CN114004146A - Method for optimizing and determining flexible operation sliding pressure curve of heat supply unit based on all working conditions - Google Patents
Method for optimizing and determining flexible operation sliding pressure curve of heat supply unit based on all working conditions Download PDFInfo
- Publication number
- CN114004146A CN114004146A CN202111260256.2A CN202111260256A CN114004146A CN 114004146 A CN114004146 A CN 114004146A CN 202111260256 A CN202111260256 A CN 202111260256A CN 114004146 A CN114004146 A CN 114004146A
- Authority
- CN
- China
- Prior art keywords
- unit
- working condition
- data
- heat supply
- load
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000005457 optimization Methods 0.000 claims abstract description 30
- 230000008859 change Effects 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000010977 unit operation Methods 0.000 claims description 25
- 238000010438 heat treatment Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 17
- 230000007613 environmental effect Effects 0.000 claims description 17
- 238000012360 testing method Methods 0.000 claims description 16
- 238000012216 screening Methods 0.000 claims description 12
- 238000009826 distribution Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 239000002245 particle Substances 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 4
- 230000001172 regenerating effect Effects 0.000 claims description 3
- 238000000528 statistical test Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims 1
- 238000013461 design Methods 0.000 abstract description 4
- 238000005065 mining Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 6
- 230000033228 biological regulation Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000015556 catabolic process Effects 0.000 description 4
- 238000006731 degradation reaction Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 229910052799 carbon Inorganic materials 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a method for optimizing and determining a sliding pressure curve based on flexible operation of a full-working-condition heat supply unit, which comprises the following steps: establishing a sliding pressure curve optimization database, and storing the acquired and preprocessed historical data in the database; establishing a linear programming model based on the unit load change boundary conditions based on the preprocessing result, solving a steady-state data set under each working condition obtained according to the preprocessing, constructing a heat consumption rate prediction model by using an RNN-LSTM algorithm, and obtaining an optimal sliding pressure value under a related working condition division unit; and solving an optimal sliding pressure curve based on the optimal sliding pressure value by using an SGD algorithm. According to the invention, a slip pressure operation curve which is in negative accordance with the current operation condition of the unit is established by mining a large amount of historical operation data, and compared with the original design curve, the optimized slip pressure curve of the turboset can reduce the heat consumption rate of the unit under the current load of the unit to a certain extent, and improve the economic operation efficiency of the unit.
Description
Technical Field
The invention relates to the technical field of thermal power generating unit operation optimization, in particular to a method for optimizing and determining a sliding pressure curve based on flexible operation of a full-working-condition heat supply unit.
Background
With the successive carbon neutralization and carbon peak reaching commitments in China, the installed capacity of clean energy can be expected to be further increased, and the clean energy, particularly wind power, has instability and serious peak reversal regulation characteristics, so that the peak regulation degree of the thermal power generating unit is further increased, the thermal power generating unit operates under a medium-low load working condition for a long time, the unit often deviates from a design working condition, and the performance degradation of the unit equipment is accelerated along with the long-time deviation of the unit from the design working condition.
The thermal power generating unit operates at constant pressure under high load and low load, and operates at sliding pressure under intermediate load. The sliding pressure curve of the thermal power generating unit shows main steam pressure values which the unit should have under different loads, the valve opening degree of a main steam regulating valve under the current load can be obtained by combining opening degree characteristic curves of valves under different operation modes, so that the economic operation of operators is guided, the general sliding pressure operation curve is provided by a steam turbine manufacturer, but due to deep peak regulation and equipment degradation, the designed sliding pressure curve of the unit cannot meet the actual requirements of a site, and the designed curve needs to be optimized.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, the technical problem solved by the invention is as follows: in the prior art, due to the phenomena of deep peak regulation and equipment degradation, the designed sliding pressure curve of the unit can not meet the actual requirements of the site.
In order to solve the technical problems, the invention provides the following technical scheme: establishing a sliding pressure curve optimization database, and storing the acquired and preprocessed historical data in the database; establishing a linear programming model based on the unit load change boundary condition based on the preprocessing result and solving the linear programming model; according to the steady-state data set under each working condition obtained by the preprocessing, a heat consumption rate prediction model is constructed by utilizing an RNN-LSTM algorithm, and the optimal sliding pressure value under the relevant working condition division unit is obtained; and solving an optimal sliding pressure curve based on the optimal sliding pressure value by using an SGD algorithm.
