CN117308136A - Industrial boiler load distribution method based on historical operation data statistics - Google Patents

Abstract

The invention relates to an industrial boiler load distribution method based on historical operation data statistics, which comprises the following steps: acquiring historical operation data of a boiler group; respectively constructing a boiler total load section operation time length matrix, a boiler group total load matrix and a boiler group comprehensive efficiency matrix based on historical operation data; multiplying the matrix elements of the total load section operation time length matrix of the boiler, the total load matrix of the boiler group and the comprehensive efficiency matrix of the boiler group one by one in sequence to obtain an operation efficiency matrix of the boiler group; the matrix dimension of the running duration matrix of the total load section of the boiler, the matrix dimension of the total load matrix of the boiler group, the matrix dimension of the comprehensive efficiency matrix of the boiler group and the matrix dimension of the running efficiency matrix of the boiler group are the same; and solving the running efficiency matrix of the boiler group based on a dynamic programming algorithm comprising constraint conditions to determine an optimal boiler load distribution scheme, so that the overall production efficiency of the boiler group can be improved.

Description

Industrial boiler load distribution method based on historical operation data statistics

Technical Field

The invention relates to the technical field of thermoelectric production, in particular to an industrial boiler load distribution method based on historical operation data statistics.

Background

In the field of thermoelectric production, industrial boilers operating in parent tube are common. Compared with unit operation, the operation mode of the main pipe boiler is more stable and reliable. Meanwhile, because the production efficiency of different boilers is different, when the downstream steam load is fixed, the overall comprehensive production efficiency is affected by different load distribution modes. Therefore, the reasonable load distribution method is used for adjusting the output force of the boiler group, and the overall production efficiency of the boiler group can be effectively improved.

At present, the existing boiler load distribution modes include modes of load proportion distribution according to boiler groups, adjustment according to priority orders, principle distribution according to fuel consumption micro-increment rates and the like.

However, the effectiveness of allocation cannot be ensured by preset according to manual experience in modes of proportional allocation, priority allocation and the like; accurate boiler efficiency curves are required as a precondition in the manner of equal-micron-scale distribution, which is generally difficult to achieve.

Therefore, a reasonable boiler load distribution method is found based on the historical operation data of the boiler group, and the method has important significance for ensuring the operation energy efficiency of the boiler group.

Disclosure of Invention

First, the technical problem to be solved

In view of the above-mentioned shortcomings and disadvantages of the prior art, the invention provides an industrial boiler load distribution method based on historical operation data statistics, which solves the technical problems of inaccurate manual experience and low comprehensive operation efficiency of a boiler group caused by difficult identification of a boiler efficiency curve in the prior art.

(II) technical scheme

In order to achieve the above purpose, the main technical scheme adopted by the invention comprises the following steps:

in a first aspect, an embodiment of the present invention provides an industrial boiler load distribution method based on historical operation data statistics, including: acquiring historical operation data of a boiler group; respectively constructing a boiler total load section operation time length matrix, a boiler group total load matrix and a boiler group comprehensive efficiency matrix based on historical operation data; multiplying the matrix elements of the total load section operation time length matrix of the boiler, the total load matrix of the boiler group and the comprehensive efficiency matrix of the boiler group one by one in sequence to obtain an operation efficiency matrix of the boiler group; the matrix dimension of the running duration matrix of the total load section of the boiler, the matrix dimension of the total load matrix of the boiler group, the matrix dimension of the comprehensive efficiency matrix of the boiler group and the matrix dimension of the running efficiency matrix of the boiler group are the same; and solving the boiler group operation efficiency matrix based on a dynamic programming algorithm comprising constraint conditions so as to determine an optimal boiler load distribution scheme.

In one possible embodiment, the historical operating data for each of the plurality of boilers included in the boiler bank includes a time stamp, a boiler load, and a fuel consumption.

