Hydropower station gate opening cooperative control method based on Beidou technology

Abstract

The invention relates to the technical field of data prediction, in particular to a hydropower station gate opening cooperative control method based on the Beidou technology. According to the method, state parameters are constructed, the transfer condition of the state parameters in a historical time period is analyzed, and the transfer probability of each state parameter under the transfer condition is obtained. Continuously weighting the transition probability in combination with the correlation between the meteorological data and the opening data and the correlation between the historical meteorological data and the predicted meteorological data to obtain a second weighted transition probability; and counting the quantity characteristics of the state transition condition of the flood discharge channel gate under the predicted state transition condition of the previous stage of non-flood discharge channel gate, thereby obtaining the superior influence weight, obtaining a second state transition matrix of the flood discharge channel gate, and carrying out state prediction. According to the embodiment of the invention, an accurate gate state prediction result is obtained by combining the influence of historical meteorological data and further combining the control influence between gates.

Description

Technical Field

[0001] The present invention relates to the technical field of data prediction, and in particular to a method for coordinated control of gate opening of a hydropower station based on Beidou technology. Background Art

[0002] Gate control of hydropower stations is an important means to ensure multiple tasks such as reservoir water level, flow regulation and flood prevention. In large-scale hydropower stations, real-time data transmission of multiple hydropower station gates is involved. This data is crucial for monitoring and regulating equipment.

[0003] The emergence of the Beidou Satellite Navigation System (BDS) can provide high-precision positioning and time synchronization functions for passive communication and control systems in areas where ordinary mobile communication signals cannot cover or in emergency situations when communication fiber optic lines are damaged. By using the Beidou satellite system to establish a comprehensive monitoring model, combined with historical data and real-time data, the operating status of the gate can be effectively evaluated and the opening error can be accurately adjusted.

[0004] In the prior art, Markov chains can be used to predict the state transition of gates. In the actual prediction process, the future state predicted by the Markov chain is only strongly correlated with the current state, and the historical state is not considered. As a fixed large-scale water conservancy project, the data of a hydropower station is obviously periodic and seasonal. Therefore, the state prediction results of the Markov chain in the prior art will be inaccurate. Summary of the invention

[0005] In order to solve the technical problem that the prior art does not consider historical data when predicting the opening state of the hydropower station gate using the Markov chain, resulting in inaccurate prediction results, the purpose of the present invention is to provide a hydropower station gate opening collaborative control method based on Beidou technology, and the technical scheme adopted is as follows:

[0006] The present invention proposes a coordinated control method for gate opening of a hydropower station based on Beidou technology, the method comprising:

[0007] For each gate, the state parameters at each historical moment are determined according to the historical water level data and the historical opening data; the number of transfers between the state parameters at adjacent historical moments in the historical period is counted to obtain the transfer probability under each state parameter transfer condition;

[0008] According to the correlation between the historical meteorological data and the historical opening data of each gate, the meteorological impact weight of each gate is obtained and the transfer probability is weighted to obtain a first weighted transfer probability; according to the correlation between the predicted meteorological data and the historical meteorological data, the meteorological change weight is obtained, and the first weighted transfer probability and the transfer probability are weighted and adjusted to obtain a second weighted transfer probability;

[0009] The second weighted transfer probability under each state parameter transfer condition of the non-flood discharge channel gate constitutes a first state transfer matrix of each non-flood discharge channel gate, and the predicted state transfer condition of each non-flood discharge channel gate is determined by using a Markov chain according to the first state transfer matrix;

[0010] In the historical data, the number of transfer situations of each state parameter of the flood spillway gate under the predicted state transfer of the upper-level gate of the flood spillway gate is counted to obtain the upper-level influence weight, and the second weighted transfer probability and the transfer probability of the flood spillway gate are weightedly adjusted according to the upper-level influence weight to obtain the third weighted transfer probability, construct the second state transfer matrix of the flood spillway gate, and determine the predicted state transfer situation.

