A method and system for optimizing temperature control in boiler combustion

Abstract

This invention provides a method and system for optimizing boiler combustion temperature control, belonging to the field of data processing technology. The method includes obtaining the design dimensions of the target boiler; acquiring images of the target boiler using an image acquisition device; constructing a three-dimensional fitting model based on the image acquisition results and design dimensions; setting up infrared acoustic temperature measurement devices at furnace wall temperature measurement points using the three-dimensional fitting model; acquiring temperature data using the infrared acoustic temperature measurement devices; obtaining a temperature data collection set; obtaining real-time control parameters for the target boiler; optimizing the real-time control parameters using the temperature data collection set; and controlling the combustion temperature of the target boiler using the optimized parameter control results. This invention solves the technical problem in existing technologies where boiler combustion temperature adjustment and control rely on human experience, leading to deviations between the actual combustion temperature and the planned combustion temperature, resulting in incomplete fuel combustion.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, specifically relating to a method and system for temperature optimization control of boiler combustion. Background Technology

[0002] A boiler is an energy conversion device in a power plant that converts thermal energy into kinetic steam to drive a steam turbine generator to generate electricity. To improve the combustion efficiency of coal in a boiler, current methods often involve regulating and controlling the boiler combustion temperature and co-firing coal to achieve the desired combustion efficiency.

[0003] At present, the regulation and control of boiler combustion temperature relies on human experience. Whether the actual boiler combustion temperature obtained by regulation and control meets the preset temperature requirements is random, which leads to the waste of coal resources and interference with the normal production of power resources during the regulation and control process.

[0004] Existing technologies rely on human experience to regulate and control boiler combustion temperature, which can lead to discrepancies between the actual combustion temperature and the planned combustion temperature, resulting in incomplete fuel combustion. Summary of the Invention

[0005] This invention provides a method and system for optimizing boiler combustion temperature control. Its purpose is to solve the technical problem that the adjustment and control of boiler combustion temperature in the prior art relies on human experience, which easily leads to a deviation between the actual combustion temperature and the planned combustion temperature of the boiler, resulting in incomplete fuel combustion.

[0006] This invention provides a method for optimizing temperature control in boiler combustion, comprising: obtaining design dimension parameters of a target boiler; acquiring images of the target boiler using an image acquisition device to obtain image acquisition results; constructing a three-dimensional fitting model based on the image acquisition results and the design dimension parameters; setting furnace wall temperature measurement points using the three-dimensional fitting model; deploying infrared acoustic temperature measurement devices at the furnace wall temperature measurement points and acquiring temperature data using the infrared acoustic temperature measurement devices to obtain a temperature data collection set, wherein the temperature data collection set includes acquisition time and location identifiers; obtaining real-time control parameters of the target boiler; optimizing the real-time control parameters using the temperature data collection set to obtain parameter optimization results; and controlling the combustion temperature of the target boiler using the parameter optimization results.

[0007] By adopting the above technical solution, the boiler temperature reaches the required segmented temperature control value during the operation of the target boiler. Based on the parameter control optimization results, the combustion temperature of the target boiler is controlled so that the target boiler performs fuel combustion with the expected combustion efficiency, thereby achieving the technical effect of obtaining scientific and accurate control parameters that enable the target boiler to operate at the segmented temperature control value.

[0008] Further, segmented temperature control values ​​are set; the first set of control parameters in the real-time control parameters is obtained, and the first set of temperature data is obtained from the temperature data acquisition set, wherein the first set of temperature data and the first set of control parameters are corresponding parameters; the first set of control parameters is used as the historical optimal solution, and the tabu table is set to empty to complete the initialization; the real-time control parameters are iteratively searched through the tabu table, and the nth set of control parameters and the nth set of temperature data are output in each iteration; similarity analysis is performed on all n sets of temperature data and the segmented temperature control values ​​to obtain p sets of temperature data, wherein the p sets of temperature data are the most similar data among the n sets of temperature data; the pth set of control parameters is used as the parameter control optimization result.

[0009] By adopting the above technical solutions, the dependence on human experience in obtaining the optimal control parameters of the target boiler is reduced, and the technical objective of obtaining scientific and accurate control parameters that enable the target boiler to operate at segmented temperature control values ​​is achieved.

[0010] Further, the first parameter feature among the real-time control parameters is selected as the optimization direction, and optimization search is performed; a first optimization search result is obtained, wherein the first optimization search result is a local optimum result within a predetermined interval; the first optimization search result is recorded as the second set of control parameters, the temperature data corresponding to the second set of control parameters is recorded as the second set of temperature data, and the first parameter feature is added to the taboo table, and the taboo table is updated; the real-time control parameters are iteratively searched using the updated taboo table.

