CN117728504B - Black start system and method for diesel-engine combined combustion engine - Google Patents
Black start system and method for diesel-engine combined combustion engine Download PDFInfo
- Publication number
- CN117728504B CN117728504B CN202410179650.0A CN202410179650A CN117728504B CN 117728504 B CN117728504 B CN 117728504B CN 202410179650 A CN202410179650 A CN 202410179650A CN 117728504 B CN117728504 B CN 117728504B
- Authority
- CN
- China
- Prior art keywords
- weight
- overvoltage
- error
- weight set
- black start
- 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.)
- Active
Links
- 241001672018 Cercomela melanura Species 0.000 title claims abstract description 94
- 238000000034 method Methods 0.000 title claims abstract description 84
- 238000002485 combustion reaction Methods 0.000 title claims description 24
- 238000003062 neural network model Methods 0.000 claims abstract description 33
- 230000008569 process Effects 0.000 claims abstract description 31
- 125000004122 cyclic group Chemical group 0.000 claims abstract description 29
- 238000005457 optimization Methods 0.000 claims description 53
- 230000015654 memory Effects 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 description 7
- 230000000306 recurrent effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 2
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
- Feedback Control In General (AREA)
Abstract
The application relates to the technical field of black start overvoltage prediction, in particular to a black start system and a method of a diesel-engine combined gas turbine, wherein the method comprises the steps of obtaining the closing overvoltage and various voltage influence parameters of an idle circuit in the historical black start process of a power grid; calculating a first weight set and a second weight set by using the pearson correlation coefficient and the cosine similarity; determining a first error and a second error based on the closing overvoltage, the plurality of voltage influence parameters, the first weight set and the second weight set by using a cyclic neural network model; updating the first weight set and the second weight set according to the preset iteration times based on the first error and the second error to obtain a target weight set; and (3) utilizing a cyclic neural network model, obtaining a switching-on overvoltage target predicted value set based on a target weight set and various real-time voltage influence parameters in the current black start process, and selecting a line where the minimum value in the switching-on overvoltage target predicted value set is located as an optimal line to supply power to a power grid so as to finish the black start of the power grid.
Description
Technical Field
The application relates to the technical field of black start overvoltage prediction, in particular to a black start system and a black start method of a diesel-engine combined combustion engine.
Background
In recent years, large-area power failure accidents are often caused by potential dangerous factors in the power grid, and the power grid is broken down or crashed under the action of certain inducing factors. The black start is the help of other networks after the whole power grid or the system is stopped because of faults, and the unit without the self-starting capability is driven by the start of the unit with the self-starting capability in the system, so that the recovery range of the power system is gradually enlarged, and finally the recovery of the whole power system is realized. However, the existing black start system has poor voltage stability and slow start in the start process, so that the regional power grid cannot safely and stably run.
In the prior art, although an artificial intelligent method is proposed to rapidly predict the no-load closing overvoltage. However, the factors influencing the black start overvoltage (namely the no-load line switching-on overvoltage) are numerous, the influence of the factors such as line parameters, a breaker switching-on initial phase angle and the like on the overvoltage is not considered in the prior art, the prediction result is inaccurate, and in addition, the difference of the influence degree of different factors on the overvoltage is not considered, so that the prediction result is influenced.
Disclosure of Invention
The present application aims to solve at least one of the technical problems in the related art to some extent.
Therefore, a first object of the present application is to provide a black start method of a diesel-electric combined combustion engine, so as to better predict the closing overvoltage of different start paths, and thus select an optimal path.
A second object of the application is to propose a black start system for a diesel-electric combined combustion engine.
A third object of the present application is to propose an electronic device.
A fourth object of the present application is to propose a computer readable storage medium.
To achieve the above object, an embodiment of the first aspect of the present application provides a black start method for a diesel-electric combined gas turbine, configured with a diesel-electric black start unit, the diesel-electric black start unit being configured to start a gas generator through a gas generator start device when a power grid is lost and the gas generator is stopped, the black start method comprising the steps of:
Acquiring switching-on overvoltage and various voltage influence parameters of an idle circuit in a historical black start process of a power grid;
calculating a first weight set and a second weight set of the switching-on overvoltage and the various voltage influence parameters by using the pearson correlation coefficient and the cosine similarity;
Determining a first error and a second error based on the closing overvoltage, the plurality of voltage influencing parameters, the first weight set and the second weight set by using a cyclic neural network model;
Updating the first weight set and the second weight set according to preset iteration times based on the first error and the second error to obtain a first weight optimized set and a second weight optimized set, and further obtaining a target weight set;
And obtaining a switching-on overvoltage target predicted value set based on the target weight set and various real-time voltage influence parameters in the current black start process by using a cyclic neural network model, and selecting a line where the minimum value in the switching-on overvoltage target predicted value set is located as an optimal line to supply power to a power grid so as to finish the black start of the power grid.
In the method of the first aspect of the present application, the calculating the first weight set and the second weight set of the closing overvoltage and the plurality of voltage influencing parameters by using pearson correlation coefficient and cosine similarity includes: calculating a first correlation coefficient set of the switching-on overvoltage and the plurality of voltage influence parameters by using a pearson correlation coefficient; obtaining a first weight set based on the sum of the absolute value of each first correlation coefficient in the first correlation coefficient set and the absolute value of all the first correlation coefficients; calculating a second phase relation number set of the switching-on overvoltage and the multiple voltage influence parameters by using cosine similarity; and obtaining a second weight set based on the sum of the absolute value of each second correlation coefficient in the second correlation number set and the absolute values of all second correlation coefficients.
