CN116292057A - Control method, device, equipment and medium for variable-speed pumped storage unit - Google Patents
Control method, device, equipment and medium for variable-speed pumped storage unit Download PDFInfo
- Publication number
- CN116292057A CN116292057A CN202310331162.2A CN202310331162A CN116292057A CN 116292057 A CN116292057 A CN 116292057A CN 202310331162 A CN202310331162 A CN 202310331162A CN 116292057 A CN116292057 A CN 116292057A
- Authority
- CN
- China
- Prior art keywords
- neural network
- network model
- storage unit
- training
- power
- 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
- 238000003860 storage Methods 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000003062 neural network model Methods 0.000 claims abstract description 66
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 49
- 238000012549 training Methods 0.000 claims abstract description 47
- 238000012795 verification Methods 0.000 claims abstract description 19
- 238000010276 construction Methods 0.000 claims abstract description 10
- 238000013528 artificial neural network Methods 0.000 claims abstract description 6
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 5
- 230000008569 process Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 9
- 238000003491 array Methods 0.000 claims description 7
- 125000004122 cyclic group Chemical group 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 6
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 2
- 230000001537 neural effect Effects 0.000 claims 1
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 7
- 238000005259 measurement Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03B—MACHINES OR ENGINES FOR LIQUIDS
- F03B15/00—Controlling
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/20—Hydro energy
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Chemical & Material Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Mechanical Engineering (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Combustion & Propulsion (AREA)
- Control Of Water Turbines (AREA)
Abstract
The invention discloses a control method, a device, equipment and a medium of a variable-speed pumped storage unit, wherein the method comprises the following steps: acquiring the water head and the power of a current target pumped storage unit; inputting the acquired water head and power into a pre-constructed BP neural network model, and acquiring the rotating speed and the opening degree of the guide vane; controlling the target pumped storage unit according to the acquired rotating speed and the guide vane opening; the construction of the BP neural network model comprises the following steps: acquiring historical operation data of a pumped storage unit, and constructing a sample set; dividing a sample set into a training set and a verification set according to a preset proportion; initializing a BP neural network model, training the initialized BP neural network model through a training set, and verifying the trained BP neural network model through a verification set to obtain a final BP neural network model; the invention can be based on the rotating speed and the opening optimizing method of the BP neural network algorithm, and provides a guarantee for the accurate and stable operation of the variable-speed pumped storage unit.
Description
Technical Field
The invention relates to a control method, a device, equipment and a medium of a variable-speed pumped storage unit, and belongs to the technical field of power systems.
Background
The output of the water turbine can be regarded as a ternary function of the head, flow and unit speed, and its operating state can be expressed and solved by the related differential equation. In actual operation, the flow of water in the water turbine is complex, and although various methods can be used for solving and analyzing the flow in the water turbine in principle, or some geometrical parameters are used for qualitatively representing the excessive flow and moment of the water turbine, the quantitative representation of the characteristics of the water turbine can still be obtained only by a model test method. The comprehensive characteristics, the runaway characteristics and the like of the water turbine model are steady-state characteristics of the water turbine. In principle, the dynamic behavior of the water turbine should be used for the analysis of the hydraulic mechanical transient process, but since the latter has not been found by model experiments until now, only the steady state behavior of the water turbine can be used for the analysis of the dynamic process. The processing of turbine characteristics in a computer typically uses arrays to store turbine characteristics: the opening degree of the guide vane, the unit rotating speed, the unit operating water head of the unit and the unit output of the unit. The opening, rotation speed, water head and output which appear in the actual calculation are not just the values stored in the array, and the corresponding data can be calculated by interpolation. The traditional water turbine unit always operates at the synchronous rotating speed, the influence of the change of the rotating speed can be ignored, the operation characteristic of the traditional water turbine unit is expressed as the relation between the output of the unit and the opening degree of the guide vanes under different water heads, and the traditional water turbine unit can be expressed as a plurality of curves under different water heads by using a least square method or Lagrange interpolation, so that the corresponding opening degree of the guide vanes of the unit under the target output is determined. Because the measurement of the running state of the unit is not completely accurate, the measurement is possibly affected by errors in the actual measurement process, and the order of interpolation fitting cannot be determined, the under-fitting or over-fitting condition possibly occurs in the fitting process, and the whole fitting curve has larger errors outside the measurement points or at the two ends of the fitting curve. The variable-speed pumped storage unit has the capability of efficiently and quickly adjusting the output of the unit, and has higher requirements on control precision. The rotating speed can be changed in a certain range, when the target power and the water head are determined, the optimal rotating speed and the opening of the unit are required to be simultaneously calculated, and the traditional least square method and Lagrange interpolation fitting obviously cannot meet the precision requirement.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides a control method, a device, equipment and a medium for a variable-speed pumped storage unit, which can effectively improve the accuracy and the sensitivity of the coordinated control of the variable-speed pumped storage unit and have certain potential economic benefit.