[0011] Furthermore, the method for obtaining the state parameter includes:

[0012] For each dimension in the historical water level data and the historical opening data, the data range in the dimension is divided into ten level intervals; the two level intervals corresponding to each gate at a historical moment constitute a tuple, and the tuple is used as a state parameter.

[0013] Furthermore, the historical meteorological data includes historical temperature data and historical precipitation data.

[0014] Furthermore, the method for obtaining the meteorological impact weight includes:

[0015] Taking any one dimension of the historical temperature data and the historical precipitation data as the meteorological dimension to be analyzed;

[0016] For the meteorological dimension to be analyzed, segment the historical period with a time length of one year to obtain a data sequence of the dimension to be analyzed and a gate opening data sequence for each year;

[0017] Obtain the difference distance and periodic difference between the dimension data sequence to be analyzed and the gate opening data sequence in the same time period; take the product of the periodic difference and the difference distance as the initial impact factor in each time period; negatively correlate and normalize the average initial impact factors of all time periods to obtain the meteorological impact factor in the meteorological dimension to be analyzed;

[0018] The meteorological impact factor under the dimension of historical temperature data is used as the denominator, and the meteorological impact factor under the dimension of historical precipitation data is used as the numerator. The obtained ratio is normalized to obtain the meteorological impact weight.

[0019] Furthermore, the method for obtaining the meteorological change weight includes:

[0020] The predicted meteorological data includes predicted temperature data and predicted precipitation data; a first Pearson correlation coefficient between the predicted meteorological data and the historical temperature data is obtained; a second Pearson correlation coefficient between the predicted precipitation data and the historical precipitation data is obtained; and an average value of the first Pearson correlation coefficient and the second Pearson correlation coefficient is used as the meteorological change weight.

[0021] Furthermore, the method for obtaining the first weighted transition probability includes:

[0022] The meteorological impact weight is multiplied by the transition probability to obtain the first weighted transition probability.

[0023] Furthermore, the method for obtaining the second weighted transition probability includes:

[0024] The meteorological change weight is used as the weight of the first weighted transfer probability, the result of the negative correlation mapping of the meteorological change weight is used as the weight of the transfer probability, and the first weighted transfer probability and the transfer probability are weightedly summed to obtain the second weighted transfer probability.

[0025] Furthermore, the method for obtaining the superior influence weight includes:

[0026] For any state parameter transfer situation in the flood discharge channel gate, the state parameter transfer situation is taken as the target transfer situation; the number of target transfer situations of the flood discharge channel gate in the predicted state transfer situation of the previous gate in the historical data is counted to obtain a first number; the total number of target transfer situations of the flood discharge channel gate in the historical data is counted as the second number; the ratio of the first number to the second number is taken as the initial superior influence weight, and the ratio of the initial superior influence weight to the second weighted transfer probability of the previous gate in the predicted state transfer situation is taken as the superior influence weight.

[0027] Furthermore, the method for obtaining the third weighted transition probability includes:

[0028] For each state parameter transfer of the flood discharge channel gate, the corresponding superior influence weight is used as the weight of the second weighted transfer probability, and the negative correlation mapping result of the superior influence weight is used as the weight of the transfer probability. The second weighted transfer probability and the transfer probability are weighted and summed to obtain the third weighted transfer probability.

[0029] Furthermore, the method for obtaining the transition probability includes:

[0030] Take any state parameter as the target state parameter, and take the total number of all state parameter transfer situations of the target state parameter in the historical period as the third number; for each state parameter transfer situation of the target state parameter, take the ratio of the number of each state parameter transfer situation to the third number as the transfer probability.