[0011] By adopting the above technical solutions, the technical objective of improving optimization efficiency has been achieved.

[0012] Furthermore, a taboo period is set based on the number of parameter features of the real-time control parameters; it is determined whether the first parameter feature in the taboo table meets the taboo period; when the first parameter feature can meet the taboo period, the first parameter feature is unbanned, and the taboo table is updated based on the unbanning result.

[0013] By adopting the above technical solution, we can avoid local optimization, improve optimization efficiency, and enhance the scientific nature and timeliness of the obtained optimal control parameters for the target boiler.

[0014] Further, the second parameter feature among the real-time control parameters is selected as the optimization direction for optimization search, wherein the second parameter feature is a parameter feature not in the taboo table; a second optimization search result is obtained, wherein the second optimization search result is a local optimum result within a predetermined interval; the second optimization search result is recorded as the third group of control parameters, the temperature data corresponding to the third group of control parameters is recorded as the third group of temperature data, and the second parameter feature is added to the taboo table, and the taboo table is updated; the real-time control parameters are iteratively searched using the updated taboo table.

[0015] By adopting the above technical solution, the global parameter control optimization result is obtained by selecting parameter features and updating the taboo table, thus avoiding local optimization.

[0016] Furthermore, a preset iteration number threshold and a similarity constraint threshold are set; when the number of iterations meets the preset iteration number threshold and / or the similarity analysis result meets the similarity constraint threshold, the parameter control optimization is stopped, and the parameter control optimization result is obtained.

[0017] By adopting the above technical solution, the waste of system computing resources caused by infinite iterative optimization can be avoided, while avoiding local optimization.

[0018] Furthermore, the infrared acoustic temperature measuring device is used to continuously monitor the temperature and obtain continuous temperature monitoring results; stability analysis data is generated from the continuous temperature monitoring results; and control compensation is performed on the parameter control optimization results using the stability analysis data.

[0019] By adopting the above technical solutions, the technical effect of improving the operational stability of the target boiler at the preset operating temperature was achieved.

[0020] The beneficial effects of this invention are as follows:

[0021] This invention obtains the design dimensions of a target boiler, acquires images of the target boiler using an image acquisition device, and obtains image acquisition results. The design dimensions and image acquisition results provide reference data and images for subsequent reconstruction of the target boiler by constructing a 3D model through 3D fitting. A 3D fitting model is constructed based on the image acquisition results and the design dimensions. Temperature measurement points on the furnace wall are set using the 3D fitting model. The effective selection of these furnace wall temperature measurement points provides a reference for accurate and effective temperature measurement during the operation of the target boiler by installing temperature measurement devices. Infrared acoustic temperature measurement devices are deployed at the furnace wall temperature measurement points, and the temperature is measured using these infrared acoustic temperature measurement devices. Data acquisition involves obtaining a temperature data set, which includes acquisition time and location identifiers. Real-time control parameters of the target boiler are obtained, and the real-time control parameter set and the temperature data set provide an optimization traversal dataset for subsequent optimization to determine the optimal control parameters of the target boiler. Parameter control optimization is performed on the real-time control parameters using the temperature data set to obtain the optimization results. The combustion temperature of the target boiler is then controlled using the optimization results. This process reduces the reliance on human experience in obtaining the optimal control parameters for the target boiler, achieving the technical effect of obtaining scientifically accurate control parameters that enable the target boiler to operate at segmented temperature control values.

[0022] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description and the drawings. Attached Figure Description

[0023] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0024] Figure 1 This is a schematic flowchart of a temperature optimization control method for boiler combustion in one embodiment;

[0025] Figure 2 This is a schematic diagram of the process for generating parameter control optimization results in a temperature optimization control method for boiler combustion in one embodiment;

[0026] Figure 3 This is a structural block diagram of a temperature optimization control system for boiler combustion in one embodiment.

[0027] Figure labeling: Image acquisition and execution module 1, furnace wall temperature measurement and positioning module 2, temperature data acquisition module 3, control parameter acquisition module 4, parameter control optimization module 5, combustion temperature control module 6. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. The same reference numerals in the drawings represent the same components. It should be noted that the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0029] Reference Figure 1 This application provides a temperature optimization control method for boiler combustion. The method is applied to a temperature optimization control system, which is communicatively connected to an image acquisition device and an infrared acoustic temperature measurement device. The method includes:

[0030] S100: Obtain the design dimension parameters of the target boiler, and acquire images of the target boiler through the image acquisition device to obtain the image acquisition results;

[0031] Specifically, in this embodiment, the target boiler is a pulverized coal boiler with a three-stage temperature gradient control design. Design dimensional parameters, including but not limited to boiler height and furnace wall thickness, are obtained based on the target boiler's architectural drawings. Simultaneously, the image acquisition device is used to acquire omnidirectional, multi-angle images of the completed target boiler structure, obtaining the image acquisition results.

