A data mining method, system, terminal and medium for operation rules of an electric power plant

Abstract

The application discloses a kind of data mining methods, systems, terminals and media of electric pumping station operation rule, it is related to electric pumping station data analysis technical field, its technical scheme main point is: to the cumulative rainfall in pump station operation record sequence and pump station opening state are carried out sliding correlation analysis, obtain the time offset scale of correlation reaching peak value;Determine the perspective time scale not less than time offset scale, and according to the original electric pumping station data is carried out data perspective according to perspective time scale, obtain data perspective result;According to data perspective result, the correlation analysis is carried out to cumulative rainfall and pump station state, and with the rainfall of the highest correlation of cumulative rainfall corresponding as the rainfall response value of pump station opening state.The application can greatly improve the correctness of electric pumping station operation rule compared with original water level start boundary, improve the matching degree of electric pumping station model simulation and actual operation condition, provide better basis for hydrology and hydrodynamic matching of later model.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power station data analysis, more particularly, it relates to a data mining method, system, terminal and medium for power station operation rules. BACKGROUND

[0002] The power station operation rule is an important part of the hydrodynamic water quality model, and the simplification result of the rule directly affects the rationality of the result of the hydrodynamic water quality model.

[0003] At present, most of the power station operation rules are set by water level, and the power station is started when the water level reaches a certain value, and the power station is stopped when the water level decreases to a low water level. However, in the actual operation process of the power station, the actual operation condition is greatly affected by human factors, and the method of presetting water level response in the hydrological and hydrodynamic model cannot reflect the real operation condition of the power station, which is not conducive to the later calibration of the hydrodynamic water quality model.

[0004] Therefore, how to research and design a data mining method, system, terminal and medium for power station operation rules which can overcome the above defects is a problem we need to solve urgently. SUMMARY

[0005] To solve the problems in the prior art, the purpose of the present application is to provide a data mining method, system, terminal and medium for power station operation rules, which can greatly improve the correctness of the power station operation rules, improve the matching degree of the power station model simulation and the actual operation condition, provide a better basis for the later hydrological and hydrodynamic matching of the model, for example, applied to small basins with an area of less than 100km 2 .

[0006] The above technical purpose of the present application is realized by the following technical scheme:

[0007] In a first aspect, a data mining method for power station operation rules is provided, comprising the following steps:

[0008] Performing sliding correlation analysis on the cumulative rainfall and the pump station opening state in the pump station operation record sequence to obtain a time offset scale at which the correlation reaches a peak value;

[0009] Determining a perspective time scale not less than the time offset scale, and performing data perspective on the original power station data according to the perspective time scale to obtain a data perspective result;

[0010] Performing correlation analysis on the cumulative rainfall and the pump station state according to the data perspective result, and taking the rainfall corresponding to the cumulative rainfall with the highest correlation as the rainfall response value of the pump station opening state.

[0011] Preferably, the pump station operation record sequence comprises the inner river water level, the outer river water level, the pump station state and the accumulated rainfall.

[0012] Preferably, the data in the pump station operation record sequence is in an interval time of 5-30 min.

[0013] Preferably, the process of obtaining the time offset scale is specifically as follows:

[0014] The time point corresponding to the maximum correlation coefficient in the sliding correlation analysis is selected as the sliding termination point;

[0015] The interval time between the sliding start point and the sliding termination point in the sliding correlation analysis is taken as the time offset scale.

[0016] Preferably, the process of determining the perspective time scale is specifically as follows:

[0017] The correlation time point with a correlation coefficient greater than a set coefficient in the sliding correlation analysis is selected;

[0018] The time region with the maximum correlation density is selected;

[0019] The sum of the interval time length of the time region and the time offset scale is taken as the perspective time scale;

[0020] Or, the shortest perspective scale greater than the time offset scale in the Excel table is taken as the perspective time scale.

[0021] Preferably, the correlation density is the ratio of the number of correlation time points in the time region to the interval time length of the time region.