In one possible embodiment, the boiler bank includes a plurality of boilers; based on historical operation data, respectively constructing a boiler total load section operation time length matrix, a boiler group total load matrix and a boiler group comprehensive efficiency matrix, wherein the method comprises the following steps of: respectively constructing three empty matrixes; wherein each dimension of each empty matrix in the three empty matrices corresponds to one boiler, the column number in each dimension is equal to the load segmentation number of the corresponding boiler, and each column corresponds to the load segment of the boiler from small to large; based on the time mark and the boiler load, respectively counting the total operation time length corresponding to each cell in the first empty matrix, and filling the total operation time length into the first empty matrix to obtain a boiler total load section operation time length matrix; based on the boiler load, respectively counting the total load of the boiler group corresponding to each cell in the second empty matrix, and filling the total load of the boiler group into the second empty matrix to obtain a total load matrix of the boiler group; based on the boiler load and the fuel consumption, respectively counting the total operating steam yield and the total fuel consumption corresponding to each unit cell in the third empty matrix, calculating the quotient of the total fuel consumption and the total operating steam yield, and filling the quotient into the third empty matrix to obtain the comprehensive efficiency matrix of the boiler group.

In one possible embodiment, the statistical process of the total operating time period, the total load of the boiler group, the total steam production and the total fuel consumption comprises: discretizing the load of each boiler from the minimum load to the maximum load according to a preset step length, and determining the corresponding relation between the actual load and the discretized load section according to a rounding principle; based on the corresponding relation, respectively counting the total operation duration, the total load of the boiler group, the total operation steam production and the total fuel consumption.

In one possible embodiment, the matrix elements of the total load section operation duration matrix, the total load matrix of the boiler group and the total efficiency matrix of the boiler group are multiplied one by one in sequence to obtain a boiler group operation efficiency matrix, which comprises the following steps: filling the running time length matrix of the total load section of the boiler by using a data smoothing method to obtain the filled running time length matrix of the total load section of the boiler; filling the comprehensive efficiency matrix of the boiler group by using an interpolation method to obtain a filled comprehensive efficiency matrix of the boiler group; and multiplying matrix elements of the filled total load section operation time length matrix, the total load matrix of the boiler group and the filled comprehensive efficiency matrix of the boiler group one by one in sequence to obtain an operation efficiency matrix of the boiler group.

In one possible embodiment, the method for filling the running duration matrix of the total load section of the boiler by using the data smoothing method to obtain the filled running duration matrix of the total load section of the boiler includes: marking unfilled first cells in a boiler total load section operation time length matrix; wherein the unfilled first cell corresponds to a total load of the boiler that does not occur in the historical operating data; filling the marked first unit cells in the boiler total load section operation time length matrix by using a data smoothing method to obtain the filled boiler total load section operation time length matrix.

In one possible embodiment, the boiler bank integrated efficiency matrix is filled by an interpolation method to obtain a filled boiler bank integrated efficiency matrix, including: marking unfilled second cells in the boiler bank comprehensive efficiency matrix; wherein the unfilled second cell corresponds to a combination of boiler loads that does not occur in the historical operating data; filling the marked second cell in the boiler group comprehensive efficiency matrix by using an interpolation method to obtain a filled boiler group comprehensive efficiency matrix.

In one possible embodiment, solving the boiler bank operational effectiveness matrix based on a dynamic programming algorithm including constraints to determine an optimal boiler load distribution scheme includes: marking infeasible load segments of each boiler in a boiler group operation efficiency matrix; determining a recurrence function of the corresponding cost of the boiler load distribution scheme of the boiler group; implementing a dynamic programming algorithm based on the infeasible load segments and the recursive function to determine an optimal path with minimum total weight from a lowest total load in an upper left corner to a highest total load in a lower right corner of the boiler bank operational efficiency matrix; the optimal path is the optimal boiler load distribution scheme.

In a second aspect, embodiments of the present application provide a storage medium having stored thereon a computer program which, when executed by a processor, performs the method of the first aspect or any alternative implementation of the first aspect.

In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory in communication via the bus when the electronic device is running, the machine-readable instructions when executed by the processor performing the method of the first aspect or any alternative implementation of the first aspect.

In a fourth aspect, the present application provides a computer program product which, when run on a computer, causes the computer to perform the method of the first aspect or any of the possible implementations of the first aspect.

