A method and system for optimizing operation of a thermal power unit based on energy efficiency optimization

Abstract

The application discloses a kind of based on energy efficiency optimization of thermal power unit operation optimization method and system, method includes: real-time acquisition thermal power unit operating data, screening thermal power unit is in steady-state operating condition energy efficiency index operating data, obtain data set;Thermal power unit operating condition is divided, and the data set under steady-state operating condition is divided into corresponding data subset, in each data subset, according to energy efficiency high and low as energy efficiency index is given corresponding weight value;Weighted support vector machine model is trained using data subset, parameter optimization is carried out in training process according to the weight value of energy efficiency index;New data subset is input into trained weighted support vector machine model, obtain the optimal value of energy efficiency index under corresponding operating condition, with the optimal value of energy efficiency index as benchmark, real-time evaluation is carried out to energy efficiency index, and thermal power unit operation is adjusted according to evaluation result.The application can obtain relatively accurate energy efficiency optimal value of thermal power unit, and realize the operation optimization of thermal power unit accordingly.

Description

TECHNICAL FIELD

[0001] The present application relates to power generation unit operation optimization technology, in particular to a method and system for optimizing the operation of a thermal power generation unit based on energy efficiency. BACKGROUND

[0002] With the construction of new power systems, new energy installations continue to increase, and most thermal power units are in a long-term peak shaving operation state, resulting in increased energy consumption and increased energy saving and efficiency.

[0003] Currently, for most thermal power units, operation optimization still completely relies on the operating experience of personnel, and the main parameters of the unit are optimized and adjusted by the operating personnel according to the unit operating conditions, but the optimization effect of this method completely depends on personal experience and cognitive level, and the optimization effect cannot be accurately measured; some scholars use the operation data of thermal power units to self-optimize specific indicators that affect the energy efficiency of the unit (such as flue gas oxygen content, heater end difference), etc., and guide the operating personnel to optimize and adjust by means of deviation warning of energy efficiency indicators, but this method does not consider the overall energy efficiency level of the unit; some scholars use clustering analysis to obtain the minimum value of the energy efficiency index in the clustering center as the evaluation reference value, but if the unit is in a non-energy efficiency optimal state during daily operation, the energy efficiency reference value obtained by this method has deviated from the actual optimal value. SUMMARY

[0004] The technical problem to be solved by the present application is to provide a method and system for optimizing the operation of a thermal power unit based on energy efficiency, which establishes the optimal value of the energy efficiency of a thermal power unit through data analysis, and realizes the operation optimization of the thermal power unit, and improves the energy efficiency of the unit.

[0005] To solve the above technical problems, the technical scheme adopted by the present application is:

[0006] A method for optimizing the operation of a thermal power unit based on energy efficiency, comprising the following steps:

[0007] Real-time acquisition of thermal power unit operation data, screening of operation data of specified energy efficiency indicators of the thermal power unit in steady state, and obtaining a data set in steady state;

[0008] Dividing the operating conditions of the thermal power unit, and dividing the data set in steady state into corresponding data subsets according to the division results, and assigning corresponding weight values to the energy efficiency indicators in each data subset according to the energy efficiency level;

[0009] training the weighted support vector machine model using the data subset, so that the trained weighted support vector machine model predicts the optimal value of the energy efficiency index under each working condition and outputs, and the weighted support vector machine model is parameter optimized according to the weight value of the energy efficiency index during the training process;

[0010] inputting the new data subset into the trained weighted support vector machine model to obtain the optimal value of the energy efficiency index under the corresponding working condition, taking the optimal value of the energy efficiency index as a benchmark to evaluate the energy efficiency index in real time, and adjusting the operation of the thermal power unit according to the evaluation result.

[0011] Further, when screening the operation data of the energy efficiency index selected under the steady state working condition of the thermal power unit, the following steps are included:

[0012] specifying at least one characteristic parameter in the specified energy efficiency index;

[0013] collecting the operation data in the current time window, and obtaining the maximum value of the operation data of each characteristic parameter in the current time window and the minimum value

[0014] obtaining the maximum value y of the operation data of each characteristic parameter in all time windows i,max and the minimum value y i,min ;

[0015] judging whether the difference between the maximum value and the minimum value of each characteristic parameter is less than or equal to the difference between the maximum value y i,max and the minimum value y i,min ;

[0016] If the difference is less than or equal to the preset threshold value, the operation data in the current time window is added to the data set under the steady state working condition, and the current time window is moved backward by a specified time span, and the step of collecting the operation data in the current time window is executed again.