[0032] The design dimension parameters and the image acquisition results provide reference data and reference images for the subsequent reconstruction of the target boiler by constructing a 3D model of the target boiler through 3D fitting.

[0033] S200: Construct a three-dimensional fitting model based on the image acquisition results and the design dimension parameters, and set the furnace wall temperature measurement points through the three-dimensional fitting model;

[0034] Specifically, in this embodiment, the basic structure of the target boiler is modeled in professional 3D modeling software based on the design size parameters. The basic structure modeling results are optimized by referring to the multi-angle and all-round target boiler images in the image acquisition results, so as to obtain the 3D fitting model that can realistically restore the physical appearance structure of the target boiler.

[0035] It should be understood that the target boiler is designed with a three-stage temperature gradient control. Therefore, the locations of the furnace wall temperature measuring points include temperature measuring points that are emphasized in key locations and temperature measuring points that are evenly distributed in non-key locations. In this embodiment, the bottom of the partition screen, the outlet of the final superheater, and the inlet after the turning chamber are located based on the three-dimensional fitting model. Based on the location results of the key locations, the furnace wall temperature measuring points are emphasized, and furnace wall temperature measuring points are evenly distributed in the remaining non-key locations of the target boiler. This achieves the setting of furnace wall temperature measuring points based on the three-dimensional fitting model. The effective selection of the furnace wall temperature measuring points provides a reference for the subsequent installation of temperature measuring devices to accurately and effectively measure the temperature during the operation of the target boiler.

[0036] S300: The infrared acoustic temperature measuring device is deployed through the temperature measuring point on the furnace wall, and temperature data is collected through the infrared acoustic temperature measuring device to obtain a temperature data collection set, wherein the temperature data collection set has a collection time and location identifier.

[0037] S400: Obtain the real-time control parameters of the target boiler;

[0038] Specifically, in this embodiment, the temperature measuring device is positioned and installed based on the furnace wall temperature measuring point. The preferred temperature measuring device is the infrared acoustic temperature measuring device, which is not affected by changes in weather conditions to ensure the accuracy of data measurement. Temperature data is collected through the infrared acoustic temperature measuring device to obtain a temperature data collection set. The temperature data of each target boiler in the temperature data collection set is marked with the collection time and location. The location mark is the specific furnace wall temperature measuring point location of the infrared acoustic temperature measuring device on the target boiler.

[0039] The control parameters of the target boiler are a collective term for the parameters and control indicators of the target boiler during normal operation, including conventional power plant boiler normal operation parameters and control indicators such as steam drum pressure, main steam pressure, and steam drum water level.

[0040] The control parameters of the target boiler during operation are collected in real time to obtain a real-time control parameter set consisting of real-time control parameters with acquisition time identifiers. The real-time control parameter set and the temperature data acquisition set have a one-to-one mapping relationship based on the acquisition time identifiers. The real-time control parameter set and the temperature data acquisition set provide an optimization traversal dataset for subsequent optimization to determine the optimal control parameters of the target boiler.

[0041] S500: Optimize the real-time control parameters using the temperature data acquisition set to obtain the parameter control optimization result;

[0042] In one embodiment, reference Figure 2 The method steps provided in this application also include:

[0043] S510: Set segmented temperature control values;

[0044] S520: Obtain the first set of control parameters from the real-time control parameters, and obtain the first set of temperature data from the temperature data acquisition set, wherein the first set of temperature data and the first set of control parameters are corresponding parameters;

[0045] S530: Use the first set of control parameters as the historical optimal solution and empty the tabu table to complete the initialization;

[0046] S540: The real-time control parameters are iteratively searched using the taboo table, and the nth set of control parameters and the nth set of temperature data are output in each iteration;

[0047] S550: Perform a similarity analysis between all n sets of temperature data and the segmented temperature control values ​​to obtain p sets of temperature data, wherein the p sets of temperature data are the most similar data among the n sets of temperature data;

[0048] S560: Use the p-th group of control parameters as the result of parameter control optimization.

[0049] Specifically, it should be understood that the target boiler is a high-combustion-rate pulverized coal boiler with a three-stage temperature gradient control design. Therefore, in this embodiment, segmented temperature control values ​​are set, which are three temperature control thresholds. For example, the temperature control thresholds can be set as follows: flue gas temperature at the inlet of the partition screen ≤ 1350℃, flue gas temperature at the outlet of the final superheater ≤ 970℃, and flue gas temperature at the inlet of the final stage after the diverting chamber ≤ 850℃. The segmented temperature control values ​​provide a comparison reference for subsequent judgment on whether a certain set of control parameters is the optimal solution for the target boiler parameter control.