As an optimal scheme of the method for determining the sliding pressure curve optimization based on the flexible operation of the all-condition heat supply unit, the method comprises the following steps: establishing the sliding pressure curve optimization database, storing the acquired and preprocessed historical data in the database, wherein the selected important temperature, pressure and flow rate points of a unit steam turbine body, a regenerative system, a heating system and a cold end system in the power plant SIS system are selected, the selected time interval is 10 seconds, and the selected time duration is 2 years, so that a training sample is formed; selecting the unit load P and the ambient temperature t in the training sample datacFlow rate Q of heat supply steamgrAnd forming a probability distribution P of the datap(x)、Ptc(x)、Pqgr(x) Where x ∈ (0, + ∞);
forming a probability distribution p for each parameter from historical datai(y) and the load P of the unit and the ambient temperature tcFlow rate Q of heat supply steamgrForming a joint probability distribution pp(x,y)、ptc(x,y)、pqgr(x,y);
Respectively calculating mutual information number H with unit loadpNumber of mutual information with ambient temperature HtcAnd the mutual information number H with the flow of the heating steamqThe calculation method is as follows:
wherein x, y ∈ (0, + ∞);
determining the influence weight w of the unit load, the environment temperature and the heat supply steam flow on the total mutual information numberp、wtc、wqgr;
Determining a total mutual information number calculation mode according to the influence weight determined in the previous step:
H(x,y)=wpHp+wtcHtc+wqgrHq
and when the total mutual information number is more than 0.85, the data is considered to have large parameter relevance with the unit operation boundary conditions, and the data needs to be brought into the sliding pressure curve optimization database.
As an optimal scheme of the method for determining the sliding pressure curve optimization based on the flexible operation of the all-condition heat supply unit, the method comprises the following steps: the data preprocessing process comprises steady-state data screening and working condition division of unit operation data.
As an optimal scheme of the method for determining the sliding pressure curve optimization based on the flexible operation of the all-condition heat supply unit, the method comprises the following steps: the steady-state data screening comprises the following steps of selecting six indexes of a data acquisition type table: the main steam temperature, the main steam pressure, the reheater temperature, the reheated steam pressure, the unit load and the environment temperature are used as steady-state data indexes; selecting historical data of the six indexes in each interval by adopting a sliding window algorithm, wherein the sliding window sliding interval is 1min, and the length of the sliding window is set to be 40 min; for each sliding window, respectively adopting a CTS statistical test algorithm to judge the stability of the historical operating data for the four indexes; defining the influence weight of the four indexes on the stable operation state of the unit; and establishing a unit operation steady-state index S, determining that the current state of the unit is a steady state when the S is more than or equal to 0.80, recording current operation data as stable data in real time, and storing the stable data into a steady-state database.
As an optimal scheme of the method for determining the sliding pressure curve optimization based on the flexible operation of the all-condition heat supply unit, the method comprises the following steps: the calculation formula of the unit operation steady state index S comprises,
S=ωzrwθzq+ωzqyμzq+ωzrwθzr+ωzryμzr+ωpδP+ωtcδtc
wherein, ω iszqw、ωzqy、ωzrw、ωzry、ωp、ωtcRespectively representing the steady state weight values of main steam temperature, main steam pressure, reheat steam temperature, reheat steam pressure, unit load and environment temperaturezq、μzq、θzr、μzr、δP、δtcAnd CTS test values respectively representing main steam temperature, main steam pressure, reheat steam temperature, reheat steam pressure, unit load and ambient temperature.
As an optimal scheme of the method for determining the sliding pressure curve optimization based on the flexible operation of the all-condition heat supply unit, the method comprises the following steps: the working condition division of the unit operation data comprises the steps of carrying out DBSCAN algorithm classification on a steady-state data set by taking an environment temperature tc parameter as an object to obtain a classification number, defining the environment temperature classification working condition number as alpha and each class of classification interval, and carrying out classification storage on the steady-state data according to the classification interval; for the steady-state data set under each type of environmental temperature classification in the steps, the heating steam flow G is used as a dividing object, the KNN algorithm is used for calculating the unit operation data under each type of unit load interval to obtain classification numbers, and the ith environmental temperature classification is definedThe number of the unit load classification working conditions under the temperature classification is betaiAnd a classification interval of each class, and storing the steady-state data in a classification mode according to the classification interval, wherein i is 1,2, … and alpha; classifying the steady state data set under each type of environmental temperature and heat supply steam flow classification by using the unit load P as a division object and using a DBSCAN algorithm to obtain classification numbers, and defining the unit load classification working condition number under the j heat supply steam flow working condition under the ith environmental temperature classification working condition as gammaijAnd a classification interval for each class, and storing the steady-state data in classification according to the classification interval, wherein j is 1,2, …, betai(ii) a And completing the working condition division of the unit operation stable state data through the steps, and dividing the unit stable state data into S working condition division units.
As an optimal scheme of the method for determining the sliding pressure curve optimization based on the flexible operation of the all-condition heat supply unit, the method comprises the following steps: the calculation mode of S is as follows:
as an optimal scheme of the method for determining the sliding pressure curve optimization based on the flexible operation of the all-condition heat supply unit, the method comprises the following steps: establishing a linear programming model based on the unit load change boundary conditions based on the preprocessing result and solving the linear programming model, wherein for each working condition division unit, the main steam pressure p of the heat supply unit is adjusted when the working condition division unit operateszqSubject to four constraints: the linear programming problem of the power grid load change requirement, the environment temperature constraint, the heat supply steam flow constraint and the main steam pressure constraint and listing the sliding pressure operation curve by taking the lowest heat consumption rate as a target function is as follows:
the objective function is:
wherein:
wherein h represents the heat consumption rate of the unit;
load constraint conditions:
Nmin≤P≤Nmax
wherein N isminRepresenting the minimum load value, N, of the steady-state data contained in the current working condition division unitmaxRepresenting the maximum load value of the steady-state data contained in the current working condition division unit;
and (3) pressure constraint conditions:
wherein the content of the first and second substances,representing the unit in the load interval P ∈ [ N ]min,Nmax]The minimum allowable pressure of the lower part of the tank,representing the unit in the load interval P ∈ [ N ]min,Nmax]Lower maximum allowable pressure;
environmental temperature constraint conditions:
Tmin≤tc≤Tmax
wherein, TminThe minimum environmental temperature value T of the unit under the working condition division unit is representedmaxThe maximum ambient temperature value of the unit under the working condition division unit is represented
And (3) heat supply steam flow constraint conditions:
Gmin≤tc≤Gmax
wherein G isminThe minimum heating steam flow value G of the unit under the working condition division unit is representedmaxIndicating the maximum heating steam flow of the unit under the working condition division unitMagnitude.