[0017] If the difference between the maximum value and the minimum value of at least one characteristic parameter is greater than the difference between the maximum value y i,max and the minimum value y i,min , the current time window is moved backward by one sampling time, and the step of collecting the operation data in the current time window is executed again.

[0018] Further, the thermal power unit working condition is divided by taking the unit load, the environmental temperature and the coal quality as the boundary conditions.

[0019] Further, the energy efficiency indicators include energy efficiency indicators of each subsystem of the thermal power generating unit and a comprehensive energy efficiency indicator of the thermal power generating unit, and the parameter vector of each data sample in the data subset includes a parameter vector formed by the energy efficiency indicators of all the subsystems of the data sample and the comprehensive energy efficiency indicator of the thermal power generating unit, and when each data subset is assigned with corresponding weight values according to the energy efficiency indicators from high to low, the following is included:

[0020] According to the order from high to low of the comprehensive energy efficiency indicators, the corresponding label values are calculated by using a linear interpolation algorithm, and then the parameter vector of each data sample in the data subset is assigned with a corresponding label value as a weight value.

[0021] Further, the weighted support vector machine model takes the parameter vector formed by the energy efficiency indicators of all the subsystems as an input and takes the comprehensive energy efficiency indicator as an output, and the expression is as follows:

[0022]

[0023] Wherein, is a nonlinear mapping function, ω is a weight vector, b is a bias, ξ i , is a slack variable; ε is an insensitive loss function parameter, C is a penalty coefficient; s i ,t i respectively represent the weighting coefficients of the i th data sample in the data subset to the parameters C and ε, 0≤s i ,t i ≤1; wherein s i is the weight value of the i th data sample; N l represents the number of data samples in the data subset, x i represents the parameter vector formed by the energy efficiency indicators of all the subsystems of the i th data sample in the data subset, y i represents the comprehensive energy efficiency indicator of the i th data sample in the data subset.

[0024] Further, when the energy efficiency indicators are evaluated in real time based on the optimal value of the energy efficiency indicators, the following is included:

[0025] The running data of the energy efficiency indicators of the specified working condition at the current time is normalized to obtain the current value of the energy efficiency indicators of the specified working condition;

[0026] The deviation and the deviation change rate of the current value and the optimal value of the energy efficiency indicators of the specified working condition are calculated, and the real-time quantitative evaluation value of the energy efficiency indicators of the specified working condition is calculated according to the deviation and the deviation change rate.

[0027] Further, the real-time quantitative evaluation value is expressed as follows:

[0028]

[0029] wherein, E i (k) is the deviation of the current value and the optimal value of the i th energy efficiency index, (k) is the deviation of the current value and the optimal value of the i th energy efficiency index,

[0030] Further, the method further comprises: if the real-time quantitative evaluation value of the energy efficiency index of the specified working condition is less than a specified value, adjusting the operation state of the thermal power unit according to the deviation between the optimal value and the current value of the energy efficiency index of the specified working condition.

[0031] The application further provides a thermal power unit operation optimization system based on energy efficiency optimization, comprising a microprocessor and a computer readable storage medium connected to each other, wherein the microprocessor is programmed or configured to execute any one of the thermal power unit operation optimization methods based on energy efficiency optimization.

[0032] The application further provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is used to program or configure the microprocessor to execute any one of the thermal power unit operation optimization methods based on energy efficiency optimization.

[0033] Compared with the prior art, the application has the following advantages:

[0034] The application performs "labeling" processing on the operation data, that is, higher weights are given to the data with high energy efficiency, and lower weights are given to the data with low energy efficiency, and the weighted support vector machine model is trained by using the processed operation data, so that the trained model can reflect the optimal energy efficiency of the unit.

[0035] The application takes the optimal value of the energy efficiency index output by the trained weighted support vector machine model as a benchmark, and comprehensively judges the deviation and the change rate of the deviation of the normalized energy efficiency index from the optimal value, so as to realize real-time quantitative evaluation of the energy efficiency index, and the evaluation method is simple, the calculation workload is small, and the method is convenient for engineering application. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 The figure is a method flowchart of an embodiment of the application.

[0037] Figure 2 The figure is a division diagram of the deviation and the change rate of the deviation of the normalized i th energy efficiency index in an embodiment of the application.