[0050] Based on the real-time control parameter set, any set of control parameters is extracted as the first set of control parameters. Based on the acquisition time identifier of the first set of control parameters, the first set of temperature data with consistent acquisition time identifiers is extracted from the temperature data acquisition set. The first set of temperature data is consistent with the acquisition time identifier of the first set of control parameters, that is, the first set of temperature data is the furnace wall temperature data generated by the combustion of the target boiler when the target boiler is controlled in real time by the first set of control parameters. The first set of temperature data and the first set of control parameters are corresponding parameters.

[0051] The first set of control parameters is defined as the historical optimal solution, and the tabu table is set to empty to complete the initialization. The real-time control parameters are iteratively searched through the tabu table. Each iteration outputs the nth set of control parameters and the nth set of temperature data. It should be understood that the nth set of control parameters and the nth set of temperature data are corresponding parameters.

[0052] Based on the segmented temperature control values, the location information of the temperature acquisition points for each temperature control threshold within the target boiler is obtained. Based on this location information, n sets of segmented temperature data with the same location identifier are extracted from all n sets of temperature data. Based on the correspondence between the n sets of segmented temperature data and the location identifiers of the segmented temperature control values, the temperature deviation is calculated one by one to complete the similarity analysis. This is then compared with a preset temperature deviation threshold to determine whether each of the n sets of segmented temperature values ​​meets the preset temperature deviation threshold. p sets of temperature data that meet the preset temperature deviation threshold are obtained. These p sets of temperature data are the most similar to the furnace wall temperature requirement of the segmented temperature control values ​​among the n sets of temperature data. The p-th set of control parameters is used as the parameter control optimization result. This embodiment, based on parameter control optimization, reduces the dependence on human experience in obtaining the optimal control parameters for the target boiler, achieving the technical effect of scientifically and accurately obtaining the control parameters that enable the target boiler to operate at the segmented temperature control values.

[0053] S600: The combustion temperature of the target boiler is controlled by the optimization results of the parameters.

[0054] Specifically, in this embodiment, the parameter control optimization result is to enable the target boiler to achieve the required furnace wall temperature for segmented temperature control during operation. Based on the parameter control optimization result, the combustion temperature of the target boiler is controlled so that the target boiler performs fuel combustion with the expected combustion efficiency.

[0055] This embodiment obtains the design dimensions of the target boiler, acquires images of the target boiler using the image acquisition device, and obtains image acquisition results. The design dimensions and image acquisition results provide reference data and images for subsequent reconstruction of the target boiler by constructing a 3D model through 3D fitting. A 3D fitting model is constructed based on the image acquisition results and the design dimensions. Temperature measurement points on the furnace wall are set using the 3D fitting model. The effective selection of these furnace wall temperature measurement points provides a reference for accurate and effective temperature measurement during the operation of the target boiler after the installation of temperature measurement devices. Infrared acoustic temperature measurement devices are deployed at the furnace wall temperature measurement points, and temperature is measured using these devices. Temperature data is collected to obtain a temperature data set, wherein the temperature data set includes collection time and location identifiers; real-time control parameters of the target boiler are obtained, and the real-time control parameter set and the temperature data set provide an optimization traversal dataset for subsequent optimization to determine the optimal control parameters of the target boiler; parameter control optimization is performed on the real-time control parameters using the temperature data set to obtain parameter control optimization results; the combustion temperature of the target boiler is controlled using the parameter control optimization results, thereby reducing the dependence of obtaining the optimal control parameters of the target boiler on human experience and achieving the technical effect of obtaining scientifically accurate control parameters that enable the target boiler to operate at segmented temperature control values.

[0056] In one embodiment, the method steps provided in this application further include:

[0057] S521: Select the first parameter feature among the real-time control parameters as the optimization direction and perform optimization search;

[0058] S522: Obtain the first optimization search result, wherein the first optimization search result is a local optimum result within a predetermined interval;

[0059] S523: Record the first optimization search result as the second set of control parameters, record the temperature data corresponding to the second set of control parameters as the second set of temperature data, add the first parameter feature to the taboo table, and update the taboo table;

[0060] S524: Iteratively search the real-time control parameters using the updated taboo table.