As an optimal scheme of the method for determining the sliding pressure curve optimization based on the flexible operation of the all-condition heat supply unit, the method comprises the following steps: the heat rate prediction model is constructed by utilizing an RNN-LSTM algorithm, and the optimal sliding pressure value under the relevant working condition division unit is obtained by selecting the following parameters: p, Pzq,tcG, h as characteristic parameter vectorSelecting the heat rate h as an input sample, using the heat rate h as an output sample, using the data of the fixed proportion obtained after the steady-state screening for model training, and using the data of the fixed proportion of the other part for model test; optimizing model parameters of RNN-LSTM by adopting a PSO particle optimization group algorithm; and testing the trained model through the test set, and establishing the RNN-LSTM model under each working condition division unit.
As an optimal scheme of the method for determining the sliding pressure curve optimization based on the flexible operation of the all-condition heat supply unit, the method comprises the following steps: the method for solving the optimal sliding pressure curve based on the optimal sliding pressure value by using the SGD algorithm comprises the steps of dividing the clustering centers of unit parameters according to the obtained S working conditions, and judging whether the unit boundary conditions are in the ith working condition of the environmental temperatureThe j-th heating steam flow working condition G can be obtained by solving the linear programming problem under the working condition to obtain the optimal sliding pressure operating value under the working condition, and the corresponding ambient temperature, heating steam flow and load thereof, wherein i is 0,1,2, …, α, j is 0,1,2, …, k.
The invention has the beneficial effects that: according to the invention, a slip pressure operation curve which is in negative accordance with the current operation condition of the unit is established by mining a large amount of historical operation data, and compared with the original design curve, the optimized slip pressure curve of the turboset can reduce the heat consumption rate of the unit under the current load of the unit to a certain extent, and improve the economic operation efficiency of the unit.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is a schematic basic flow chart of a method for determining sliding pressure curve optimization based on flexible operation of a full-condition heat supply unit according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a data acquisition parameter selection process of a method for determining the optimal sliding pressure curve of a flexible operation of a heat supply unit based on an all-condition according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a steady-state data screening process of a method for determining the optimal sliding pressure curve of a flexible operation of a heat supply unit based on an all-condition according to an embodiment of the present invention;
fig. 4 is a schematic diagram of working condition division of a method for determining a sliding pressure curve optimization based on flexible operation of a full-working-condition heat supply unit according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a RNN-LSTM algorithm construction flow of a flexible operation sliding pressure curve optimization determination method based on a full-condition heat supply unit according to an embodiment of the present invention;
fig. 6 is a schematic diagram of determining a heat supply steam flow and an optimal sliding pressure curve under an environment temperature condition based on a method for determining an optimal sliding pressure curve for flexible operation of a full-condition heat supply unit according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to fig. 1 to 5, an embodiment of the present invention provides a method for determining a sliding pressure curve for flexible operation of a heat supply unit based on an all-condition, including:
s1: establishing a sliding pressure curve optimization database, and storing the acquired and preprocessed historical data in the database;
it should be noted that, firstly, the acquisition interval and the acquisition type of the acquired historical data are determined, the requirement on the acquisition interval is to give consideration to the running state and the algorithm speed of the unit in quick response, and as the unit is generally kept stable within 30 minutes, the unit can be considered to be in a stable state, the acquisition interval is specified to be 10 seconds, the acquisition range is the historical running data of the unit within 2 years, and as the sliding pressure curve is determined to take the lowest heat consumption rate as the final target, the data acquisition type is selected according to the basis, and the invention adopts a weighted mutual information number method to determine the data measuring point which is greatly related to the running state of the unit.
Because the existing thermal power generating units generally undertake heavier peak regulation tasks, the states of the units are frequently changed to adapt to the load requirements of a power grid, but unsteady data recorded when the operating states of the units are switched cannot usually represent the current operating states of the units, because the transmission of influences on the internal operating states of the units caused by the change of external boundary conditions of the units is delayed, and therefore, in order to accurately express the current operating states of the units, including heat balance and working medium balance, steady-state screening must be performed on historical data.
The method comprises the steps of determining the load P and the ambient temperature tc of the unit, using the heat supply steam flow Q as a working condition division basis, and simultaneously adopting a multi-step density-based DBSCAN clustering method to divide the working condition of the screened steady-state historical data.