[0038] Figure 3 The figure is the change trend of the main steam pressure of the thermal power unit and the evaluation result of the energy efficiency index under a certain working condition in an embodiment of the application. DETAILED DESCRIPTION

[0039] The application will be further described in conjunction with the accompanying drawings and specific preferred embodiments, but the protection scope of the application is not limited thereby.

[0040] Embodiment one

[0041] The embodiment proposes a thermal power unit operation optimization method based on energy efficiency optimization. The optimal value of energy efficiency index of the unit under each working condition is obtained by data analysis and nonlinear modeling method using the operation data of the thermal power unit. In the operation process of the unit, the real-time evaluation of each energy efficiency index of the thermal power unit is carried out by comparing the current energy efficiency index with its optimal value according to the deviation and its deviation change rate, thereby providing guidance for the optimized operation of the thermal power unit.

[0042] As shown in Figure 1 , the method of the embodiment comprises the following steps:

[0043] S101, selecting the energy efficiency index of the thermal power unit, thereby determining the energy efficiency index set of the thermal power unit; obtaining the operation data of the thermal power unit in real time, and screening the operation data of the selected energy efficiency index of the thermal power unit under the steady state working condition from the operation data, thereby obtaining the data set Ω under the steady state working condition;

[0044] S102, dividing the operation working condition of the thermal power unit, and dividing the data set Ω under the steady state working condition into corresponding data subsets Ω l according to the division result; assuming that it can be divided into m working conditions, for the obtained data set Ω under the steady state working condition, it is divided into m data subsets Ω l (l=1, 2, …, m); the data samples of each data subset are processed by "labeling", and the "labeling" processing specifically means that the corresponding weight value is given to the energy efficiency index according to the energy efficiency level;

[0045] S103, using weighted support vector machine to establish the energy efficiency index model of the thermal power unit under each working condition, training the model using the data subsets, and optimizing the parameters according to the weight value of the energy efficiency index in the training process, so that the trained weighted support vector machine model predicts the optimal value of the energy efficiency index under each working condition and outputs, thereby obtaining the optimal value of the energy efficiency index according to the model;

[0046] S104, taking the optimal value of the energy efficiency index as a benchmark, real-time evaluation is performed on the current value of the energy efficiency index to provide a reference for the optimized operation of the unit, specifically, according to steps S101 and S102, real-time acquisition is performed on the operation data of the thermal power unit under one or more working conditions, and the operation data of the energy efficiency index under stable working conditions is screened out, then one or more data subsets corresponding to the working conditions are obtained according to the working condition division result, then the new data subset is input into the trained weighted support vector machine model to obtain the optimal value of the energy efficiency index under the corresponding working condition, and the energy efficiency index in the new data subset is evaluated in real time based on the optimal value of the energy efficiency index, and the subsequent operation of the thermal power unit is adjusted according to the evaluation result.

[0047] In the following, a 660 MW ultra-supercritical thermal power unit is taken as an object, and the unit operation optimization based on energy efficiency optimization is performed according to the above steps, and each step is described in detail.

[0048] In step S101 of this embodiment, when determining the energy efficiency index set of the thermal power unit, the thermal system of the thermal power unit is divided into a boiler and its auxiliary system, and a steam turbine and its auxiliary system. Among them, the boiler and its auxiliary system is further divided into three subsystems of the boiler body, the air and smoke system and the coal pulverizing system; the steam turbine and its auxiliary system is further divided into three subsystems of the steam turbine body, the regenerative system and the cold end system. So that the energy efficiency index includes the energy efficiency index of each subsystem of the thermal power unit and the comprehensive energy efficiency index of the thermal power unit.

[0049] In this embodiment, the energy efficiency index of each subsystem is determined according to the mechanism model of the process flow and equipment of the thermal power unit as shown in Table 1; and the coal consumption rate for power supply is used as the comprehensive energy efficiency index representing the overall energy efficiency of the unit.

[0050] Table 1 Energy efficiency index of each subsystem of the thermal power unit

[0051]

[0052] The energy efficiency index in Table 1 is directly obtained by collecting the operation data of the thermal power unit, or obtained by calculation according to the standards such as “Performance Test Code for Utility Boilers” (GB / T-10184) and “Calculation Method of Technical and Economic Indicators for Thermal Power Plants” (DL / T-904).