[0061] In one embodiment, the method steps provided in this application further include:

[0062] S523-1: Set a prohibition period based on the number of parameter characteristics of the real-time control parameters;

[0063] S523-2: Determine whether the first parameter feature in the taboo table satisfies the taboo period;

[0064] S523-3: When the first parameter feature can satisfy the taboo period, the first parameter feature is unbanned, and the taboo table is updated based on the unbanning result.

[0065] Specifically, in this embodiment, the real-time control parameters are a collective term for the real-time parameters and control indicators of the target boiler during normal operation, including drum pressure, main steam pressure, drum water level, etc. A control indicator is randomly selected from these real-time control parameters as the first parameter feature. Using the first parameter feature as the optimization direction means fixing all other control indicator parameters except the first parameter feature, and performing an optimization search among multiple sets of real-time control parameters where only the first parameter feature is a variable value.

[0066] By selecting the first parameter feature among the real-time control parameters as the optimization direction, an optimization search is performed to obtain multiple sets of real-time temperature data corresponding to multiple sets of real-time control parameters with only the first parameter feature as the variable value. The multiple sets of temperature data are compared with the segmented temperature control value, and the real-time control parameter corresponding to the set of temperature data with the smallest temperature data deviation from the segmented temperature control value is obtained as the first optimization search result. The first optimization search result includes the optimal parameter value of the other parameter features as constant values ​​and the first parameter feature. The first optimization search result is a local optimum result.

[0067] The first optimization search result is recorded as the second set of control parameters, and the temperature data corresponding to the second set of control parameters is recorded as the second set of temperature data. The first parameter feature is added to the taboo table, and the taboo table is updated. By adding the first parameter feature to the taboo table, the occurrence of the parameter feature during the subsequent optimization process is stopped, which would cause the optimization to get stuck in local optimization. The real-time control parameters are iteratively searched using the updated taboo table.

[0068] The first parameter feature is added to the taboo table so that when optimizing the real-time control parameters in the future, the real-time control parameters containing the first optimization search result will no longer be compared for optimization. This is to avoid taking the first optimization search result of the local optimum as the optimal solution again, which would cause the real-time control parameter optimization to get stuck in local optimization.

[0069] Meanwhile, the first parameter feature is not always placed in the taboo table. The parameter feature entering the taboo table has a taboo period. During the taboo period, the first parameter feature cannot be selected. After the taboo period is reached, the first parameter feature in the table is released, so that the first parameter feature can participate in the real-time control parameter optimization again without causing the optimization to fall into local optimization.

[0070] The taboo period is determined based on the number of parameter features of the real-time control parameters. For example, when the number of parameter features is 7, the emergency period is set to 7 cycles. Within these 7 optimization cycles, the first parameter feature cannot be selected. During the iterative search of the real-time control parameters, it is determined whether the first parameter feature in the taboo table satisfies the taboo period. If the first parameter feature satisfies the taboo period, it is unbanned. Based on the unbanning result, the taboo table is updated, and the first parameter feature is released from the taboo table.

[0071] This embodiment achieves the technical effect of improving optimization efficiency by setting the optimization direction, and avoids the technical effect of local optimization by setting a taboo table. By avoiding local optimization and improving optimization efficiency, it achieves the technical effect of improving the scientificity and timeliness of the obtained optimal control parameters of the target boiler.

[0072] In one embodiment, the method steps provided in this application further include:

[0073] S523-4: Select the second parameter feature among the real-time control parameters as the optimization direction and perform optimization search, wherein the second parameter feature is a parameter feature that is not in the taboo table;

[0074] S523-5: Obtain the second optimization search result, wherein the second optimization search result is a local optimum result within a predetermined interval;

[0075] S523-6: Record the second optimization search result as the third set of control parameters, record the temperature data corresponding to the third set of control parameters as the third set of temperature data, add the second parameter feature to the taboo table, and update the taboo table;

[0076] S523-7: Iteratively search the real-time control parameters using the updated taboo table.

[0077] Specifically, in this embodiment, a control index is randomly selected from the real-time control parameters as the second parameter feature. Using the second parameter feature as the optimization direction means fixing all other control index parameters except the second parameter feature, while using the optimal solution of the first parameter feature in the first optimization search result as the fixed value of the first parameter feature, and performing optimization search among multiple sets of real-time control parameters with only the second parameter feature as the variable value.

[0078] By selecting the second parameter feature among the real-time control parameters as the optimization direction, an optimization search is performed to obtain multiple sets of real-time temperature data corresponding to multiple sets of real-time control parameters with only the second parameter feature as the variable value. The multiple sets of temperature data are compared with the segmented temperature control value, and the real-time control parameter corresponding to the set of temperature data with the smallest temperature data deviation from the segmented temperature control value is obtained as the second optimization search result. The second optimization search result includes the optimal parameter value of the second parameter feature with the other parameter features as constant values. The second optimization search result is also a local optimum result. The second parameter feature is also added to the taboo table and released after the taboo period is reached.