In order to achieve the above purpose, the invention is realized by adopting the following technical scheme:
in a first aspect, the present invention provides a method of controlling a variable speed pumped-storage unit, comprising:
acquiring the water head and the power of a current target pumped storage unit;
inputting the acquired water head and power into a pre-constructed BP neural network model, and acquiring the rotating speed and the opening degree of the guide vane;
controlling the target pumped storage unit according to the acquired rotating speed and the guide vane opening;
the construction of the BP neural network model comprises the following steps:
acquiring historical operation data of a pumped storage unit, wherein the historical operation data comprises a plurality of arrays, and each array comprises a water head, power, a guide vane opening degree and a rotating speed;
taking the water head and the power in each array as samples, taking the opening degree and the rotating speed of the guide vane as actual labels of the samples, and constructing a sample set;
dividing a sample set into a training set and a verification set according to a preset proportion;
initializing a BP neural network model, training the initialized BP neural network model through a training set, and verifying the trained BP neural network model through a verification set to obtain a final BP neural network model.
Optionally, the training the initialized BP neural network model through the training set includes:
inputting samples in the training set into an initialized BP neural network model to obtain a prediction label of the samples;
calculating root mean square error according to the predicted label and the actual label of the sample:
wherein k=1, 2 represents the head and the power, d ki 、o ki The actual label and the predicted label of the ith sample are respectively, and l is the number of the samples;
the root mean square error is used as input data of a BP neural network error back propagation algorithm to carry out cyclic reciprocating training on the BP neural network model until the root mean square error is smaller than a preset expected error E ex And finishing training and saving the current BP neural network model.
Optionally, the BP neural network model includes an input layer, a hidden layer and an output layer; the BP neural network model adopts an S-type transfer function logsig, and the expression is as follows:
the process of forward transmission of the input layer to the hidden layer is as follows:
z ji ＝f(v 1j x 1i +v 2j x 2i )j＝1,2…,m
wherein x is 1i 、x 2i Head and power, v, of the ith sample, respectively 1j 、v 2j The connection weights from the 1 st and 2 nd input layers to the j th hidden layer, z ji For the output of the ith sample through the jth hidden layer, m is the number of hidden layers;
the output z of the hidden layer ji The process of forward transfer to the output layer is:
wherein w is kj O for the connection weight from the jth hidden layer to the kth output layer ki The output of the ith sample through the kth output layer, i.e., the predictive label of the ith sample.
Optionally, the performing the cyclic reciprocating training on the BP neural network model includes correcting a connection weight from the input layer to the hidden layer and a connection weight from the hidden layer to the output layer by using a gradient descent method:
in the method, in the process of the invention,
respectively connecting weights, connecting weight correction amounts and corrected connecting weights from a jth hidden layer to a kth output layer for an nth iteration; />
Respectively connecting weight, connecting weight correction amount and corrected connecting weight from the kth input layer to the jth hidden layer for the nth iteration;
wherein, gamma is a preset weight correction coefficient; e (E) n Root mean square error for the nth iteration;
for the purpose of a partial derivative function.
