An electric dust removal intelligent energy management system

Abstract

The application relates to the technical field of energy management, in particular to an electric dust removal intelligent energy management system, which comprises an acquisition module used for acquiring a historical data set in the running process of an electric dust removal system, wherein the historical data set comprises parameter adjustment values of a high-frequency power supply of an electric dust remover under different unit load fluctuations and first dust removal evaluation values; a division module used for dividing the parameter adjustment values and the corresponding dust removal evaluation values into normal data sets and abnormal data sets; a determination module used for establishing a minimum adjustment time target function and a maximum dust removal efficiency target function and determining optimal adjustment parameters based on the normal data sets and the abnormal data sets; and a construction module used for constructing an electric dust removal system management platform based on the optimal adjustment parameters. The application solves the technical problem that there is no effective basis for scientifically adjusting the parameters of the high-frequency power supply of the electric dust remover, the timeliness of operation and control cannot be achieved, and the dust removal effect of the equipment cannot be improved.

Description

Technical Field

[0001] This application relates to the field of energy management technology, and in particular to an intelligent energy management system for electrostatic precipitators. Background Technology

[0002] The function of an electrostatic precipitator is to reduce the dust content in the dusty gas as much as possible so that the gas discharged into the atmosphere meets the standards. However, due to fluctuations in unit load, changes in coal quality, flue gas volume, inlet flue gas temperature, and dust inlet concentration, the high-frequency power supply parameters of the electrostatic precipitator need to be adjusted multiple times.

[0003] In existing technologies, parameter adjustments for electrostatic precipitators largely rely on operational experience and a sense of responsibility, involving manual operation. There is no effective scientific basis for adjusting the high-frequency power supply parameters of the electrostatic precipitator, resulting in both a lack of timely control and an inability to improve the equipment's dust removal efficiency. Therefore, improving both the timeliness of control and dust removal efficiency is a technical problem that needs to be solved in this field. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides an intelligent energy management system for electrostatic precipitators, aiming to solve the technical problem that parameter adjustments for electrostatic precipitators often rely on manual operation based on operational experience and a sense of responsibility, lacking a scientific basis for adjusting the parameters. This results in neither timely control nor improved dust removal efficiency.

[0005] In some embodiments of this application, historical datasets of the electrostatic precipitator system are obtained, and parameter adjustment values ​​and first dust removal evaluation values ​​of the high-frequency power supply under different operating conditions are determined based on the historical datasets. Normal datasets and abnormal datasets are determined based on the parameter adjustment values ​​and the first dust removal evaluation values. Objective functions for minimizing adjustment time and maximizing dust removal efficiency are constructed. Optimal adjustment parameters are determined based on the adjustment model. Based on the adjustment method, adjustment capability, and adjustment sub-methods corresponding to the optimal adjustment parameters, an optimal adjustment model is constructed. Multiple optimal adjustment models are combined to construct an electrostatic precipitator system management platform. The optimal adjustment parameters enable the electrostatic precipitator system to achieve the goal of shortest adjustment time and highest dust removal efficiency, solving the technical problem of lacking effective basis for scientifically adjusting the high-frequency power supply parameters of the electrostatic precipitator, which results in neither timely control nor improved dust removal effect.

[0006] In some embodiments of this application, an intelligent energy management system for electrostatic precipitators is provided, comprising:

[0007] The acquisition module is used to acquire historical datasets during the operation of the electrostatic precipitator system. The historical datasets include coal quality changes, flue gas volume, inlet flue gas temperature, dust inlet concentration, and corresponding parameter adjustment values ​​of the high-frequency power supply of the electrostatic precipitator and corresponding first dust removal evaluation values ​​under different unit load fluctuations.

[0008] The partitioning module is used to analyze the parameter adjustment values ​​and the corresponding first dust removal evaluation values, and divide them into normal datasets and abnormal datasets;

[0009] The determination module is used to establish the objective function of minimizing the adjustment time and the objective function of maximizing the dust removal efficiency. Based on normal datasets, abnormal datasets, and the objective functions of minimizing the adjustment time and maximizing the dust removal efficiency, the optimal adjustment parameters are determined under different unit load fluctuations.

[0010] The module is used to build a management platform for the electrostatic precipitator system based on the optimal adjustment parameters.

[0011] In some embodiments of this application, the parameter adjustment values ​​and the corresponding first dust removal evaluation values ​​are analyzed, including:

[0012] S1 objects are randomly selected from several parameter adjustment values ​​under different unit load fluctuations in the historical dataset as the first center, and S2 objects are selected from the first dust removal evaluation values ​​corresponding to several parameter adjustment values ​​as the second center.

[0013] The adjustment time of the remaining parameter adjustment value under the load fluctuation of the same unit in the historical dataset is calculated for each first center to determine the first subset based on the first center, and the first center is determined to be replaced based on the first subset.

[0014] If not needed, set the corresponding first center as the third center; if needed, set the point in the first subset that satisfies the principle of shortest adjustment time as the third center.

[0015] Each second center is calculated against the remaining dust removal evaluation values ​​in the historical dataset to determine a second subset based on each second center, and the second subset is used to determine whether the second center needs to be replaced.

[0016] If not needed, the corresponding second center is set as the fourth center; if needed, the point in the second subset that satisfies the principle of maximizing dust removal efficiency is taken as the fourth center point.

[0017] In some embodiments of this application, the dataset is divided into normal datasets and abnormal datasets, including:

[0018] A dataset is constructed based on multiple third centers and multiple fourth centers. The dataset is analyzed to determine the adjustment capacity constraints of each third center and the time constraints, efficiency constraints, and cost constraints corresponding to each fourth center.

[0019] The historical data of the corresponding third center that simultaneously meets the constraints of adjustment capability, time, efficiency, and cost are classified into the normal data set, and the remaining historical data of the corresponding third center that do not simultaneously meet the constraints are classified into the abnormal data set.

[0020] In some embodiments of this application, the objective function of minimizing the adjustment time and the objective function of maximizing the dust removal efficiency are established, including:

[0021] The objective function for minimizing the adjustment time is:

[0022] ;

[0023] Where Y1 is the objective function for minimizing the adjustment time. The adjustment time for the mnj-th parameter adjustment value from the third center m to the fourth center n using the adjustment method Fmn, where min is the minimum value symbol;

[0024] The objective function for maximizing dust removal efficiency is:

[0025] ;

[0026] Where Y2 is the objective function for maximizing dust removal efficiency. The dust removal efficiency is determined by adjusting the mnj-th parameter value from the third center m to the fourth center using the Fmn adjustment method, where max is the maximum value symbol.

[0027] In some embodiments of this application, the optimal adjustment parameters under different unit load fluctuations are determined based on normal datasets, abnormal datasets, and objective functions that minimize adjustment time and maximize dust removal efficiency, including:

[0028] Based on several parameter adjustment values ​​in the normal dataset, the first dust removal evaluation value, the third center, the fourth center, and the corresponding coal quality changes, flue gas volume, inlet flue gas temperature, and dust inlet concentration, an adjustment model is established. The parameter adjustment values ​​under different unit load fluctuations are input into the adjustment model to simulate the adjustment under different operating conditions.

[0029] Based on the objective function of minimizing the adjustment time and the objective function of maximizing the dust removal efficiency, the adjustment model outputs multiple electrostatic precipitator operating parameters, and calculates the second dust removal evaluation value corresponding to the current adjustment simulation based on the electrostatic precipitator operating parameters;

[0030] Construct a parameter-second evaluation value mapping table based on the second dust removal evaluation value and the adjustment parameter corresponding to the second dust removal evaluation value. Filter out the maximum second dust removal evaluation value from the parameter-second evaluation value and set the adjustment parameter corresponding to the maximum second dust removal evaluation value as the first adjustment parameter.

[0031] The cause of the adjustment anomaly is determined based on the adjustment method, adjustment time, and adjustment cost of each third center in the abnormal dataset;

[0032] Based on the actual adjustment process of the adjustment method corresponding to the adjustment method in the abnormal dataset, the corresponding first adjustment parameter is adjusted to obtain the optimal adjustment parameter.