In the method of the first aspect of the present application, the determining, using a recurrent neural network model, a first error and a second error based on the closing overvoltage, the plurality of voltage influencing parameters, the first weight set and the second weight set includes: obtaining first model input data based on the various voltage influence parameters and the first weight set, inputting the first model input data into a cyclic neural network model to obtain a first overvoltage predicted value set, and obtaining a first error based on the switching-on overvoltage and the first overvoltage predicted value set; and obtaining second model input data based on the multiple voltage influence parameters and the second weight set, inputting the second model input data into a cyclic neural network model to obtain a second overvoltage predicted value set, and obtaining a second error based on the switching-on overvoltage and the second overvoltage predicted value set.
In the method of the first aspect of the present application, updating the first weight set and the second weight set according to a preset iteration number based on the first error and the second error to obtain a first weight optimized set and a second weight optimized set, thereby obtaining a target weight set, includes: judging whether the current iteration times are equal to preset iteration times, if not, comparing the first error with the second error, updating the first weight set and the second weight set according to different requirements based on the comparison result until the current iteration times are equal to the preset iteration times, and obtaining a first weight optimization set and a second weight optimization set based on the first weight set and the second weight set under each iteration time.
In the method of the first aspect of the present application, updating the first weight set and the second weight set according to a preset iteration number based on the first error and the second error to obtain a first weight optimized set and a second weight optimized set, thereby obtaining a target weight set, further includes: determining a first error target value and a second error target value based on the switching-on overvoltage, the plurality of voltage influence parameters, the first weight optimization set and the second weight optimization set by using a cyclic neural network model; and selecting a weight optimization set corresponding to the minimum value in the first error target value and the second error target value as a target weight set.
In the method of the first aspect of the present application, updating the first weight set and the second weight set according to different requirements based on the comparison result until the current iteration number is equal to the preset iteration number includes: if the first error is larger than the second error, respectively updating the first weight set and the second weight set according to the first step length and the second step length; and if the first error is smaller than or equal to the second error, respectively updating the first weight set and the second weight set according to the first proportion and the second proportion.
In the method of the first aspect of the present application, the obtaining a first weight optimization set and a second weight optimization set based on the first weight set and the second weight set under each iteration number includes: and obtaining a first weight optimization set and a second weight optimization set based on the first weight set and the second weight set at the last iteration and the first weight set and the second weight set under the corresponding iteration times when the sum of the first error and the second error is minimum.
To achieve the above object, a second aspect of the present application provides a black start system of a diesel-electric combined combustion engine, configured with a diesel black start unit for starting a gas generator via a gas generator start device when a power grid is lost and the gas generator is stopped, the black start system comprising the steps of:
The acquisition module is used for acquiring the switching-on overvoltage and various voltage influence parameters of the idle circuit in the historical black start process of the power grid;
The weight calculation module is used for calculating a first weight set and a second weight set of the switching-on overvoltage and the various voltage influence parameters by using the pearson correlation coefficient and the cosine similarity;
The error calculation module is used for determining a first error and a second error based on the switching-on overvoltage, the various voltage influence parameters, the first weight set and the second weight set by using a cyclic neural network model;
the optimization module is used for updating the first weight set and the second weight set according to the preset iteration times based on the first error and the second error to obtain a first weight optimization set and a second weight optimization set, and further obtaining a target weight set;
the prediction module is used for obtaining a switching-on overvoltage target predicted value set based on the target weight set and various real-time voltage influence parameters in the current black start process by using the cyclic neural network model, and selecting a line where the minimum value in the switching-on overvoltage target predicted value set is located as an optimal line to supply power to the power grid so as to complete the black start of the power grid.
To achieve the above object, an embodiment of a third aspect of the present application provides an electronic device, including: a processor, and a memory communicatively coupled to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method according to the first aspect of the present application.
To achieve the above object, an embodiment of a fourth aspect of the present application provides a computer-readable storage medium having stored therein computer-executable instructions for implementing the method set forth in the first aspect of the present application when executed by a processor.
The application provides a black start method, a system, electronic equipment and a storage medium of a diesel-engine combined combustion engine, which are provided with a diesel black start unit, wherein the diesel black start unit is used for starting a gas generator through the gas generator start equipment when a power grid is in power failure to stop the gas generator, and the black start method comprises the following steps: acquiring switching-on overvoltage and various voltage influence parameters of an idle circuit in a historical black start process of a power grid; calculating a first weight set and a second weight set of the switching-on overvoltage and various voltage influence parameters by using the pearson correlation coefficient and the cosine similarity; determining a first error and a second error based on the closing overvoltage, the plurality of voltage influence parameters, the first weight set and the second weight set by using a cyclic neural network model; updating the first weight set and the second weight set according to preset iteration times based on the first error and the second error to obtain a first weight optimized set and a second weight optimized set, and further obtaining a target weight set; and (3) utilizing a cyclic neural network model, obtaining a switching-on overvoltage target predicted value set based on a target weight set and various real-time voltage influence parameters in the current black start process, and selecting a line where the minimum value in the switching-on overvoltage target predicted value set is located as an optimal line to supply power to a power grid so as to finish the black start of the power grid. Under the condition, the influence of various voltage influence parameters on the switching-on overvoltage is considered, the first weight set and the second weight set are obtained by utilizing the pearson correlation coefficient and the cosine similarity, the first error and the second error are further obtained, the target weight set is obtained according to the preset iteration times based on the first error and the second error, the switching-on overvoltage target predicted value set is obtained based on the target weight set and various real-time voltage influence parameters in the current black start process, and then the optimal circuit is obtained, wherein the target weight set fully considers the influence degree of different factors on the overvoltage, the accuracy of black start switching-on overvoltage prediction is improved, and therefore the switching-on overvoltage of different start paths can be predicted better, and the optimal path can be selected.
Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a schematic diagram of a power plant and grid connection provided by an embodiment of the present application;
fig. 2 is a schematic flow chart of a black start method of a diesel-engine combined combustion engine according to an embodiment of the present application;
fig. 3 is a schematic flow chart of a black start method of a diesel-engine combined combustion engine according to an embodiment of the present application;
Fig. 4 is a block diagram of a black start system of a diesel-engine combined combustion engine according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present application and should not be construed as limiting the application.
The black start method and system of the diesel-electric combined combustion engine according to the embodiment of the application are described below with reference to the accompanying drawings.
The embodiment of the application provides a black start method of a diesel-engine combined fuel engine, which is used for predicting the closing overvoltage of different start paths better so as to select an optimal path.
In the application, the power plant is provided with a diesel blackout starting unit which is used for starting the gas generator through gas generator starting equipment when the gas generator is stopped due to power failure of the power grid.
Fig. 1 is a schematic diagram of connection between a power plant and a power grid according to an embodiment of the present application.
As shown in fig. 1, the power plant includes a diesel generator system (also called a diesel blackout start unit) and a gas generator system, the diesel generator system is connected with the gas generator system, the gas generator system is connected with a power grid through a plurality of paths, and the gas generator system includes a gas generator start device and a gas generator. Wherein the gas generator is used for generating electricity. The diesel black start unit is used for supplying power to the gas generator start equipment to recover a reference voltage value when the power grid is powered off and the gas generator is stopped, then starts the gas generator based on the reference voltage value, and then supplies power to the power grid through one of a plurality of paths to complete black start. In order to select an optimal path to finish black start of the power grid, an overvoltage prediction system is arranged to conduct switching-on overvoltage prediction on different paths. The overvoltage prediction system is also called a black start system of the diesel-engine combined combustion engine. The overvoltage prediction system is used for executing the black start method of the diesel-engine combined combustion engine.
Fig. 2 is a schematic flow chart of a black start method of a diesel-engine combined combustion engine according to an embodiment of the application. Fig. 3 is a specific flow chart of a black start method of a diesel-engine combined combustion engine provided by the embodiment of the application.
As shown in fig. 2, the black start method of the diesel-electric combined combustion engine comprises the following steps:
step S101, acquiring the switching-on overvoltage and various voltage influence parameters of an idle circuit in the historical black start process of the power grid.
In step S101, the number of the closing overvoltages of the idle line in the acquired grid history black start process may be n. All the acquired closing overvoltages may be referred to as a closing overvoltage set. The set of closing overvoltages consisting of n closing overvoltages may be denoted by the symbol Y.
In step S101, each of the closing overvoltages corresponds to a plurality of voltage influencing parameters. The multiple voltage influence parameters comprise the length of a closing line, the compensation value of a line shunt reactor, a power supply resistance, a power supply leakage reactance, the resistance of the line per kilometer, the positive sequence reactance of the line per kilometer and a closing initial phase angle. The various voltage influencing parameters in the historical black start process can be represented by historical original data X, wherein the historical original data X can be represented as x= (X 1、X2、X3、X4、X5、X6、X7), X 1 is n switching-on line lengths, X 2 is n line shunt reactor compensation values, X 3 is n power supply resistances, X 4 is n power supply leakage reactance, X 5 is n line resistances per kilometer, X 6 is n line positive sequence reactance per kilometer, and X 7 is n switching-on initial phase angles.
Step S102, a first weight set and a second weight set of the switching-on overvoltage and various voltage influence parameters are calculated by using the Pearson correlation coefficient and the cosine similarity.
In step S102, calculating a first weight set and a second weight set of the closing overvoltage and the plurality of voltage influence parameters using the pearson correlation coefficient and the cosine similarity, including: calculating a first correlation coefficient set of a switching-on overvoltage and various voltage influence parameters by using the Pearson correlation coefficient; obtaining a first weight set based on the sum of the absolute value of each first correlation coefficient in the first correlation coefficient set and the absolute value of all the first correlation coefficients; calculating a second phase relation number set of the switching-on overvoltage and various voltage influence parameters by using cosine similarity; and obtaining a second weight set based on the sum of the absolute value of each second correlation coefficient in the second correlation number set and the absolute values of all second correlation coefficients.
In step S102, it is easy to understand that the pearson correlation coefficient can measure the wireless correlation and the degree of correlation between 2 features, so that the pearson correlation coefficient is used to measure the correlation between the black start overvoltage (i.e. the closing overvoltage) and other features (i.e. various voltage influencing parameters) in step S102, and the pearson correlation coefficient satisfies:
Wherein ρ i represents the correlation strength between the ith voltage influence parameter and the closing overvoltage, ρ i is positive and represents the positive correlation between the ith voltage influence parameter and the closing overvoltage, and ρ i is negative and represents the negative correlation between the ith voltage influence parameter and the closing overvoltage. i=1, 2, …,7, i.e. the first set of correlation coefficients ρ is ρ= (ρ 1、ρ2、…、ρ7). First set of correlation coefficients Can be seen as a 7 x 1 matrix. X 1i represents the sum of n values of the i-th voltage influence parameter in the influence parameter raw data set, and Y 1 represents the sum of n closing overvoltages. E () is covariance.
Any one of the first weights in the first weight set satisfies:
In the method, in the process of the invention, The first weight of the i-th voltage influencing parameter is represented, i=1, 2, …, 7.
In step S102, it is easy to understand that the cosine similarity measures the wireless correlation and the degree of correlation between 2 features by calculating the cosine value of the included angle between two vectors. Therefore, in step S102, the correlation between the black start overvoltage and other features is measured by using the cosine similarity, and the cosine similarity satisfies:
wherein q i represents the correlation strength between the ith voltage influence parameter and the closing overvoltage, i=1, 2, …,7, i.e. the second correlation coefficient set q is . The second set of phase relations q can be seen as a 7 x 1 matrix. Where S cos () represents a cosine function.
Any one of the second weights in the second weight set satisfies:
In the method, in the process of the invention, A second weight representing an i-th voltage influencing parameter, i=1, 2, …, 7.
Step S103, determining a first error and a second error based on the switching-on overvoltage, the plurality of voltage influence parameters, the first weight set and the second weight set by using the cyclic neural network model.
In step S103, determining, using the recurrent neural network model, a first error and a second error based on the closing overvoltage, the plurality of voltage influencing parameters, the first weight set and the second weight set, including: obtaining first model input data based on various voltage influence parameters and a first weight set, inputting the first model input data into a cyclic neural network model to obtain a first overvoltage predicted value set, and obtaining a first error based on the switching-on overvoltage and the first overvoltage predicted value set; and obtaining second model input data based on the multiple voltage influence parameters and the second weight set, inputting the second model input data into the cyclic neural network model to obtain a second overvoltage predicted value set, and obtaining a second error based on the switching-on overvoltage and the second overvoltage predicted value set.
It is easy to understand that in step S103, the recurrent neural network model may be selected from a GRU (gated recurrent unit ) network model. The GRU network is an improved model of an LSTM (Long Short Term Memory networks long and short term memory) network, and the forgetting gate and the input gate are integrated into an updating gate, so that training parameters of the network are reduced to a certain extent, and meanwhile, the memory of effective information can be ensured.
In step S103, the first model input data may be represented by X ', the first set of overvoltage predictors may be represented by Y', the second model input data may be represented by X ", and the second set of overvoltage predictors may be represented by Y". Specifically, the first model input data X' satisfiesThe second model input data X' satisfies/>Wherein X represents historical raw data,/>First weight representing the i-th voltage influencing parameter,/>A second weight representing an ith voltage influencing parameter. And substituting X ' and X ' into the GRU network model to predict to obtain a first overvoltage predicted value set Y ' and a second overvoltage predicted value set Y "(see FIG. 3).
Specifically, the first error and the second error may be calculated using the average relative error. Wherein the average relative error e MAPE satisfies:
Wherein Y i is an actual value, which is the i-th value in the closing overvoltage set Y, Y i * is a predicted value, and when Y i * is the i-th value in the first overvoltage predicted value set Y', a first error is calculated When Y i * is the i-th value in the second set of overvoltage predictors Y', a second error/>, is calculated(See fig. 3), N is the total number of samples, i.e., the number of closing overvoltages in the closing overvoltage set Y.
Step S104, updating the first weight set and the second weight set according to the preset iteration times based on the first error and the second error to obtain a first weight optimized set and a second weight optimized set, and further obtaining a target weight set.
In step S104, updating the first weight set and the second weight set according to the preset iteration number based on the first error and the second error to obtain a first weight optimized set and a second weight optimized set, thereby obtaining a target weight set, including:
Judging whether the current iteration times are equal to preset iteration times, if not, comparing the first error with the second error, updating the first weight set and the second weight set according to different requirements based on the comparison result until the current iteration times are equal to the preset iteration times, and obtaining a first weight optimization set and a second weight optimization set based on the first weight set and the second weight set under each iteration time; determining a first error target value and a second error target value based on the switching-on overvoltage, the various voltage influence parameters, the first weight optimization set and the second weight optimization set by using a cyclic neural network model; and selecting a weight optimization set corresponding to the minimum value in the first error target value and the second error target value as a target weight set.
Updating the first weight set and the second weight set according to different requirements based on the comparison result until the current iteration number is equal to the preset iteration number, including: if the first error is larger than the second error, respectively updating the first weight set and the second weight set according to the first step length and the second step length; and if the first error is smaller than or equal to the second error, respectively updating the first weight set and the second weight set according to the first proportion and the second proportion.
Obtaining a first weight optimization set and a second weight optimization set based on the first weight set and the second weight set under each iteration number, including: and obtaining a first weight optimization set and a second weight optimization set based on the first weight set and the second weight set at the last iteration and the first weight set and the second weight set under the corresponding iteration times when the sum of the first error and the second error is minimum. Taking the preset iteration number as 20 as an example, any one of the first weight optimization values in the first weight optimization set satisfies:
In the method, in the process of the invention, First weight optimized value for ith voltage influencing parameter,/>The first weight of the ith voltage influence parameter when the iteration number is 20; /(I)Is the second weight of the ith voltage-influencing parameter at an iteration number of 20.
Any one of the second weight optimization values in the second weight optimization set satisfies:
In the method, in the process of the invention, Optimizing the value for the second weight of the ith voltage influencing parameter,/>For/>+/>The first weight of the ith voltage influence parameter under the corresponding iteration number of the minimum time; /(I)For/>+/>And the second weight set of the ith voltage influence parameter under the minimum corresponding iteration number.
Specifically, as shown in fig. 3, after the first error and the second error are obtained, it is determined whether the current iteration number T (the initial value of the iteration number is 1) is equal to the preset iteration number (for example, 20), and if not, the first error is comparedAnd a second error/>; If/>＞/>The first weight set and the second weight set are updated according to the first step size (such as +0.05) and the second step size (such as-0.05), namely/>, respectively，/>; Updating the iteration times (T=T+1), returning to acquire the first error and the second error based on the updated first weight set and second weight set, ending the updating if the current iteration times are equal to the preset iteration times, continuing to judge the new first error and second error if the current iteration times are not equal to the preset iteration times, ending the updating, and if the new first error and second error occur/>≤/>The first weight set and the second weight set are updated according to a first ratio (e.g. 0.99) and a second ratio (e.g. 1.01), respectively, i.e./>，/>; Updating the iteration times (T=T+1), and returning to acquire the first error and the second error based on the updated first weight set and second weight set again until the current iteration times are equal to the preset iteration times, and ending the updating jump-out loop;
As shown in fig. 3, a first weight optimization set and a second weight optimization set are obtained through calculation; obtaining corresponding model input data based on a first weight optimization set and a second weight optimization set, wherein the first weight optimization set corresponds to the model input data X '(2), and the corresponding model input data X' (2) meets the following requirements The second set of weight optimizations corresponds to model input data X '(2), the model input data X' (2) satisfying/>Wherein X represents historical original data, and X ' (2) and X ' ' (2) are respectively substituted into the GRU network model to be predicted so as to obtain a corresponding overvoltage predicted value set; combining the closing overvoltage and referring to the average relative error to calculate a corresponding first error target value and a corresponding second error target value, and selecting the smaller weight coefficient (namely a weight optimization set) in the first error target value and the second error target value as a final weight coefficient/>(I.e., a set of target weights).
Step S105, a cyclic neural network model is utilized, a switching-on overvoltage target predicted value set is obtained based on a target weight set and various real-time voltage influence parameters in the current black start process, and a line where the minimum value in the switching-on overvoltage target predicted value set is located is selected as an optimal line to supply power to a power grid so as to complete black start of the power grid.
In step S105, a plurality of real-time voltage influencing parameters may be used with the real-time data set X 0. The real-time data set X 0 comprises the step of acquiring the length of a closing line, the compensation value of a line shunt reactor, the power supply resistance, the leakage reactance of the power supply, the resistance of each kilometer of the line, the positive sequence reactance of each kilometer of the line and the closing initial phase angle in real time in the current black start process.
Based on the target weight setAnd the real-time data set X 0 to obtain target model input data M, i.e., m=/>X 0. And substituting the target model input data M into the GRU network model to predict to obtain a final prediction result (namely a closing overvoltage target prediction value set). And selecting a line where the minimum switching overvoltage target predicted value is located from the switching overvoltage target predicted value set as an optimal line to supply power to the power grid so as to finish black start of the power grid.
In order to verify the effect of the method, an equivalent network for calculating the closing overvoltage of the 500 kV no-load line in the black start process is constructed. The effectiveness of the combined model-based statistical overvoltage fast prediction method for the black-start idle line is verified by using the network as an example.
Setting a power supply resistor Rs=15-45 Ω, the interval is 10Ω, the line length l=280-350 km, the interval is 40 km, and the parallel reactor compensation Q=70-80 MVAR, the interval is 5 MVAR; the leakage reactance xs=125-140 Ω,5 Ω interval.
The various voltage influence parameters comprise 7 voltage influence parameters including a closing line length, a line shunt reactor compensation value, a power supply resistance, a power supply leakage reactance, a line resistance per km, a line positive sequence reactance per km and a closing initial phase angle.
Mean absolute error (Mean absolute error, MAE), mean absolute percent error (Mean absolute percentage error, MAPE) and root mean square error (Root mean square error, RMSE) were chosen as model evaluation criteria, where all models used MAE as a loss function during training. The experiment was also compared with independent pearson coefficient-GRU model and cosine similarity-GRU model. The results are shown in Table 1.
Table 1 model evaluation criteria table
From the table, the model of the application has higher prediction accuracy than the model of the application which singly adopts the pearson coefficient or cosine similarity, and the importance of the inertia weight coefficient for improving the accuracy is proved.
In order to achieve the above embodiment, the application further provides a black start system of the diesel-electric combined gas turbine, which is provided with a diesel black start unit, wherein the diesel black start unit is used for starting the gas generator through the gas generator start device when the gas generator is stopped due to power failure of a power grid.
Fig. 4 is a block diagram of a black start system of a diesel-engine combined combustion engine according to an embodiment of the present application.
As shown in fig. 4, the black start system of the diesel-electric combined combustion engine comprises an acquisition module 11, a weight calculation module 12, an error calculation module 13, an optimization module 14 and a prediction module 15, wherein:
The acquisition module 11 is used for acquiring the switching-on overvoltage and various voltage influence parameters of the idle circuit in the historical black start process of the power grid;
the weight calculation module 12 is configured to calculate a first weight set and a second weight set of the closing overvoltage and various voltage influence parameters by using the pearson correlation coefficient and the cosine similarity;
An error calculation module 13, configured to determine a first error and a second error based on the switching-on overvoltage, the plurality of voltage influencing parameters, the first weight set and the second weight set using the recurrent neural network model;
the optimizing module 14 is configured to update the first weight set and the second weight set according to a preset iteration number based on the first error and the second error to obtain a first weight optimized set and a second weight optimized set, thereby obtaining a target weight set;
the prediction module 15 is configured to obtain a set of target predicted values of the closing overvoltage based on the target weight set and multiple real-time voltage influence parameters in the current black start process by using the cyclic neural network model, and select a line where a minimum value in the set of target predicted values of the closing overvoltage is located as an optimal line to supply power to the power grid so as to complete black start of the power grid.
Further, in one possible implementation of the embodiment of the present application, the weight calculation module 12 is specifically configured to: calculating a first correlation coefficient set of a switching-on overvoltage and various voltage influence parameters by using the Pearson correlation coefficient; obtaining a first weight set based on the sum of the absolute value of each first correlation coefficient in the first correlation coefficient set and the absolute value of all the first correlation coefficients; calculating a second phase relation number set of the switching-on overvoltage and various voltage influence parameters by using cosine similarity; and obtaining a second weight set based on the sum of the absolute value of each second correlation coefficient in the second correlation number set and the absolute values of all second correlation coefficients.
Further, in one possible implementation manner of the embodiment of the present application, the error calculation module 13 is specifically configured to: obtaining first model input data based on various voltage influence parameters and a first weight set, inputting the first model input data into a cyclic neural network model to obtain a first overvoltage predicted value set, and obtaining a first error based on the switching-on overvoltage and the first overvoltage predicted value set; and obtaining second model input data based on the multiple voltage influence parameters and the second weight set, inputting the second model input data into the cyclic neural network model to obtain a second overvoltage predicted value set, and obtaining a second error based on the switching-on overvoltage and the second overvoltage predicted value set.
Further, in one possible implementation of the embodiment of the present application, the optimization module 14 is specifically configured to: judging whether the current iteration times are equal to preset iteration times, if not, comparing the first error with the second error, updating the first weight set and the second weight set according to different requirements based on the comparison result until the current iteration times are equal to the preset iteration times, and obtaining a first weight optimization set and a second weight optimization set based on the first weight set and the second weight set under each iteration time; determining a first error target value and a second error target value based on the switching-on overvoltage, the various voltage influence parameters, the first weight optimization set and the second weight optimization set by using a cyclic neural network model; and selecting a weight optimization set corresponding to the minimum value in the first error target value and the second error target value as a target weight set.
Further, in a possible implementation manner of the embodiment of the present application, the optimizing module 14 updates the first weight set and the second weight set according to different requirements based on the comparison result until the current iteration number is equal to the preset iteration number, including: if the first error is larger than the second error, respectively updating the first weight set and the second weight set according to the first step length and the second step length; and if the first error is smaller than or equal to the second error, respectively updating the first weight set and the second weight set according to the first proportion and the second proportion.
Further, in a possible implementation manner of the embodiment of the present application, the optimizing module 14 obtains a first weight optimization set and a second weight optimization set based on the first weight set and the second weight set under each iteration number, including: and obtaining a first weight optimization set and a second weight optimization set based on the first weight set and the second weight set at the last iteration and the first weight set and the second weight set under the corresponding iteration times when the sum of the first error and the second error is minimum.
It should be noted that the explanation of the foregoing embodiment of the black start method of the diesel-hybrid gas turbine is also applicable to the black start system of the diesel-hybrid gas turbine of this embodiment, and will not be repeated here.
In the embodiment of the application, a diesel blackening starting unit is configured, and the diesel blackening starting unit is used for starting the gas generator through gas generator starting equipment when the gas generator is stopped due to power failure of a power grid, and the black starting method comprises the following steps: acquiring switching-on overvoltage and various voltage influence parameters of an idle circuit in a historical black start process of a power grid; calculating a first weight set and a second weight set of the switching-on overvoltage and various voltage influence parameters by using the pearson correlation coefficient and the cosine similarity; determining a first error and a second error based on the closing overvoltage, the plurality of voltage influence parameters, the first weight set and the second weight set by using a cyclic neural network model; updating the first weight set and the second weight set according to preset iteration times based on the first error and the second error to obtain a first weight optimized set and a second weight optimized set, and further obtaining a target weight set; and (3) utilizing a cyclic neural network model, obtaining a switching-on overvoltage target predicted value set based on a target weight set and various real-time voltage influence parameters in the current black start process, and selecting a line where the minimum value in the switching-on overvoltage target predicted value set is located as an optimal line to supply power to a power grid so as to finish the black start of the power grid. Under the condition, the influence of various voltage influence parameters on the switching-on overvoltage is considered, the first weight set and the second weight set are obtained by utilizing the pearson correlation coefficient and the cosine similarity, the first error and the second error are further obtained, the target weight set is obtained according to the preset iteration times based on the first error and the second error, the switching-on overvoltage target predicted value set is obtained based on the target weight set and various real-time voltage influence parameters in the current black start process, and then the optimal circuit is obtained, wherein the target weight set fully considers the influence degree of different factors on the overvoltage, the accuracy of the black start switching-on overvoltage prediction is improved, and therefore the switching-on overvoltage of different start paths can be predicted better, and the optimal path (namely the optimal circuit) is selected.
The method and the system consider different influence degrees of different factors on the overvoltage, quantitatively analyze the different factors, and can better predict the pore-o-line switching-on overvoltage of different starting paths so as to select the optimal path.
In order to achieve the above embodiment, the present application further provides an electronic device, including: a processor, a memory communicatively coupled to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the methods provided by the previous embodiments.
In order to implement the above embodiment, the present application also proposes a computer-readable storage medium having stored therein computer-executable instructions, which when executed by a processor are configured to implement the method provided in the foregoing embodiment.
In order to implement the above embodiments, the present application also proposes a computer program product comprising a computer program which, when executed by a processor, implements the method provided by the above embodiments.
In the foregoing description of embodiments, reference has been made to the terms "one embodiment," "some embodiments," "example," "a particular example," or "some examples," etc., meaning that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.
Claims (8)
1. The black start method of the diesel-electric combined combustion engine is characterized by being provided with a diesel black start unit, wherein the diesel black start unit is used for starting a gas generator through gas generator starting equipment when a power grid is powered off to stop the gas generator, and the black start method comprises the following steps of:
Acquiring switching-on overvoltage and various voltage influence parameters of an idle circuit in a historical black start process of a power grid;
calculating a first weight set and a second weight set of the switching-on overvoltage and the various voltage influence parameters by using the pearson correlation coefficient and the cosine similarity;
Obtaining first model input data based on the multiple voltage influence parameters and the first weight set, inputting the first model input data into a cyclic neural network model to obtain a first overvoltage predicted value set, determining a first error based on the first overvoltage predicted value set and the closing overvoltage, obtaining second model input data based on the multiple voltage influence parameters and the second weight set, inputting the second model input data into the cyclic neural network model to obtain a second overvoltage predicted value set, and determining a second error based on the second overvoltage predicted value set and the closing overvoltage;
judging whether the current iteration times are equal to preset iteration times, if not, comparing the first error with the second error, updating the first weight set and the second weight set according to different requirements based on the comparison result until the current iteration times are equal to the preset iteration times, and acquiring a first weight optimization set and a second weight optimization set based on the first weight set and the second weight set under each iteration time, thereby acquiring a target weight set;
And obtaining a switching-on overvoltage target predicted value set based on the target weight set and various real-time voltage influence parameters in the current black start process by using a cyclic neural network model, and selecting a line where the minimum value in the switching-on overvoltage target predicted value set is located as an optimal line to supply power to a power grid so as to finish the black start of the power grid.
2. The black start method of a diesel-electric combined combustion engine according to claim 1, wherein the calculating the first weight set and the second weight set of the closing overvoltage and the plurality of voltage influence parameters using pearson correlation coefficient and cosine similarity includes:
Calculating a first correlation coefficient set of the switching-on overvoltage and the plurality of voltage influence parameters by using a pearson correlation coefficient; obtaining a first weight set based on the sum of the absolute value of each first correlation coefficient in the first correlation coefficient set and the absolute value of all the first correlation coefficients;
Calculating a second phase relation number set of the switching-on overvoltage and the multiple voltage influence parameters by using cosine similarity; and obtaining a second weight set based on the sum of the absolute value of each second correlation coefficient in the second correlation number set and the absolute values of all second correlation coefficients.
3. The method for black start of a diesel-electric combined combustion engine according to claim 1, wherein the method for determining the target weight set further comprises:
Determining a first error target value and a second error target value based on the switching-on overvoltage, the plurality of voltage influence parameters, the first weight optimization set and the second weight optimization set by using a cyclic neural network model;
And selecting a weight optimization set corresponding to the minimum value in the first error target value and the second error target value as a target weight set.
4. The black start method of a diesel-engine combined combustion engine according to claim 1, wherein updating the first weight set and the second weight set according to different requirements based on the comparison result until the current iteration number is equal to the preset iteration number comprises:
If the first error is larger than the second error, respectively updating the first weight set and the second weight set according to the first step length and the second step length;
And if the first error is smaller than or equal to the second error, respectively updating the first weight set and the second weight set according to the first proportion and the second proportion.
5. The black start method of a diesel-engine combined combustion engine according to claim 1, wherein the obtaining the first weight optimized set and the second weight optimized set based on the first weight set and the second weight set for each iteration number includes:
And obtaining a first weight optimization set and a second weight optimization set based on the first weight set and the second weight set at the last iteration and the first weight set and the second weight set under the corresponding iteration times when the sum of the first error and the second error is minimum.
6. The black start system of the diesel-electric combined combustion engine is characterized in that a diesel black start unit is configured, the diesel black start unit is used for starting a gas generator through gas generator starting equipment when a power grid is powered off to stop the gas generator, and the black start system comprises the following steps:
The acquisition module is used for acquiring the switching-on overvoltage and various voltage influence parameters of the idle circuit in the historical black start process of the power grid;
The weight calculation module is used for calculating a first weight set and a second weight set of the switching-on overvoltage and the various voltage influence parameters by using the pearson correlation coefficient and the cosine similarity;
The error calculation module is used for obtaining first model input data based on the various voltage influence parameters and the first weight set, inputting the first model input data into a cyclic neural network model to obtain a first overvoltage predicted value set, determining a first error based on the first overvoltage predicted value set and the closing overvoltage, obtaining second model input data based on the various voltage influence parameters and the second weight set, inputting the second model input data into the cyclic neural network model to obtain a second overvoltage predicted value set, and determining a second error based on the second overvoltage predicted value set and the closing overvoltage;
The optimization module is used for judging whether the current iteration times are equal to preset iteration times, if not, comparing the first error with the second error, updating the first weight set and the second weight set according to different requirements based on a comparison result until the current iteration times are equal to the preset iteration times, and acquiring a first weight optimization set and a second weight optimization set based on the first weight set and the second weight set under each iteration times, so as to acquire a target weight set;
the prediction module is used for obtaining a switching-on overvoltage target predicted value set based on the target weight set and various real-time voltage influence parameters in the current black start process by using the cyclic neural network model, and selecting a line where the minimum value in the switching-on overvoltage target predicted value set is located as an optimal line to supply power to the power grid so as to complete the black start of the power grid.
7. An electronic device, comprising: a processor, and a memory communicatively coupled to the processor;
The memory stores computer-executable instructions;
the processor executes computer-executable instructions stored in the memory to implement the method of any one of claims 1-5.
8. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410179650.0A CN117728504B (en) | 2024-02-18 | 2024-02-18 | Black start system and method for diesel-engine combined combustion engine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410179650.0A CN117728504B (en) | 2024-02-18 | 2024-02-18 | Black start system and method for diesel-engine combined combustion engine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117728504A CN117728504A (en) | 2024-03-19 |
| CN117728504B true CN117728504B (en) | 2024-05-07 |
Family
ID=90200259
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410179650.0A Active CN117728504B (en) | 2024-02-18 | 2024-02-18 | Black start system and method for diesel-engine combined combustion engine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117728504B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106557813A (en) * | 2016-10-25 | 2017-04-05 | 华南理工大学 | The black-start scheme technical problem appraisal procedure of gas turbine distributing-supplying-energy system |
| WO2022052601A1 (en) * | 2020-09-10 | 2022-03-17 | 华为技术有限公司 | Neural network model training method, and image processing method and device |
| CN116073435A (en) * | 2023-03-30 | 2023-05-05 | 西安热工研究院有限公司 | Black start system and method for diesel-engine combined combustion engine |
| CN117057258A (en) * | 2023-10-12 | 2023-11-14 | 西安热工研究院有限公司 | Black-start overvoltage prediction method and system based on weight distribution correlation coefficient |
| CN117353386A (en) * | 2023-08-18 | 2024-01-05 | 湖南华能长江环保科技有限公司 | Black start system and method based on diesel generator coupled combustion engine |
-
2024
- 2024-02-18 CN CN202410179650.0A patent/CN117728504B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106557813A (en) * | 2016-10-25 | 2017-04-05 | 华南理工大学 | The black-start scheme technical problem appraisal procedure of gas turbine distributing-supplying-energy system |
| WO2022052601A1 (en) * | 2020-09-10 | 2022-03-17 | 华为技术有限公司 | Neural network model training method, and image processing method and device |
| CN116073435A (en) * | 2023-03-30 | 2023-05-05 | 西安热工研究院有限公司 | Black start system and method for diesel-engine combined combustion engine |
| CN117353386A (en) * | 2023-08-18 | 2024-01-05 | 湖南华能长江环保科技有限公司 | Black start system and method based on diesel generator coupled combustion engine |
| CN117057258A (en) * | 2023-10-12 | 2023-11-14 | 西安热工研究院有限公司 | Black-start overvoltage prediction method and system based on weight distribution correlation coefficient |
Non-Patent Citations (2)
| Title |
|---|
| A Model Predictive Control Based Generator Start-Up Optimization Strategy for Restoration With Microgrids as Black-Start Resources;Yuxuan Zhao etal.;IEEE Transactions on Power Systems;20181130;第33卷(第6期);第7189-7203页 * |
| 李膨源 ; 顾雪平 ; .基于神经网络的黑启动操作过电压快速预测.电网技术.2006,第30卷(第03期),第66-70页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117728504A (en) | 2024-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | An advanced Lithium-ion battery optimal charging strategy based on a coupled thermoelectric model | |
| Zhou et al. | Online monitoring of voltage stability margin using an artificial neural network | |
| Yi et al. | Robust scheduling scheme for energy storage to facilitate high penetration of renewables | |
| US20230029810A1 (en) | Battery model construction method and battery degradation prediction device | |
| CN110988723B (en) | LSTM-based battery internal resistance prediction and fault early warning method | |
| CN108205114B (en) | Method and system for predicting service life of battery | |
| CN105469156A (en) | MOA condition management and fault prediction method and MOA condition management and fault prediction system | |
| CN117748501B (en) | Wind power prediction method and system for energy storage auxiliary black start | |
| CN117728504B (en) | Black start system and method for diesel-engine combined combustion engine | |
| DE102019125375A1 (en) | State value for rechargeable batteries | |
| CN109522615B (en) | Method and device for evaluating zero-sequence inrush current tolerance of relay protection of power system | |
| CN106680722B (en) | Method and device for predicting OCV-SOC curve on line in real time | |
| CN104201723A (en) | Off-network microgrid reliability assessment method based on timing simulation | |
| CN116718921A (en) | Battery state of charge prediction method and device based on multiple models | |
| CN113933718B (en) | Retired battery capacity sorting method, retired battery capacity sorting device, retired battery capacity sorting equipment and storage medium | |
| CN115856641A (en) | Method and device for predicting remaining charging time of battery and electronic equipment | |
| CN114757548A (en) | Wind power energy storage equipment adjusting performance evaluation method adopting scene construction | |
| Aharon et al. | Premeditated generic energy storage model for sources rating selection in grid applications | |
| CN117744893B (en) | Wind speed prediction method and system for energy storage auxiliary black start | |
| CN110568362B (en) | Method and device for determining cell performance parameters | |
| CN114328473A (en) | Battery data detection method and device | |
| CN117829202B (en) | Energy storage auxiliary black start wind speed prediction method and system based on double errors | |
| CN110797906B (en) | Method and device for determining maximum installed capacity of wind power base and storage medium | |
| CN110601251B (en) | Voltage prediction method and device in wind power plant | |
| Guo et al. | Analysis of Short-Term Voltage Stability Influencing Factors and Mechanisms in Low Inertia Active Distribution Networks |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |