AGC performance index real-time evaluation method and system based on multi-source data fusion

Abstract

The invention belongs to the technical field of power system optimization, and discloses an AGC performance index real-time evaluation method and system based on multi-source data fusion, and the method comprises the steps: obtaining all-condition operation parameters of a unit based on a distributed data collection system, and carrying out the screening and correction through a multi-factor weighted analysis and data quality evaluation algorithm, establishing a multi-source heterogeneous data set; carrying out characteristic decomposition on the multi-source heterogeneous data set at different time scales by utilizing a sliding time window method, and extracting a performance characteristic vector under each time scale to obtain a multi-dimensional characteristic matrix; according to the multi-dimensional feature matrix, real-time performance indexes of the unit are obtained through feature dimensionality reduction and data fusion, and an AGC performance grade evaluation result is generated through an interval mapping method in combination with a quantitative threshold value of an evaluation result. The comprehensive utilization of the AGC control signal, the boiler combustion parameter, the steam turbine thermal parameter and the coal quality test data is realized, and the accuracy of the evaluation result is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system optimization, and particularly to a real-time evaluation method and system for AGC performance indicators based on multi-source data fusion. Background Art

[0002] With the rapid development of the power system and the continuous growth of the scale of new energy grid connection, the tasks of frequency modulation and peak regulation of the power grid are becoming increasingly onerous, and higher requirements are put forward for the automatic generation control (AGC) performance of thermal power units. As an important means of power system frequency control, the performance of the AGC system directly affects the safe and stable operation of the power grid. Therefore, it is of great significance to conduct real-time evaluation and optimization of AGC performance.

[0003] For the evaluation and optimization of AGC performance, traditional methods mainly rely on simple statistical analysis of historical operation data and model simulation based on fixed parameters; these methods usually take indicators such as the regulation time and regulation deviation of the unit as the core, and realize the preliminary evaluation of AGC performance through offline analysis. At the same time, some studies have also tried to combine on-site operation data and empirical knowledge to construct a data-driven analysis model to improve the diagnosis and optimization of AGC performance.

[0004] However, the existing AGC performance evaluation methods have problems such as single data source, one-sided evaluation indicators, and insufficient real-time performance; due to the failure to fully utilize multi-source heterogeneous data such as the DCS system, AGC system, and coal quality analysis, it is difficult to comprehensively reflect various factors affecting AGC performance; at the same time, the lack of in-depth mining and analysis of historical data makes it impossible to timely discover and warn of the deterioration trend of AGC performance, affecting the accuracy and guiding significance of the evaluation results.

[0005] Therefore, how to provide a solution that can realize real-time fusion and analysis of multi-source data and accurately evaluate AGC performance indicators has become an urgent problem to be solved at present. Summary of the Invention

[0006] Embodiments of the present invention provide a real-time evaluation method and system for AGC performance indicators based on multi-source data fusion to solve the problems of insufficient data utilization, single evaluation dimension, and insufficient real-time performance in the prior art.

[0007] To have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary part is not a general review, nor is it intended to identify key / important constituent elements or delineate the protection scope of these embodiments. Its sole purpose is to present some concepts in a simple form as a prelude to the subsequent detailed description.

[0008] According to the first aspect of the embodiments of the present invention, a real-time evaluation method for AGC performance indicators based on multi-source data fusion is provided.

[0009] In one embodiment, the real-time evaluation method for AGC performance indicators based on multi-source data fusion includes:

[0010] Based on a distributed data acquisition system, obtain the operating parameters of the unit under all operating conditions, and use a multi-factor weighted analysis and data quality evaluation algorithm for screening and correction to establish a multi-source heterogeneous data set;

[0011] Using the sliding time window method, perform feature decomposition of the multi-source heterogeneous data set at different time scales, and extract the performance feature vectors at each time scale to obtain a multi-dimensional feature matrix;

[0012] According to the multi-dimensional feature matrix, through feature dimensionality reduction and data fusion, obtain the real-time performance indicators of the unit, and combine the quantization threshold of the evaluation result, and use the interval mapping method to generate the AGC performance level evaluation result.

[0013] In one embodiment, the operating parameters of the unit under all operating conditions include AGC control signal data, boiler combustion parameters, steam turbine thermal parameters, and coal quality test data; the performance feature vectors at each time scale include the unit regulation ability feature vector, the unit operating state feature vector, and the unit adaptability feature vector.

[0014] In one embodiment, based on a distributed data acquisition system, obtain the operating parameters of the unit under all operating conditions, and use a multi-factor weighted analysis and data quality evaluation algorithm to screen and correct abnormal data, and establish a multi-source heterogeneous data set including:

[0015] Through the distributed data acquisition system, obtain the AGC control signal data, use the multi-factor weighted analysis of the AGC response characteristics, and perform outlier detection through the data quality evaluation algorithm to obtain the AGC control parameters of the unit;

[0016] According to the boiler combustion parameters and steam turbine thermal parameters, solve the boiler combustion state index and the steam turbine thermal state index, and combine the data compensation algorithm to repair the missing values to obtain the thermal operation parameters;

[0017] Based on the coal quality test data, use the comprehensive coal quality characteristics analysis and data smoothing algorithm for noise filtering to obtain the coal quality parameters, and integrate the AGC control parameters and thermal operation parameters of the unit to establish a multi-source heterogeneous data set.

[0018] In one embodiment, the AGC control signal data includes the AGC command value, the actual output of the unit, and the AGC response time;

[0019] The expression of the AGC control parameters of the unit is:

[0020] P a =w 1 ×(P s -Pr ) / P s + w 2 × T r / T s ;

[0021] In the formula, P s is the AGC command value; P r is the actual output of the unit; T r is the AGC response time; T s is the standard response time; w 1 and w 2 are the control deviation coefficient and the response time coefficient respectively.

[0022] In one embodiment, the boiler combustion parameters include the coal feeding amount and the furnace temperature, and the steam turbine thermal parameters include the main steam pressure and the main steam temperature;

[0023] The expression of the thermal operation parameter is:

[0024] P b = α × P c + β × P d ;

[0025] In the formula, P b is the thermal operation parameter, P c is the boiler combustion state index; P d is the steam turbine thermal state index; α and β are the boiler index weight and the steam turbine index weight respectively;

[0026] The expression of the boiler combustion state index is:

[0027] P c = k 1 × (F / F n ) + k 2 × (H / H n );

[0028] The expression of the steam turbine thermal state index is:

[0029] P d = k 3 × (L / L n ) + k 4 × (M / M n );

[0030] In the formula, F is the coal feeding amount; H is the furnace temperature; L is the main steam pressure; M is the main steam temperature; F n is the standard coal feeding amount at the full load of the unit; H n is the standard furnace temperature at the rated load of the boiler; L n is the standard main steam pressure at the rated load of the steam turbine; M nis the standard main steam temperature at the rated load of the steam turbine; k 1 and k 2 are respectively the coal feeding amount influence coefficient and the furnace temperature influence coefficient; k 3 and k 4 are respectively the steam pressure influence coefficient and the steam temperature influence coefficient.

[0031] In one embodiment, the coal quality test data includes the calorific value of coal, the moisture content, and the ash content;

[0032] The expression of the coal quality parameter is:

[0033] P e =λ 1 ×(Q / Q n )+λ 2 ×(1 - W / W m )+λ 3 ×(1 - A / A m );

[0034] In the formula, Q is the calorific value of coal; W is the moisture content; A is the ash content; Q n is the calorific value of the designed coal type; W m is the maximum allowable moisture content; A m is the maximum allowable ash content; λ 1 , λ 2 and λ 3 are respectively the calorific value characteristic coefficient, the moisture characteristic coefficient, and the ash characteristic coefficient.

[0035] In one embodiment, using the sliding time window method, the multi-source heterogeneous data set is decomposed into features at different time scales, and the performance feature vectors at each time scale are extracted to obtain a multi-dimensional feature matrix including:

[0036] Based on the minute-level sliding time window, dynamic features of the unit AGC control parameters are extracted to obtain the unit regulation ability feature vector;

[0037] Using the hour-level sliding time window, steady-state features of the thermal operation parameters are extracted to obtain the unit operation state feature vector;

[0038] According to the day-level sliding time window, trend features of the coal quality parameters are extracted to obtain the unit adaptability feature vector, and combined with the unit regulation ability feature vector and the unit operation state feature vector, a multi-dimensional feature matrix is constructed.

[0039] In one embodiment, according to the multi-dimensional feature matrix, through feature dimensionality reduction and data fusion, the real-time performance index of the unit is obtained, and combined with the quantization threshold of the evaluation result, the AGC performance level evaluation result is generated using the interval mapping method, including:

[0040] Based on the multi-dimensional feature matrix, the principal component analysis method is used for feature dimensionality reduction and data fusion to obtain the real-time performance indicators of the unit;

[0041] According to the historical operation data of the unit, the statistical analysis method is used to calculate the distribution characteristics of the performance indicators, and the grading evaluation criteria are determined by the standard deviation segmentation method to obtain the quantization threshold of the evaluation results;

[0042] Based on the real-time performance indicators of the unit, combined with the quantization threshold of the evaluation results, multi-level comparison is carried out, and the interval mapping method is used to generate the AGC performance level evaluation results.

[0043] In one embodiment, the real-time performance indicators of the unit include the unit regulation ability indicator, the unit operation status indicator, and the unit adaptability indicator;

[0044] The distribution characteristics of the performance indicators include the average value of the unit historical performance indicators and the standard deviation of the unit historical performance indicators.

[0045] According to the second aspect of the embodiments of the present invention, a real-time evaluation system for AGC performance indicators based on multi-source data fusion is provided.

[0046] In one embodiment, the real-time evaluation system for AGC performance indicators based on multi-source data fusion includes:

[0047] A data acquisition module, configured to obtain the full-condition operation parameters of the unit based on a distributed data acquisition system, and perform screening and correction using a multi-factor weighted analysis and data quality evaluation algorithm to establish a multi-source heterogeneous data set;

[0048] A feature extraction module, configured to use the sliding time window method to perform feature decomposition of the multi-source heterogeneous data set at different time scales, and extract the performance feature vectors at each time scale to obtain a multi-dimensional feature matrix;

[0049] A performance evaluation module, configured to obtain the real-time performance indicators of the unit through feature dimensionality reduction and data fusion according to the multi-dimensional feature matrix, and generate the AGC performance level evaluation results using the interval mapping method in combination with the quantization threshold of the evaluation results.

[0050] According to the third aspect of the embodiments of the present invention, a computer device is provided.

[0051] In one embodiment, the computer device includes a memory and a processor, and a computer program is stored in the memory. When the processor executes the computer program, the steps of the above method are implemented.

[0052] According to the fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided.

[0053] In one embodiment, a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0054] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0055] (1) The present invention obtains the full-condition operation parameters of the unit through a distributed data acquisition system, and uses a multi-factor weighted analysis and data quality assessment algorithm to establish a multi-source heterogeneous data set, realizing the comprehensive utilization of AGC control signals, boiler combustion parameters, steam turbine thermal parameters, and coal quality test data, overcoming the limitation of the single data source of the existing methods; at the same time, the sliding time window method is used to perform feature decomposition on the multi-source heterogeneous data set at three time scales of minutes, hours, and days, extract the feature vectors of the unit's regulation ability, operation state, and adaptability, and construct a multi-dimensional feature matrix, realizing a comprehensive assessment of various factors affecting AGC performance.

[0056] (2) The present invention performs dimensionality reduction and data fusion on the multi-dimensional feature matrix based on the principal component analysis method to obtain the real-time performance indicators of the unit, and combines the historical operation data of the unit. The grading evaluation criteria are determined by the standard deviation segmentation method, and the interval mapping method is used to generate the AGC performance grade evaluation result, realizing the in-depth mining and analysis of historical data, improving the accuracy and real-time performance of the evaluation result; by establishing a multi-level fusion evaluation system, it can not only reflect the AGC performance state of the unit in real time, but also timely discover and warn the performance degradation trend, providing an effective guiding basis for the operation optimization and maintenance decision-making of the unit.

[0057] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present invention, and are used together with the specification to explain the principles of the present invention.

[0059] Figure 1 is a schematic flowchart of a real-time evaluation method for AGC performance indicators based on multi-source data fusion shown according to an exemplary embodiment;

[0060] Figure 2 is a structural block diagram of a real-time evaluation system for AGC performance indicators based on multi-source data fusion shown according to an exemplary embodiment;

[0061] Figure 3 is a schematic structural diagram of a computer device shown according to an exemplary embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0062] The following description and the accompanying drawings fully disclose specific embodiments herein, enabling those skilled in the art to practice them. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments herein includes the entire scope of the claims and all available equivalents of the claims. In this document, terms such as "first," "second," etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the term "comprising," "including," or any other variant thereof is intended to cover non-exclusive inclusion, such that a structure, device, or apparatus comprising a series of elements not only includes those elements but also other elements not expressly listed, or elements inherent to such structure, device, or apparatus. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the structure, device, or apparatus comprising the element. The various embodiments herein are described in a progressive manner, with each embodiment highlighting the differences from other embodiments. The same or similar parts among the various embodiments can be referred to each other.

[0063] In this document, the orientation or positional relationships indicated by terms such as "longitudinal," "transverse," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," etc. are based on the orientation or positional relationships shown in the drawings. These are only for the convenience of describing this document and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation on the present invention. In the description herein, unless otherwise specified and defined, the terms "mounted," "connected," and "coupled" shall be understood in a broad sense. For example, it can be a mechanical connection or an electrical connection, or it can be the communication inside two elements. It can be directly connected or indirectly connected through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to specific circumstances.

[0064] In this document, unless otherwise stated, the term "plurality" means two or more.

[0065] In this document, the character " / " indicates that the objects before and after are in an "or" relationship. For example, A / B means: A or B.

[0066] In this document, the term "and / or" is a description of the associated relationship of an object, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B these three relationships.

[0067] It should be understood that although the steps in the flowchart are shown sequentially in the direction of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless specifically stated herein, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the figure may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential either, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0068] Each module in the device or system of the present application can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0069] Without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0070] Figure 1 An embodiment of the real-time evaluation method for AGC performance indicators based on multi-source data fusion of the present invention is shown.

[0071] In this alternative embodiment, the real-time evaluation method for AGC performance indicators based on multi-source data fusion includes:

[0072] Step S101: Based on the distributed data acquisition system, obtain the full-condition operation parameters of the unit, and perform screening and correction using the multi-factor weighted analysis and data quality evaluation algorithm to establish a multi-source heterogeneous data set;

[0073] Step S102: Use the sliding time window method to perform feature decomposition of the multi-source heterogeneous data set at different time scales, and extract the performance feature vectors at each time scale to obtain a multi-dimensional feature matrix;

[0074] Step S103: According to the multi-dimensional feature matrix, obtain the real-time performance indicators of the unit through feature dimension reduction and data fusion, and combine the quantization threshold of the evaluation result to generate the AGC performance level evaluation result using the interval mapping method.

[0075] In this alternative embodiment, the full-condition operation parameters of the unit include AGC control signal data, boiler combustion parameters, steam turbine thermal parameters, and coal quality test data; the performance feature vectors at each time scale include the unit regulation ability feature vector, the unit operation state feature vector, and the unit adaptability feature vector.

[0076] In this alternative embodiment, based on the distributed data acquisition system, the full-condition operation parameters of the unit are obtained. By using the multi-factor weighted analysis and data quality assessment algorithm, abnormal data is screened and corrected, and a multi-source heterogeneous data set is established, including:

[0077] Step S1011: Through the distributed data acquisition system, obtain the AGC control signal data, perform multi-factor weighted analysis on the AGC response characteristics, and detect outliers through the data quality assessment algorithm to obtain the AGC control parameters of the unit.

[0078] Step S1012: Collect the boiler combustion parameters and steam turbine thermal parameters, solve the boiler combustion state index and steam turbine thermal state index, and repair the missing values by combining the data compensation algorithm to obtain the thermal operation parameters.

[0079] Step S1013: Obtain the coal quality test data, perform noise filtering by using the comprehensive coal quality characteristics analysis and data smoothing algorithm to obtain the coal quality parameters, and integrate the AGC control parameters of the unit and the thermal operation parameters to establish a multi-source heterogeneous data set.

[0080] In this alternative embodiment, the AGC control signal data includes the AGC command value, the actual output of the unit, and the AGC response time.

[0081] The expression for the AGC control parameters of the unit is:

[0082] P a =w 1 ×(P s -P r ) / P s +w 2 ×T r / T s ;

[0083] In the formula, P s is the AGC command value; P r is the actual output of the unit; T r is the AGC response time; T s is the standard response time; w 1 and w 2 are the control deviation coefficient and the response time coefficient respectively, and w 1 +w 2 = 1.

[0084] In this alternative embodiment, the boiler combustion parameters include the coal feeding amount and the furnace temperature, and the steam turbine thermal parameters include the main steam pressure and the main steam temperature.

[0085] The expression for the thermal operation parameters is:

[0086] P b =α×P c+β×P d ;

[0087] Wherein, P b is the thermal operation parameter, P c is the boiler combustion state index; P d is the steam turbine thermal state index; α and β are the boiler index weight and the steam turbine index weight respectively, and α + β = 1;

[0088] The expression of the boiler combustion state index is:

[0089] P c = k 1 × (F / F n ) + k 2 × (H / H n );

[0090] The expression of the steam turbine thermal state index is:

[0091] P d = k 3 × (L / L n ) + k 4 × (M / M n );

[0092] Wherein, F is the coal feeding amount; H is the furnace temperature; L is the main steam pressure; M is the main steam temperature; F n is the standard coal feeding amount at the full load of the unit; H n is the standard furnace temperature at the rated load of the boiler; L n is the standard main steam pressure at the rated load of the steam turbine; M n is the standard main steam temperature at the rated load of the steam turbine; k 1 and k 2 are the coal feeding amount influence coefficient and the furnace temperature influence coefficient respectively, and k 1 + k 2 = 1; k 3 and k 4 are the steam pressure influence coefficient and the steam temperature influence coefficient respectively, and k 3 + k 4 = 1.

[0093] In this alternative embodiment, the coal quality test data includes the calorific value of coal, the moisture content and the ash content;

[0094] The expression of the coal quality parameter is:

[0095] P e = λ 1 × (Q / Q n ) + λ 2 × (1 - W / W m ) + λ 3×(1 - A / A m );

[0096] Wherein, Q is the calorific value of the coal quality; W is the moisture content; A is the ash content; Q n is the calorific value of the designed coal type; W m is the maximum allowable moisture content; A m is the maximum allowable ash content; λ 1 , λ 2 and λ 3 are respectively the calorific value characteristic coefficient, the moisture characteristic coefficient and the ash characteristic coefficient, and λ 1 + λ 2 + λ 3 = 1.

[0097] In this alternative embodiment, the sliding time window method is used to perform feature decomposition of the multi-source heterogeneous data set at different time scales, and the performance feature vectors at each time scale are extracted to obtain a multi-dimensional feature matrix including:

[0098] Step S1021: Based on the minute-level sliding time window, dynamic feature extraction is performed on the AGC control parameters of the unit to obtain the unit regulation ability feature vector;

[0099] Specifically, the expression of the unit regulation ability feature vector Va is:

[0100] V a = [P am , P as , P ax , P an ;

[0101] Wherein, P am is the mean value of the AGC control parameters of the unit within the minute-level time window; P as is the standard deviation; P ax is the maximum value; P an is the minimum value.

[0102] Step S1022: Using the hour-level sliding time window, steady-state feature extraction is performed on the thermal operation parameters to obtain the unit operation state feature vector;

[0103] Specifically, the expression of the unit operation state feature vector V b is:

[0104] V b = [P bm , P bv , P bt ;

[0105] Wherein, P bm is the mean value of the thermal operation parameters within the hour-level time window; P bvis the variance; P bt is the linear trend coefficient, obtained by least squares fitting.

[0106] Step S1023: Extract the trend characteristics of the coal quality parameters according to the daily sliding time window to obtain the unit adaptability feature vector, and combine the unit regulation ability feature vector and the unit operation state feature vector to construct a multi-dimensional feature matrix.

[0107] Specifically, the unit adaptability feature vector V c has the following expression:

[0108] Vc = [P em , P es , P er ;

[0109] In the formula, P em is the mean value of the coal quality parameters within the daily time window; P es is the change rate, calculated by the difference between adjacent time points; P er is the fluctuation range, equal to the difference between the maximum value and the minimum value.

[0110] Specifically, the expression of the multi-dimensional feature matrix V is:

[0111] V = [V a , V b , V c ;

[0112] = [P am , P as , P ax , P an

[0113] P bm , P bv , P bt , 0

[0114] P em , P es , P er , 0];

[0115] In the formula, to make the matrix dimensions consistent, 0 is appended after the V b and V c vectors to form a 3×4 feature matrix.

[0116] In this alternative embodiment, according to the multi-dimensional feature matrix, by feature dimensionality reduction and data fusion, the real-time performance index of the unit is obtained, and combined with the quantization threshold of the evaluation result, the AGC performance level rating result is generated using the interval mapping method, including:

[0117] Step S1031: Based on the multi-dimensional feature matrix, use the principal component analysis method for feature reduction and data fusion to obtain the real-time performance index of the unit.

[0118] Specifically, the calculation formula for the real-time performance index I of the unit is: I = V × U;

[0119] In the formula, V is the multi-dimensional feature matrix; U is the principal component feature vector matrix.

[0120] I = [I g , I s , I a ;

[0121] In the formula, I g is the unit regulation ability index, which is obtained by weighted calculation of the principal component contribution of the V a vector, reflecting the response ability of the unit to the AGC command; I s is the unit operation status index, which is obtained by weighted calculation of the principal component contribution of the V b vector, characterizing the operation stability of the unit's thermal system; I a is the unit adaptability index, which is obtained by weighted calculation of the principal component contribution of the V c vector, reflecting the adaptability of the unit to coal quality changes. The calculation of each index takes into account the relative importance of each parameter in the corresponding feature vector, and the eigenvalue obtained by principal component analysis is used as the weight coefficient.

[0122] Step S1032: According to the historical operation data of the unit, use the statistical analysis method to calculate the distribution characteristics of the performance index, and determine the grading evaluation standard through the standard deviation segmentation method to obtain the quantization threshold of the evaluation result.

[0123] Specifically, the expression of the quantization threshold T is:

[0124] T = [T 1 , T 2 , T 3 , T 4 ;

[0125] T 1 = μ + 1.5σ;

[0126] T 2 = μ + 0.5σ;

[0127] T 3 = μ - 0.5σ;

[0128] T 4 = μ - 1.5σ;

[0129] In the formula, μ is the average value of the unit's historical performance index; σ is the standard deviation of the unit's historical performance index.

[0130] Step S1033: Based on the real-time performance indicators of the unit, perform multi-level comparison in combination with the quantization threshold of the evaluation result, and use the interval mapping method to generate the AGC performance level evaluation result.

[0131] Specifically, the determination rule for the AGC performance level evaluation result G is as follows:

[0132] When I ≥ T 1 then G = 1 (excellent);

[0133] When T 2 ≤ I < T 1 then G = 2 (good);

[0134] When T 3 ≤ I < T 2 then G = 3 (qualified);

[0135] When T 4 ≤ I < T 3 then G = 4 (unqualified);

[0136] When I < T 4 then G = 5 (deteriorated).

[0137] In this alternative embodiment, the real-time performance indicators of the unit include the unit regulation ability indicator, the unit operation status indicator, and the unit adaptability indicator;

[0138] The distribution characteristics of the performance indicators include the average value of the unit historical performance indicators and the standard deviation of the unit historical performance indicators.

[0139] Figure 2 Fig. shows an embodiment of the AGC performance indicator real-time evaluation system based on multi-source data fusion of the present invention.

[0140] In this alternative embodiment, the AGC performance indicator real-time evaluation system based on multi-source data fusion includes:

[0141] A data acquisition module 201, configured to obtain the full-condition operation parameters of the unit based on a distributed data acquisition system, and perform screening and correction using a multi-factor weighted analysis and data quality evaluation algorithm to establish a multi-source heterogeneous data set;

[0142] A feature extraction module 202, configured to perform feature decomposition of the multi-source heterogeneous data set at different time scales using a sliding time window method, and extract the performance feature vectors at each time scale to obtain a multi-dimensional feature matrix;

[0143] The performance evaluation module 203 is used to obtain the real-time performance indicators of the unit through feature dimension reduction and data fusion based on the multi-dimensional feature matrix, and generate the AGC performance level evaluation result by using the interval mapping method in combination with the quantization threshold of the evaluation result.

[0144] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as Figure 3 shown. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.

[0145] Those skilled in the art can understand that Figure 3 the structure shown in

[0146] is only a block diagram of some structures related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0147] In addition, the present invention also provides a computer device including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiment are implemented.

[0148] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0149] The present invention is not limited to the structures already described and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A real-time evaluation method of AGC performance indicators based on multi-source data fusion, characterized in that: The AGC performance indicator real-time evaluation method based on multi-source data fusion includes: Based on the distributed data acquisition system, the full-condition operating parameters of the unit are obtained, and multi-factor weighted analysis and data quality assessment algorithms are used for screening and correction to establish a multi-source heterogeneous data set; Using the sliding time window method, the multi-source heterogeneous data sets are decomposed into features at different time scales, and the performance feature vectors at each time scale are extracted to obtain a multi-dimensional feature matrix. According to the multi-dimensional feature matrix, the real-time performance indicators of the unit are obtained through feature dimensionality reduction and data fusion. Combined with the quantitative threshold of the evaluation result, the interval mapping method is used to generate the AGC performance level evaluation result.

2. The AGC performance index real-time evaluation method based on multi-source data fusion according to claim 1 is characterized in that: The full-condition operating parameters of the unit include AGC control signal data, boiler combustion parameters, turbine thermal parameters and coal quality test data; The performance characteristic vectors at each time scale include a unit regulation capability characteristic vector, a unit operation status characteristic vector and a unit adaptability characteristic vector.

3. The AGC performance index real-time evaluation method based on multi-source data fusion according to claim 1 is characterized in that: The distributed data acquisition system is used to obtain the full-condition operating parameters of the unit, and a multi-factor weighted analysis and data quality assessment algorithm are used to screen and correct abnormal data to establish a multi-source heterogeneous data set, including: The AGC control signal data is obtained through the distributed data acquisition system, and the multi-factor weighted analysis of the AGC response characteristics is adopted. The abnormal value detection is performed through the data quality assessment algorithm to obtain the unit AGC control parameters; According to the boiler combustion parameters and the steam turbine thermal parameters, the boiler combustion state index and the steam turbine thermal state index are solved, and the missing values ​​are repaired by combining the data compensation algorithm to obtain the thermal operation parameters; Based on the coal quality test data, the comprehensive coal quality characteristics analysis and data smoothing algorithm are used to filter the noise to obtain the coal quality parameters. The AGC control parameters and thermal operation parameters of the unit are integrated to establish a multi-source heterogeneous data set.

4. The AGC performance index real-time evaluation method based on multi-source data fusion according to claim 3 is characterized in that: The AGC control signal data includes the AGC command value, the actual output of the unit and the AGC response time; The expression of the AGC control parameter of the unit is: P a =w1×(P s -P r ) / P s +w2×T r / T s ; Where P s is the AGC command value; P r The actual output of the unit; T r is the AGC response time; T s is the standard response time; w1 and w2 are the control deviation coefficient and response time coefficient respectively.

5. The AGC performance index real-time evaluation method based on multi-source data fusion according to claim 3 is characterized in that: The boiler combustion parameters include coal feed rate and furnace temperature, and the turbine thermal parameters include main steam pressure and main steam temperature; The expression of the thermal operation parameter is: P b =α×P c +β×P d ; Where P b is the thermal operation parameter, P c It is the boiler combustion status index; P d is the thermal state index of the steam turbine; α and β are the boiler index weight and the steam turbine index weight respectively; The expression of the boiler combustion state index is: P c =k1×(F / F n )+k2×(H / H n ); The expression of the steam turbine thermal state index is: P d =k3×(L / L n )+k4×(M / M n ); In the formula, F is the coal feed rate; H is the furnace temperature; L is the main steam pressure; M is the main steam temperature; F n is the standard coal supply when the unit is at full load; H n L is the standard furnace temperature of the boiler at rated load; n M is the standard main steam pressure at rated load of the steam turbine; n is the standard main steam temperature at rated load of the steam turbine; k1 and k2 are the influence coefficient of coal feed rate and furnace temperature respectively; k3 and k4 are the influence coefficient of steam pressure and steam temperature respectively.

6. The AGC performance index real-time evaluation method based on multi-source data fusion according to claim 3 is characterized in that: The coal quality test data include coal calorific value, moisture content and ash content; The expression of the coal quality parameter is: P e =λ1×(Q / Q n )+λ2×(1-W / W m )+λ3×(1-A / A m ); In the formula, Q is the calorific value of coal; W is the moisture content; A is the ash content; Q n W is the calorific value of the designed coal; m is the maximum allowable moisture content; A m is the maximum allowable ash content; λ1, λ2 and λ3 are the calorific value characteristic coefficient, moisture characteristic coefficient and ash characteristic coefficient respectively.

7. The AGC performance index real-time evaluation method based on multi-source data fusion according to claim 1 is characterized in that: The sliding time window method is used to perform feature decomposition of multi-source heterogeneous data sets at different time scales, and the performance feature vectors at each time scale are extracted to obtain a multi-dimensional feature matrix including: Based on the minute-level sliding time window, the dynamic features of the unit AGC control parameters are extracted to obtain the unit regulation capability feature vector; Using the hourly sliding time window, the steady-state characteristics of thermal operation parameters are extracted to obtain the unit operation state characteristic vector; According to the daily sliding time window, the trend characteristics of coal quality parameters are extracted to obtain the unit adaptability characteristic vector. The multi-dimensional characteristic matrix is ​​constructed by combining the unit regulation capacity characteristic vector and the unit operation status characteristic vector.

8. The AGC performance index real-time evaluation method based on multi-source data fusion according to claim 1 is characterized in that: The method of obtaining the real-time performance index of the unit by feature dimension reduction and data fusion according to the multi-dimensional feature matrix, and generating the AGC performance level evaluation result by using the interval mapping method in combination with the quantitative threshold of the evaluation result includes: Based on the multi-dimensional feature matrix, the principal component analysis method is used to perform feature dimension reduction and data fusion to obtain the real-time performance indicators of the unit; Based on the historical operation data of the unit, the distribution characteristics of the performance indicators are calculated using statistical analysis methods, and the grading evaluation standards are determined through the standard deviation segmentation method to obtain the quantitative threshold of the evaluation results; Based on the real-time performance indicators of the unit, multi-level comparison is carried out in combination with the quantitative threshold of the evaluation results, and the interval mapping method is used to generate the AGC performance level assessment results.

9. The method for real-time evaluation of AGC performance indicators based on multi-source data fusion according to claim 8, characterized in that: The real-time performance indicators of the unit include the unit regulation capability indicator, the unit operation status indicator and the unit adaptability indicator; The distribution characteristics of the performance indicators include an average value of the historical performance indicators of the unit and a standard deviation of the historical performance indicators of the unit.

10. AGC performance index real-time evaluation system based on multi-source data fusion, characterized in that: The AGC performance index real-time evaluation system based on multi-source data fusion includes: The data acquisition module is used to obtain the full-condition operating parameters of the unit based on the distributed data acquisition system, and uses multi-factor weighted analysis and data quality assessment algorithms to screen and correct them to establish a multi-source heterogeneous data set; The feature extraction module is used to perform feature decomposition of multi-source heterogeneous data sets at different time scales using a sliding time window method, and extract the performance feature vectors at each time scale to obtain a multi-dimensional feature matrix; The performance evaluation module is used to obtain the real-time performance indicators of the unit based on the multi-dimensional feature matrix through feature dimension reduction and data fusion, and generate the AGC performance level evaluation results using the interval mapping method in combination with the quantitative threshold of the evaluation results.

Images