[0033] In some embodiments of this application, the first dust removal evaluation value and the second dust removal evaluation value are:

[0034] +(Rj-R) O3;

[0035] Where Wi is the i-th dust removal evaluation value, i=1,2, a1 is the first constant, U1 is the maximum operating voltage, U2 is the average operating voltage, s is the total dust collection area, r is the flue gas flow rate, e is the exponential function, t1 is the maximum preset adjustment time, t2 is the actual adjustment time, Rj is the maximum preset dust removal cost, R is the actual dust removal cost, O1 is the weighting coefficient corresponding to dust removal efficiency, O2 is the weighting coefficient corresponding to dust removal time, and O3 is the weighting coefficient corresponding to dust removal cost.

[0036] In some embodiments of this application, the difference between the evaluation values ​​of the first dust removal evaluation value and the second dust removal evaluation value corresponding to the same parameter adjustment value of the second dust removal evaluation value is calculated. The correction coefficient of the adjustment model is selected according to the relationship between the evaluation value difference and the preset evaluation value difference range. The electrostatic precipitator working parameters output by the adjustment model are corrected according to the correction coefficient.

[0037] The first preset evaluation value difference range, the second preset evaluation value difference range, the third preset evaluation value difference range, and the fourth preset evaluation value difference range are preset; the first preset correction coefficient, the second preset correction coefficient, the third preset correction coefficient, and the fourth preset correction coefficient are also preset.

[0038] When the difference in evaluation values ​​falls within the first preset range of evaluation value differences, the first preset correction coefficient is selected to correct the working parameters of the electrostatic precipitator.

[0039] When the difference in evaluation values ​​falls within the second preset range of evaluation value differences, the second preset correction coefficient is selected to correct the working parameters of the electrostatic precipitator.

[0040] When the difference in evaluation values ​​falls within the third preset range, the third preset correction coefficient is selected to correct the working parameters of the electrostatic precipitator.

[0041] When the difference in evaluation values ​​falls within the fourth preset range, the fourth preset correction coefficient is selected to correct the working parameters of the electrostatic precipitator.

[0042] In some embodiments of this application, an electrostatic precipitator system management platform is constructed based on optimal adjustment parameters, including:

[0043] Based on the adjustment methods, adjustment capabilities, and adjustment sub-methods among all optimal adjustment parameters, an optimal adjustment model is constructed.

[0044] By combining multiple optimal adjustment models, a management platform for the electrostatic precipitator system is constructed.

[0045] The intelligent energy management system for electrostatic precipitators according to embodiments of this application has the following advantages compared with the prior art:

[0046] By acquiring historical datasets of the electrostatic precipitator (ESP) system, the parameter adjustment values ​​and first dust removal evaluation values ​​of the high-frequency power supply under different operating conditions are determined based on the historical datasets. Normal and abnormal datasets are then identified based on the parameter adjustment values ​​and the first dust removal evaluation values. Objective functions for minimizing adjustment time and maximizing dust removal efficiency are constructed. Optimal adjustment parameters are determined based on the adjustment model. An optimal adjustment model is constructed based on the adjustment method, adjustment capability, and adjustment sub-methods corresponding to the optimal adjustment parameters. Multiple optimal adjustment models are combined to construct an ESP system management platform. The optimal adjustment parameters enable the ESP system to achieve the goal of shortest adjustment time and highest dust removal efficiency, solving the technical problem of lacking a scientific basis for adjusting the high-frequency power supply parameters of the ESP, which prevents timely control and improves the dust removal effect of the equipment. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of a smart energy management system for electrostatic precipitators in a preferred embodiment of this application. Detailed Implementation

[0048] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are used to illustrate this application, but are not intended to limit the scope of this application.

[0049] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0050] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0051] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0052] like Figure 1 As shown in the preferred embodiment of this application, a smart energy management system for electrostatic precipitators includes:

[0053] The acquisition module is used to acquire historical datasets during the operation of the electrostatic precipitator system. The historical datasets include coal quality changes, flue gas volume, inlet flue gas temperature, dust inlet concentration, and corresponding parameter adjustment values ​​of the high-frequency power supply of the electrostatic precipitator and corresponding first dust removal evaluation values ​​under different unit load fluctuations.