Specifically, as shown in fig. 2, important temperature, pressure and flow rate points of a unit turbine body, a regenerative system, a heating system and a cold end system in the power plant SIS system are selected, the selection time interval is 10 seconds, and the selection time is 2 years, so that a training sample is formed;
selecting unit load P and ambient temperature t in training sample datacFlow rate Q of heat supply steamgrAnd forming a probability distribution P of the datap(x)、Ptc(x)、Pqgr(x) Where x ∈ (0, + ∞);
forming a probability distribution p for each parameter from historical datai(y) and the load P of the unit and the ambient temperature tcFlow rate Q of heat supply steamgrForming a joint probability distribution pp(x,y)、ptc(x,y)、pqgr(x,y);
Respectively calculating mutual information number H with unit loadpNumber of mutual information with ambient temperature HtcAnd the mutual information number H with the flow of the heating steamqThe calculation method is as follows:
wherein x, y ∈ (0, + ∞);
determining the influence weight w of the unit load, the environment temperature and the heat supply steam flow on the total mutual information numberp、wtc、wqgrThe determination was empirically determined in the following table:
table 1: and (4) a unit operation index weight table.
Determining a total mutual information number calculation mode according to the influence weight determined in the previous step:
H(x,y)=wpHp+wtcHtc+wqgrHq
and when the total mutual information number is more than 0.85, the data is considered to have large parameter relevance with the unit operation boundary conditions, and the data needs to be brought into a sliding pressure curve optimization database.
The station data determined using the following table:
table 2: and a data acquisition table required by sliding pressure optimization.
Further, as shown in fig. 3, the steady state data screening includes:
selecting six indexes of a data acquisition type table: the main steam temperature, the main steam pressure, the reheater temperature, the reheated steam pressure, the unit load and the environment temperature are used as steady-state data indexes;
selecting historical data of six indexes in each interval by adopting a sliding window algorithm, wherein the sliding window sliding interval is 1min, and the length of the sliding window is set to be 40 min;
and in each sliding window, distinguishing the stability of the historical operating data by respectively adopting a CTS statistical test algorithm for the four indexes, wherein the result of the CTS test is shown in the following table:
table 3: and (4) steady-state screening CTS test result table.
Data type | (symbol) | CTS check value symbol | Stabilization | Is unstable | |
Temperature of main steam | tzq | θzq | 1 | 0 | |
Main steam pressure | pzq | μzq | 1 | 0 | |
Reheat steam temperature | tzr | θzr | 1 | 0 | |
Reheat steam pressure | pzr | μzr | 1 | 0 | |
Load of | P | δ | P | 1 | 0 |
Ambient temperature | tc | δtc | 1 | 0 |
Defining the weight of the influence of four indexes on the unit operation steady state, as shown in the following table:
table 4: steady state weight impact table.
And establishing a unit operation steady-state index S, determining that the current state of the unit is a steady state when the S is more than or equal to 0.80, recording the current operation data as stable data in real time, and storing the stable data into a steady-state database.
The calculation formula of the unit operation steady state index S comprises the following steps:
S=ωzqwθzq+ωzqyμzq+ωzrwθzr+ωzryμzr+ωpδP+ωtcδtc
furthermore, as shown in fig. 4, with the ambient temperature tc parameter as an object, performing DBSCAN algorithm classification on the steady-state data set to obtain classification numbers (defining the number of classification conditions of the ambient temperature as α) and classification intervals of each class, and performing classification storage on the steady-state data according to the classification intervals;
for the steady-state data set under each type of environment temperature classification in the above steps, the heating steam flow G is used as a dividing object, the KNN algorithm is used for the unit operation data under each type of unit load interval, and the unit load classification working condition number under the classification number (i is 1,2, …, alpha) environment temperature classification is obtained as betai) And classification interval of each class, and storing the steady-state data according to classification intervalStoring;
classifying the steady state data set under each type of environment temperature and heat supply steam flow classification by using a DBSCAN algorithm with the unit load P as a division object to obtain the classification number (i is 1,2, …, alpha), j is 1,2, …, beta under the environment temperature classification working conditioni) The unit load classification working condition number under the working condition of heat supply steam flow is gammaij) And classification intervals under each class, and storing the steady-state data in a classification mode according to the classification intervals;
and completing the working condition division of the unit operation stable state data through the steps, and dividing the unit stable state data into S working condition division units.
Wherein, the calculation mode of S is as follows:
s2: establishing a linear programming model based on the unit load change boundary condition based on the preprocessing result and solving the linear programming model;
it should be noted that, this embodiment mainly aims to classify data according to working conditions, divide the data of units for each working condition, combine constraint conditions of unit variable load, valve adjustment and unit safety, and change the calculation of the optimal slip pressure value of a unit under a certain working condition into a linear programming problem through linear programming, where the linear programming problem takes the lowest heat rate as an objective function, and takes several aspects of unit load interval constraint, power grid load response constraint, unit safety load response constraint, valve opening constraint, and main steam pressure constraint as constraint conditions.
Specifically, as shown in fig. 5, the main purpose of this step is to construct a linear programming problem of optimal sliding pressure operation with the power plant heat economy as a guide (i.e., with the lowest heat consumption rate of unit operation under the same working condition), and solve the optimal sliding pressure value under the current working condition partition unit that meets the constraint condition.