[0031] The present invention has the following beneficial effects:

[0032] The embodiment of the present invention first analyzes the historical data of each gate. For the gate, the opening and water level at each moment characterize the main state of the gate. Therefore, the state parameters are constructed and the transfer of the state parameters in the historical period is analyzed to obtain the transfer probability under each state parameter transfer condition. The transfer probability is the basic data characterizing the state transfer characteristics of the gate in the historical data. The transfer probability is further weighted by combining the correlation between the meteorological data and the opening data, and the correlation between the historical meteorological data and the predicted meteorological data, so that the obtained second weighted transfer probability combines the change factors of the historical meteorological information and the factors related to the opening data, thereby ensuring the accuracy of the state transfer matrix. Further considering that the flood discharge channel gate is a low-level gate, its opening is affected by the gate of the upper level. Therefore, the quantitative characteristics of the state transfer of the flood discharge channel gate under the predicted state transfer condition of the upper level non-flood discharge channel gate are statistically analyzed, and then the upper level influence weight is obtained, and the second state transfer matrix of the flood discharge channel gate is obtained. That is, the flood discharge channel gate is combined with the influence of the upper level gate on the basis of the above-mentioned historical data factors, so that the predicted state result is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1 A flow chart of a method for coordinated control of gate opening of a hydropower station based on Beidou technology provided by an embodiment of the present invention;

[0035] Figure 2 A schematic diagram of the structure of a hydropower station diagram provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0036] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a hydropower station gate opening collaborative control method based on Beidou technology proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0037] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0038] The specific scheme of the coordinated control method of the gate opening of a hydropower station based on Beidou technology provided by the present invention is described in detail below with reference to the accompanying drawings.

[0039] See also Figure 1 , which shows a flow chart of a method for coordinated control of gate opening of a hydropower station based on Beidou technology provided by an embodiment of the present invention, the method comprising:

[0040] Step S1: For each gate, determine the state parameters at each historical moment according to the historical water level data and the historical opening data; count the number of transfers between the state parameters at adjacent historical moments in the historical period, and obtain the transfer probability under each state parameter transfer condition.

[0041] The hydropower station targeted by the embodiment of the present invention includes a Beidou communication system. A Beidou communication terminal device cabinet is arranged at the location of the ecological unit of the hydropower station, and a number of sensors are installed at each gate position. The Beidou satellite positioning system is used to obtain relevant monitoring status information data at the gate in a regular and quantitative manner, including gate opening data, water level data, and meteorological data. In the embodiment of the present invention, data is obtained once a day, and statistical integration is performed every quarter. The Beidou system can transmit the collected information data to the server terminal, and the terminal records, stores, and analyzes the data.

[0042] In large hydropower stations, the opening control of multiple gates directly affects the normal operation of the hydropower station. The opening of the sluice gates usually depends on the influence of multiple factors, the most important of which are water level, temperature, precipitation and other data. Under different hydrological conditions, such as when the reservoir water storage reaches the warning water level during the flood season and heavy rain is about to come, in order to avoid dam break or flood disasters, it is necessary to open multiple gates at the same time to quickly discharge excess water. The opening between different gates needs to be accurately adjusted according to the current water storage capacity of the reservoir, weather changes and the water discharge capacity of each gate. The embodiment of the present invention aims to optimize the Markov chain prediction gate state process in the prior art, so it is first necessary to determine the state transition of the gate in the historical data and determine the basic transition probability.

[0043] The embodiment of the present invention is described by taking a gate as an example. For a gate, the gate opening and water level data are important states. Therefore, the state parameters at each historical moment are first determined based on the historical water level data and the historical opening data. That is, each state parameter represents a state, and the change from one state to another can be observed by advancing the time series. Therefore, the embodiment of the present invention counts the number of transitions between state parameters at adjacent historical moments in the historical period, and obtains the transition probability of each state parameter transition. For example, within the historical period, there are more cases of transition from state 1 to state 2, then this state parameter transition has a stronger transition probability, which can be used as an important basis for Markov chain prediction of gate state.