[0054] The partitioning module is used to analyze the parameter adjustment values ​​and the corresponding first dust removal evaluation values, and divide them into normal datasets and abnormal datasets;

[0055] The determination module is used to establish the objective function of minimizing the adjustment time and the objective function of maximizing the dust removal efficiency. Based on normal datasets, abnormal datasets, and the objective functions of minimizing the adjustment time and maximizing the dust removal efficiency, the optimal adjustment parameters are determined under different unit load fluctuations.

[0056] The module is used to build a management platform for the electrostatic precipitator system based on the optimal adjustment parameters.

[0057] In some embodiments of this application, the parameter adjustment values ​​and the corresponding first dust removal evaluation values ​​are analyzed, including:

[0058] S1 objects are randomly selected from several parameter adjustment values ​​under different unit load fluctuations in the historical dataset as the first center, and S2 objects are selected from the first dust removal evaluation values ​​corresponding to several parameter adjustment values ​​as the second center.

[0059] The adjustment time of the remaining parameter adjustment value under the load fluctuation of the same unit in the historical dataset is calculated for each first center to determine the first subset based on the first center, and the first center is determined to be replaced based on the first subset.

[0060] If not needed, set the corresponding first center as the third center; if needed, set the point in the first subset that satisfies the principle of shortest adjustment time as the third center.

[0061] Each second center is calculated against the remaining dust removal evaluation values ​​in the historical dataset to determine a second subset based on each second center, and the second subset is used to determine whether the second center needs to be replaced.

[0062] If not needed, the corresponding second center is set as the fourth center; if needed, the point in the second subset that satisfies the principle of maximizing dust removal efficiency is taken as the fourth center point.

[0063] In this embodiment, the first center refers to S1 parameter adjustment value objects randomly selected based on the number of parameter adjustment values ​​under different unit load fluctuations, and the second center refers to S2 dust removal evaluation value objects randomly selected based on the number of first dust removal evaluation values ​​corresponding to the parameter adjustment values ​​under different unit load fluctuations.

[0064] In this embodiment, the first subset of each first center is specifically the parameter adjustment value in the load fluctuation of the same unit, and the adjustment time of the first center is less than the adjustment time of each parameter adjustment value in the first subset.

[0065] In this embodiment, if the first center is the point that satisfies the principle of the shortest adjustment time under the same unit load fluctuation, that is, the adjustment time corresponding to each parameter adjustment value in the first subset under the same unit load fluctuation is greater than the adjustment time of the first center, then the first center is set as the third center. If the first center is not the point that satisfies the principle of the shortest adjustment time under the same unit load fluctuation, the point with the shortest adjustment time in the first subset is set as the third center.

[0066] In this embodiment, if the second center is the point that satisfies the principle of maximum dust removal efficiency under the same unit load fluctuation, the second center is set as the fourth center, that is, the dust removal efficiency corresponding to each dust removal evaluation value in the second subset is less than the dust removal efficiency of the first center; otherwise, the point with the maximum dust removal efficiency in the second subset is set as the fourth center.

[0067] In this embodiment, by using the parameter adjustment values ​​under different unit load fluctuations and the corresponding first dust removal evaluation values, the third and fourth center points with the shortest adjustment time and the highest dust removal efficiency are generated, which can provide a basis for the subsequent establishment of an electrostatic precipitator energy management system.

[0068] In some embodiments of this application, the dataset is divided into normal datasets and abnormal datasets, including:

[0069] A dataset is constructed based on multiple third centers and multiple fourth centers. The dataset is analyzed to determine the adjustment capacity constraints of each third center and the time constraints, efficiency constraints, and cost constraints corresponding to each fourth center.

[0070] The historical data of the corresponding third center that simultaneously meets the constraints of adjustment capability, time, efficiency, and cost are classified into the normal data set, and the remaining historical data of the corresponding third center that do not simultaneously meet the constraints are classified into the abnormal data set.

[0071] In this embodiment, the dataset includes the adjustment method, adjustment time, adjustment cost, and adjustment capability of the third center corresponding to each fourth center, as well as the dust removal efficiency of each fourth center under the adjustment method.

[0072] In this embodiment, the adjustment capability constraint means that the adjustment capability of all adjustment methods in each third center is not less than the limited adjustment capability of all adjustment methods in which each third center generates the fourth center; the time constraint means that the adjustment time of all adjustment methods in each third center does not exceed the limited adjustment time of all adjustment methods in which each third center generates the fourth center; the efficiency constraint means that the dust removal efficiency of all adjustment methods in each third center is not less than the limited dust removal efficiency of all adjustment methods in which each third center generates the fourth center; and the cost constraint means that the dust removal cost of all adjustment methods in each third center does not exceed the limited dust removal cost of all adjustment methods in which each third center generates the fourth center.

[0073] In this embodiment, by adjusting the capacity constraint, time constraint, efficiency constraint, and time constraint, the normal data set and the abnormal data set are determined, which improves the data foundation for determining the optimal adjustment parameters, shortening the adjustment time, improving dust removal efficiency, and reducing dust removal costs.

[0074] In some embodiments of this application, the objective function of minimizing the adjustment time and the objective function of maximizing the dust removal efficiency are established, including:

[0075] The objective function for minimizing the adjustment time is:

[0076] ;

[0077] Where Y1 is the objective function for minimizing the adjustment time. The adjustment time for the mnj-th parameter adjustment value from the third center m to the fourth center n using the adjustment method Fmn, where min is the minimum value symbol;

[0078] The objective function for maximizing dust removal efficiency is:

[0079] ;

[0080] Where Y2 is the objective function for maximizing dust removal efficiency. The dust removal efficiency is determined by adjusting the mnj-th parameter value from the third center m to the fourth center using the Fmn adjustment method, where max is the maximum value symbol.

[0081] In this embodiment, the objective function of minimizing adjustment time minimizes the sum of adjustment times used by different adjustment sub-methods from the third center to the corresponding fourth center. The objective function of maximizing dust removal efficiency maximizes the dust removal efficiency and minimizes the dust removal cost after adjusting the methods from the third center to the fourth center.

[0082] In this embodiment, by determining the objective function of minimizing the adjustment time and the objective function of maximizing the dust removal efficiency, the adjustment time can be effectively shortened and the dust removal efficiency can be improved, thereby enhancing the timeliness of operation and the dust removal effect of the electrostatic precipitator system.

[0083] In some embodiments of this application, the optimal adjustment parameters under different unit load fluctuations are determined based on normal datasets, abnormal datasets, and objective functions that minimize adjustment time and maximize dust removal efficiency, including:

[0084] Based on several parameter adjustment values ​​in the normal dataset, the first dust removal evaluation value, the third center, the fourth center, and the corresponding coal quality changes, flue gas volume, inlet flue gas temperature, and dust inlet concentration, an adjustment model is established. The parameter adjustment values ​​under different unit load fluctuations are input into the adjustment model to simulate the adjustment under different operating conditions.

[0085] Based on the objective function of minimizing the adjustment time and the objective function of maximizing the dust removal efficiency, the adjustment model outputs multiple electrostatic precipitator operating parameters, and calculates the second dust removal evaluation value corresponding to the current adjustment simulation based on the electrostatic precipitator operating parameters;

[0086] Construct a parameter-second evaluation value mapping table based on the second dust removal evaluation value and the adjustment parameter corresponding to the second dust removal evaluation value. Filter out the maximum second dust removal evaluation value from the parameter-second evaluation value and set the adjustment parameter corresponding to the maximum second dust removal evaluation value as the first adjustment parameter.

[0087] The cause of the adjustment anomaly is determined based on the adjustment method, adjustment time, and adjustment cost of each third center in the abnormal dataset;

[0088] Based on the actual adjustment process of the adjustment method corresponding to the adjustment method in the abnormal dataset, the corresponding first adjustment parameter is adjusted to obtain the optimal adjustment parameter.

[0089] In this embodiment, an adjustment model is constructed to simulate different operating conditions such as coal quality changes, flue gas volume, inlet flue gas temperature, and dust inlet concentration under different unit load fluctuations. The parameters corresponding to different operating conditions are input into the adjustment model. Based on the objective function of minimizing the adjustment time and the objective function of maximizing the dust removal efficiency, multiple operating parameters of the electrostatic precipitator system are obtained. The operating parameters include operating voltage, dust collection area and flue gas flow rate, adjustment time, and operating parameters corresponding to the calculable dust removal efficiency. A second dust removal evaluation value is calculated based on the operating parameters, and the parameter adjustment value corresponding to the maximum second dust removal evaluation value is set as the first adjustment parameter.