[0053] In step S101 of this embodiment, when screening the operation data of the selected energy efficiency index of the thermal power unit under stable working conditions, the following steps are included:

[0054] S201, determine the time span, and specify at least one characteristic parameter in the selected energy efficiency index; in this embodiment, the time span t=10min is determined to judge whether the thermal power unit is in a stable state; and the unit power, the main steam temperature and the main steam pressure are selected as the characteristic parameters;

[0055] S202, collect the running data within the current time window, and obtain the maximum value of the running data for each characterizing parameter within the current time window. and minimum value In this embodiment, based on the real-time acquired thermal power unit operation data, the starting point and ending point of the data with a time span of t are determined, forming a data set within that time period;

[0056] S203, obtain the maximum value y of each characterization parameter in the running data over all time windows. i,max With minimum value y i,min Determine the maximum value of each characterization parameter. and minimum value The difference between the maximum value y and the maximum value y i,max With minimum value y i,min Whether the differences are all less than or equal to a preset threshold; in this embodiment, the following formula is used to determine whether the unit is in a stable state within a time window:

[0057]

[0058] In equation (1), and The i-th representation parameter y i The maximum and minimum values ​​of y within a time window i,max and y i,min The i-th representation parameter y i The maximum and minimum values ​​across all time windows, where δ is a preset threshold percentage; in this embodiment, δ = 0.5%.

[0059] S204, if all values ​​are less than or equal to the preset threshold, add the operating data in the current time window to the data set under steady-state conditions, and move the current time window backward by a specified time span, and execute the step of collecting the operating data in the current time window again; in this embodiment, if equation (1) is true, it is determined that the unit is in a stable state in the current time window, and the dataset in the current time window is retained; then the start and end points of the time window are moved backward by a time span t to obtain a new time window and jump to execute step S202; otherwise, execute step S205;

[0060] S205, if the maximum value of at least one characterization parameter and minimum value The difference between the maximum value y and the maximum value y i,max With minimum value y i,min If the difference is greater than the preset threshold, the current time window will be moved forward by one sampling time to obtain a new time window, and the process will jump to step S202 to collect the running data within the current time window again.

[0061] Step S102 of the embodiment specifically includes:

[0062] S301, the operating conditions of the thermal power unit are divided, in the embodiment, the operating conditions of the thermal power unit are divided by taking the unit load, the ambient temperature and the coal quality as the boundary conditions, the operating condition range and the division standard are shown in Table 2.

[0063] Table 2: Division of the operating conditions of the thermal power unit

[0064]

[0065] According to Table 2, the operating conditions of the thermal power unit are divided into 132 operating conditions, therefore, the data set Ω obtained in step S101 under the steady state operating conditions is divided into 132 data subsets Ω l (l = 1, 2, …, 132);

[0066] S302, the parameter vector of each data subset is constructed. For the data subset Ω l , it is assumed that the number of data samples contained is N l . It is set that the energy efficiency indexes of each subsystem of the boiler and its auxiliary system, the steam turbine and its auxiliary system jointly constitute the parameter vector x, and the comprehensive energy efficiency index of the thermal power unit is b, then the data subset can constitute the parameter vectors z l =(x i ,b i )(i = 1, 2, …, N l ) of N i data samples, that is, the parameter vector z i of each thermal power unit sample in the data subset contains the parameter vector x i composed of the energy efficiency indexes of all subsystems of the data sample and the comprehensive energy efficiency index b of the data sample.

[0067] S303, in each data subset, the corresponding weight value is given to the energy efficiency index according to the energy efficiency from high to low, specifically, the corresponding label value η i (0≤η i ≤1.0) is calculated by using the linear interpolation algorithm according to the order of the comprehensive energy efficiency index b i from high to low, and then the parameter vector z i of each data sample is respectively given the corresponding label value η i as the weight value.

[0068] In this embodiment, the comprehensive energy efficiency index is divided into four categories—good, average, and poor—based on expert scoring. In the "good" category, the label coefficient ranges from 0.8 to 1.0; in the "good" category, it ranges from 0.6 to 0.8; in the "average" category, it ranges from 0.4 to 0.6; and in the "poor" category, it ranges from 0.0 to 0.4.

[0069] Based on the parameter vector z i Comprehensive Energy Efficiency Index b i The classification allows us to determine the parameter vector z. i The label value is located within the label coefficient range, and then the specific label value can be obtained through a linear interpolation algorithm. The relevant calculation process is well known to those skilled in the art, and the specific calculation process will not be described in detail in this embodiment.

[0070] In step S103 of this embodiment, the weighted support vector machine model takes the parameter vector x, which is composed of the energy efficiency indices of all subsystems in the data subset, as input, and the comprehensive energy efficiency index b in the data subset as output. The expression is as follows:

[0071]

[0072] in, Let ω be a nonlinear mapping function, b be the weight vector, and ξ be the bias. i , ε is a slack variable; C is a penalty coefficient; s i t i Let s and ε represent the weighting coefficients of the i-th data sample in the data subset with respect to parameters C and ε, respectively, where 0 ≤ s i ,t i ≤1; where s i Determined by the label coefficients of the data samples, it is the weight value of the i-th data sample; N l x represents the number of data samples contained in the data subset. i y represents the parameter vector formed by the energy efficiency indices of all subsystems in the i-th data sample of the data subset. i This represents the comprehensive energy efficiency index of the i-th data sample in the data subset.

[0073] In step S104 of this embodiment, when evaluating the energy efficiency index in real time based on the optimal value of the energy efficiency index, the following steps are included:

[0074] S501, normalize the current operating data of the energy efficiency index under the specified operating condition to obtain the current value of the energy efficiency index under the specified operating condition.

[0075] S501, calculate the deviation and the deviation change rate of the current value and the optimal value of the energy efficiency index of the specified working condition, and calculate the real-time quantitative evaluation value of the energy efficiency index of the specified working condition according to the deviation and the deviation change rate.

[0076] In this embodiment, at a certain working condition point, the deviation E i (k) of the current value and the optimal value of the i th energy efficiency index x At the k th moment, the deviation E i (k) and the deviation change rate of the current value and the optimal value of the i th energy efficiency index of the new data subset after normalization can be expressed as:

[0077]

[0078] In the above formula, are the maximum value and the minimum value in the running data of the i th energy efficiency index x i , and x i (k) respectively represent the optimal value and the normalized current value of the i th energy efficiency index x i . i , The value diagram is shown in Figure 2 . As can be seen from Figure 2 , by formula (3) and formula (4), the deviation and the deviation change rate of the process value and the optimal value of the energy efficiency index can be uniformly attributed to the range of (-1, 1), which can not only reflect the positive and negative effects of the deviation and the deviation change rate, but also avoid the influence of different energy efficiency indexes on the evaluation results due to different dimensions. For example, when the deviation of the optimal value and its process value is negative, but the deviation change rate is positive, it means that the deviation is tending to eliminate, so the evaluation score should be higher; otherwise, the deviation is tending to expand, so the evaluation score should be lower.

[0079] Correspondingly, the real-time quantitative evaluation value expression is as follows:

[0080]

[0081] Wherein, E i (k) is the deviation of the current value and the optimal value of the i th energy efficiency index, is the deviation change rate of the current value and the optimal value of the i th energy efficiency index.

[0082] Under a certain working condition, the main steam pressure is evaluated in real time according to the above formula, and the evaluation result is shown in Figure 3As shown, it can be seen that when the real-time data of the main steam pressure is close to or equal to the reference value, the evaluation result is higher, and vice versa, when the real-time data of the main steam pressure is far from the reference value or exceeds the reference value by a large margin, the evaluation result is lower.

[0083] Based on the influence of the deviation between the real-time data and the optimal value of the energy efficiency index on the evaluation result, in the embodiment, adjusting the operation of the thermal power generating unit according to the evaluation result comprises: if the real-time quantitative evaluation value of the energy efficiency index of the specified working condition is less than the specified value, adjusting the operation state of the thermal power generating unit according to the deviation between the optimal value and the current value of the energy efficiency index of the specified working condition.

[0084] Specifically, if the real-time quantitative evaluation value of the energy efficiency index is greater than the specified value, it indicates that the actual value of the energy efficiency index under the working condition has approached the optimal value, and therefore the operation state of the thermal power generating unit does not need to be adjusted; on the contrary, if the real-time quantitative evaluation value of the energy efficiency index is less than the specified value, it indicates that there is still a large gap between the actual value and the optimal value of the energy efficiency index under the working condition, and therefore the operation state of the thermal power generating unit can be adjusted according to the deviation between the two values, for example, if the real-time quantitative evaluation value of the energy efficiency index of a certain subsystem is less than the specified value, the operation state of the corresponding subsystem of the thermal power generating unit is adjusted according to the deviation between the optimal value and the current value, and if the real-time quantitative evaluation value of the comprehensive energy efficiency index is less than the specified value, the operation state of multiple subsystems of the thermal power generating unit is adjusted according to the deviation between the optimal value and the current value. How to adjust the operation state of the thermal power generating unit according to the deviation between the actual value and the optimal value is known to those skilled in the art, and the embodiment will not repeat the specific implementation process.