[0044] It should be noted that, in order to facilitate the Markov chain to predict the state of the gate, the embodiment of the present invention uses the gates of each level of the hydropower station as nodes in the graph structure to construct a gate graph structure; in the gate graph structure, the edge weights between nodes are the size of the gate coordination relationship, and the edges between nodes include the water flow control relationship between the gates; the superior-subordinate relationship between the gates can be intuitively obtained through the graph structure. Figure 2 , which shows a schematic diagram of a hydropower station structure provided by an embodiment of the present invention, Figure 2 In the figure, node A is the main control gate of the hydropower station, and node A can directly control gates B, C, and D. Gate B is the dam gate of the hydropower station, and gate C is the flood discharge channel gate. The opening of gate C is affected by gates A and B. Gate D is the water inlet gate of the power generation equipment. The control and influence between the gates can be clearly seen through the graph structure.

[0045] It should be noted that the method for constructing the graph structure is a technical means well known to those skilled in the art and will not be elaborated here.

[0046] Preferably, in one embodiment of the present invention, the method for obtaining the state parameter includes:

[0047] For each dimension in the historical water level data and historical opening data, the data range in the dimension is divided into ten level intervals; the two level intervals corresponding to each gate at a historical moment constitute a tuple, and the tuple is used as a state parameter. For example, if the tuple at a certain historical moment is (5,6), it means that the water level data corresponding to the gate at that moment is a level interval of level 5, and the opening is a level interval of level 6; if the tuple at the next moment of this moment is (6,5), it means that a state parameter transfer has occurred, and the transfer from (5,6) to (6,5) is a state parameter transfer situation.

[0048] Preferably, in one embodiment of the present invention, the method for obtaining the transition probability includes:

[0049] Any state parameter is taken as the target state parameter, and the total number of all state parameter transitions of the target state parameter in the historical period is taken as the third number. For each state parameter transition of the target state parameter, the ratio of the number of each state parameter transition to the third number is taken as the transition probability. The transition probability is expressed by the formula: Where P ij is the transition probability of state parameter i to state parameter j, N ij is the number of times the state parameter transition occurs in the historical data, N ik is the number of state parameter transfers from state parameter i to state parameter k, n is the number of types of state parameters other than state parameter i, is the total number of state parameter i transferred to each other state parameter, that is The third quantity.

[0050] Step S2: According to the correlation between historical meteorological data and the historical opening data of each gate, the meteorological impact weight of each gate is obtained and the transfer probability is weighted to obtain a first weighted transfer probability; according to the correlation between the predicted meteorological data and the historical meteorological data, the meteorological change weight is obtained, and the first weighted transfer probability and the transfer probability are weighted and adjusted to obtain a second weighted transfer probability.

[0051] The transfer probability of each state parameter transfer situation obtained in step S1 is only the basic data obtained by statistics. The greater the transfer probability, the greater the probability of the state parameter transfer situation. It does not take into account the impact of meteorological data on the gate opening. As for the impact of meteorological data on the gate opening, the increase in precipitation will increase the water storage of the hydropower station, so a larger gate opening is required for flood discharge and water release; and the increase in temperature will cause the water in the hydropower station environment to evaporate, and the gate opening needs to be reduced so that the hydropower station can generate electricity normally. Therefore, meteorological data has a significant impact on the gate opening, and it is necessary to further combine the historical meteorological data and historical opening data in the historical data to correct the transfer probability.

[0052] First, based on the correlation between historical meteorological data and historical opening data, the meteorological impact weight of each gate can be obtained. Figure 2 The gate D in the figure is mainly used for power generation. In order to ensure the operation of power generation, its water level and opening are not easily affected by the weather. The gates C and B are mainly used for water storage or flood discharge, and are greatly affected by meteorological data. Therefore, for each gate, the degree of influence can be determined based on the correlation between historical meteorological data and historical opening data, and then the transfer probability can be weighted to obtain the first weighted transfer probability.