[0090] In some embodiments of this application, the first dust removal evaluation value and the second dust removal evaluation value are:

[0091] +(Rj-R) O3;

[0092] Where Wi is the i-th dust removal evaluation value, i=1,2, a1 is the first constant, U1 is the maximum operating voltage, U2 is the average operating voltage, s is the total dust collection area, r is the flue gas flow rate, e is the exponential function, t1 is the maximum preset adjustment time, t2 is the actual adjustment time, Rj is the maximum preset dust removal cost, R is the actual dust removal cost, O1 is the weighting coefficient corresponding to dust removal efficiency, O2 is the weighting coefficient corresponding to dust removal time, and O3 is the weighting coefficient corresponding to dust removal cost.

[0093] In some embodiments of this application, the difference between the evaluation values ​​of the first dust removal evaluation value and the second dust removal evaluation value corresponding to the same parameter adjustment value of the second dust removal evaluation value is calculated. The correction coefficient of the adjustment model is selected according to the relationship between the evaluation value difference and the preset evaluation value difference range. The electrostatic precipitator working parameters output by the adjustment model are corrected according to the correction coefficient.

[0094] The first preset evaluation value difference range, the second preset evaluation value difference range, the third preset evaluation value difference range, and the fourth preset evaluation value difference range are preset; the first preset correction coefficient, the second preset correction coefficient, the third preset correction coefficient, and the fourth preset correction coefficient are also preset.

[0095] When the difference in evaluation values ​​falls within the first preset range of evaluation value differences, the first preset correction coefficient is selected to correct the working parameters of the electrostatic precipitator.

[0096] When the difference in evaluation values ​​falls within the second preset range of evaluation value differences, the second preset correction coefficient is selected to correct the working parameters of the electrostatic precipitator.

[0097] When the difference in evaluation values ​​falls within the third preset range, the third preset correction coefficient is selected to correct the working parameters of the electrostatic precipitator.

[0098] When the difference in evaluation values ​​falls within the fourth preset range, the fourth preset correction coefficient is selected to correct the working parameters of the electrostatic precipitator.

[0099] In this embodiment, the first preset evaluation value difference interval < the second preset evaluation value difference interval < the third preset evaluation value difference interval < the fourth preset evaluation value difference interval, and the first preset correction coefficient < the second preset correction coefficient < the third preset correction coefficient < the fourth preset correction coefficient. The electrostatic precipitator operating parameters are corrected according to the preset correction coefficients so that the corrected electrostatic precipitator operating parameters better reflect the actual parameters of the current electrostatic precipitator system, laying the foundation for subsequent calculation of dust removal evaluation values.

[0100] In some embodiments of this application, an electrostatic precipitator system management platform is constructed based on optimal adjustment parameters, including:

[0101] Based on the adjustment methods, adjustment capabilities, and adjustment sub-methods among all optimal adjustment parameters, an optimal adjustment model is constructed.

[0102] By combining multiple optimal adjustment models, a management platform for the electrostatic precipitator system is constructed.

[0103] In this embodiment, the electrostatic precipitator system management platform also includes a data management platform. The data management platform provides dedicated communication interfaces for parameters such as boiler load and outlet dust concentration. Data can be exchanged with a high-frequency power supply through the dedicated communication interface to achieve mutual communication.

[0104] In summary, this invention discloses an intelligent energy management system for electrostatic precipitators, comprising: an acquisition module for acquiring historical datasets during the operation of the electrostatic precipitator system, wherein the historical datasets include coal quality changes, flue gas volume, inlet flue gas temperature, dust inlet concentration, and corresponding parameter adjustment values ​​of the high-frequency power supply of the electrostatic precipitator and corresponding first dust removal evaluation values ​​under different unit load fluctuations; a division module for analyzing the parameter adjustment values ​​and the corresponding first dust removal evaluation values ​​and dividing them into normal datasets and abnormal datasets; a determination module for establishing a minimum adjustment time objective function and a maximum dust removal efficiency objective function, and determining the optimal adjustment parameters under different unit load fluctuations based on the normal dataset, the abnormal dataset, and the minimum adjustment time objective function and the maximum dust removal efficiency objective function; and a construction module for constructing an electrostatic precipitator system management platform based on the optimal adjustment parameters.

[0105] Based on the first concept of this application, by acquiring historical datasets of the electrostatic precipitator system, the parameter adjustment values ​​of the high-frequency power supply under different operating conditions and the first dust removal evaluation value are determined based on the historical datasets. Normal and abnormal datasets are determined based on the parameter adjustment values ​​and the first dust removal evaluation value. Objective functions for minimizing adjustment time and maximizing dust removal efficiency are constructed. Optimal adjustment parameters are determined based on the adjustment model. Based on the adjustment method, adjustment capability, and adjustment sub-methods corresponding to the optimal adjustment parameters, an optimal adjustment model is constructed. Multiple optimal adjustment models are combined to construct an electrostatic precipitator system management platform. The optimal adjustment parameters enable the electrostatic precipitator system to achieve the goal of shortest adjustment time and highest dust removal efficiency, solving the technical problem of lacking effective scientific basis for adjusting the high-frequency power supply parameters of the electrostatic precipitator, which fails to achieve timely control and improve the dust removal effect of the equipment.

[0106] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and substitutions can be made without departing from the technical principles of this application, and these improvements and substitutions should also be considered within the scope of protection of this application.

Claims

1. A smart energy management system for electrostatic precipitators, characterized in that, include: The acquisition module is used to acquire historical datasets during the operation of the electrostatic precipitator system. The historical datasets include coal quality changes, flue gas volume, inlet flue gas temperature, dust inlet concentration, and corresponding parameter adjustment values ​​of the high-frequency power supply of the electrostatic precipitator and corresponding first dust removal evaluation values ​​under different unit load fluctuations. The partitioning module is used to analyze the parameter adjustment values ​​and the corresponding first dust removal evaluation values, and divide them into normal datasets and abnormal datasets; The determination module is used to establish the objective function of minimizing the adjustment time and the objective function of maximizing the dust removal efficiency. Based on normal datasets, abnormal datasets, and the objective functions of minimizing the adjustment time and maximizing the dust removal efficiency, the optimal adjustment parameters are determined under different unit load fluctuations. The module is used to build a management platform for the electrostatic precipitator system based on the optimal adjustment parameters; The parameter adjustment values ​​and the corresponding first dust removal evaluation values ​​were analyzed, including: S1 objects are randomly selected from several parameter adjustment values ​​under different unit load fluctuations in the historical dataset as the first center, and S2 objects are selected from the first dust removal evaluation values ​​corresponding to several parameter adjustment values ​​as the second center. The adjustment time of the remaining parameter adjustment value under the load fluctuation of the same unit in the historical dataset is calculated for each first center to determine the first subset based on the first center, and the first center is determined to be replaced based on the first subset. If not needed, set the corresponding first center as the third center; if needed, set the point in the first subset that satisfies the principle of shortest adjustment time as the third center. Each second center is calculated against the remaining first dust removal evaluation values ​​in the historical dataset to determine a second subset based on each second center, and the second subset is used to determine whether the second center needs to be replaced. If not needed, the corresponding second center is set as the fourth center; if needed, the point in the second subset that satisfies the principle of maximizing dust removal efficiency is taken as the fourth center point. The dataset is divided into normal and abnormal datasets, including: A dataset is constructed based on multiple third centers and multiple fourth centers. The dataset is analyzed to determine the adjustment capacity constraints of each third center and the time constraints, efficiency constraints, and cost constraints corresponding to each fourth center. The historical data of the corresponding third center that simultaneously meets the constraints of adjustment capability, time, efficiency, and cost are classified into the normal data set, and the remaining historical data of the corresponding third center that do not simultaneously meet the constraints are classified into the abnormal data set.

2. The intelligent energy management system for electrostatic precipitators as described in claim 1, characterized in that, Establish objective functions for minimizing adjustment time and maximizing dust removal efficiency, including: The objective function for minimizing the adjustment time is: ； Where Y1 is the objective function for minimizing the adjustment time. The adjustment time for the mnj-th parameter adjustment value from the third center m to the fourth center n using the adjustment method Fmn, where min is the minimum value symbol; The objective function for maximizing dust removal efficiency is: ； Where Y2 is the objective function for maximizing dust removal efficiency. The dust removal efficiency is determined by adjusting the mnj-th parameter value from the third center m to the fourth center n using the adjustment method of Fmn, where max is the maximum value symbol.

