An industrial boiler load distribution method based on historical operation data statistics

Abstract

This invention relates to a method for industrial boiler load allocation based on historical operating data statistics, comprising: acquiring historical operating data of the boiler group; constructing a total boiler load segment duration matrix, a total boiler group load matrix, and a comprehensive boiler group efficiency matrix based on the historical operating data; multiplying the matrix elements of the total boiler load segment duration matrix, the total boiler group load matrix, and the comprehensive boiler group efficiency matrix item by item to obtain a boiler group operating efficiency matrix; wherein the matrix dimensions of the total boiler load segment duration matrix, the total boiler group load matrix, the comprehensive boiler group efficiency matrix, and the boiler group operating efficiency matrix are all the same; solving the boiler group operating efficiency matrix based on a dynamic programming algorithm including constraints to determine the optimal boiler load allocation scheme, thereby improving the overall production efficiency of the boiler group.

Description

Technical Field

[0001] This invention relates to the field of thermal power generation technology, and in particular to a method for load allocation of industrial boilers based on historical operating data statistics. Background Technology

[0002] In the field of thermal power generation, industrial boilers operating with a main pipe system are common. Compared to unit-based operation, main pipe boilers offer more stable and reliable operation. However, because different boilers have varying production efficiencies, different load distribution methods will affect the overall production efficiency when the downstream steam load is constant. Therefore, adjusting the boiler output using a reasonable load distribution method can effectively improve the overall production efficiency of the boiler group.

[0003] Currently, existing boiler load allocation methods include allocation based on the load ratio of boiler groups, adjustment based on priority order, and allocation based on the principle of equal incremental rate of fuel consumption.

[0004] However, allocation by proportion or priority is based on human experience and cannot guarantee the effectiveness of the allocation; allocation by equal incremental rate requires a precise boiler efficiency curve as a prerequisite, which is usually difficult to achieve.

[0005] Therefore, finding a reasonable boiler load allocation method based on historical boiler operation data is of great significance for ensuring the operating energy efficiency of boiler units. Summary of the Invention

[0006] (a) Technical problems to be solved

[0007] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides an industrial boiler load allocation method based on historical operating data statistics, which solves the technical problems of low overall operating efficiency of boiler groups caused by inaccurate human experience and difficulty in identifying boiler efficiency curves in the prior art.

[0008] (II) Technical Solution

[0009] To achieve the above objectives, the main technical solutions adopted by the present invention include:

[0010] In a first aspect, embodiments of the present invention provide a method for industrial boiler load allocation based on historical operating data statistics, comprising: acquiring historical operating data of the boiler group; constructing a total boiler load segment duration matrix, a total boiler group load matrix, and a comprehensive boiler group efficiency matrix based on the historical operating data; multiplying the matrix elements of the total boiler load segment duration matrix, the total boiler group load matrix, and the comprehensive boiler group efficiency matrix item by item to obtain a boiler group operating efficiency matrix; wherein the matrix dimensions of the total boiler load segment duration matrix, the total boiler group load matrix, the comprehensive boiler group efficiency matrix, and the boiler group operating efficiency matrix are all the same; and solving the boiler group operating efficiency matrix based on a dynamic programming algorithm including constraints to determine the optimal boiler load allocation scheme.

[0011] In one possible embodiment, the historical operating data of each of the multiple boilers in the boiler group includes timestamps, boiler load, and fuel consumption.

[0012] In one possible embodiment, the boiler group includes multiple boilers; based on historical operating data, a total boiler load segment runtime matrix, a total boiler group load matrix, and a comprehensive boiler group efficiency matrix are constructed, including: constructing three empty matrices; wherein each dimension of each empty matrix corresponds to one boiler, and the number of columns in each dimension is equal to the number of load segments of the corresponding boiler, and each column, from smallest to largest, corresponds to the load segments of the boilers from smallest to largest; based on time markers and boiler load, the total operating time corresponding to each cell in the first empty matrix is ​​calculated, and... Fill the total operating time into the first empty matrix to obtain the boiler total load segment operating time matrix; based on the boiler load, calculate the total boiler load corresponding to each cell in the second empty matrix, and fill the total boiler load into the second empty matrix to obtain the boiler total load matrix; based on the boiler load and fuel consumption, calculate the total steam production and total fuel consumption corresponding to each cell in the third empty matrix, calculate the quotient of total fuel consumption and total steam production, and fill the quotient into the third empty matrix to obtain the boiler group comprehensive efficiency matrix.