[0053] Preferably, in an embodiment of the present invention, the historical meteorological data includes historical temperature data and historical precipitation data. Because it includes two dimensions, the method for obtaining the meteorological impact weight includes:

[0054] Take any dimension of historical temperature data and historical precipitation data as the meteorological dimension to be analyzed;

[0055] For the meteorological dimension to be analyzed, the historical period is segmented with a time length of one year to obtain the data sequence of the dimension to be analyzed and the gate opening data sequence for each year. That is, a historical time period can contain multiple sequences, and each sequence represents a period.

[0056] Obtain the difference distance between the dimension data sequence to be analyzed and the gate opening data sequence in the same period, as well as the periodic difference. Since meteorological data has obvious periodic changes, the greater the difference between the opening cycle of Zaman and the cycle of precipitation, the less the gate opening is affected by the weather. Similarly, the greater the difference distance, the less similar the data changes between the two sequences are, and the less the gate opening is affected by the weather.

[0057] The product of the periodic difference and the difference distance is taken as the initial impact factor in each period. That is, the larger the initial impact factor, the less the gate opening data is affected by the weather. Therefore, the average initial impact factor of all periods is negatively correlated and normalized to obtain the meteorological impact factor under the meteorological dimension to be analyzed.

[0058] Taking into account that temperature is negatively correlated with gate opening, while precipitation is positively correlated with gate opening, the meteorological impact factor under the dimension of historical temperature data is used as the denominator, and the meteorological impact factor under the dimension of historical precipitation data is used as the numerator. The obtained ratio is normalized to obtain the meteorological impact weight.

[0059] In one embodiment of the present invention, the meteorological influence factor is expressed by the formula:

[0060] Where qJ is the meteorological impact factor, M is the total number of time periods, TJ k is the periodicity of the dimensional data sequence to be analyzed in the kth period, TS k is the gate opening data sequence in the kth period, xJ is the dimension data sequence to be analyzed in the kth period, xS k is the gate opening data sequence in the kth time period, DTW() is the dynamic time warping distance calculation function, and exp() is an exponential function with a natural constant as the base.

[0061] That is, in the above formula, the dynamic time warping distance is used as the difference distance, and the negative correlation mapping of the data is achieved and normalized through the exponential function.

[0062] In the embodiment of the present invention, the periodicity of the sequence may be obtained by STL decomposition, which is a technical means well known to those skilled in the art and will not be described in detail here.

[0063] In the embodiment of the present invention, the normalization method may be linear normalization, or other technical means well known to those skilled in the art such as function mapping method may be selected for implementation, which is not limited here.

[0064] Preferably, in one embodiment of the present invention, the meteorological influence weight is multiplied by the transition probability to obtain a first weighted transition probability. That is, by multiplying, the transition probability of each state parameter transition of the gate is combined with the influence of the gate by the meteorological data to obtain the first weighted transition probability.

[0065] Because the embodiment of the present invention is intended to predict the state transition result of the gate at a future moment, and the data of the meteorological influence obtained above are all obtained by statistically analyzing historical data, their reference degree for the future moment needs to be re-evaluated. For the future moment, the stronger the correlation between the predicted meteorological data and the historical meteorological data, the stronger the reference degree of the data result obtained above. Therefore, the embodiment of the present invention further obtains the meteorological change weight according to the correlation between the predicted meteorological data and the historical meteorological data, and the first weighted transfer probability and the transfer probability can be weightedly adjusted according to the meteorological change weight to obtain the second weighted transfer probability. That is, the larger the meteorological change weight, the more important the first weighted transfer probability information is, and the weaker the reference degree of the original transfer probability data.

[0066] It should be noted that the predicted meteorological data can be integrated and processed based on the local meteorological forecast results, and the details will not be repeated here.

[0067] Preferably, in one embodiment of the present invention, the method for obtaining the meteorological change weight includes:

[0068] The predicted meteorological data includes predicted temperature data and predicted precipitation data; the first Pearson correlation coefficient between the predicted meteorological data and the historical temperature data is obtained; the second Pearson correlation coefficient between the predicted precipitation data and the historical precipitation data is obtained; and the average value of the first Pearson correlation coefficient and the second Pearson correlation coefficient is used as the meteorological change weight.