[0085] Embodiment Two

[0086] The embodiment proposes a thermal power generating unit operation optimization system based on energy efficiency optimization, which comprises a microprocessor and a computer readable storage medium connected to each other, and the microprocessor is programmed or configured to execute the thermal power generating unit operation optimization method based on energy efficiency optimization described in Embodiment One.

[0087] The embodiment also proposes a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is used to program or configure the microprocessor to execute the thermal power generating unit operation optimization method based on energy efficiency optimization described in Embodiment One.

[0088] In summary, the application discloses a thermal power unit operation optimization method and system based on energy efficiency optimization, the operation data of the energy efficiency index is subjected to "labeling" processing, that is, higher weight values are given to the data with high energy efficiency, and lower weight values are given to the data with low energy efficiency, and meanwhile, the energy efficiency index model is established through training of the weighted support vector machine, so that the established energy efficiency index model can obtain the optimal benchmark value of the energy efficiency index under each working condition, the energy efficiency optimal value obtained is more general, and the energy efficiency index model avoids the defects that the optimal value of the energy efficiency index obtained by the conventional clustering algorithm is affected by "data volume" and deviates from the actual optimal value, and the optimal value of the energy efficiency obtained is more general. The application also quantitatively evaluates the normalized energy efficiency index and the deviation and the change rate of the deviation of the optimal value in real time, the evaluation method is simple, the calculation workload is small, and the engineering application is facilitated.

[0089] Those skilled in the art will appreciate that embodiments of the application can be supplied as methods, systems, or computer program products. Accordingly, the application can be embodied in the form of complete hardware embodiments, complete software embodiments, or embodiments combining software and hardware aspects. Furthermore, the application can take the form of a computer program product embodied on one or more computer readable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) having computer usable program code embodied thereon. The application is described herein with reference to flowchart and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and / or block of the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing system, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowcharts and / or block diagrams block or blocks. Figure 1 The flowchart and / or block diagram block or blocks Figure 1 The flowchart and / or block diagram block or blocks Figure 1 The flowchart and / or block diagram block or blocks Figure 1 The flowchart and / or block diagram block or blocks Figure 1 The flowchart and / or block diagram block or blocks Figure 1steps of the functions specified in the one or more blocks.

[0090] The above merely describes the preferred embodiments of the present application, and the protection scope of the present application is not limited to the above-mentioned embodiments. Any technical scheme falling within the concept of the present application shall fall within the protection scope of the present application. It should be noted that, for ordinary skilled persons in the art, some improvements and refinements without departing from the principles of the present application shall also be considered as falling within the protection scope of the present application.

Claims

1. A method for optimizing the operation of thermal power units based on energy efficiency optimization, characterized in that, Includes the following steps: Real-time acquisition of thermal power unit operating data, filtering of operating data of specified energy efficiency indicators of thermal power units under steady-state operating conditions, and obtaining a data set under steady-state operating conditions; The operating conditions of thermal power units are divided, and based on the division results, the data set under steady-state conditions is divided into corresponding data subsets. In each data subset, the energy efficiency index is assigned a corresponding weight value according to the energy efficiency level. The weighted support vector machine (SVM) model is trained using the aforementioned data subset. The trained SVM model predicts and outputs the optimal values ​​for energy efficiency indicators under various operating conditions. During training, the parameters of the SVM model are optimized based on the weights of the energy efficiency indicators. The SVM model takes a parameter vector composed of the energy efficiency indicators of all subsystems as input and outputs a comprehensive energy efficiency indicator. The expression is as follows: in, φ It is a nonlinear mapping function. ω For weight vectors, b This is the bias value. ξ i , These are slack variables; ε For insensitive loss function parameters, C This is the penalty coefficient; s i , t i Representing the first in the data subset i Data samples pair parameters C and ε The weighting coefficients, 0≤ s i , t i ≤1; where s i Determined by the label coefficients of the data samples, it is the first... i The weight values ​​of each data sample; N l This indicates the number of data samples contained in the data subset. x i Represents the first in the data subset i The parameter vector formed by the energy efficiency indices of all subsystems in a given data sample. y i Represents the first in the data subset i The comprehensive energy efficiency index of each data sample; The new data subset is input into the trained weighted support vector machine model to obtain the optimal value of the energy efficiency index under the corresponding operating conditions. The energy efficiency index is evaluated in real time based on the optimal value of the energy efficiency index, and the operation of the thermal power unit is adjusted according to the evaluation results.

2. The method for optimizing the operation of thermal power units based on energy efficiency optimization according to claim 1, characterized in that, When selecting operating data for energy efficiency indicators of thermal power units under steady-state operating conditions, the following steps are included: Specify at least one characterization parameter in the specified energy efficiency index; Collect runtime data within the current time window and obtain the maximum value of each characterizing parameter within the current time window. and minimum value ; Obtain the maximum value of each characterization parameter across all time windows of running data. and minimum value ; Determine the maximum value of each characterization parameter and minimum value The difference compared to the maximum value and minimum value Are all differences less than or equal to a preset threshold? If all values ​​are less than or equal to the preset threshold, the running data in the current time window is added to the data set under steady-state conditions, and the current time window is moved backward by a specified time span. The step of collecting running data in the current time window is then executed again. If the maximum value of at least one characterization parameter and minimum value The difference compared to the maximum value and minimum value If the difference is greater than a preset threshold, the current time window will be moved forward by one sampling time, and the step of collecting running data within the current time window will be executed again.

3. The method for optimizing the operation of thermal power units based on energy efficiency optimization according to claim 1, characterized in that, The classification of operating conditions for thermal power units specifically refers to classifying the operating conditions of thermal power units based on unit load, ambient temperature, and coal quality as boundary conditions.

4. The method for optimizing the operation of thermal power units based on energy efficiency optimization according to claim 1, characterized in that, The energy efficiency indicators include the energy efficiency indicators of each subsystem of the thermal power unit and the comprehensive energy efficiency indicator of the thermal power unit. The parameter vector of each data sample in the data subset contains a parameter vector composed of the energy efficiency indicators of all subsystems of that data sample and the comprehensive energy efficiency indicator of the thermal power unit. When assigning corresponding weight values ​​to the energy efficiency indicators in each data subset according to their energy efficiency level, the following is included: Based on the comprehensive energy efficiency index from best to worst, a linear interpolation algorithm is used to calculate the corresponding label values. Then, the parameter vector of each data sample in the data subset is assigned the corresponding label value as a weight value.

5. The method for optimizing the operation of thermal power units based on energy efficiency optimization according to claim 1, characterized in that, When evaluating energy efficiency indicators in real time based on their optimal values, this includes: Normalize the current operating data of the energy efficiency index under the specified operating condition to obtain the current value of the energy efficiency index under the specified operating condition. Calculate the deviation and rate of change of the current value and the optimal value of the energy efficiency index under a specified working condition, and calculate the real-time quantitative evaluation value of the energy efficiency index under the specified working condition based on the deviation and the rate of change of the deviation.

6. The method for optimizing the operation of thermal power units based on energy efficiency optimization according to claim 5, characterized in that, The expression for the real-time quantitative evaluation value is as follows: in, For the first i The deviation between the current and optimal values ​​of each energy efficiency indicator. For the first i The rate of change of the deviation between the current value and the optimal value of each energy efficiency indicator.

7. The method for optimizing the operation of thermal power units based on energy efficiency optimization according to claim 5, characterized in that, Adjusting the operation of thermal power units based on evaluation results includes: if the real-time quantitative evaluation value of the energy efficiency index for a specified operating condition is less than the specified value, adjusting the operating status of the thermal power unit based on the deviation between the optimal value and the current value of the energy efficiency index for the specified operating condition.

8. A thermal power unit operation optimization system based on energy efficiency optimization, characterized in that, It includes an interconnected microprocessor and a computer-readable storage medium, the microprocessor being programmed or configured to execute the energy efficiency optimization method for thermal power unit operation based on any one of claims 1 to 7.

9. A computer-readable storage medium storing a computer program, characterized in that, The computer program is used to be programmed or configured by a microprocessor to execute the energy efficiency optimization method for thermal power unit operation as described in any one of claims 1 to 7.

Images