[0079] Similarly, a control index is randomly selected from the real-time control parameters as the third parameter feature, while other control index parameters are fixed. At the same time, the optimal solution of the first parameter feature in the first optimization search result is used as the fixed value of the first parameter feature, and the optimal solution of the second parameter feature in the second optimization search result is used as the fixed value of the second parameter feature. Optimization search is performed on multiple sets of real-time control parameters with only the third parameter feature as the variable value, and a tabu list is added until all control parameters in the real-time control parameters are traversed. Based on parameter feature selection and tabu list updating, the technical effect of obtaining global parameter control optimization results by avoiding local optimization is achieved.

[0080] In one embodiment, the method steps provided in this application further include:

[0081] S610: Set the preset iteration number threshold and similarity constraint threshold;

[0082] S620: When the number of iterations meets the preset iteration number threshold and / or the similarity analysis result can meet the similarity constraint threshold, then stop the parameter control optimization and obtain the parameter control optimization result.

[0083] Specifically, in the foregoing, this embodiment avoids getting stuck in local optimization by setting a taboo list and setting the taboo period for taboo objects in the taboo list.

[0084] To avoid getting stuck in an infinite search, this implementation presets an iteration number threshold and a similarity constraint threshold. The similarity constraint threshold is used to determine whether the temperature deviation at the same position between the temperature data corresponding to a set of control parameters obtained through optimization and the segmented temperature control value can be considered as non-existent. For example, if the flue gas temperature at the inlet of the partition screen corresponding to a set of control parameters obtained through optimization is 1345℃, and the required flue gas temperature at the inlet of the partition screen in the segmented temperature control value is ≤1350℃, the temperature deviation between the two is 5℃, which falls within the similarity constraint threshold range of ±10℃. Therefore, it is considered that there is no temperature deviation between the two flue gas temperatures at the inlet of the partition screen.

[0085] When the number of iterations meets the preset iteration number threshold and / or the results of the multi-location furnace wall temperature similarity analysis can meet the similarity constraint threshold, the parameter control optimization is stopped and the parameter control optimization result is obtained. This embodiment avoids the waste of system computing resources caused by infinite optimization while avoiding local optimization.

[0086] In one embodiment, the method steps provided in this application further include:

[0087] S710: Continuous temperature monitoring is performed using the infrared acoustic temperature measuring device to obtain continuous temperature monitoring results;

[0088] S720: Generate stability analysis data based on the continuous temperature monitoring results;

[0089] S730: Perform control compensation on the parameter control optimization results using the stability analysis data.

[0090] Specifically, in this embodiment, the combustion temperature of the target boiler is controlled by the parameter control optimization result. Under the control of the parameter control optimization result by the infrared acoustic temperature measuring device, the temperature of the target boiler is continuously monitored to obtain continuous temperature monitoring results. The continuous temperature monitoring results are multiple sets of temperature data with location identifiers and acquisition time identifiers. Data is extracted using the location identifier as the data extraction benchmark to obtain temperature data from multiple acquisition times at the same location, generating a temperature-time variation curve. Based on the temperature-time variation curve, the curve volatility is obtained as the stability analysis data of temperature change at that location.

[0091] The same method is used to obtain temperature change stability analysis data at each furnace wall temperature measurement point, generate the stability analysis data, and perform control compensation on the parameter control optimization results based on the corresponding position of the stability analysis data and the correspondence between each control parameter in the parameter optimization results, so as to obtain the optimized parameter control optimization results that achieve constant control of the target boiler temperature, thereby achieving the technical effect of improving the operating stability of the target boiler at the preset operating temperature.

[0092] In one embodiment, such as Figure 3 As shown, a temperature optimization control system for boiler combustion is provided, comprising: an image acquisition and execution module 1, a furnace wall temperature measurement and positioning module 2, a temperature data acquisition module 3, a control parameter acquisition module 4, a parameter control optimization module 5, and a combustion temperature control module 6, wherein:

[0093] Image acquisition execution module 1 is used to obtain the design dimension parameters of the target boiler, and to acquire images of the target boiler through an image acquisition device to obtain image acquisition results.

[0094] Furnace wall temperature measurement and positioning module 2 is used to construct a three-dimensional fitting model based on the image acquisition results and the design dimension parameters, and to set the furnace wall temperature measurement point through the three-dimensional fitting model.