In a second aspect, the present invention provides a control device for a variable speed pumped-storage unit, the device comprising:
the data acquisition module is used for acquiring the water head and the power of the current target pumped storage unit;
the model prediction module is used for inputting the acquired water head and power into a pre-constructed BP neural network model, and acquiring the rotating speed and the opening of the guide vane;
the unit control module is used for controlling the target pumped storage unit according to the acquired rotating speed and the guide vane opening;
the construction of the BP neural network model comprises the following steps:
the historical data acquisition module is used for acquiring historical operation data of the pumped storage unit, wherein the historical operation data comprises a plurality of arrays, and each array comprises a water head, power, guide vane opening and rotating speed;
the sample set construction module is used for taking the water head and the power in each array as samples, taking the opening degree and the rotating speed of the guide vane as actual labels of the samples, and constructing a sample set;
the sample set dividing module is used for dividing the sample set into a training set and a verification set according to a preset proportion;
the training verification module is used for initializing the BP neural network model, training the initialized BP neural network model through the training set, and verifying the trained BP neural network model through the verification set to obtain a final BP neural network model.
In a third aspect, the present invention provides an electronic device, including a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is operative according to the instructions to perform steps according to the method described above.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above method.
Compared with the prior art, the invention has the beneficial effects that:
the control method, the device, the equipment and the medium of the variable-speed pumped storage unit provided by the invention provide a rotating speed and opening optimizing method based on a BP neural network algorithm, realize high-precision fitting and calculation of a characteristic curve of the pumped storage unit through self-adaptive optimization improvement of the BP neural network, and provide a guarantee for accurate and stable operation of the variable-speed pumped storage unit; the method solves the technical problems that the traditional Lagrangian interpolation method and the least square fitting method have the defects of over fitting and under fitting respectively, random errors existing in measurement are difficult to eliminate, and the accuracy of calculation results is difficult to guarantee.
Drawings
FIG. 1 is a flow chart of a method of controlling a variable speed pumped-storage unit according to a first embodiment of the present invention;
fig. 2 is a flowchart of a process for constructing a BP neural network model according to an embodiment of the present invention;
FIG. 3 is a graph showing the root mean square error of measured data according to an embodiment of the present invention;
FIG. 4 is a graph of the relationship between the opening degree, the power and the water head of a guide vane fitted by a BP neural network model provided by the embodiment of the invention;
fig. 5 is a graph of the relationship between the rotational speed, the power and the water head of the BP neural network model fitting according to the first embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present invention, and are not intended to limit the scope of the present invention.
Embodiment one:
as shown in fig. 1, an embodiment of the present invention provides a control method of a variable speed pumped-storage unit, including the following steps:
1. acquiring the water head and the power of a current target pumped storage unit;
2. inputting the acquired water head and power into a pre-constructed BP neural network model, and acquiring the rotating speed and the opening degree of the guide vane;
3. and controlling the target pumped storage unit according to the acquired rotating speed and the guide vane opening.
As shown in fig. 2, the construction of the BP neural network model includes:
s1, acquiring historical operation data of a pumped storage unit, wherein the historical operation data comprises a plurality of arrays, and each array comprises a water head, power, a guide vane opening degree and a rotating speed;
s2, taking the water head and the power in each array as samples, taking the opening degree and the rotating speed of the guide vane as actual labels of the samples, and constructing a sample set;
s3, dividing the sample set into a training set and a verification set according to a preset proportion;
s4, initializing a BP neural network model, training the initialized BP neural network model through a training set, and verifying the trained BP neural network model through a verification set (if verification does not meet the requirement, retraining through the training set is needed), so as to obtain a final BP neural network model.
Specifically, training the initialized BP neural network model through the training set includes:
(1) Inputting samples in the training set into an initialized BP neural network model to obtain a prediction label of the samples;
(2) Calculating root mean square error according to the predicted label and the actual label of the sample:
wherein k=1, 2 represents the head and the power, d ki 、o ki The actual label and the predicted label of the ith sample are respectively, and l is the number of the samples;
(3) The root mean square error is used as input data of a BP neural network error back propagation algorithm to carry out cyclic reciprocating training on the BP neural network model until the root mean square error is smaller than a preset expected error E ex And finishing training and saving the current BP neural network model.
