training sample vector Y^*(n × 1) by the following procedure:

1.1) averaging:

${\stackrel{\‾}{x}}_j=\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{x}_{\mathrm{ij}},$ （i=1,2,…,n；j=1,2,…,p）（1）

$\stackrel{\‾}{y}=\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{y}_i,$ （i=1,2,…,n）（2）

1.2) calculating the standard deviation

$s_{x,j}=\sqrt{\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(x_{\mathrm{ij}}-{\stackrel{\‾}{x}}_j)}^2},$ （i=1,2,…,n；j=1,2,…,p）（3）

$s_y=\sqrt{\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(y_i-\stackrel{\‾}{y})}^2},$ （i=1,2,…,n）（4）

1.3) normalization

$x_{\mathrm{ij}}^{*}=\frac{x_{\mathrm{ij}}-{\stackrel{\‾}{x}}_j}{s_{x,j}},$ （i=1,2,…,n；j=1,2,…,p）（5）

$y_i^{*}=\frac{y_i-\stackrel{\‾}{y}}{s_y},$ （i=1,2,…,n）（6）

Wherein x is_ij、y_iIs the original value of the training sample point, n is the number of training samples, p is the number of independent variables, is the mean of the training samples, s_x,j、s_yIn order to train the standard deviation of the sample, the normalized values of the training sample points are shown, wherein the subscripts i and j represent the ith training sample point and the jth argument, respectively.

A prediction mechanism forming module 8, configured to build a prediction model, which includes the following steps:

2.1) solving a prediction coefficient vector beta according to the formula (7):

β=(X^*TX^*)^-1X^*TY^*（7）

wherein, the superscript: t, -1 respectively represents the transposition of the matrix and the inverse of the matrix;

2.2) transferring and storing the prediction coefficient vector beta to a prediction execution module.

The prediction execution module 9 is used for predicting the bed temperature according to the operation condition of the circulating fluidized bed boiler and the set operation variable, and the implementation steps are as follows:

3.1) processing the input independent variable signal according to the formula (8):

$x{\left(t\right)}_j^{*}=\frac{x{\left(t\right)}_j-{\stackrel{\‾}{x}}_j}{s_{x,j}},$ （j=1,2,…,p）（8）

wherein, x (t)_jFor the jth original value of the independent variable at the time t,is the mean, s, of the jth independent variable training sample_x,jFor the standard deviation of the jth independent variable training sample,is the jth independent variable dimensionless value at the t moment, and t represents time and unit is second;

3.2) the dimensionless predicted value of the bed temperature is determined according to the following formula:

$\hat{y}{\left(t\right)}^{*}=\left(\begin{array}{cccc}x{\left(t\right)}_1^{*}& x{\left(t\right)}_2^{*}& ...& x{\left(t\right)}_p^{*}\end{array}\right)\mathrm{\β}---\left(9\right)$

wherein,a dimensionless predicted value of the bed temperature at the moment t is obtained;

3.3) solving the original dimensional forecast value of the bed temperature according to the following formula:

$\hat{y}\left(t\right)=\hat{y}{\left(t\right)}^{*}\·s_y+\stackrel{\‾}{y}---\left(10\right)$

wherein,is the original dimensional forecast value of the bed temperature at the time t.

The upper computer 6 further comprises: and the signal acquisition module 11 is used for acquiring real-time data from the field intelligent instrument according to a set sampling time interval and acquiring historical data from a database.

The upper computer 6 further comprises: and the model updating module 12 is used for comparing the actual bed temperature with the predicted value according to a set time interval, adding new data into training sample data if the relative error is more than 10%, and executing the standardization processing module and the prediction mechanism forming module again.

The upper computer 6 further comprises: and the result display module 10 is used for reading the setting parameters from the control station, transmitting the predicted bed temperature value to the control station for display and giving an operation suggestion: under the current working condition, how to adjust the operation variables is most beneficial to controlling the bed temperature in the optimal range, so that the control station workers can adjust the operation conditions in time according to the predicted value of the bed temperature and the operation suggestion to control the bed temperature in the optimal range, and the safe and environment-friendly operation of the circulating fluidized bed boiler is effectively ensured. How to adjust the operation variables is most beneficial to controlling the bed temperature in the optimal range, and a simple method is to substitute various combination values of the operation variables into a bed temperature prediction system to obtain corresponding bed temperature prediction values, so that the bed temperature prediction values can be obtained visually by comparing the sizes of the operation variables.

The hardware part of the upper computer 6 comprises: the I/O element is used for collecting data and transmitting information; the data memory is used for storing data samples, operation parameters and the like required by operation; a program memory storing a software program for realizing the functional module; an arithmetic unit that executes a program to realize a designated function; and the display module displays the set parameters and the running result and gives an operation suggestion.

Example 2

Referring to fig. 1 and 2, a method for predicting bed temperature of a circulating fluidized bed boiler includes the following steps:

1) collecting historical records of operation condition variables and operation variables from a database to form a training sample matrix X of independent variables, collecting the historical records of corresponding average bed temperature signals to form a dependent variable training sample vector Y, standardizing training samples X, Y to ensure that the mean value of each variable is 0 and the variance is 1, and obtaining the standardized independent variable training sample matrix X^*(nxp), normalized dependent variable training sample vector Y^*(n × 1) by the following procedure:

1.1) averaging:

${\stackrel{\‾}{x}}_j=\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{x}_{\mathrm{ij}},$ （i=1,2,…,n；j=1,2,…,p）（1）

$\stackrel{\‾}{y}=\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{y}_i,$ （i=1,2,…,n）（2）

1.2) calculating the standard deviation

$s_{x,j}=\sqrt{\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(x_{\mathrm{ij}}-{\stackrel{\‾}{x}}_j)}^2},$ （i=1,2,…,n；j=1,2,…,p）（3）

$s_y=\sqrt{\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(y_i-\stackrel{\‾}{y})}^2},$ （i=1,2,…,n）（4）

1.3) normalization

$x_{\mathrm{ij}}^{*}=\frac{x_{\mathrm{ij}}-{\stackrel{\‾}{x}}_j}{s_{x,j}},$ （i=1,2,…,n；j=1,2,…,p）（5）

$y_i^{*}=\frac{y_i-\stackrel{\‾}{y}}{s_y},$ （i=1,2,…,n）（6）

Wherein x is_ij、y_iIs the original value of the training sample point, n is the number of training samples, p is the number of independent variables, is the mean of the training samples, s_x,j、s_yIn order to train the standard deviation of the sample, the normalized values of the training sample points are shown, wherein the subscripts i and j represent the ith training sample point and the jth argument, respectively.

2) And establishing a prediction model by the obtained standardized training sample through the following processes:

2.1) solving a prediction coefficient vector beta according to the formula (7):

β=(X^*TX^*)^-1X^*TY^*（7）

wherein, the superscript: t, -1 respectively represents the transposition of the matrix and the inverse of the matrix;

2.2) saving the obtained prediction coefficient vector beta.

3) The method comprises the following steps of taking operating condition variables and set operating variables of the circulating fluidized bed boiler as input signals, and predicting the bed temperature according to a prediction coefficient vector, wherein the method comprises the following steps:

3.1) processing the input independent variable signal according to the formula (8):

$x{\left(t\right)}_j^{*}=\frac{x{\left(t\right)}_j-{\stackrel{\‾}{x}}_j}{s_{x,j}},$ （j=1,2,…,p）（8）

wherein, x (t)_jFor the jth original value of the independent variable at the time t,is the mean, s, of the jth independent variable training sample_x,jFor the standard deviation of the jth independent variable training sample,is the jth independent variable dimensionless value at the t moment, and t represents time and unit is second;

3.2) the dimensionless predicted value of the bed temperature is determined according to the following formula:

$\hat{y}{\left(t\right)}^{*}=\left(\begin{array}{cccc}x{\left(t\right)}_1^{*}& x{\left(t\right)}_2^{*}& ...& x{\left(t\right)}_p^{*}\end{array}\right)\mathrm{\β}---\left(9\right)$

wherein,a dimensionless predicted value of the bed temperature at the moment t is obtained;

3.3) solving the original dimensional forecast value of the bed temperature according to the following formula:

$\hat{y}\left(t\right)=\hat{y}{\left(t\right)}^{*}\·s_y+\stackrel{\‾}{y}---\left(10\right)$

wherein,is the original dimensional forecast value of the bed temperature at the time t.

The method further comprises the following steps: 4) and (3) acquiring field intelligent instrument signals according to a set sampling time interval, comparing the obtained actual bed temperature with a predicted value, adding new data into training sample data if the relative error is more than 10%, and re-executing the steps 1) and 2) to update the prediction model.

In the step 3), reading the setting parameters from the control station, transmitting the predicted bed temperature value to the control station for display, and giving an operation suggestion: under the current working condition, how to adjust the operation variables is most beneficial to controlling the bed temperature in the optimal range, so that the control station workers can adjust the operation conditions in time according to the predicted value of the bed temperature and the operation suggestion to control the bed temperature in the optimal range, and the safe and environment-friendly operation of the circulating fluidized bed boiler is effectively ensured. How to adjust the operation variables is most beneficial to controlling the bed temperature in the optimal range, and a simple method is to substitute various combination values of the operation variables into a bed temperature prediction system to obtain corresponding bed temperature prediction values, so that the bed temperature prediction values can be obtained visually by comparing the sizes of the operation variables.

The independent variables include: the operation condition variables are as follows: main steam flow, environment temperature, water supply temperature, hearth negative pressure, bed pressure, coal moisture, coal volatile matter, coal ash and coal sulfur; the operation variables are as follows: the total air volume of the primary air and the total air volume of the secondary air.

While the system and method for predicting the bed temperature of a circulating fluidized bed boiler according to the present invention have been described with reference to the above embodiments, it will be apparent to those skilled in the art that the present invention can be implemented by modifying or appropriately changing or combining the apparatus and method of operation described herein without departing from the spirit, scope and spirit of the present invention. It is expressly intended that all such similar substitutes and modifications which would be obvious to those skilled in the art are deemed to be within the spirit, scope and content of the invention.

Claims (2)

1. A bed temperature prediction system of a circulating fluidized bed boiler is characterized by comprising an on-site intelligent instrument, a database, a data interface, a control station and an upper computer which are connected with the circulating fluidized bed boiler; on-spot intelligent instrument and control station, database and host computer connection, data interface and database, control station and host computer connection, the host computer include:

a standardization processing module for collecting the historical records of the operation condition variables and the operation variables from the database, forming a training sample matrix X of independent variables, and collecting corresponding bed temperature signalsThe history records of the training matrix X are combined into a dependent variable training sample vector Y, the training sample matrix X and the dependent variable training sample vector Y are standardized to ensure that the mean value of each variable is 0 and the variance is 1, and the normalized independent variable training sample matrix X is obtained^*(nxp), normalized dependent variable training sample vector Y^*(n × 1) by the following procedure:

1.1) averaging:

${\stackrel{\‾}{x}}_j=\frac{1}{n}\underset{i=1}{\overset{n}{\Σ}}{x}_{ij},i=1,2,...,n;j=1,2,...,p;---\left(1\right)$

$\stackrel{\‾}{y}=\frac{1}{n}\underset{i=1}{\overset{n}{\Σ}}{y}_i,---\left(2\right)$

1.2) calculating the standard deviation

$s_{x,j}=\sqrt{\frac{1}{n}\underset{i=1}{\overset{n}{\Σ}}{(x_{ij}-{\stackrel{\‾}{x}}_j)}^2},---\left(3\right)$

$s_y=\sqrt{\frac{1}{n}\underset{i=1}{\overset{n}{\Σ}}{(y_i-\stackrel{\‾}{y})}^2},---\left(4\right)$

1.3) normalization

$x_{ij}^{*}=\frac{x_{ij}-{\stackrel{\‾}{x}}_j}{s_{x,j}},---\left(5\right)$

$y_i^{*}=\frac{y_i-\stackrel{\‾}{y}}{s_y},---\left(6\right)$

Wherein x is_ij、y_iIs the original value of the training sample point, n is the number of training samples, p is the number of independent variables,is the mean of the training samples, s_x,j、s_yIn order to train the standard deviation of the sample,the normalized values of the training sample points are shown, wherein subscripts i and j respectively represent the ith training sample point and the jth independent variable;

the prediction mechanism forming module is used for establishing a prediction model and comprises the following implementation steps:

2.1) solving a prediction coefficient vector beta according to the formula (7):

β＝((X^*(n×p))^TX^*(n×p))^-1(X^*(n×p))^TY^*(nx1) and (7) wherein, the superscript T and-1 respectively represent the transposition of a matrix and the inverse of the matrix;

2.2) transferring and storing the prediction coefficient vector beta to a prediction execution module;

the prediction execution module is used for predicting the bed temperature according to the running working condition of the circulating fluidized bed boiler and the set operation variable, and the implementation steps are as follows:

3.1) processing the input independent variable signal according to the formula (8):

$x{\left(t\right)}_j^{*}=\frac{x{\left(t\right)}_j-{\stackrel{\‾}{x}}_j}{s_{x,j}},---\left(8\right)$

wherein, x (t)_jFor the jth original value of the independent variable at the time t,is the mean, s, of the jth independent variable training sample_x,jFor the standard deviation of the jth independent variable training sample,is the jth independent variable dimensionless value at the t moment, and t represents time and unit is second;

3.2) the dimensionless predicted value of the bed temperature is determined according to the following formula:

$\hat{y}{\left(t\right)}^{*}=\left(\begin{array}{cccc}x{\left(t\right)}_1^{*}& x{\left(t\right)}_2^{*}& ...& x{\left(t\right)}_p^{*}\end{array}\right)\mathrm{\β},---\left(9\right)$

wherein,a dimensionless predicted value of the bed temperature at the moment t is obtained;

3.3) solving the original dimensional forecast value of the bed temperature according to the following formula:

$\hat{y}\left(t\right)=\hat{y}{\left(t\right)}^{*}\·s_y+\stackrel{\‾}{y},---\left(10\right)$

wherein,is the original dimension prediction value of the bed temperature at the time t;

the host computer still include:

the signal acquisition module is used for acquiring real-time data from the field intelligent instrument and historical data from the database according to a set sampling time interval;

the model updating module is used for comparing the actual bed temperature with the predicted value according to a set time interval, if the relative error is more than 10%, adding new data into training sample data, and executing the standardization processing module and the prediction mechanism forming module again;

and the result display module is used for reading the setting parameters from the control station, transmitting the predicted bed temperature value to the control station for display and giving an operation suggestion: under the current working condition, how to adjust the operation variables is most beneficial to controlling the bed temperature in the optimal range, so that a control station worker can adjust the operation conditions in time according to the predicted value and the operation suggestion of the bed temperature to control the bed temperature in the optimal range, and the safe and environment-friendly operation of the circulating fluidized bed boiler is effectively ensured; the method for controlling the bed temperature in the optimal range by adjusting the operation variables is to substitute various combination values of the operation variables into a bed temperature prediction system to obtain corresponding bed temperature prediction values, so that the bed temperature prediction values can be obtained visually by comparing the sizes of the operation variables;

the independent variables include: the operation condition variables are as follows: main steam flow, environment temperature, water supply temperature, hearth negative pressure, bed pressure, coal moisture, coal volatile matter, coal ash and coal sulfur; the operation variables are as follows: the total air volume of the primary air and the total air volume of the secondary air.

2. A bed temperature prediction method implemented by the circulating fluidized bed boiler bed temperature prediction system of claim 1, wherein the prediction method comprises the steps of:

1) collecting historical records of operation condition variables and operation variables from a database to form a training sample matrix X of independent variables, collecting the historical records of corresponding bed temperature signals to form a dependent variable training sample vector Y, standardizing training samples X, Y to ensure that the mean value of each variable is 0 and the variance is 1, and obtaining the standardized independent variable training sample matrix X^*(nxp), normalized dependent variable training sample vector Y^*(n × 1) by the following procedure:

1.1) averaging:

${\stackrel{\‾}{x}}_j=\frac{1}{n}\underset{i=1}{\overset{n}{\Σ}}{x}_{ij},i=1,2,...,n;j=1,2,...,p;---\left(1\right)$

$\stackrel{\‾}{y}=\frac{1}{n}\underset{i=1}{\overset{n}{\Σ}}{y}_i,---\left(2\right)$

1.2) calculating the standard deviation

$s_{x,j}=\sqrt{\frac{1}{n}\underset{i=1}{\overset{n}{\Σ}}{(x_{ij}-{\stackrel{\‾}{x}}_j)}^2},---\left(3\right)$

$s_y=\sqrt{\frac{1}{n}\underset{i=1}{\overset{n}{\Σ}}{(y_i-\stackrel{\‾}{y})}^2},---\left(4\right)$

1.3) normalization

$x_{ij}^{*}=\frac{x_{ij}-{\stackrel{\‾}{x}}_j}{s_{x,j}},---\left(5\right)$

$y_i^{*}=\frac{y_i-\stackrel{\‾}{y}}{s_y},---\left(6\right)$

Wherein x is_ij、y_iIs the original value of the training sample point, n is the number of training samples, p is the number of independent variables,is the mean of the training samples, s_x,j、s_yIn order to train the standard deviation of the sample,the normalized values of the training sample points are shown, wherein subscripts i and j respectively represent the ith training sample point and the jth independent variable;

2) and establishing a prediction model by the obtained standardized training sample through the following processes:

2.1) solving a prediction coefficient vector beta according to the formula (7):

β＝((X^*(n×p))^TX^*(n×p))^-1(X^*(n×p))^TY^*(n×1)，(7)

wherein, the superscript: t, -1 respectively represents the transposition of the matrix and the inverse of the matrix;

2.2) storing the obtained prediction coefficient vector beta;

3) the method comprises the following steps of taking operating condition variables and set operating variables of the circulating fluidized bed boiler as input signals, and predicting the bed temperature according to a prediction coefficient vector, wherein the method comprises the following steps:

3.1) processing the input independent variable signal according to the formula (8):

$x{\left(t\right)}_j^{*}=\frac{x{\left(t\right)}_j-{\stackrel{\‾}{x}}_j}{s_{x,j}},---\left(8\right)$

wherein, x (t)_jFor the jth original value of the independent variable at the time t,is the mean, s, of the jth independent variable training sample_x,jFor the standard deviation of the jth independent variable training sample,is the jth independent variable dimensionless value at the t moment, and t represents time and unit is second;

3.2) the dimensionless predicted value of the bed temperature is determined according to the following formula:

$\hat{y}{\left(t\right)}^{*}=\left(\begin{array}{cccc}x{\left(t\right)}_1^{*}& x{\left(t\right)}_2^{*}& ...& x{\left(t\right)}_p^{*}\end{array}\right)\mathrm{\β},---\left(9\right)$

wherein,a dimensionless predicted value of the bed temperature at the moment t is obtained;

3.3) solving the original dimensional forecast value of the bed temperature according to the following formula:

$\hat{y}\left(t\right)=\hat{y}{\left(t\right)}^{*}\·s_y+\stackrel{\‾}{y},---\left(10\right)$

wherein,is the original dimension prediction value of the bed temperature at the time t;

4) collecting on-site intelligent instrument signals according to a set sampling time interval, comparing the obtained actual bed temperature with a predicted value, if the relative error is more than 10%, adding new data into training sample data, and executing the steps 1) and 2) again to update the prediction model;

in the step 3), reading the setting parameters from the control station, transmitting the predicted bed temperature value to the control station for display, and giving an operation suggestion: under the current working condition, how to adjust the operation variables is most beneficial to controlling the bed temperature in the optimal range, so that a control station worker can adjust the operation conditions in time according to the predicted value and the operation suggestion of the bed temperature to control the bed temperature in the optimal range, and the safe and environment-friendly operation of the circulating fluidized bed boiler is effectively ensured; the method for controlling the bed temperature in the optimal range by adjusting the operation variables is to substitute various combination values of the operation variables into a bed temperature prediction system to obtain corresponding bed temperature prediction values, so that the bed temperature prediction values can be obtained visually by comparing the sizes of the operation variables;

the independent variables include: the operation condition variables are as follows: main steam flow, environment temperature, water supply temperature, hearth negative pressure, bed pressure, coal moisture, coal volatile matter, coal ash and coal sulfur; the operation variables are as follows: the total air volume of the primary air and the total air volume of the secondary air.