[0069] Preferably, in one embodiment of the present invention, the method for obtaining the second weighted transition probability includes:

[0070] The meteorological change weight is used as the weight of the first weighted transfer probability, the result of the negative correlation mapping of the meteorological change weight is used as the weight of the transfer probability, and the first weighted transfer probability and the transfer probability are weighted and summed to obtain the second weighted transfer probability. It should be noted that the meteorological change weight in the embodiment of the present invention is a result with a value range between 0 and 1, so the selected negative correlation mapping method can directly use the positive integer 1 minus the meteorological change weight to obtain the weight of the transfer probability. That is, the relationship between the weight of the transfer probability and the weight of the first weighted transfer probability is opposite, so the weighted summation can obtain the accurate second weighted transfer probability after the influence of meteorological data is introduced.

[0071] Step S3: The second weighted transfer probability under each state parameter transfer condition of the non-flood discharge channel gate constitutes the first state transfer matrix of each non-flood discharge channel gate, and the predicted state transfer condition of each non-flood discharge channel gate is determined by using the Markov chain according to the first state transfer matrix.

[0072] For non-flood discharge channel gates, the gate opening has a strong autonomy, while the flood discharge channel gates bear the important responsibility of flood discharge and water storage, so they are obviously affected by the gates of the upper level. Therefore, the embodiment of the present invention analyzes the non-flood discharge channel gates and the flood discharge channel gates separately. For non-flood discharge channel gates, the first state transfer matrix of each non-flood discharge gate can be directly formed by the second weighted transfer probability obtained by each state parameter transfer situation, and the predicted state transfer situation of each non-flood discharge gate can be determined by combining the existing Markov chain with the real-time state.

[0073] Step S4: In the historical data, the number of transfer situations of each state parameter of the flood spillway gate under the predicted state transfer of the upper-level gate of the flood spillway gate is counted to obtain the upper-level influence weight, and the second weighted transfer probability and the transfer probability of the flood spillway gate are weightedly adjusted according to the upper-level influence weight to obtain the third weighted transfer probability, construct the second state transfer matrix of the flood spillway gate, and determine the predicted state transfer situation.

[0074] For the flood discharge channel gate, its function is to discharge excess water to the designated area in time when the water level is too high or a flood occurs, so as to avoid the dam from breaking due to excessive water accumulation. Therefore, during the water level regulation process, the gate opening is obviously affected by the gate at the upper level. It is necessary to determine the influence of the upper gate on the flood discharge channel gate based on the statistical data of the state results predicted by the upper gate in the historical data.

[0075] In the embodiment of the present invention, in the historical data, the number of each state parameter transfer situation of the flood discharge channel gate under the predicted state transfer of the upper gate of the flood discharge channel gate is counted to obtain the upper influence weight. Similar to the above-mentioned meteorological change weight, the second weighted transfer probability and the transfer probability of the flood discharge channel gate are weighted and adjusted according to the upper influence weight to obtain the third weighted transfer probability. The second state transfer matrix of the flood discharge channel gate obtained based on the third weighted transfer probability can determine the predicted state transfer situation of the flood discharge channel gate.

[0076] Preferably, in one embodiment of the present invention, the method for obtaining the superior influence weight includes:

[0077] For any state parameter transfer situation in the flood discharge channel gate, the state parameter transfer situation is taken as the target transfer situation; the number of flood discharge channel gates that are target transfer situations in the predicted state transfer situation of the upper-level gate in the historical data is counted to obtain the first number; the total number of target transfer situations of the flood discharge channel gates in the historical data is counted as the second number; the ratio of the first number to the second number is taken as the initial upper-level influence weight. That is, the more the first number, the more state transfer times are made under the influence of the upper level among all the second numbers, and the greater the influence of the upper-level gate.