[0013] In one possible embodiment, the statistical process for the total operating time, total boiler load, total steam production, and total fuel consumption includes: discretizing the load of each boiler from minimum load to maximum load according to a preset step size, and determining the correspondence between the actual load and the discretized load segment according to the rounding principle; based on the correspondence, calculating the total operating time, total boiler load, total steam production, and total fuel consumption respectively.

[0014] In one possible embodiment, the boiler operating efficiency matrix is ​​obtained by sequentially multiplying the elements of the boiler total load segment running time matrix, the boiler group total load matrix, and the boiler group comprehensive efficiency matrix. This includes: filling the boiler total load segment running time matrix using a data smoothing method to obtain a filled boiler total load segment running time matrix; filling the boiler group comprehensive efficiency matrix using an interpolation method to obtain a filled boiler group comprehensive efficiency matrix; and sequentially multiplying the elements of the filled boiler total load segment running time matrix, the boiler group total load matrix, and the filled boiler group comprehensive efficiency matrix to obtain the boiler group operating efficiency matrix.

[0015] In one possible embodiment, the boiler total load segment runtime matrix is ​​filled using a data smoothing method to obtain a filled boiler total load segment runtime matrix, including: marking the first unfilled cell in the boiler total load segment runtime matrix; wherein the unfilled first cell corresponds to the boiler total load that did not appear in the historical operation data; and filling the marked first cell in the boiler total load segment runtime matrix using a data smoothing method to obtain a filled boiler total load segment runtime matrix.

[0016] In one possible embodiment, the boiler group comprehensive efficiency matrix is ​​filled using an interpolation method to obtain a filled boiler group comprehensive efficiency matrix, including: marking the second unfilled cells in the boiler group comprehensive efficiency matrix; wherein the unfilled second cells correspond to boiler load combinations that do not appear in historical operating data; and filling the marked second cells in the boiler group comprehensive efficiency matrix using an interpolation method to obtain a filled boiler group comprehensive efficiency matrix.

[0017] In one possible embodiment, the boiler group operating efficiency matrix is ​​solved based on a dynamic programming algorithm including constraints to determine the optimal boiler load allocation scheme. This includes: marking the infeasible load segments of each boiler in the boiler group operating efficiency matrix; determining the recursive function of the cost corresponding to the boiler load allocation scheme of the boiler group; and implementing the dynamic programming algorithm based on the infeasible load segments and the recursive function to determine the optimal path with the minimum total weight from the lowest total load in the upper left corner of the boiler group operating efficiency matrix to the highest total load in the lower right corner. The optimal path is the optimal boiler load allocation scheme.

[0018] Secondly, embodiments of this application provide a storage medium storing a computer program, which, when executed by a processor, performs the method described in the first aspect or any optional implementation thereof.

[0019] Thirdly, embodiments of this application provide an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the method described in the first aspect or any optional implementation of the first aspect.

[0020] Fourthly, this application provides a computer program product that, when run on a computer, causes the computer to perform the method in the first aspect or any possible implementation thereof.

[0021] (III) Beneficial Effects

[0022] The beneficial effects of this invention are:

[0023] This application provides an industrial boiler load allocation method based on historical operating data statistics. It obtains historical operating data of the boiler group and constructs a total boiler load segment duration matrix, a total boiler load matrix, and a comprehensive boiler efficiency matrix based on this data. The method then multiplies each element of these matrices sequentially to obtain the boiler group operating efficiency matrix. The dimensions of the total boiler load segment duration matrix, the total boiler load matrix, the comprehensive boiler efficiency matrix, and the boiler group operating efficiency matrix are all identical. Finally, a dynamic programming algorithm with constraints is used to solve the boiler group operating efficiency matrix to determine the optimal boiler load allocation scheme. This solves the problems of inaccurate manual experience and difficulty in identifying boiler efficiency curves in existing allocation methods, which lead to low overall boiler group operating efficiency.

[0024] To make the above-mentioned objectives, features and advantages to be achieved by the embodiments of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0025] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This document illustrates a flowchart of an industrial boiler load allocation method based on historical operating data statistics, provided in an embodiment of this application.

[0027] Figure 2 This document illustrates a detailed flowchart of an industrial boiler load allocation method based on historical operating data statistics, as provided in an embodiment of this application.

[0028] Figure 3 A schematic diagram of a boiler total load segment operating time matrix provided in an embodiment of this application is shown;

[0029] Figure 4 A schematic diagram of a boiler group total load matrix provided in an embodiment of this application is shown;

[0030] Figure 5 A schematic diagram of a boiler group comprehensive efficiency matrix provided in an embodiment of this application is shown;

[0031] Figure 6 A schematic diagram of a boiler group operation efficiency matrix provided in an embodiment of this application is shown. Detailed Implementation

[0032] To better explain and facilitate understanding of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0033] To address the problems existing in the prior art, this application provides an industrial boiler load allocation method based on historical operating data statistics. This method involves acquiring historical operating data of the boiler group and constructing a total boiler load segment duration matrix, a total boiler group load matrix, and a comprehensive boiler group efficiency matrix based on this data. The method then multiplies each element of these matrices sequentially to obtain the boiler group operating efficiency matrix. The dimensions of the total boiler load segment duration matrix, the total boiler group load matrix, the comprehensive boiler group efficiency matrix, and the boiler group operating efficiency matrix are all identical. Finally, a dynamic programming algorithm with constraints is used to solve the boiler group operating efficiency matrix to determine the optimal boiler load allocation scheme. This solves the problems of inaccurate manual experience and difficulty in identifying boiler efficiency curves in existing allocation methods, which lead to low overall boiler group performance.

[0034] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present invention can be understood more clearly and thoroughly, and that the scope of the present invention can be fully conveyed to those skilled in the art.

[0035] Please see Figure 1 , Figure 1 A flowchart illustrating an industrial boiler load allocation method based on historical operating data statistics, provided in an embodiment of this application, is shown. It should be understood that this industrial boiler load allocation method can be executed by an electronic device, and the specific device can be configured according to actual needs; this embodiment is not limited thereto. For example, the electronic device can be a computer or a server, etc. Specifically, the industrial boiler load allocation method includes:

[0036] Step S110: Obtain historical operating data of the boiler unit.

[0037] It should be understood that the specific data included in the historical operation data can be set according to actual needs, and the embodiments of this application are not limited thereto.

[0038] Optionally, historical operating data of each boiler in the boiler group can be obtained using a preset time period as the unit time length, and the historical operating data of each boiler includes a time stamp (e.g., a timestamp), boiler load, and fuel consumption.

[0039] It should also be understood that the specific time period of the preset time period can be set according to actual needs, and the embodiments of this application are not limited thereto.

[0040] For example, the preset time period can be 1 minute or 1 hour, etc.

[0041] Step S120: Based on historical operating data, construct the boiler total load segment operating time matrix, the boiler group total load matrix, and the boiler group comprehensive efficiency matrix, respectively.

[0042] It should also be understood that the specific process of constructing the boiler total load segment runtime matrix, boiler group total load matrix and boiler group comprehensive efficiency matrix based on historical operating data can be set according to actual needs, and the embodiments of this application are not limited thereto.

[0043] Optionally, three empty matrices are constructed. Each dimension of each empty matrix corresponds to a boiler, and the number of columns in each dimension is equal to the number of load segments of the corresponding boiler. Each column, from smallest to largest, corresponds to the load segments of the boiler from smallest to largest. Based on the time stamp and boiler load, the total operating time corresponding to each cell in the first empty matrix is ​​calculated and filled into the first empty matrix to obtain the boiler total load segment operating time matrix. Based on the boiler load, the total boiler group load corresponding to each cell in the second empty matrix is ​​calculated and filled into the second empty matrix to obtain the boiler group total load matrix. Based on the boiler load and fuel consumption, the total steam production and total fuel consumption corresponding to each cell in the third empty matrix are calculated, and the quotient of total fuel consumption and total steam production is filled into the third empty matrix to obtain the boiler group comprehensive efficiency matrix.

[0044] For example, three empty multidimensional matrices are created, with each matrix having a dimension equal to the number of operating boilers (e.g., in a boiler group with two boilers, each matrix has a dimension of 2), and the number of columns in each dimension equals the number of load segments for the corresponding boiler. Each column, from smallest to largest, corresponds to a load segment for that boiler from smallest to largest. Furthermore, the historical operating data from step S110 is statistically analyzed, and the total load corresponding to each boiler's actual operating load segment is accumulated. The total operating time of the corresponding cell in the first matrix is ​​calculated and filled into the corresponding cell. The filled matrix is ​​then used as the boiler total load segment operating time matrix. Similarly, for the second matrix, the loads of each boiler corresponding to each cell are accumulated to obtain the total boiler group load corresponding to that cell. The total boiler group load is then filled into the corresponding cell, and the filled matrix is ​​used as the boiler group total load matrix. Furthermore, the historical operating data in step S110 is statistically analyzed, and based on the actual operating load segment of each boiler, the total steam production and total fuel consumption of the corresponding cell in the third matrix are calculated. The result of dividing the total fuel consumption by the total steam production (i.e., the quotient is the coal consumption per ton of steam) is then filled into the cell, and the completed matrix is ​​used as the boiler group's overall efficiency matrix. The total operating steam production can be obtained based on the boiler load.

[0045] It should also be understood that the statistical process for the total operating time, total boiler load, total steam production and total fuel consumption can be set according to actual needs, and the embodiments of this application are not limited thereto.

[0046] Optionally, the load of each boiler is discretized from minimum load to maximum load according to a preset step size. The correspondence between the actual load and the discretized load segment is determined according to the rounding principle. Based on the correspondence, the total operating time, total boiler load, total steam production, and total fuel consumption are calculated. The specific preset step size can be set according to actual needs, and this embodiment is not limited to this. For example, the preset step size can be 11 t / h.

[0047] For example, the load of each boiler can be discretized from its minimum to maximum load capacity in increments of 1% to 5%, and the correspondence between the actual load and the discretized load segments can be determined according to the rounding principle (for example, if the discretized load segments include 187t / h and 198t / h, and the current actual load is 190.5t / h, since 190.5t / h is closer to 187t / h, it can be determined that the current actual load and 187t / h have a correspondence). Subsequently, based on the correspondence between the actual load and the discretized load segments, the total operating time, total boiler load, total steam production, and total fuel consumption can be calculated respectively.

[0048] Step S130: Multiply the elements of the boiler total load segment running time matrix, the boiler group total load matrix, and the boiler group comprehensive efficiency matrix one by one to obtain the boiler group operating efficiency matrix. The dimensions of the boiler total load segment running time matrix, the boiler group total load matrix, the boiler group comprehensive efficiency matrix, and the boiler group operating efficiency matrix are all the same.

[0049] It should be understood that the specific process of multiplying the elements of the boiler total load segment running time matrix, the boiler group total load matrix, and the boiler group comprehensive efficiency matrix one by one to obtain the boiler group operating efficiency matrix can be set according to actual needs, and the embodiments of this application are not limited thereto.

[0050] Optionally, the boiler total load segment running time matrix is ​​filled using a data smoothing method to obtain the filled boiler total load segment running time matrix, and the boiler group comprehensive efficiency matrix is ​​filled using an interpolation method to obtain the filled boiler group comprehensive efficiency matrix. Then, the elements of the filled boiler total load segment running time matrix, the boiler group total load matrix, and the filled boiler group comprehensive efficiency matrix are multiplied one by one to obtain the boiler group operating efficiency matrix.

[0051] It should also be understood that the specific process of filling the boiler total load segment runtime matrix using the data smoothing method can be set according to actual needs, and the embodiments of this application are not limited thereto.

[0052] Optionally, the first unfilled cell in the boiler total load segment runtime matrix is ​​marked, where the unfilled first cell corresponds to the boiler total load that did not appear in the historical operating data. Based on the existing elements in the boiler total load segment runtime matrix, a data smoothing method is used to fill the marked first cell in the boiler total load segment runtime matrix to obtain a filled boiler total load segment runtime matrix. The specific smoothing method can be set according to actual needs, and this embodiment is not limited to this. For example, the data smoothing method can be an additive smoothing method (or a Laplace smoothing method).

[0053] It should also be understood that the specific process of filling the boiler group's overall efficiency matrix using interpolation methods can also be set according to actual needs, and the embodiments of this application are not limited thereto.

[0054] Optionally, the unfilled second cells in the boiler group comprehensive efficiency matrix are marked, where the unfilled second cells correspond to boiler load combinations not appearing in historical operating data. Based on the existing elements in the boiler group comprehensive efficiency matrix, the marked second cells are filled using an interpolation method to obtain a filled boiler group comprehensive efficiency matrix. The specific interpolation method can be set according to actual needs, and this embodiment is not limited to this. For example, the interpolation method can be a multidimensional linear interpolation method.

[0055] It should also be understood that the specific process of multiplying the matrix elements one by one using the filled boiler total load segment running time matrix, boiler group total load matrix and filled boiler group comprehensive efficiency matrix can also be set according to actual needs, and the embodiments of this application are not limited thereto.

[0056] Optionally, a multidimensional matrix (i.e., a boiler group operation efficiency matrix) can be established, such that the dimension of the multidimensional matrix is ​​equal to the number of boilers in operation within the boiler group, the number of columns in each dimension is equal to the number of load segments for the corresponding boiler, and each column, from smallest to largest, corresponds to the load segments of the boiler from smallest to largest. Furthermore, for each cell of the boiler group operation efficiency matrix, three corresponding cells in the same row and column of the boiler total load segment runtime matrix, the boiler group total load matrix, and the boiler group comprehensive efficiency matrix are found, and the product of the elements in these three cells is filled into the corresponding cell of the boiler group operation efficiency matrix.

[0057] Step S140: Solve the boiler group operation efficiency matrix based on a dynamic programming algorithm including constraints to determine the optimal boiler load allocation scheme.

[0058] It should be understood that the specific process of solving the boiler group operation efficiency matrix based on dynamic programming algorithms including constraints to determine the optimal boiler load allocation scheme can be set according to actual needs, and the embodiments of this application are not limited thereto.

[0059] Optionally, the infeasible load segment of each boiler is marked in the boiler group operation efficiency matrix, and a recursive function is determined to determine the cost corresponding to the boiler load allocation scheme of the boiler group. Based on the infeasible load segment and the recursive function, a dynamic programming algorithm is implemented to determine the optimal path with the minimum total weight from the lowest total load in the upper left corner of the boiler group operation efficiency matrix to the highest total load in the lower right corner; wherein, the optimal path is the optimal allocation scheme under the condition of the lowest to the highest total load (or, the optimal path is the optimal boiler load allocation scheme).

[0060] For example, in the boiler group operation efficiency matrix, the infeasible load segment for each boiler is marked, meaning that the boiler cannot operate under this load segment. Furthermore, in the optimal load allocation method, given two different total loads, a first total load A and a second total load B, if the second total load B is greater than the first total load A, then the load of each boiler after allocation to the first total load A is no less than the load of each boiler after allocation to the second total load B. Also, when the boiler group includes k boilers, let F(x1x2x3...xk) represent the cost corresponding to the optimal allocation method when the total load is x1+x2+x3+...+xk, and the loads of the k boilers are x1, x2, x3,..., xk respectively (it should be noted that this cost refers to the evaluation function required in the dynamic programming recursive function, and this evaluation function can also be called the estimation function or cost function), and the minimum load unit corresponding to xi for the boiler is ai (it should be noted that ai is the load segmentation or preset step size mentioned above), then the recursive function of the cost corresponding to the allocation scheme is:

[0061] F(x1x2x3...xk)=min(F((x1-a1)x2x3...xk), F(x1(x2-a2)x3...xk), F(x1x2(x3-a3)...xk),..., F(x1x2x3...(xk-ak)).

[0062] Among them, loads such as x1-a1, x2-a2, x3-a3, ..., xk-ak are not within the infeasible load range of the corresponding boiler.

[0063] It's important to clarify here that the first total load A and the second total load B determine the recursive function. This means the recursive function already covers both the first total load A and the second total load B. Therefore, implementing the dynamic programming algorithm only requires the infeasible load segment and the recursive function. In other words, the description of the first and second total loads above is actually for obtaining the recursive function.

[0064] Furthermore, based on the recursive formula and the constraints of infeasible load segments, a corresponding dynamic programming algorithm is implemented to find the optimal load allocation result under each total load, i.e., the allocation scheme with the lowest corresponding cost.

[0065] Therefore, in the boiler load allocation process, this application embodiment utilizes historical operating data to find the optimal load allocation scheme for the boiler group. It can dynamically find the optimal allocation result based on the operating conditions, which is beneficial to improving the overall production efficiency of the boiler group. Furthermore, compared to existing technologies, this application embodiment can accurately measure the comprehensive efficiency of the allocation scheme and avoid erroneous allocation results caused by inaccurate data. Moreover, the allocation scheme acquisition method described in this application embodiment is based on historical operating data, thus avoiding the problem of allocation schemes being unexecutable. Furthermore, its allocation results can guide the coordinated control between multiple boilers, providing precise support for the economical and safe operation of the unit.

[0066] To facilitate understanding of the embodiments of this application, specific embodiments are described below.

[0067] Specifically, please see Figure 2 , Figure 2 This document illustrates a flowchart of a method for industrial boiler load allocation based on historical operating data statistics, as provided in an embodiment of this application. Figure 2 The industrial boiler load distribution methods shown include:

[0068] Step S210: Obtain historical production data related to the boiler group's energy efficiency.

[0069] Specifically, historical operating data for each boiler is acquired in one-hour increments, and this historical operating data includes timestamps, fuel consumption, and boiler load.

[0070] Step S220: Based on historical production data, construct three two-dimensional matrices. These three two-dimensional matrices include a boiler total load segment runtime matrix, a boiler group total load matrix, and a boiler group comprehensive efficiency matrix.

[0071] Specifically, three two-dimensional matrices are established, with each dimension corresponding to a boiler. The number of columns in each dimension is equal to the number of load segments of the corresponding boiler, and each column from smallest to largest corresponds to the load segments of the boiler from smallest to largest.

[0072] Additionally, based on the historical data obtained in step S210, the total operating time of the corresponding cell in the first matrix is ​​calculated according to the actual operating load segment of each boiler, and then filled into that cell. The completed matrix is ​​the boiler total load segment operating time matrix. For details, please refer to [link to relevant documentation]. Figure 3 ;

[0073] Furthermore, for the second matrix, the boiler loads corresponding to each cell are summed to obtain the total boiler group load for that cell, which is then filled into that cell. The completed matrix is ​​the total boiler group load matrix. For details, please refer to [link to documentation]. Figure 4 ;

[0074] Additionally, based on the historical data obtained in step S210, and according to the actual operating load range of each boiler, the total steam production and total fuel consumption of the corresponding cell in the first matrix are calculated. The result of dividing the total fuel consumption by the total steam production is then filled into that cell. The completed matrix is ​​the boiler group's comprehensive efficiency matrix. For details, please refer to [link to relevant documentation]. Figure 5 .

[0075] Step S230: Fill the boiler group comprehensive efficiency matrix using interpolation methods.

[0076] Step S240: Fill the boiler total load segment runtime matrix using a data smoothing method.

[0077] Step S250: Multiply the matrix elements one by one using the filled boiler total load segment running time matrix, boiler group total load matrix and filled boiler group comprehensive efficiency matrix to obtain the boiler group operating efficiency matrix of the same dimension.

[0078] Specifically, a two-dimensional matrix is ​​constructed, with its dimension equal to the number of operating boilers. The number of columns in each dimension equals the number of load segments for the corresponding boiler, and each column, from smallest to largest, corresponds to the load segments of the boiler from smallest to largest. This matrix is ​​called the boiler group operation efficiency matrix. Furthermore, for each cell of this boiler group operation efficiency matrix, three corresponding cells in the same row and column are found in the boiler total load segment runtime matrix, the boiler group total load matrix, and the boiler group comprehensive efficiency matrix. The product of the elements in these three cells is then filled into the corresponding cell of the boiler group operation efficiency matrix. For details, please refer to [link to documentation]. Figure 6 .

[0079] Step S260: Based on the boiler group operation efficiency matrix, execute a constrained dynamic programming algorithm to find the optimal path with the minimum total weight from the lowest total load in the upper left corner to the highest total load in the lower right corner. The optimal path is the optimal allocation scheme under the condition of minimum to maximum total load.

[0080] Specifically, the infeasible load range for each boiler is marked, meaning that the boiler cannot operate under that load range. In this example, both boilers can operate within the range of 132t / h to 220t / h.

[0081] In the optimal load allocation method, given two different first total loads A and second total loads B, if the first total load A is greater than the second total load B, then the load of each boiler after allocating to the first total load A is no less than the load of each boiler after allocating to the second total load B.

[0082] Let F(x1x2) represent the cost of the optimal allocation method when the total load is x1+x2 and the loads of the two boilers are x1 and x2 respectively, and the minimum load unit of the two boilers is 11t / h. Then the recursive function of the cost of the optimal allocation method is: F(x1x2)=min(F((x1-11)x2),F(x1(x2-11)));

[0083] Based on the recursive formula and the constraints of infeasible load segments, a corresponding dynamic programming algorithm is implemented to find the optimal load allocation result under each total load (i.e., Figure 6 The optimal load allocation result (the gray part in the diagram) is the allocation scheme with the lowest cost that satisfies the total load demand and all constraints.

[0084] Furthermore, during online operation, the corresponding load allocation scheme can be directly selected based on the current total load. For example, when the total load of the two boilers is 325 t / h, rounding indicates that the total load falls within the 330 t / h load range. The optimal load allocation scheme corresponding to 330 t / h is for boiler 1 to operate at 154 t / h and boiler 2 to operate at 176 t / h (the gray square in the diagram where the sum of the two boilers is 330 t / h). Proportionally scaling down the total load of the two boilers from 330 t / h to 325 t / h and rounding, it can be seen that boiler 1 should operate at a load of 152 t / h and boiler 2 should operate at a load of 173 t / h.

[0085] It should be understood that the above-described industrial boiler load allocation method based on historical operating data statistics is merely exemplary. Those skilled in the art can make various modifications based on the above method, and the modified solutions also fall within the protection scope of this application.

[0086] This application provides a storage medium storing a computer program, which is executed by a processor to perform the methods described in the embodiments.

[0087] This application also provides a computer program product that, when run on a computer, causes the computer to perform the method described in the method embodiment.

[0088] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can 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, etc.) containing computer-usable program code.

[0089] This 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 block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions.

[0090] It should be noted that any reference numerals placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In claims that enumerate several means, several of these means may be embodied by the same hardware. The use of the terms first, second, third, etc., is merely for convenience of expression and does not indicate any order. These terms can be understood as part of the component names.

[0091] Furthermore, it should be noted that in the description of this specification, the terms "one embodiment," "some embodiments," "embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0092] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the claims should be interpreted to include both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0093] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, then this invention should also include these modifications and variations.

Claims

1. A method for load distribution of industrial boilers based on historical operation data statistics, characterized in that, include: Obtain historical operating data of the boiler unit; Based on the historical operating data, a boiler total load segment operating time matrix, a boiler group total load matrix, and a boiler group comprehensive efficiency matrix are constructed respectively. The boiler operating efficiency matrix is ​​obtained by sequentially multiplying the elements of the boiler total load segment running time matrix, the boiler group total load matrix, and the boiler group comprehensive efficiency matrix. The matrix dimensions of the boiler total load segment running time matrix, the boiler group total load matrix, the boiler group comprehensive efficiency matrix, and the boiler group operating efficiency matrix are all the same. The boiler group's operating efficiency matrix is ​​solved using a dynamic programming algorithm that includes constraints, in order to determine the optimal boiler load allocation scheme. The method of solving the boiler group operation efficiency matrix using a dynamic programming algorithm with constraints to determine the optimal boiler load allocation scheme includes: Mark the infeasible load segment for each boiler in the boiler group operation efficiency matrix; Determine the recursive function for the cost corresponding to the boiler load allocation scheme of the boiler group; The dynamic programming algorithm is implemented based on the infeasible load segment and the recursive function to determine the optimal path with the minimum total load from the lowest total load in the upper left corner of the boiler group operating efficiency matrix to the highest total load in the lower right corner; wherein, the optimal path is the optimal boiler load allocation scheme.

2. The industrial boiler load distribution method according to claim 1, characterized in that, The historical operating data for each of the multiple boilers in the boiler group includes timestamps, boiler load, and fuel consumption.

3. The industrial boiler load distribution method according to claim 2, characterized in that, The boiler group includes multiple boilers; the construction of a total boiler load segment runtime matrix, a total boiler group load matrix, and a comprehensive boiler group efficiency matrix based on the historical operating data includes: Construct three empty matrices respectively; wherein each dimension of each empty matrix corresponds to a boiler, and the number of columns in each dimension is equal to the number of load segments of the corresponding boiler, and each column from smallest to largest corresponds to the load segments of the boiler from smallest to largest; Based on the time stamp and the boiler load, the total running time corresponding to each cell in the first empty matrix is ​​calculated, and the total running time is filled into the first empty matrix to obtain the boiler total load segment running time matrix; Based on the boiler load, the total boiler load corresponding to each cell in the second empty matrix is ​​calculated, and the total boiler load is filled into the second empty matrix to obtain the total boiler load matrix. Based on the boiler load and the fuel consumption, the total steam production and total fuel consumption corresponding to each cell in the third empty matrix are calculated, and the quotient of the total fuel consumption and the total steam production is calculated. The quotient is then filled 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, characterized in that, The statistical process for the total operating time, the total boiler load, the total steam production, and the total fuel consumption includes: The load of each boiler is discretized from minimum load to maximum load according to a preset step size, and the correspondence between the actual load and the discretized load segment is determined according to the rounding principle. Based on the aforementioned correspondence, the total operating time, the total load of the boiler group, the total steam production, and the total fuel consumption are calculated respectively.

5. The industrial boiler load distribution method according to claim 1, characterized in that, The process of multiplying the elements of the boiler total load segment running time matrix, the boiler group total load matrix, and the boiler group comprehensive efficiency matrix one by one to obtain the boiler group operating efficiency matrix includes: The boiler total load segment runtime matrix is ​​filled using a data smoothing method to obtain the filled boiler total load segment runtime matrix. The boiler group comprehensive efficiency matrix is ​​filled using an interpolation method to obtain the filled boiler group comprehensive efficiency matrix. The boiler group operating efficiency matrix is ​​obtained by multiplying its matrix elements one by one using the filled boiler total load segment running time matrix, the boiler group total load matrix, and the filled boiler group comprehensive efficiency matrix.

6. The industrial boiler load distribution method according to claim 5, characterized in that, The step of filling the boiler total load segment runtime matrix using a data smoothing method to obtain a filled boiler total load segment runtime matrix includes: The first unfilled cell in the boiler total load segment runtime matrix is ​​marked; wherein, the unfilled first cell corresponds to the boiler total load that did not appear in the historical operation data; The first marked cell in the total boiler load segment runtime matrix is ​​filled using a data smoothing method to obtain the filled total boiler load segment runtime matrix.

7. The industrial boiler load distribution method according to claim 5, characterized in that, The process of filling the boiler group comprehensive efficiency matrix using interpolation methods to obtain the filled boiler group comprehensive efficiency matrix includes: The second cell in the boiler group's overall efficiency matrix that is not filled is marked; wherein, the second cell that is not filled corresponds to a boiler load combination that does not appear in the historical operating data; The marked second cell in the boiler group comprehensive efficiency matrix is ​​filled using an interpolation method to obtain the filled boiler group comprehensive efficiency matrix.

8. A storage medium having a computer program stored thereon, characterized in that, The computer program is executed by the processor to perform the industrial boiler load allocation method based on historical operating data statistics as described in any one of claims 1-7.

9. An electronic device comprising a processor, a memory, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the industrial boiler load allocation method based on historical operating data statistics as described in any one of claims 1-7.

Images