The BP neural network model comprises an input layer, a hidden layer and an output layer; the BP neural network model adopts an S-type transfer function logsig, and the expression is as follows:
the input layer is forwarded to the hidden layer in the following process:
z ji ＝f(v 1j x 1i +v 2j x 2i )j＝1,2…,m
wherein x is 1i 、x 2i Head and power, v, of the ith sample, respectively 1j 、v 2j The connection weights from the 1 st and 2 nd input layers to the j th hidden layer, z ji For the output of the ith sample through the jth hidden layer, m is the number of hidden layers;
output z of hidden layer ji The process of forward transfer to the output layer is:
wherein w is kj From the jth hidden layer toConnection weight of kth output layer, o ki The output of the ith sample through the kth output layer, i.e., the predictive label of the ith sample.
The cyclic reciprocating training of the BP neural network model comprises correcting the connection weight from an input layer to a hidden layer and the connection weight from the hidden layer to an output layer by adopting a gradient descent method:
in the method, in the process of the invention,
respectively connecting weights, connecting weight correction amounts and corrected connecting weights from a jth hidden layer to a kth output layer for an nth iteration; />
Respectively connecting weight, connecting weight correction amount and corrected connecting weight from the kth input layer to the jth hidden layer for the nth iteration;
wherein, gamma is a preset weight correction coefficient; e (E) n Root mean square error for the nth iteration; θ is the partial derivative function.
In order to verify the effectiveness of the control method, the following fitting simulation was performed on measured data of a certain pumped storage power station, and the measured data are shown in table 1.
Table 1: actual measurement data of certain water pumping energy storage power station
Manufacturing a training set and a verification set through actual measurement data, and performing fitting training by using a BP neural network model, wherein the final result is shown in figure 3; as can be seen from the variation in root mean square error, as the number of training times increases, the root mean square error of the system gradually decreases and eventually converges. The energy function is minimized when the training times reach about 100 times, about 10 -2 The following is given. The system model in the present case may be considered to have completed training. The corresponding characteristic relation diagram of the water turbine is drawn according to the model, as shown in the following figures 4 and 5, so that the output characteristic of the water turbine can be completely and accurately represented, and the related requirements of quick table lookup are met.
Embodiment two:
the embodiment of the invention provides a control device of a variable-speed pumped storage unit, which comprises the following components:
the data acquisition module is used for acquiring the water head and the power of the current target pumped storage unit;
the model prediction module is used for inputting the acquired water head and power into a pre-constructed BP neural network model, and acquiring the rotating speed and the opening of the guide vane;
the unit control module is used for controlling the target pumped storage unit according to the acquired rotating speed and the guide vane opening;
the construction of the BP neural network model comprises the following steps:
the historical data acquisition module is used for acquiring historical operation data of the pumped storage unit, wherein the historical operation data comprises a plurality of arrays, and each array comprises a water head, power, guide vane opening and rotating speed;
the sample set construction module is used for taking the water head and the power in each array as samples, taking the opening degree and the rotating speed of the guide vane as actual labels of the samples, and constructing a sample set;
the sample set dividing module is used for dividing the sample set into a training set and a verification set according to a preset proportion;
the training verification module is used for initializing the BP neural network model, training the initialized BP neural network model through the training set, and verifying the trained BP neural network model through the verification set to obtain a final BP neural network model.
Embodiment III:
based on the first embodiment, the embodiment of the invention provides electronic equipment, which comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is operative according to the instructions to perform steps according to the method described above.
Embodiment four:
based on the first embodiment, the embodiment of the present invention provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the above method.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations 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 flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, 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 flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that modifications and variations could be made by those skilled in the art without departing from the technical principles of the present invention, and such modifications and variations should also be regarded as being within the scope of the invention.