[0078] In order to further normalize the initial superior influence weight, the ratio of the initial superior influence weight to the second weighted transfer probability of the upper gate under the predicted state transfer is used as the superior influence weight.

[0079] Preferably, in one embodiment of the present invention, similar to the method for obtaining the second weighted transition probability, the method for obtaining the third weighted transition probability includes:

[0080] For each state parameter transfer situation of the flood discharge channel gate, the corresponding superior influence weight is used as the weight of the second weighted transfer probability, the negative correlation mapping result of the superior influence weight is used as the weight of the transfer probability, and the second weighted transfer probability and the transfer probability are weighted and summed to obtain the third weighted transfer probability. It should be noted that the superior influence weight value range in the embodiment of the present invention is also between 0 and 1, and its corresponding negative correlation mapping result is also implemented by subtracting the superior influence weight from the positive integer 1.

[0081] It should be noted that the state transfer matrix in the embodiment of the present invention is in the form of: Among them, P ij Indicates the second weighted transition probability or the third weighted transition probability that the state parameter i transitions to the state parameter j.

[0082] In an embodiment of the present invention, after obtaining the predicted state transfer conditions of all gates, the Beidou satellite system sends control instructions to the gate opening controller through the terminal. The opening controller can compare the current state with the predicted state transfer conditions to perform real-time regulation and feedback.

[0083] In summary, the embodiment of the present invention constructs state parameters and analyzes the transfer of state parameters in the historical period to obtain the transfer probability under each state parameter transfer condition. The transfer probability is continuously weighted in combination with the correlation between meteorological data and opening data, as well as the correlation between historical meteorological data and predicted meteorological data, to obtain a second weighted transfer probability. The quantitative characteristics of the state transfer of the flood discharge channel gate under the predicted state transfer of the upper-level non-flood discharge channel gate are statistically analyzed to obtain the upper-level influence weight, obtain the second state transfer matrix of the flood discharge channel gate and perform state prediction. The embodiment of the present invention obtains accurate gate state prediction results by combining the influence of historical meteorological data and further combining the control influence between gates.

[0084] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0085] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A coordinated control method for gate opening of a hydropower station based on Beidou technology, characterized in that: The method is executed with a terminal of the Beidou system, and the Beidou system is used to record meteorological data and opening data of the gate and feed back control instructions to the gate; the method includes: For each gate, the state parameters at each historical moment are determined based on the historical water level data and the historical opening data; the number of transitions between the state parameters at adjacent historical moments in the historical period is counted to obtain the transition probability under each state parameter transition condition; According to the correlation between the historical meteorological data and the historical opening data of each gate, the meteorological impact weight of each gate is obtained and the transfer probability is weighted to obtain a first weighted transfer probability; according to the correlation between the predicted meteorological data and the historical meteorological data, the meteorological change weight is obtained, and the first weighted transfer probability and the transfer probability are weighted and adjusted to obtain a second weighted transfer probability; The second weighted transfer probability under each state parameter transfer condition of the non-flood discharge channel gate constitutes a first state transfer matrix of each non-flood discharge channel gate, and the predicted state transfer condition of each non-flood discharge channel gate is determined by using a Markov chain according to the first state transfer matrix; In the historical data, the number of transfer situations of each state parameter of the flood spillway gate under the predicted state transfer of the upper-level gate of the flood spillway gate is counted to obtain the upper-level influence weight, and the second weighted transfer probability and the transfer probability of the flood spillway gate are weightedly adjusted according to the upper-level influence weight to obtain the third weighted transfer probability, construct the second state transfer matrix of the flood spillway gate, and determine the predicted state transfer situation.

2. According to a method for coordinated control of gate opening of a hydropower station based on Beidou technology according to claim 1, it is characterized in that: The method for obtaining the state parameter includes: For each dimension in the historical water level data and the historical opening data, the data range in the dimension is divided into ten level intervals; the two level intervals corresponding to each gate at a historical moment constitute a tuple, and the tuple is used as a state parameter.