[0095] Temperature data acquisition module 3 is used to deploy infrared acoustic temperature measuring devices through the temperature measuring points on the furnace wall, and to acquire temperature data through the infrared acoustic temperature measuring devices to obtain a temperature data acquisition set, wherein the temperature data acquisition set has acquisition time and location identifiers.

[0096] Control parameter acquisition module 4 is used to obtain the real-time control parameters of the target boiler;

[0097] The parameter control optimization module 5 is used to perform parameter control optimization on the real-time control parameters through the temperature data acquisition set, and obtain the parameter control optimization result.

[0098] Combustion temperature control module 6 is used to control the combustion temperature of the target boiler based on the parameter control optimization results.

[0099] In one embodiment, the parameter control optimization module 5 further includes:

[0100] The control value setting unit is used to set the segmented temperature control values;

[0101] The corresponding parameter acquisition unit is used to obtain the first set of control parameters in the real-time control parameters and obtain the first set of temperature data from the temperature data acquisition set, wherein the first set of temperature data and the first set of control parameters are corresponding parameters;

[0102] The taboo table initialization unit is used to take the first set of control parameters as the historical optimal solution and set the taboo table to empty to complete the initialization;

[0103] The iterative search execution unit is used to perform an iterative search on the real-time control parameters through the taboo table, and outputs the nth set of control parameters and the nth set of temperature data in each iteration.

[0104] The similarity analysis execution unit is used to perform similarity analysis on all n sets of temperature data and the segmented temperature control values ​​to obtain p sets of temperature data, wherein the p sets of temperature data are the most similar data among the n sets of temperature data;

[0105] The optimization result acquisition unit is used to control the optimization result by using the p-th group of control parameters as the parameters.

[0106] In one embodiment, the parameter control optimization module 5 further includes:

[0107] The optimization search execution unit is used to select the first parameter feature among the real-time control parameters as the optimization direction and perform optimization search;

[0108] A local optimal solution acquisition unit is used to obtain a first optimization search result, wherein the first optimization search result is a local optimal result within a predetermined interval;

[0109] The taboo table update unit is used to record the first optimization search result as the second set of control parameters, the temperature data corresponding to the second set of control parameters as the second set of temperature data, and add the first parameter feature to the taboo table to update the taboo table.

[0110] An iterative search execution unit is used to perform an iterative search on the real-time control parameters using the updated tabu table.

[0111] In one embodiment, the parameter control optimization module 5 further includes:

[0112] The taboo period setting unit is used to set the taboo period based on the number of parameter characteristics of the real-time control parameters;

[0113] A taboo period determination unit is used to determine whether the first parameter feature in the taboo table satisfies the taboo period.

[0114] The unbanning execution unit is used to unban the first parameter feature when the first parameter feature can satisfy the taboo period, and update the taboo table based on the unbanning result.

[0115] In one embodiment, the parameter control optimization module 5 further includes:

[0116] The optimization search execution unit is used to select the second parameter feature in the real-time control parameters as the optimization direction and perform optimization search, wherein the second parameter feature is a parameter feature that is not in the taboo table;

[0117] The optimization result acquisition unit is used to obtain the second optimization search result, wherein the second optimization search result is a local optimal result within a predetermined interval;

[0118] The taboo table update unit is used to record the second optimization search result as the third set of control parameters, the temperature data corresponding to the third set of control parameters as the third set of temperature data, and add the second parameter feature to the taboo table to update the taboo table.

[0119] The iterative search optimization unit is used to iteratively search the real-time control parameters using the updated tabu table.

[0120] In one embodiment, the combustion temperature control module 6 further includes:

[0121] The optimization threshold setting unit is used to set the preset iteration number threshold and the similarity constraint threshold;

[0122] The optimization stop execution unit is used to stop parameter control optimization and obtain the parameter control optimization result when the number of iterations meets the preset iteration number threshold and / or the similarity analysis result can meet the similarity constraint threshold.

[0123] In one embodiment, the system provided in this application further includes:

[0124] A continuous temperature monitoring unit is used to continuously monitor the temperature through the infrared acoustic temperature measuring device and obtain continuous temperature monitoring results.

[0125] A stability analysis execution unit is used to generate stability analysis data based on the continuous temperature monitoring results.

[0126] A control compensation execution unit is used to perform control compensation on the parameter control optimization results based on the stability analysis data.