Claims (7)
1. A method of controlling a variable speed pumped-storage unit comprising:
acquiring the water head and the power of a current target pumped storage unit;
inputting the acquired water head and power into a pre-constructed BP neural network model, and acquiring the rotating speed and the opening degree of the guide vane;
controlling the target pumped storage unit according to the acquired rotating speed and the guide vane opening;
the construction of the BP neural network model comprises the following steps:
acquiring historical operation data of a pumped storage unit, wherein the historical operation data comprises a plurality of arrays, and each array comprises a water head, power, a guide vane opening degree and a rotating speed;
taking the water head and the power in each array as samples, taking the opening degree and the rotating speed of the guide vane as actual labels of the samples, and constructing a sample set;
dividing a sample set into a training set and a verification set according to a preset proportion;
initializing a BP neural network model, training the initialized BP neural network model through a training set, and verifying the trained BP neural network model through a verification set to obtain a final BP neural network model.
2. The method of claim 1, wherein training the initialized BP neural network model with the training set comprises:
inputting samples in the training set into an initialized BP neural network model to obtain a prediction label of the samples;
calculating root mean square error according to the predicted label and the actual label of the sample:
wherein k=1, 2 represents the head and the power, d ki 、o ki The actual label and the predicted label of the ith sample are respectively, and l is the number of the samples;
the root mean square error is used as the input data of the BP neural network error back propagation algorithm to the BP neural networkThe complex model is trained in a cyclic and reciprocating way until the root mean square error is smaller than the preset expected error E ex And finishing training and saving the current BP neural network model.
3. The control method of a variable speed pumped-storage unit according to claim 2, wherein the BP neural network model comprises an input layer, a hidden layer and an output layer; the BP neural network model adopts an S-type transfer function logsig, and the expression is as follows:
the process of forward transmission of the input layer to the hidden layer is as follows:
z ji ＝f(v 1j x 1i +v 2j x 2i ) j＝1，2...，m
wherein x is 1i 、x 2i Head and power, v, of the ith sample, respectively 1j 、v 2j The connection weights from the 1 st and 2 nd input layers to the j th hidden layer, z ji For the output of the ith sample through the jth hidden layer, m is the number of hidden layers;
the output z of the hidden layer ji The process of forward transfer to the output layer is:
wherein w is kj O for the connection weight from the jth hidden layer to the kth output layer ki The output of the ith sample through the kth output layer, i.e., the predictive label of the ith sample.
4. A control method of a variable speed pumped-storage unit according to claim 3, wherein the cyclic training of the BP neural network model comprises modifying the connection weights of the input layer to the hidden layer and the connection weights of the hidden layer to the output layer by a gradient descent method:
in the method, in the process of the invention,
respectively connecting weights, connecting weight correction amounts and corrected connecting weights from a jth hidden layer to a kth output layer for an nth iteration; />
Respectively connecting weight, connecting weight correction amount and corrected connecting weight from the kth input layer to the jth hidden layer for the nth iteration;
wherein, gamma is a preset weight correction coefficient; e (E) n Root mean square error for the nth iteration;
for the purpose of a partial derivative function.
5. A control device for a variable speed pumped-storage unit, the device comprising:
the data acquisition module is used for acquiring the water head and the power of the current target pumped storage unit;
the model prediction module is used for inputting the acquired water head and power into a pre-constructed BP neural network model, and acquiring the rotating speed and the opening of the guide vane;
the unit control module is used for controlling the target pumped storage unit according to the acquired rotating speed and the guide vane opening;
the construction of the BP neural network model comprises the following steps:
the historical data acquisition module is used for acquiring historical operation data of the pumped storage unit, wherein the historical operation data comprises a plurality of arrays, and each array comprises a water head, power, guide vane opening and rotating speed;
the sample set construction module is used for taking the water head and the power in each array as samples, taking the opening degree and the rotating speed of the guide vane as actual labels of the samples, and constructing a sample set;
the sample set dividing module is used for dividing the sample set into a training set and a verification set according to a preset proportion;
the training verification module is used for initializing the BP neural network model, training the initialized BP neural network model through the training set, and verifying the trained BP neural network model through the verification set to obtain a final BP neural network model.
6. An electronic device, comprising a processor and a storage medium;
the storage medium is used for storing instructions;
the processor being operative according to the instructions to perform the steps of the method according to any one of claims 1-4.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310331162.2A CN116292057A (en) | 2023-03-30 | 2023-03-30 | Control method, device, equipment and medium for variable-speed pumped storage unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310331162.2A CN116292057A (en) | 2023-03-30 | 2023-03-30 | Control method, device, equipment and medium for variable-speed pumped storage unit |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116292057A true CN116292057A (en) | 2023-06-23 |
Family
ID=86779726
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310331162.2A Pending CN116292057A (en) | 2023-03-30 | 2023-03-30 | Control method, device, equipment and medium for variable-speed pumped storage unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116292057A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117469077A (en) * | 2023-11-15 | 2024-01-30 | 南方电网调峰调频发电有限公司检修试验分公司 | Method and device for judging operation condition of pumping and storage unit and pumping and storage unit protection equipment |
-
2023
- 2023-03-30 CN CN202310331162.2A patent/CN116292057A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117469077A (en) * | 2023-11-15 | 2024-01-30 | 南方电网调峰调频发电有限公司检修试验分公司 | Method and device for judging operation condition of pumping and storage unit and pumping and storage unit protection equipment |
| CN117469077B (en) * | 2023-11-15 | 2024-04-09 | 南方电网调峰调频发电有限公司检修试验分公司 | Method and device for judging operation condition of pumping and storage unit and pumping and storage unit protection equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113158582A (en) | Wind speed prediction method based on complex value forward neural network | |
| CN107194625B (en) | Wind power plant wind curtailment electric quantity evaluation method based on neural network | |
| JP6404909B2 (en) | How to calculate the output model of a technical system | |
| CN111723440B (en) | Thin-wall part machining precision prediction hybrid modeling method | |
| CN110942194A (en) | Wind power prediction error interval evaluation method based on TCN | |
| CN106991212B (en) | Root strength prediction method based on GA _ PSO (genetic Algorithm-particle swarm optimization) GRNN (generalized regression neural network) algorithm | |
| CN103778482B (en) | Aquaculture dissolved oxygen short term prediction method based on multiscale analysis | |
| CN113919221B (en) | BP neural network-based fan load prediction and analysis method, device and storage medium | |
| CN101813920B (en) | Virtual redundancy method for temperature sensor of power station turboset | |
| CN116292057A (en) | Control method, device, equipment and medium for variable-speed pumped storage unit | |
| CN113343606B (en) | Method for predicting full flow field from sparse sensor information based on compressed sensing reduced order model | |
| CN103106331B (en) | Based on the lithographic line width Intelligent Forecasting of dimensionality reduction and increment type extreme learning machine | |
| CN114492191A (en) | Heat station equipment residual life evaluation method based on DBN-SVR | |
| CN111709569A (en) | Method and device for predicting and correcting output power of wind power plant | |
| CN118040678A (en) | Short-term offshore wind power combination prediction method | |
| CN103902813A (en) | Steam-driven draught fan full working condition online monitoring model modeling method based on CPSO-LSSVM | |
| CN118054400A (en) | Wind power prediction method and system based on interpretability and model fusion | |
| CN117371581A (en) | New energy generated power prediction method, device and storage medium | |
| CN112232570A (en) | Forward active total electric quantity prediction method and device and readable storage medium | |
| CN110276478B (en) | Short-term wind power prediction method based on segmented ant colony algorithm optimization SVM | |
| CN111210877A (en) | Method and device for deducing physical property parameters | |
| CN114819382B (en) | LSTM-based photovoltaic power prediction method | |
| CN110909492A (en) | Sewage treatment process soft measurement method based on extreme gradient lifting algorithm | |
| CN116522752A (en) | Compressed air energy storage system simulation method based on mechanism and data fusion | |
| CN115907192A (en) | Method and device for generating wind power fluctuation interval prediction model and electronic equipment |
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 |