3. The method for coordinated control of gate opening of a hydropower station based on Beidou technology according to claim 1 is characterized in that: The historical meteorological data includes historical temperature data and historical precipitation data.

4. A method for coordinated control of gate opening of a hydropower station based on Beidou technology according to claim 3, characterized in that: The method for obtaining the meteorological influence weight includes: Taking any one dimension of the historical temperature data and the historical precipitation data as the meteorological dimension to be analyzed; For the meteorological dimension to be analyzed, segment the historical period with a time length of one year to obtain a data sequence of the dimension to be analyzed and a gate opening data sequence for each year; Obtain the difference distance and periodic difference between the dimension data sequence to be analyzed and the gate opening data sequence in the same time period; take the product of the periodic difference and the difference distance as the initial impact factor in each time period; negatively correlate and normalize the average initial impact factors of all time periods to obtain the meteorological impact factor in the meteorological dimension to be analyzed; The meteorological impact factor under the dimension of historical temperature data is used as the denominator, and the meteorological impact factor under the dimension of historical precipitation data is used as the numerator. The obtained ratio is normalized to obtain the meteorological impact weight.

5. A method for coordinated control of gate opening of a hydropower station based on Beidou technology according to claim 4, characterized in that: The method for obtaining the meteorological change weight comprises: The predicted meteorological data includes predicted temperature data and predicted precipitation data; a first Pearson correlation coefficient between the predicted meteorological data and the historical temperature data is obtained; a second Pearson correlation coefficient between the predicted precipitation data and the historical precipitation data is obtained; and an average value of the first Pearson correlation coefficient and the second Pearson correlation coefficient is used as the meteorological change weight.

6. The method for coordinated control of gate opening of a hydropower station based on Beidou technology according to claim 1 is characterized in that: The method for obtaining the first weighted transition probability includes: The meteorological impact weight is multiplied by the transition probability to obtain the first weighted transition probability.

7. The method for coordinated control of gate opening of a hydropower station based on Beidou technology according to claim 1 is characterized in that: The method for obtaining the second weighted transition probability includes: The meteorological change weight is used as the weight of the first weighted transfer probability, the result of the negative correlation mapping of the meteorological change weight is used as the weight of the transfer probability, and the first weighted transfer probability and the transfer probability are weightedly summed to obtain the second weighted transfer probability.

8. The method for coordinated control of gate opening of a hydropower station based on Beidou technology according to claim 1 is characterized in that: The method for obtaining the superior influence weight includes: For any state parameter transfer situation in the flood discharge channel gate, the state parameter transfer situation is taken as the target transfer situation; the number of target transfer situations of the flood discharge channel gate in the predicted state transfer situation of the previous gate in the historical data is counted to obtain a first number; the total number of target transfer situations of the flood discharge channel gate in the historical data is counted as the second number; the ratio of the first number to the second number is taken as the initial superior influence weight, and the ratio of the initial superior influence weight to the second weighted transfer probability of the previous gate in the predicted state transfer situation is taken as the superior influence weight.

9. The method for coordinated control of gate opening of a hydropower station based on Beidou technology according to claim 1 is characterized in that: The method for obtaining the third weighted transition probability includes: For each state parameter transfer of the flood discharge channel gate, the corresponding superior influence weight is used as the weight of the second weighted transfer probability, and the negative correlation mapping result of the superior influence weight is used as the weight of the transfer probability. The second weighted transfer probability and the transfer probability are weighted and summed to obtain the third weighted transfer probability.

10. The method for coordinated control of gate opening of a hydropower station based on Beidou technology according to claim 1 is characterized in that: The method for obtaining the transition probability includes: Take any state parameter as the target state parameter, and take the total number of all state parameter transfer situations of the target state parameter in the historical period as the third number; for each state parameter transfer situation of the target state parameter, take the ratio of the number of each state parameter transfer situation to the third number as the transfer probability.

Images