[0127] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for optimizing temperature control in boiler combustion, characterized in that, The method is applied to a temperature optimization control system, which is communicatively connected to an image acquisition device and an infrared acoustic temperature measurement device. The method includes: The design dimensions of the target boiler are obtained, and images of the target boiler are acquired using the image acquisition device to obtain the image acquisition results. A three-dimensional fitting model is constructed based on the image acquisition results and the design size parameters, and the furnace wall temperature measurement points are set through the three-dimensional fitting model. The infrared acoustic temperature measuring device is deployed through the temperature measuring points on the furnace wall, and temperature data is collected through the infrared acoustic temperature measuring device to obtain a temperature data collection set, wherein the temperature data collection set has a collection time and location identifier. Obtain the real-time control parameters of the target boiler; The real-time control parameters are optimized using the temperature data acquisition set to obtain the parameter optimization result. The combustion temperature of the target boiler is controlled by the optimization results of the parameters. The real-time control parameters include steam drum pressure, main steam pressure, and steam drum water level. The real-time control parameters and the temperature data acquisition set have a one-to-one mapping relationship based on the acquisition time identifier. The parameter control optimization includes: setting segmented temperature control values; obtaining a first set of control parameters from the real-time control parameters and obtaining a first set of temperature data from the temperature data acquisition set, wherein the first set of temperature data and the first set of control parameters are corresponding parameters; using the first set of control parameters as the historical optimal solution and setting the tabu list to empty to complete initialization; performing an iterative search on the real-time control parameters through the tabu list, outputting the nth set of control parameters and the nth set of temperature data in each iteration; performing a similarity analysis on all n sets of temperature data and the segmented temperature control values ​​to obtain p sets of temperature data, wherein the p sets of temperature data are the most similar data among the n sets of temperature data; and using the pth set of control parameters as the parameter control optimization result. The iterative search of the real-time control parameters using the taboo table includes: selecting a first parameter feature among the real-time control parameters as the optimization direction and performing an optimization search; obtaining a first optimization search result, wherein the first optimization search result is a local optimum result within a predetermined interval; recording the first optimization search result as a second set of control parameters, recording the temperature data corresponding to the second set of control parameters as a second set of temperature data, adding the first parameter feature to the taboo table, and updating the taboo table; and performing an iterative search of the real-time control parameters using the updated taboo table. The method further includes: setting a taboo period based on the number of parameter features of the real-time control parameters; determining whether the first parameter feature in the taboo table meets the taboo period; when the first parameter feature can meet the taboo period, then performing unbanning processing on the first parameter feature, and updating the taboo table based on the unbanning processing result; The iterative search of the real-time control parameters using the updated taboo table further includes: selecting a second parameter feature among the real-time control parameters as the optimization direction and performing an optimization search, wherein the second parameter feature is a parameter feature not in the taboo table; obtaining a second optimization search result, wherein the second optimization search result is a local optimum result within a predetermined interval; recording the second optimization search result as a third set of control parameters, recording the temperature data corresponding to the third set of control parameters as a third set of temperature data, adding the second parameter feature to the taboo table, and updating the taboo table; and performing an iterative search of the real-time control parameters using the updated taboo table. The method further includes: setting a preset iteration number threshold and a similarity constraint threshold; When the number of iterations meets the preset iteration number threshold and / or the similarity analysis result meets the similarity constraint threshold, the parameter control optimization is stopped and the parameter control optimization result is obtained. Specifically, the combustion temperature of the target boiler is controlled by the parameter optimization results, so that the target boiler operates at the segmented temperature control value and performs fuel combustion with the expected combustion efficiency.

2. The method as described in claim 1, characterized in that, The method includes: The infrared acoustic temperature measuring device is used to continuously monitor the temperature and obtain continuous temperature monitoring results. Stability analysis data is generated based on the continuous temperature monitoring results; The stability analysis data is used to perform control compensation on the parameter control optimization results.

3. A temperature optimization control system for boiler combustion, characterized in that, The temperature optimization control system performs the method of claim 1 or 2, wherein the system comprises: The image acquisition execution module is used to obtain the design dimension parameters of the target boiler, and to acquire images of the target boiler through the image acquisition device to obtain image acquisition results. The furnace wall temperature measurement and positioning module is used to construct a three-dimensional fitting model based on the image acquisition results and the design dimension parameters, and to set the furnace wall temperature measurement points through the three-dimensional fitting model. The temperature data acquisition module is used to deploy infrared acoustic temperature measuring devices through the temperature measuring points on the furnace wall, and to acquire temperature data through the infrared acoustic temperature measuring devices to obtain a temperature data acquisition set, wherein the temperature data acquisition set has acquisition time and location identifiers. A control parameter acquisition module is used to obtain the real-time control parameters of the target boiler; The parameter control optimization module is used to perform parameter control optimization on the real-time control parameters through the temperature data acquisition set, and obtain the parameter control optimization result. The combustion temperature control module is used to control the combustion temperature of the target boiler based on the optimization results of the parameter control.

4. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method of claim 1 or 2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method of claim 1 or 2.

Images