(III) beneficial effects

The beneficial effects of the invention are as follows:

the embodiment of the application provides an industrial boiler load distribution method based on historical operation data statistics, which is characterized in that a boiler group operation efficiency matrix is obtained by respectively constructing a boiler total load section operation time length matrix, a boiler group total load matrix and a boiler group comprehensive efficiency matrix based on the historical operation data and multiplying matrix elements of the boiler total load section operation time length matrix, the boiler group total load matrix and the boiler group comprehensive efficiency matrix one by utilizing the boiler total load section operation time length matrix, the boiler group total load matrix and the boiler group comprehensive efficiency matrix to obtain the boiler group operation efficiency matrix, wherein the matrix dimension of the boiler group total load section operation time length matrix, the matrix dimension of the boiler group comprehensive efficiency matrix and the matrix dimension of the boiler group operation efficiency matrix are the same, and the boiler group operation efficiency matrix is solved based on a dynamic programming algorithm comprising constraint conditions, so that the problem of inaccurate artificial experience and difficult identification of a boiler efficiency curve in the existing distribution method is solved.

In order to make the above objects, features and advantages of the embodiments of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 illustrates a flow chart of an industrial boiler load distribution method based on historical operating data statistics provided by an embodiment of the present application;

FIG. 2 shows a specific flow chart of an industrial boiler load distribution method based on historical operating data statistics provided by an embodiment of the present application;

FIG. 3 is a schematic diagram of a total load segment operation duration matrix of a boiler according to an embodiment of the present disclosure;

FIG. 4 shows a schematic diagram of a total load matrix of a boiler bank provided in an embodiment of the present application;

FIG. 5 shows a schematic diagram of a boiler bank integrated efficiency matrix provided by an embodiment of the present application;

FIG. 6 is a schematic diagram of a boiler bank operating performance matrix provided in an embodiment of the present application.

Detailed Description

The invention will be better explained by the following detailed description of the embodiments with reference to the drawings.

In order to solve the problems existing in the prior art, the embodiment of the application provides an industrial boiler load distribution method based on historical operation data statistics, by acquiring the historical operation data of a boiler group, respectively constructing a boiler total load section operation duration matrix, a boiler group total load matrix and a boiler group comprehensive efficiency matrix based on the historical operation data, and sequentially multiplying matrix elements of the boiler total load section operation duration matrix, the boiler group total load matrix and the boiler group comprehensive efficiency matrix one by one to obtain a boiler group operation efficiency matrix, wherein the matrix dimension of the boiler total load section operation duration matrix, the matrix dimension of the boiler group total load matrix, the matrix dimension of the boiler group comprehensive efficiency matrix and the matrix dimension of the boiler group operation efficiency matrix are the same, and solving the boiler group operation efficiency matrix based on a dynamic planning algorithm comprising constraint conditions to determine an optimal boiler load distribution scheme, so that the problems of inaccurate manual experience and low comprehensive operation of the boiler group caused by difficult identification of a boiler efficiency curve determined in the existing distribution method are solved.

In order that the above-described aspects may be better understood, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

Referring to fig. 1, fig. 1 shows a flowchart of an industrial boiler load distribution method based on historical operation data statistics according to an embodiment of the present application. It should be understood that the industrial boiler load distribution method may be performed by an electronic device, and specific devices of the electronic device may be set according to actual requirements, and embodiments of the present application are not limited thereto. For example, the electronic device may be a computer, a server, or the like. Specifically, the industrial boiler load distribution method comprises the following steps:

step S110, acquiring historical operation data of the boiler group.

It should be understood that the specific data included in the historical operating data may be set according to the actual requirement, and the embodiment of the application is not limited thereto.

Alternatively, the historical operation data of each boiler in the boiler group is acquired in a unit time length of a preset time period, and each boiler's historical operation data includes a time stamp (which may be a time stamp or the like, for example), a boiler load, and a fuel consumption amount.

It should also be appreciated that the specific time period of the preset time period may be set according to actual requirements, and embodiments of the present application are not limited thereto.

For example, the preset time period may be 1 minute, 1 hour, or the like.

Step S120, based on the historical operation data, respectively constructing a boiler total load section operation time length matrix, a boiler group total load matrix and a boiler group comprehensive efficiency matrix.

It should also be understood that, based on the historical operating data, the specific processes of respectively constructing the boiler total load section operating time length matrix, the boiler group total load matrix and the boiler group comprehensive efficiency matrix may be set according to actual requirements, and the embodiment of the present application is not limited thereto.

Optionally, three empty matrixes are respectively constructed, wherein each dimension of each empty matrix in the three empty matrixes corresponds to a boiler, the number of columns in each dimension is equal to the number of load segments of the corresponding boiler, each column is from small to large and corresponds to the load segment of the corresponding boiler, the operation total time length corresponding to each cell in the first empty matrix is respectively counted based on the time mark and the boiler load, the operation total time length is filled into the first empty matrix to obtain a boiler total load segment operation time length matrix, the boiler group total load corresponding to each cell in the second empty matrix is respectively counted based on the boiler load, the boiler group total load is filled into the second empty matrix to obtain a boiler group total load matrix, the operation total yield and the total fuel consumption corresponding to each cell in the third empty matrix are respectively counted based on the boiler load and the fuel consumption, the operation total fuel consumption and the operation total fuel consumption are calculated, the quotient value is filled into the third empty matrix to obtain a total steam yield matrix.

For example, three empty multidimensional matrices are established separately, and each matrix has dimensions equal to the number of boiler runs (e.g., 2 in the case of a boiler bank comprising 2 boilers, etc.), and columns in each dimension equal to the number of load segments of the corresponding boiler, with each column corresponding from small to large to small load segments of the boiler. And counting the historical operation data in the step S110, accumulating the corresponding total load according to the actual operation load sections of each boiler, counting the total operation time length of the corresponding cells in the first matrix, filling the corresponding total operation time length into the corresponding cells, and taking the filled matrix as the operation time length matrix of the total load sections of the boiler. And for the second matrix, accumulating the boiler loads corresponding to each cell to obtain the total load of the boiler group corresponding to the cell, filling the total load of the boiler group into the corresponding cell, and taking the filled matrix as the total load matrix of the boiler group. And, counting the historical operation data in the step S110, counting the total steam generation amount and the total fuel consumption amount of the operation of the corresponding cell in the third matrix according to the actual operation load section of each boiler, filling the cell with the result of dividing the total fuel consumption amount by the total steam generation amount (namely, the quotient value is the ton steam consumption amount), and taking the filled matrix as the comprehensive efficiency matrix of the boiler group. Wherein the total steam production is obtained according to the boiler load.

It should also be appreciated that the above-described statistical process of total operating duration, total load of the boiler bank, total operating steam production, and total fuel consumption may be set according to actual requirements, and the embodiments of the present application are not limited thereto.

Optionally, discretizing the load of each boiler from the minimum load to the maximum load according to a preset step length, determining the corresponding relation between the actual load and the discretized load section according to a rounding principle, and respectively counting the total operation duration, the total load of the boiler group, the total operation steam production and the total fuel consumption based on the corresponding relation. The specific step length of the preset step length can be set according to actual requirements, and the embodiment of the application is not limited to this. For example, the preset step size may be 11t/h.

For example, each boiler may be discretized in steps of 1% to 5% from the minimum load to the maximum load of its own load capacity, and the correspondence between the actual load and the discretized load segment may be determined in accordance with the rounding principle (for example, in the case where the discretized load segment includes 187t/h and 198t/h and the current actual load is 190.5t/h, since 190.5t/h is closer to 187t/h, it may be determined that the current actual load and 187t/h have the correspondence). Subsequently, the total operating time period, the total load of the boiler group, the total steam generation amount of operation, and the total fuel consumption amount can be counted based on the correspondence between the actual load and the discretized load segment, respectively.

Step S130, sequentially multiplying matrix elements of the total load section operation time length matrix of the boiler, the total load matrix of the boiler group and the comprehensive efficiency matrix of the boiler group item by item to obtain an operation efficiency matrix of the boiler group. The matrix dimension of the running duration matrix of the total load section of the boiler, the matrix dimension of the total load matrix of the boiler group, the matrix dimension of the comprehensive efficiency matrix of the boiler group and the matrix dimension of the running efficiency matrix of the boiler group are the same.

It should be understood that, the specific process of multiplying the matrix elements of the total load section operation duration matrix, the total load matrix of the boiler group and the comprehensive efficiency matrix of the boiler group sequentially item by item to obtain the operation efficiency matrix of the boiler group may be set according to actual requirements, and the embodiment of the present application is not limited thereto.

Optionally, filling the boiler total load section operation time length matrix by using a data smoothing method to obtain a filled boiler total load section operation time length matrix, filling the boiler group comprehensive efficiency matrix by using an interpolation method to obtain a filled boiler group comprehensive efficiency matrix, and multiplying matrix elements of the filled boiler total load section operation time length matrix, the boiler group total load matrix and the filled boiler group comprehensive efficiency matrix one by one in sequence to obtain a boiler group operation efficiency matrix.

It should also be understood that the specific process of filling the boiler total load segment operation duration matrix by using the data smoothing method may be set according to actual requirements, and the embodiment of the present application is not limited thereto.

Optionally, marking unfilled first cells in the boiler total load section operation duration matrix, wherein the unfilled first cells correspond to the total load of the boiler which does not occur in the historical operation data, and filling the marked first cells in the boiler total load section operation duration matrix by using a data smoothing method according to the existing elements in the boiler total load section operation duration matrix so as to obtain a filled boiler total load section operation duration matrix. The specific smoothing method of the data smoothing method may be set according to actual requirements, and the embodiment of the application is not limited thereto. For example, the data smoothing method may be a plus-one smoothing method (alternatively referred to as a laplace smoothing method).

It should also be understood that the specific process of filling the boiler bank comprehensive efficiency matrix by using the interpolation method may also be set according to actual requirements, and the embodiment of the present application is not limited thereto.

Optionally, marking the unfilled second cells in the boiler group comprehensive efficiency matrix, wherein the unfilled second cells correspond to the combination of the boiler loads which do not occur in the historical operation data, and filling the marked second cells in the boiler group comprehensive efficiency matrix by using an interpolation method according to the existing elements in the boiler group comprehensive efficiency matrix so as to obtain the filled boiler group comprehensive efficiency matrix. The specific interpolation method of the interpolation method may be set according to actual requirements, and the embodiment of the application is not limited thereto. For example, the interpolation method may be a multidimensional linear interpolation method.

It should also be understood that the specific process of multiplying the matrix elements thereof one by one in sequence by using the filled total load section operation duration matrix, the total load matrix of the boiler group and the filled total efficiency matrix of the boiler group may also be set according to actual requirements, and the embodiment of the present application is not limited thereto.

Alternatively, a multi-dimensional matrix (i.e., the matrix may be a boiler bank operation efficiency matrix) may be established, and the dimensions of the multi-dimensional matrix are made equal to the number of boiler operations of the boiler bank, and the number of columns in each dimension is made equal to the number of load segments of the corresponding boiler, and each column corresponds from small to large to small to large load segments of the boiler. And for each cell of the boiler group operation efficiency matrix, finding three cells corresponding to the same row and the same column in the boiler group total load section operation time length matrix, the boiler group total load matrix and the boiler group comprehensive efficiency matrix, and filling products of elements in the three cells into corresponding cells of the boiler group operation efficiency matrix.

And step S140, solving the boiler group operation efficiency matrix based on a dynamic programming algorithm comprising constraint conditions to determine an optimal boiler load distribution scheme.

It should be appreciated that the specific process of solving the boiler bank operating efficiency matrix based on a dynamic programming algorithm including constraints to determine an optimal boiler load distribution scheme may be set according to actual needs, and embodiments of the present application are not limited thereto.

Optionally, marking an infeasible load segment of each boiler in the boiler group operation efficiency matrix, determining a recursive function of a cost corresponding to a boiler load distribution scheme of the boiler group, and implementing a dynamic programming algorithm based on the infeasible load segment and the recursive function to determine an optimal path with minimum total weight from the lowest total load of the upper left corner to the highest total load of the lower right corner of the boiler group operation efficiency matrix; the optimal path is an optimal distribution scheme under the condition of the lowest to highest total load (or the optimal path is an optimal boiler load distribution scheme).

For example, the infeasible load segments for each boiler are identified in the boiler bank operating performance matrix, i.e., the boiler cannot operate at the load segment. And in the optimal load distribution method, giving a first total load A and a second total load B of two different total loads, and if the second total load B is larger than the first total load A, distributing the load of each boiler after the first total load A is not smaller than the load of each boiler after the second total load B is distributed. And, in the case where the boiler group includes k boilers, let F (x 1x2x 3..xk) denote the cost corresponding to the optimal allocation method when the total load is x1+x2+x3.+ xk, where the k boiler loads are x1, x2, x3,..and xk, respectively (here, the cost refers to an evaluation function required in the dynamic programming recursive function, and the evaluation function may also be referred to as an evaluation function or a cost function), and the minimum load unit of xi corresponding to the boiler is ai (here, the ai is a load segment or a preset step size as described above), the recursive function of the allocation scheme corresponds to the cost is:

F(x1x2x3...xk)＝min(F((x1-a1)x2x3...xk)，F(x1(x2-a2)x3...xk)，F(x1x2(x3-a3)...xk)，...，F(x1x2x3...(xk-ak))。

wherein the loads of x1-a1, x2-a2, x3-a3, x.i., xk-ak, etc. are not within the infeasible load segments of the corresponding boiler.

It should be noted that, the first total load a and the second total load B determine the recurrence function, that is, the recurrence function already covers the first total load a and the second total load B, and only infeasible load segments and recurrence functions are needed to implement the dynamic programming algorithm. That is, the content of the first total load and the second total load described above is actually to obtain a recursive function.

And realizing a corresponding dynamic programming algorithm based on a recursive formula and the constraint of the infeasible load segment to find an optimal load distribution result under each total load, namely a distribution scheme with the lowest corresponding cost.

Therefore, in the load distribution process of the boiler group, the embodiment of the application utilizes the historical operation data to find the optimal distribution scheme of the load of the boiler group, and can dynamically find the optimal distribution result according to the operation condition, thereby being beneficial to the overall production efficiency improvement of the boiler group. Compared with the prior art, the method and the device have the advantages that the comprehensive efficiency of the metering and distributing scheme can be improved accurately, and error distributing results caused by inaccurate data are avoided. And the acquisition methods of the distribution schemes are all based on historical operation data, so that the problem that the distribution schemes cannot be executed is avoided, and the distribution results can guide coordination control among multiple furnaces, so that accurate support is provided for economic and safe operation of the unit.

In order to facilitate an understanding of the embodiments of the present application, the following description is made by way of specific embodiments.

Specifically, referring to fig. 2, fig. 2 shows a specific flowchart of an industrial boiler load distribution method based on historical operation data statistics according to an embodiment of the present application. The industrial boiler load distribution method as shown in fig. 2 includes:

step S210, acquiring historical production data of the boiler group related to production energy efficiency.

Specifically, the historical operation data of each boiler was acquired in a unit time length of 1 hour, and the historical operation data contained a time stamp, a fuel consumption amount, and a boiler load.

Step S220, three two-dimensional matrixes are constructed according to the historical production data. The three two-dimensional matrixes comprise a running time length matrix of a total load section of the boiler, a total load matrix of the boiler group and a comprehensive efficiency matrix of the boiler group.

Specifically, three two-dimensional matrixes are established, each dimension corresponds to one boiler respectively, the column number in each dimension is equal to the load segmentation number of the corresponding boiler, and each column corresponds to the load segment of the boiler from small to large;

and, counting the historical data obtained in the step S210, and counting the total operation time length of a corresponding cell in the first matrix according to the actual operation load sections of each boiler, and filling the cell with the total operation time length matrix of the total operation time length of each boiler, wherein the filled matrix is the total operation time length matrix of each boiler, and particularly, see FIG. 3;

and accumulating the loads of the boilers corresponding to each cell for the second matrix to obtain the total load of the boiler group corresponding to the cell and filling the total load of the boiler group into the cell, wherein the filled matrix is the total load matrix of the boiler group, and particularly, see FIG. 4;

and, counting the historical data obtained in the step S210, and counting the total steam generation amount and the total fuel consumption amount of the operation of the corresponding cells in the first matrix according to the actual operation load segments of each boiler, and filling the result of dividing the total fuel consumption amount by the total steam generation amount into the cells, wherein the filled matrix is a comprehensive efficiency matrix of the boiler group, and particularly can be seen in fig. 5.

Step S230, filling the boiler group comprehensive efficiency matrix by using an interpolation method.

Step S240, filling the running time length matrix of the total load section of the boiler by using a data smoothing method.

Step S250, sequentially multiplying matrix elements item by utilizing the filled boiler total load section operation time length matrix, the boiler group total load matrix and the filled boiler group comprehensive efficiency matrix to obtain a boiler group operation efficiency matrix with the same dimension.

Specifically, a two-dimensional matrix is established, the dimension of the matrix is equal to the running number of the boilers, the column number in each dimension is equal to the load segmentation number of the corresponding boiler, and each column corresponds to the load segment of the boiler from small to large; the matrix is called a boiler group operation efficiency matrix, and for each cell of the boiler group operation efficiency matrix, three cells corresponding to the same row and the same column in the boiler group total load section operation time length matrix, the boiler group total load matrix and the boiler group comprehensive efficiency matrix are found, and products of elements in the three cells are filled into corresponding cells of the boiler group operation efficiency matrix, and particularly, the method can be seen in fig. 6.

Step S260, based on the boiler group operation efficiency matrix, executing a dynamic programming algorithm containing constraints, and searching an optimal path with the minimum total weight from the lowest total load at the upper left corner to the highest total load at the lower right corner, wherein the optimal path is an optimal distribution scheme under the condition from the lowest total load to the highest total load.

Specifically, marking an infeasible load section of each boiler, i.e. the boiler cannot operate under the load section, wherein in the example, two boilers can operate in the interval of 132t/h to 220 t/h;

in the optimal load distribution method, two different first total loads A and second total loads B are given, and if the first total load A is larger than the second total load B, the loads of all boilers after the first total load A is distributed are not smaller than the loads of all boilers after the second total load B is distributed;

let F (x 1x 2) represent the cost of the optimal allocation method when the total load is x1+x2, the loads of the two boilers are respectively x1 and x2, and the minimum load unit of the corresponding boilers of the two boilers is 11t/h, then the recursive function of the cost of the optimal allocation method is: f (x 1x 2) =min (F ((x 1-11) x 2), F (x 1 (x 2-11)));

based on the recursive formula and the constraint of the infeasible load segment, a corresponding dynamic programming algorithm is implemented to find an optimal load distribution result (i.e., gray part in fig. 6) under each total load, and the optimal load distribution result is the distribution scheme with the minimum cost when meeting the total load demand and all constraints.

In addition, when running online, the corresponding allocation scheme can be directly selected according to the current total load. For example, when the total load of two boilers is 325t/h, the total load is found to belong to a 330t/h load section according to the rounding method, and the optimal load distribution scheme corresponding to 330t/h is that the boiler 1 is operated 154t/h while the boiler 2 is operated 176t/h (two boilers and a gray square lattice of 330t/h in the figure). Scaling the total load of the two boilers from 330t/h to 325t/h, rounded off, shows that boiler 1 should operate at 152t/h while boiler 2 should operate at 173 t/h.

It should be understood that the above-described method of distributing load to an industrial boiler based on statistics of historical operating data is only exemplary, and those skilled in the art can make various modifications according to the above-described method, and the solutions after the modifications are also within the scope of protection of the present application.

The present application provides a storage medium having stored thereon a computer program which, when executed by a processor, performs the method of the embodiments.

The present application also provides a computer program product which, when run on a computer, causes the computer to perform the method of the method embodiments.

It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions.

It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the terms first, second, third, etc. are for convenience of description only and do not denote any order. These terms may be understood as part of the component name.

Furthermore, it should be noted that in the description of the present specification, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to a specific feature, structure, material, or characteristic described in connection with the embodiment or example being included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art upon learning the basic inventive concepts. Therefore, the appended claims should be construed to include preferred embodiments and all such variations and modifications as fall within the scope of the invention.

It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, the present invention should also include such modifications and variations provided that they come within the scope of the following claims and their equivalents.

Claims (10)

1. An industrial boiler load distribution method based on historical operating data statistics, comprising:

acquiring historical operation data of a boiler group;

respectively constructing a boiler total load section operation time length matrix, a boiler group total load matrix and a boiler group comprehensive efficiency matrix based on the historical operation data;

multiplying matrix elements of the total load section operation time length matrix of the boiler group, the total load matrix of the boiler group and the comprehensive efficiency matrix of the boiler group one by one in sequence to obtain an operation efficiency matrix of the boiler group; the matrix dimension of the running duration matrix of the total load section of the boiler, the matrix dimension of the total load matrix of the boiler group, the matrix dimension of the comprehensive efficiency matrix of the boiler group and the matrix dimension of the running efficiency matrix of the boiler group are the same;

and solving the boiler group operation efficiency matrix based on a dynamic programming algorithm comprising constraint conditions so as to determine an optimal boiler load distribution scheme.

2. The industrial boiler load distribution method according to claim 1, wherein the historical operating data of each of the plurality of boilers included in the boiler group includes a time stamp, a boiler load, and a fuel consumption.

3. The industrial boiler load distribution method according to claim 2, wherein the boiler group includes a plurality of boilers; the method for respectively constructing the operation duration matrix of the total load section of the boiler, the total load matrix of the boiler group and the comprehensive efficiency matrix of the boiler group based on the historical operation data comprises the following steps:

respectively constructing three empty matrixes; wherein each dimension of each empty matrix in the three empty matrices corresponds to one boiler, the column number in each dimension is equal to the load segmentation number of the corresponding boiler, and each column corresponds to the load segment of the boiler from small to large;

based on the time mark and the boiler load, respectively counting the total operation time length corresponding to each cell in a first empty matrix, and filling the total operation time length into the first empty matrix to obtain a boiler total load section operation time length matrix;

based on the boiler load, respectively counting the total load of the boiler group corresponding to each cell in a second empty matrix, and filling the total load of the boiler group into the second empty matrix to obtain a total load matrix of the boiler group;

based on the boiler load and the fuel consumption, respectively counting the total operating steam yield and the total fuel consumption corresponding to each cell in a third empty matrix, calculating the quotient of the total fuel consumption and the total operating steam yield, and filling the quotient into the third empty matrix to obtain the comprehensive efficiency matrix of the boiler group.

4. The industrial boiler load distribution method according to claim 3, wherein the statistical process of the total operating duration, the total load of the boiler group, the total operating steam production and the total fuel consumption includes:

discretizing the load of each boiler from the minimum load to the maximum load according to a preset step length, and determining the corresponding relation between the actual load and the discretized load section according to a rounding principle;

and respectively counting the total operation duration, the total load of the boiler group, the total operation steam yield and the total fuel consumption based on the corresponding relation.

5. The industrial boiler load distribution method according to claim 1, wherein the sequentially multiplying matrix elements of the boiler group total load matrix, the boiler group total load matrix and the boiler group comprehensive efficiency matrix item by using the boiler total load section operation duration matrix to obtain a boiler group operation efficiency matrix, comprises:

filling the operation duration matrix of the total load section of the boiler by using a data smoothing method to obtain the operation duration matrix of the total load section of the boiler after filling;

filling the boiler group comprehensive efficiency matrix by using an interpolation method to obtain a filled boiler group comprehensive efficiency matrix;

and multiplying matrix elements of the filled total load section operation time length matrix, the total load matrix of the boiler group and the filled total efficiency matrix of the boiler group one by one in sequence to obtain the operation efficiency matrix of the boiler group.

6. The method for distributing load to industrial boilers according to claim 5, wherein the filling the operation duration matrix of the total load section of the boiler by using the data smoothing method to obtain the operation duration matrix of the total load section of the boiler after filling comprises:

marking unfilled first cells in the running time length matrix of the total load section of the boiler; wherein the unfilled first cell corresponds to a total load of the boiler that does not occur in the historical operating data;

and filling the marked first unit cell in the boiler total load section operation time length matrix by using a data smoothing method to obtain the filled boiler total load section operation time length matrix.

7. The industrial boiler load distribution method according to claim 5, wherein the filling the boiler bank integrated efficiency matrix by interpolation method to obtain a filled boiler bank integrated efficiency matrix comprises:

marking unfilled second cells in the boiler bank comprehensive efficiency matrix; wherein the unfilled second cell corresponds to a combination of boiler loads that does not occur in the historical operating data;

filling the marked second unit lattice in the boiler group comprehensive efficiency matrix by using an interpolation method to obtain the filled boiler group comprehensive efficiency matrix.

8. The industrial boiler load distribution method according to claim 1, wherein the solving the boiler group operational effectiveness matrix based on the dynamic programming algorithm including constraints to determine an optimal boiler load distribution scheme comprises:

marking infeasible load segments of each boiler in the boiler group operation efficiency matrix;

determining a recurrence function of a cost corresponding to a boiler load distribution scheme of the boiler group;

implementing the dynamic programming algorithm based on the infeasible load segments and the recurrence function to determine an optimal path with minimum total weight from a lowest total load in an upper left corner to a highest total load in a lower right corner of a boiler bank operational efficiency matrix; the optimal path is the optimal boiler load distribution scheme.

9. A storage medium having stored thereon a computer program, which when executed by a processor performs the method of industrial boiler load distribution based on historical operating data statistics according to any of claims 1-8.

10. An electronic device comprising a processor, a memory and a computer program stored on the memory, wherein the processor executes the computer program to implement the method of industrial boiler load distribution based on historical operating data statistics of any one of claims 1-8.