3. The intelligent energy management system for electrostatic precipitators as described in claim 2, characterized in that, Based on normal and abnormal datasets, and objective functions of minimizing adjustment time and maximizing dust removal efficiency, the optimal adjustment parameters under different unit load fluctuations are determined, including: Based on several parameter adjustment values ​​in the normal dataset, the first dust removal evaluation value, the third center, the fourth center, and the corresponding coal quality changes, flue gas volume, inlet flue gas temperature, and dust inlet concentration, an adjustment model is established. The parameter adjustment values ​​under different unit load fluctuations are input into the adjustment model to simulate the adjustment under different operating conditions. Based on the objective function of minimizing the adjustment time and the objective function of maximizing the dust removal efficiency, the adjustment model outputs multiple electrostatic precipitator operating parameters, and calculates the second dust removal evaluation value corresponding to the current adjustment simulation based on the electrostatic precipitator operating parameters; Construct a parameter-second evaluation value mapping table based on the second dust removal evaluation value and the adjustment parameter corresponding to the second dust removal evaluation value. Filter out the maximum second dust removal evaluation value from the parameter-second evaluation value and set the adjustment parameter corresponding to the maximum second dust removal evaluation value as the first adjustment parameter. The cause of the adjustment anomaly is determined based on the adjustment method, adjustment time, and adjustment cost of each third center in the abnormal dataset; Based on the actual adjustment process of the adjustment method corresponding to the adjustment method in the abnormal dataset, the corresponding first adjustment parameter is adjusted to obtain the optimal adjustment parameter.

4. The intelligent energy management system for electrostatic precipitators as described in claim 3, characterized in that, The first dust removal evaluation value and the second dust removal evaluation value are: +(Rj-R) O3; Where Wi is the i-th dust removal evaluation value, i=1,2, a1 is the first constant, U1 is the maximum operating voltage, U2 is the average operating voltage, s is the total dust collection area, r is the flue gas flow rate, e is the exponential function, t1 is the maximum preset adjustment time, t2 is the actual adjustment time, Rj is the maximum preset dust removal cost, R is the actual dust removal cost, O1 is the weighting coefficient corresponding to dust removal efficiency, O2 is the weighting coefficient corresponding to dust removal time, and O3 is the weighting coefficient corresponding to dust removal cost.

5. The intelligent energy management system for electrostatic precipitators as described in claim 4, characterized in that, Calculate the difference between the evaluation values ​​of the first dust removal evaluation value and the second dust removal evaluation value corresponding to the same parameter adjustment value. Select the correction coefficient of the adjustment model based on the relationship between the evaluation value difference and the preset evaluation value difference range. Correct the electrostatic precipitator operating parameters output by the adjustment model based on the correction coefficient. The first preset evaluation value difference range, the second preset evaluation value difference range, the third preset evaluation value difference range, and the fourth preset evaluation value difference range are preset. It also has a first preset correction coefficient, a second preset correction coefficient, a third preset correction coefficient, and a fourth preset correction coefficient. When the difference in evaluation values ​​falls within the first preset range of evaluation value differences, the first preset correction coefficient is selected to correct the working parameters of the electrostatic precipitator. When the difference in evaluation values ​​falls within the second preset range of evaluation value differences, the second preset correction coefficient is selected to correct the working parameters of the electrostatic precipitator. When the difference in evaluation values ​​falls within the third preset range, the third preset correction coefficient is selected to correct the working parameters of the electrostatic precipitator. When the difference in evaluation values ​​falls within the fourth preset range, the fourth preset correction coefficient is selected to correct the working parameters of the electrostatic precipitator.

6. The intelligent energy management system for electrostatic precipitators as described in claim 5, characterized in that, Based on the optimal adjustment parameters, a management platform for the electrostatic precipitator system is constructed, including: Based on the adjustment methods, adjustment capabilities, and adjustment sub-methods among all optimal adjustment parameters, an optimal adjustment model is constructed. By combining multiple optimal adjustment models, a management platform for the electrostatic precipitator system is constructed.

Images