[0022] Preferably, the rainfall response value can be taken as the boundary condition of the hydrological and hydrodynamic model and incorporated into the model.

[0023] In a second aspect, a data mining system for pump station operation rules is provided, comprising:

[0024] a sliding analysis module, configured to perform sliding correlation analysis on the accumulated rainfall and the pump station start state in the pump station operation record sequence, and obtain a time offset scale with an extreme correlation;

[0025] a perspective analysis module, configured to determine a perspective time scale not less than the time offset scale, and perform data perspective on the original pump station data according to the perspective time scale, and obtain a data perspective result;

[0026] a response analysis module, configured to perform correlation analysis on the accumulated rainfall and the pump station start state according to the data perspective result, and take the rainfall corresponding to the accumulated rainfall with the highest correlation as the rainfall response value of the pump station start state.

[0027] In a third aspect, a computer terminal is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the data mining method of the operation rule of the pumping station according to any one of the first aspect when executing the program.

[0028] In a fourth aspect, a computer readable medium is provided, and a computer program is stored on the computer readable medium, and the computer program is executable on the processor to implement the data mining method of the operation rule of the pumping station according to any one of the first aspect.

[0029] Compared with the prior art, the present application has the following beneficial effects:

[0030] 1. The data mining method of the operation rule of the pumping station provided by the present application can effectively avoid the influence of the original accumulated rainfall and the opening state of the pumping station in the operation record sequence on the accuracy and reliability of data mining, because the original accumulated rainfall and the opening state of the pumping station in the operation record sequence do not have correlation.

[0031] 2. The sum of the interval length of the time region and the time offset scale is used as the perspective time scale, so that at least two regions with the strongest correlation can be ensured in the data perspective processing process, and the accuracy of the rainfall response value obtained is enhanced. BRIEF DESCRIPTION OF DRAWINGS

[0032] The accompanying drawings, which are included to provide a further understanding of the embodiments of the present application and constitute a part of the application, do not constitute limitations to the embodiments of the present application. In the drawings:

[0033] Figure 1 is a flow chart in the embodiments of the present application;

[0034] Figure 2 is a pumping station opening diagram when the accumulated rainfall reaches 40mm in the embodiments of the present application;

[0035] Figure 3 is a result diagram of model verification in the embodiments of the present application;

[0036] Figure 4 is a system block diagram in the embodiments of the present application. DETAILED DESCRIPTION

[0037] In order to make the objects, technical solutions and advantages of the present application clearer, further detailed description will be made to the present application in combination with embodiments and drawings, the illustrative embodiments and the description thereof are only used to explain the present application, and do not limit the present application.

[0038] Embodiment 1: a data mining method for operation rules of an electric pumping station, as shown in the following formula, comprising the following steps: Figure 1

[0039] Step one: performing sliding correlation analysis on the accumulated rainfall and the opening state of the pumping station in the pumping station operation record sequence to obtain a time offset scale at which the correlation reaches a peak value;

[0040] Step two: determining a perspective time scale not less than the time offset scale, and performing data perspective on the original electric pumping station data according to the perspective time scale to obtain a data perspective result;

[0041] Step three: performing correlation analysis on the accumulated rainfall and the pumping station state according to the data perspective result, and taking the rainfall corresponding to the accumulated rainfall with the highest correlation as the rainfall response value of the opening state of the pumping station.

[0042] In the present embodiment, the pumping station operation record sequence includes but is not limited to the inner river level, the outer river level, the pumping station state, the accumulated rainfall and other data items. The data in the pumping station operation record sequence adopts an interval time of 5 min, 10 min, 15 min, 30 min, etc., and the rainfall data event interval is 5-60 min.

[0043] In the present embodiment, the obtaining process of the time offset scale is specifically: selecting the time point corresponding to the maximum correlation coefficient between the accumulated rainfall and the pumping station state in the sliding correlation analysis as the sliding termination point; taking the interval time between the sliding start point and the sliding termination point of the sliding correlation analysis as the time offset scale. The sliding correlation analysis can be completed by using the CCF module in the Statsmodels data statistical analysis library in Python.

[0044] As an optional implementation, the perspective time scale can be randomly selected to be a time scale greater than or equal to the time offset scale. For example, the shortest perspective scale in the Excel table greater than the time offset scale is selected as the perspective time scale, and the data perspective table function scale in the Excel table includes but is not limited to hourly, daily, monthly, quarterly, annual, etc.

[0045] ​As an alternative implementation, to ensure at least two highly correlated regions and thus enhance the accuracy of rainfall response values, the perspective time scale can be determined as follows: Select relevant time points in the sliding correlation analysis where the correlation coefficient is greater than a set coefficient; select the time region with the highest correlation density; and use the sum of the time interval duration and the time offset scale as the perspective time scale. Here, correlation density is the ratio of the number of relevant time points within the time region to the time interval duration of the time region.

[0046] The rainfall response values ​​obtained above can be incorporated into the hydrological and hydrodynamic model as boundary conditions.

[0047] The following is an example of an electric pumping station operation time series data set containing 50,000 data points with a time interval of 5 minutes. The data columns include the water level of the inner river, the water level of the outer river, the pumping station's operating status, and the cumulative rainfall.

[0048] The correlation between the water levels of the inner and outer rivers, cumulative rainfall, and the operation status of the pumping stations was analyzed. Here, nei represents the water level of the inner river, wai represents the water level of the outer river, nminusw represents the difference between the two water levels, state represents the pumping station status, and rainacc108 represents the cumulative rainfall after the shift. The analysis shows that the correlation coefficient between state and nei is 0.02***, between state and wai is 0.11***, and between state and nminusw is -0.11***. Before the shift, the correlation coefficient between the pumping station status state and rainacc108 was 0 and not significant. However, after the shift, the correlation coefficient between rainacc108 and the pumping station status state is 0.21***, indicating a significant correlation. Figure 2 As shown, the electric pumping station is activated after the cumulative rainfall reaches 40mm.

[0049] like Figure 3 As shown, the CCF module analysis revealed that the highest time series correlation coefficient was obtained when the time offset scale was 9h. The original time series data was then viewed using a random perspective time scale, with a perspective time scale of 24h used here. Under the condition of 40mm cumulative rainfall, the correlation with the pump station's operating status was relatively high.

[0050] The rainfall boundary conditions were internalized into the model and validated through the model results. The pump station start-up and shutdown states in the model were matched with the actual pump station operation patterns, and the state matching rate reached over 80%.

[0051] Example 2: A data mining system for the operation rules of electric pumping stations. This system is used to implement the data mining method in Example 1, such as... Figure 4 As shown, it includes a sliding analysis module, a perspective analysis module, and a response analysis module.

[0052] The sliding analysis module is configured to perform sliding correlation analysis on the accumulated rainfall and the pump station opening state in the pump station operation record sequence to obtain a time offset scale at which the correlation reaches an extreme value. The perspective analysis module is configured to determine a perspective time scale that is not less than the time offset scale, and perform data perspective on the original electric pumping station data according to the perspective time scale to obtain a data perspective result. The response analysis module is configured to perform correlation analysis on the accumulated rainfall and the pump station state according to the data perspective result, and take the rainfall corresponding to the accumulated rainfall with the highest correlation as the rainfall response value of the pump station opening state.

[0053] Working principle: firstly, the accumulated rainfall and the pump station opening state in the pump station operation record sequence are subjected to sliding correlation analysis and data perspective processing, which can effectively avoid the influence of the original accumulated rainfall and the pump station opening state in the pump station operation record sequence on the accuracy and reliability of data mining; and then, through time sequence correlation analysis, the actual operation condition boundary data of the electric pumping station are mined, which can greatly improve the correctness of the electric pumping station operation rules and improve the matching degree of the electric pumping station model simulation and the actual operation condition, thereby providing a better basis for the hydrological and hydrodynamic matching of the model in the later period.

[0054] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0055] The present application is described with reference to flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks.

[0056] These computer program instructions can 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 instructions which implement the flow Figure 1 The functions of a flow or multiple flows and / or a block or multiple blocks in conjunction with the disclosed methods can be implemented on a single device or distributed across several devices. Figure 1

[0057] These computer program instructions can 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 flow Figure 1 The functions of a flow or multiple flows and / or a block or multiple blocks in conjunction with the disclosed methods can be implemented on a single device or distributed across several devices. Figure 1

[0058] The above detailed description has been presented for the purposes of illustration and description. It is not intended to be exhaustive or to limit the application to the precise form disclosed. Many modifications and variations are possible in the light of the above teachings. It is intended that the scope of the application be limited not with this detailed description, but rather by the claims appended hereto.​​

Claims

1. A data mining method for operating rules of an electric power plant, characterized by, The method comprises the following steps: performing a sliding correlation analysis on the accumulated rainfall and the pump station opening state in the pump station operation record sequence to obtain a time offset scale at which the correlation reaches a peak value; determining a perspective time scale not less than the time offset scale, and performing data perspective on the original data of the electric drainage station according to the perspective time scale to obtain a data perspective result; the determination process of the perspective time scale is specifically as follows: selecting a correlation time point with a correlation coefficient greater than a set coefficient in the sliding correlation analysis; selecting a time region with the largest correlation density; taking the sum of the interval length of the time region and the time offset scale as the perspective time scale; or, selecting an Excel table with the shortest perspective scale greater than the time offset scale as the perspective time scale; performing a correlation analysis on the accumulated rainfall and the pump station state according to the data perspective result, and taking the rainfall corresponding to the accumulated rainfall with the highest correlation as the rainfall response value of the pump station opening state.

2. The data mining method for operating rules of an electric power plant according to claim 1, wherein The pump station operation record sequence comprises an inner river water level, an outer river water level, a pump station state and accumulated rainfall.

3. The data mining method for operating rules of an electric power plant according to claim 1, wherein The data in the pump station operation record sequence has an interval time of 5-30 min.

4. The data mining method for operating rules of an electric power plant according to claim 1, wherein The obtaining process of the time offset scale is specifically as follows: selecting a time point corresponding to the maximum correlation coefficient in the sliding correlation analysis as a sliding termination point; taking the interval time between the sliding start point and the sliding termination point of the sliding correlation analysis as the time offset scale.

5. The data mining method of operating rules of an electric power plant according to claim 4, wherein The correlation density is a ratio of the number of correlation time points in the time region to the interval length of the time region.

6. The data mining method of operating rules of an electric power plant according to claim 1, wherein, The rainfall response value can be taken as a boundary condition of a hydrological and hydrodynamic model and incorporated into the model.

7. A data mining system for operating rules of an electric power plant, characterized by, The method is suitable for a data mining method of an electric drainage station operation rule as claimed in any one of claims 1-6, and comprises: a sliding analysis module configured to perform a sliding correlation analysis on the accumulated rainfall and the pump station opening state in the pump station operation record sequence to obtain a time offset scale at which the correlation reaches an extreme value; a perspective analysis module configured to determine a perspective time scale not less than the time offset scale, and perform data perspective on the original data of the electric drainage station according to the perspective time scale to obtain a data perspective result; a response analysis module configured to perform a correlation analysis on the accumulated rainfall and the pump station state according to the data perspective result, and take the rainfall corresponding to the accumulated rainfall with the highest correlation as the rainfall response value of the pump station opening state.

8. A computer terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor implements the data mining method of the electric drainage station operation rule as claimed in any one of claims 1-6 when executing the program.

9. A computer readable medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the data mining method of the electric drainage station operation rule as claimed in any one of claims 1-6.

Images