For each working condition division unit, the analysis heat supply unit adjusts the main steam pressure p when the working condition division unit operateszqSubject to four constraints: the linear programming problem of the power grid load change requirement, the environment temperature constraint, the heat supply steam flow constraint and the main steam pressure constraint, and listing the sliding pressure operation curve by taking the lowest heat consumption rate as a target function is as follows:
an objective function:
wherein:
wherein h represents the heat consumption rate of the unit, kJ/kg;
load constraint conditions:
Nmin≤P≤Nmax
wherein N isminRepresenting the minimum load value, N, of the steady-state data contained in the current working condition division unitmaxRepresenting the maximum load value of the steady-state data contained in the current working condition division unit;
and (3) pressure constraint conditions:
wherein the content of the first and second substances,representing the unit in the load interval P ∈ [ N ]min,Nmax]The minimum allowable pressure of the lower part of the tank,representing the unit in the load interval P ∈ [ N ]min,Nmax]Lower maximum allowable pressure;
environmental temperature constraint conditions:
Tmin≤tc≤Tmax
wherein, TminThe minimum environmental temperature value T of the unit under the working condition division unit is representedmaxThe maximum ambient temperature value of the unit under the working condition division unit is represented
And (3) heat supply steam flow constraint conditions:
Gmin≤tc≤Gmax
wherein G isminThe minimum heating steam flow value G of the unit under the working condition division unit is representedmaxAnd the maximum heating steam flow value of the unit under the working condition division unit is represented.
S3: according to the steady-state data set under each working condition obtained by preprocessing, constructing a heat consumption rate prediction model by utilizing an RNN-LSTM algorithm, and obtaining an optimal sliding pressure value under a related working condition division unit;
it should be noted that, because the heat rate of the unit is affected by various factors and is difficult to be expressed by a specific analytic expression, a heat rate prediction model needs to be established through a data sample, and a relational expression between an influencing factor cluster and the heat rate needs to be established through the model, so that the change of the heat rate can be predicted when some variables in the influencing factor cluster change. Therefore, the linear programming problem of obtaining the main steam pressure value under a certain working condition can be solved. The long-time and short-time neural memory network is used as a widely applied mature algorithm, inequality constraints in the SVM are converted into equality constraints, and the long-time and long-time neural memory network has the advantages of simple calculation mode, fewer parameters and shorter calculation time, so that the heat consumption rate prediction model is constructed based on the RNN-LSTM algorithm.
Because model parameters in the RNN-LSTM algorithm have great influence on the accuracy of the model, the model parameters need to be optimized through the algorithm, the two parameters are determined through the PSO particle swarm optimization algorithm, the PSO algorithm needs to determine whether the current particles are the optimal particles through fitness calculation, and the RMSE (residual error equation) is used as a fitness calculation formula.
Specifically, the following parameters are selected: p, Pzq,tcG, h as characteristic parameter vectorSelecting the heat rate h as an input sample, using the heat rate h as an output sample, using the data of the fixed proportion obtained after the steady-state screening for model training, and using the data of the fixed proportion of the other part for model test;
optimizing model parameters of RNN-LSTM by adopting a PSO particle optimization group algorithm;
and testing the trained model through the test set, and establishing the RNN-LSTM model under each working condition division unit.
S4: and solving the optimal sliding pressure curve based on the optimal sliding pressure value by using an SGD algorithm.
It should be noted that, after the RNN-LSTM heat rate prediction model is trained by using the data set under each operating condition unit to obtain a non-linear mathematical model meeting the accuracy requirement, the linear programming problem of the sliding pressure operation under each load interval under the operating condition of determining the current ambient temperature and the heat supply steam flow is solved by using the SGD algorithm, so as to obtain the optimal value of the sliding pressure operation under each load interval. And connecting the optimal sliding pressure values in each load interval into a line, so that an optimal sliding pressure curve of the unit at the current environment temperature can be obtained and used for guiding the daily operation of the unit.
Specifically, the cluster centers of the unit parameters are divided according to the obtained S working conditions, and when the unit boundary condition is in the ith working condition of the environmental temperatureThe j-th heating steam flow working condition G can be obtained by solving the linear programming problem under the working condition to obtain the optimal sliding pressure operating value under the working condition, and the corresponding ambient temperature, heating steam flow and load thereof, wherein i is 0,1,2, …, α, j is 0,1,2, …, k.
The invention firstly proposes that 6 parameters of main steam temperature, main steam pressure, reheat steam temperature, reheat steam pressure, unit load and environment temperature are adopted as indexes for unit operation steady state screening, and the unit operation state can be well described through the indexes; secondly, because the influence degrees of the 6 indexes on the unit running state are different, for example, the main steam temperature and the reheat steam temperature of the unit are obviously changed only when the unit load is low, and the unit is positioned at high load or full load, no matter whether the unit is in a variable working condition or not is very stable, and the main steam pressure and the reheat steam pressure are very sensitive to the variable working condition of the unit, the difference is needed.
Example 2
Referring to fig. 6, another embodiment of the present invention is different from the first embodiment in that a verification test based on the full-operating-condition heat supply unit flexible operation sliding pressure curve optimization determination method is provided, and in order to verify and explain the technical effects adopted in the method, the embodiment adopts a conventional technical scheme and the method of the present invention to perform a comparison test, and compares the test results by means of scientific demonstration to verify the real effects of the method.
For convenience of illustration, under the condition, there are l unit load working conditions, the optimal model parameters obtained by optimizing through the PSO algorithm and the steady-state data under the working conditions are substituted into the RNN-LSTM heat rate prediction model, and the linear programming problem listed in the step three and based on the given load is solved through the SGD (random gradient descent method), so that l optimal sliding pressure operation main steam pressure values can be obtainedAnd relative toLoad value of
When l is 1,2,3 points are connected to the load-initial pressure diagramAnd main steam pressures specified for 30% and 85% load power plants, the current ambient temperature can be obtainedThe lower optimum slip pressure curve is shown schematically.
As can be seen from fig. 6, compared with the conventional proportional slip pressure curve, the slip pressure curve obtained by the method of the present invention does not necessarily show a proportional increase trend, which is more suitable for the actual situation of the unit, and the method can more effectively guide the power plant operator to adjust the slip pressure value in consideration of the characteristics of the unit such as equipment degradation and complex working condition environment during the long-term operation, so as to improve the thermal economy of the heat supply unit.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (10)
1. A method for optimizing and determining a sliding pressure curve based on flexible operation of a full-working-condition heat supply unit is characterized by comprising the following steps:
establishing a sliding pressure curve optimization database, and storing the acquired and preprocessed historical data in the database;
establishing a linear programming model based on the unit load change boundary condition based on the preprocessing result and solving the linear programming model;
according to the steady-state data set under each working condition obtained by the preprocessing, a heat consumption rate prediction model is constructed by utilizing an RNN-LSTM algorithm, and the optimal sliding pressure value under the relevant working condition division unit is obtained;
and solving an optimal sliding pressure curve based on the optimal sliding pressure value by using an SGD algorithm.
2. The method for optimizing and determining the sliding pressure curve based on the flexible operation of the full-working-condition heat supply unit according to claim 1, is characterized in that: establishing the sliding pressure curve optimization database, storing the collected and preprocessed historical data in the database,
selecting important temperature, pressure and flow measurement points of a unit steam turbine body, a regenerative system, a heating system and a cold end system in a power plant SIS system, wherein the selection time interval is 10 seconds, and the selection time is 2 years to form a training sample;
selecting the unit load P and the ambient temperature t in the training sample datacFlow rate Q of heat supply steamgrAnd forming a probability distribution P of the datap(x)、Ptc(x)、Pqgr(x) Where x ∈ (0, + ∞);
forming a probability distribution p for each parameter from historical datai(y) and the load P of the unit and the ambient temperature tcFlow rate Q of heat supply steamgrForming a joint probability distribution pp(x,y)、ptc(x,y)、pqgr(x,y);
Respectively calculating mutual information number H with unit loadpNumber of mutual information with ambient temperature HtcAnd the mutual information number H with the flow of the heating steamqThe calculation method is as follows:
wherein x, y ∈ (0, + ∞);
determining the influence weight w of the unit load, the environment temperature and the heat supply steam flow on the total mutual information numberp、wtc、wqgr;
Determining a total mutual information number calculation mode according to the influence weight determined in the previous step:
H(x,y)=wpHp+wtcHtc+wqgrHq
and when the total mutual information number is more than 0.85, the data is considered to have large parameter relevance with the unit operation boundary conditions, and the data needs to be brought into the sliding pressure curve optimization database.
3. The sliding pressure curve optimization determination method based on the flexible operation of the full-working-condition heat supply unit as claimed in claim 1 or 3, characterized in that: the data preprocessing process comprises steady-state data screening and working condition division of unit operation data.
4. The method for optimizing and determining the sliding pressure curve based on the flexible operation of the full-working-condition heat supply unit according to claim 3, is characterized in that: the steady-state data screening includes the steps of,
selecting six indexes of a data acquisition type table: the main steam temperature, the main steam pressure, the reheater temperature, the reheated steam pressure, the unit load and the environment temperature are used as steady-state data indexes;
selecting historical data of the six indexes in each interval by adopting a sliding window algorithm, wherein the sliding window sliding interval is 1min, and the length of the sliding window is set to be 40 min;
for each sliding window, respectively adopting a CTS statistical test algorithm to judge the stability of the historical operating data for the four indexes;
defining the influence weight of the four indexes on the stable operation state of the unit;
and establishing a unit operation steady-state index S, determining that the current state of the unit is a steady state when the S is more than or equal to 0.80, recording current operation data as stable data in real time, and storing the stable data into a steady-state database.
5. The method for optimizing and determining the sliding pressure curve based on the flexible operation of the full-working-condition heat supply unit according to claim 4, is characterized in that: the calculation formula of the unit operation steady state index S comprises,
S=ωzqwθzq+ωzqyμzq+ωzrwθzr+ωzryμzr+ωpδP+ωtcδtc
wherein, ω iszqw、ωzqy、ωzrw、ωzry、ωp、ωtcRespectively representing the steady state weight values of main steam temperature, main steam pressure, reheat steam temperature, reheat steam pressure, unit load and environment temperaturezq、μzq、θzr、μzr、δP、δtcAnd CTS test values respectively representing main steam temperature, main steam pressure, reheat steam temperature, reheat steam pressure, unit load and ambient temperature.
6. The method for optimizing and determining the sliding pressure curve based on the flexible operation of the full-working-condition heat supply unit according to claim 3, is characterized in that: the working condition division of the unit operation data comprises the following steps,
at ambient temperature tcThe method comprises the steps that parameters are objects, a steady state data set is classified through a DBSCAN algorithm to obtain classification numbers, the environment temperature classification working condition number is defined to be alpha, and classification intervals of each class are defined, and steady state data are classified and stored according to the classification intervals;
for the steady-state data set under each type of environmental temperature classification in the steps, the heating steam flow G is used as a dividing object, the KNN algorithm is used for calculating the unit operation data under each type of unit load interval to obtain classification number, and the unit load classification working condition number under the ith environmental temperature classification is defined as betaiAnd a classification interval of each class, and storing the steady-state data in a classification mode according to the classification interval, wherein i is 1,2, … and alpha;
classifying the steady state data set under each type of environmental temperature and heat supply steam flow classification by using the unit load P as a division object and using a DBSCAN algorithm to obtain classification numbers, and defining the unit load classification working condition number under the j heat supply steam flow working condition under the ith environmental temperature classification working condition as gammaijAnd a classification interval for each class, and storing the steady-state data in classification according to the classification interval, wherein j is 1,2, …, betai;
And completing the working condition division of the unit operation stable state data through the steps, and dividing the unit stable state data into S working condition division units.
8. the sliding pressure curve optimization determination method based on the flexible operation of the full-working-condition heat supply unit as claimed in claim 6 or 7, characterized in that: establishing a linear programming model based on the unit load change boundary condition based on the preprocessing result and solving the linear programming model,
for each working condition division unit, analyzing and adjusting main steam pressure p when the heat supply unit operates in the working condition division unitzqSubject to four constraints: the linear programming problem of the power grid load change requirement, the environment temperature constraint, the heat supply steam flow constraint and the main steam pressure constraint and listing the sliding pressure operation curve by taking the lowest heat consumption rate as a target function is as follows:
the objective function is:
wherein:
wherein h represents the heat consumption rate of the unit;
load constraint conditions:
Nmin≤P≤Nmax
wherein N isminRepresenting the minimum load value, N, of the steady-state data contained in the current working condition division unitmaxRepresenting the steady state data contained in the current working condition division unitThe maximum load value of (a);
and (3) pressure constraint conditions:
wherein the content of the first and second substances,representing the unit in the load interval P ∈ [ N ]min,Nmax]The minimum allowable pressure of the lower part of the tank,representing the unit in the load interval P ∈ [ N ]min,Nmax]Lower maximum allowable pressure;
environmental temperature constraint conditions:
Tmin≤tc≤Tmax
wherein, TminThe minimum environmental temperature value T of the unit under the working condition division unit is representedmaxThe maximum ambient temperature value of the unit under the working condition division unit is represented
And (3) heat supply steam flow constraint conditions:
Gmin≤tc≤Gmax
wherein G isminThe minimum heating steam flow value G of the unit under the working condition division unit is representedmaxAnd the maximum heating steam flow value of the unit under the working condition division unit is represented.
9. The method for optimizing and determining the sliding pressure curve based on the flexible operation of the full-working-condition heat supply unit according to claim 1, is characterized in that: constructing the heat rate prediction model by using an RNN-LSTM algorithm, and solving the optimal sliding pressure value under the relevant working condition division unit,
the following parameters were selected: p, Pzq,tcG, h as characteristic parameter vectorSelecting the heat rate h as an input sample, using the heat rate h as an output sample, using the data of the fixed proportion obtained after the steady-state screening for model training, and using the data of the fixed proportion of the other part for model test;
optimizing model parameters of RNN-LSTM by adopting a PSO particle optimization group algorithm;
and testing the trained model through the test set, and establishing the RNN-LSTM model under each working condition division unit.
10. The method for optimizing and determining the sliding pressure curve based on the flexible operation of the full-working-condition heat supply unit according to claim 1, is characterized in that: solving an optimal slip pressure curve based on the optimal slip pressure value using the SGD algorithm includes,
dividing the cluster center of the unit parameters according to the obtained S working conditions, and judging whether the unit boundary conditions are in the ith environmental temperature working conditionThe j-th heating steam flow working condition G can be obtained by solving the linear programming problem under the working condition to obtain the optimal sliding pressure operating value under the working condition, and the corresponding ambient temperature, heating steam flow and load thereof, wherein i is 0,1,2, …, α, j is 0,1,2, …, k.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111260256.2A CN114004146A (en) | 2021-10-28 | 2021-10-28 | Method for optimizing and determining flexible operation sliding pressure curve of heat supply unit based on all working conditions |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111260256.2A CN114004146A (en) | 2021-10-28 | 2021-10-28 | Method for optimizing and determining flexible operation sliding pressure curve of heat supply unit based on all working conditions |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114004146A true CN114004146A (en) | 2022-02-01 |
Family
ID=79924485
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111260256.2A Pending CN114004146A (en) | 2021-10-28 | 2021-10-28 | Method for optimizing and determining flexible operation sliding pressure curve of heat supply unit based on all working conditions |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114004146A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115450710A (en) * | 2022-09-06 | 2022-12-09 | 哈尔滨工业大学 | Method for optimizing sliding pressure operation of steam turbine |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109299582A (en) * | 2018-12-03 | 2019-02-01 | 黑龙江苑博信息技术有限公司 | Steam turbine sliding pressure optimization of profile method based on unit operation big data multidimensional ordering |
CN111539154A (en) * | 2020-04-16 | 2020-08-14 | 哈尔滨工业大学 | Quantitative evaluation method for operation performance change of steam turbine |
CN111652418A (en) * | 2020-05-25 | 2020-09-11 | 西安西热节能技术有限公司 | Method for generating sliding pressure curve of dynamic refined composite parameter of thermal power generating unit |
CN112576326A (en) * | 2020-12-07 | 2021-03-30 | 润电能源科学技术有限公司 | Sliding pressure optimal operation control method, device and equipment for thermal power generating unit |
-
2021
- 2021-10-28 CN CN202111260256.2A patent/CN114004146A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109299582A (en) * | 2018-12-03 | 2019-02-01 | 黑龙江苑博信息技术有限公司 | Steam turbine sliding pressure optimization of profile method based on unit operation big data multidimensional ordering |
CN111539154A (en) * | 2020-04-16 | 2020-08-14 | 哈尔滨工业大学 | Quantitative evaluation method for operation performance change of steam turbine |
CN111652418A (en) * | 2020-05-25 | 2020-09-11 | 西安西热节能技术有限公司 | Method for generating sliding pressure curve of dynamic refined composite parameter of thermal power generating unit |
CN112576326A (en) * | 2020-12-07 | 2021-03-30 | 润电能源科学技术有限公司 | Sliding pressure optimal operation control method, device and equipment for thermal power generating unit |
Non-Patent Citations (3)
Title |
---|
江浩;常东锋;蒋辉;黄嘉驷;李欣;李钊;王勇;: "高压调节阀配置方式对机组运行经济性的影响", 热力发电, no. 12, 31 December 2014 (2014-12-31) * |
耿娜: "基于卷积神经网络的火电机组初压实时优化", 《控制工程》, 20 July 2020 (2020-07-20), pages 1223 - 1230 * |
董竹林;牛玉广;董恩伏;周桂平;罗桓桓;张国斌;: "适应火电机组灵活运行的滑压曲线优化方法", 动力工程学报, no. 03, 15 March 2020 (2020-03-15) * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115450710A (en) * | 2022-09-06 | 2022-12-09 | 哈尔滨工业大学 | Method for optimizing sliding pressure operation of steam turbine |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2019174040A1 (en) | Coupling and clustering analysis and decision-making tree based short-term power generation scheduling method for cascaded hydroelectric station group | |
US11755976B2 (en) | Method for predicting oxygen load in iron and steel enterprises based on production plan | |
CN111369070B (en) | Multimode fusion photovoltaic power prediction method based on envelope clustering | |
CN111722046B (en) | Transformer fault diagnosis method based on deep forest model | |
CN111008504B (en) | Wind power prediction error modeling method based on meteorological pattern recognition | |
CN108954375B (en) | Coal-saving control method for boiler | |
CN108898251A (en) | Consider the marine wind electric field power forecasting method of meteorological similitude and power swing | |
CN107274067B (en) | Distribution transformer overload risk assessment method | |
CN111291514A (en) | Method for rapidly predicting fatigue life of wind turbine generator | |
CN104408562A (en) | Photovoltaic system generating efficiency comprehensive evaluation method based on BP (back propagation) neural network | |
CN113807570A (en) | Reservoir dam risk level evaluation method and system based on XGboost | |
CN105005878B (en) | A kind of comprehensive estimation method of strong intelligent grid | |
CN106778838A (en) | A kind of method for predicting air quality | |
CN112163371A (en) | Transformer bushing state evaluation method | |
CN115689353A (en) | Hydropower station speed regulation system health assessment method based on GS-SVM algorithm | |
CN114021483A (en) | Ultra-short-term wind power prediction method based on time domain characteristics and XGboost | |
CN114004146A (en) | Method for optimizing and determining flexible operation sliding pressure curve of heat supply unit based on all working conditions | |
CN112288157A (en) | Wind power plant power prediction method based on fuzzy clustering and deep reinforcement learning | |
CN110991689B (en) | Distributed photovoltaic power generation system short-term prediction method based on LSTM-Morlet model | |
CN113991711B (en) | Capacity configuration method for energy storage system of photovoltaic power station | |
CN112818525A (en) | Hydroelectric generating set state evaluation method and system | |
CN113205125A (en) | XGboost-based extra-high voltage converter valve operation state evaluation method | |
CN116151799A (en) | BP neural network-based distribution line multi-working-condition fault rate rapid assessment method | |
CN115681597A (en) | Fusion drive-based waste heat valve control optimization method | |
CN104200106A (en) | Longitudinal time axis clustering method in generalized load modeling on basis of seasonality |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |