Hydropower station generating capacity prediction method and equipment

Abstract

The invention relates to a hydropower station generating capacity prediction method and equipment, and belongs to the technical field of hydropower station generating capacity prediction.The method comprises the steps that meteorological data, hydrological data and equipment operation data are obtained, the fractional derivative order, the snow water attenuation coefficient and meteorological data are set by considering drainage basin characteristics when the reservoir inflow is calculated, and the method is more scientific and accurate compared with a traditional mode. A reservoir capacity water head model is constructed by utilizing reservoir inflow and hydrological data to obtain a hair water head, and a water purification head is calculated by combining equipment operation data. And obtaining vibration data of the water-turbine generator set, constructing a vibration vector, obtaining a modal component through a variational mode decomposition algorithm VMD, and determining the working efficiency of the set. Obtaining an effective water head according to the downstream water level and the water purification head, and calculating the generation power probability density by combining the working efficiency. And integrating various data, the power generation power probability density and the effective water head to accurately predict the generating capacity of the hydropower station.

Description

Technical Field

[0001] This invention relates to a method and equipment for predicting the power generation of a hydropower station, belonging to the field of hydropower station power generation prediction technology. Background Technology

[0002] With the continuous growth of global energy demand and the increasing emphasis on renewable energy, hydropower, as a clean, renewable, and relatively stable energy source, is playing an increasingly important role in the energy structure. The power generation of a hydropower station is not only closely related to natural conditions but also affected by various factors such as equipment operating status. Accurately predicting the power generation of hydropower stations is of paramount importance for grid dispatching, energy planning, and the stable operation of hydropower stations. Currently, traditional methods for predicting hydropower generation mainly rely on meteorological data and simple hydrological models. While these methods can provide estimates of power generation to some extent, their accuracy and reliability are limited because they do not fully consider the complex operating environment and multimodal data related to equipment status at hydropower stations.

[0003] Existing technologies, such as Chinese invention patent application CN114970945A, disclose a method, device, and system for calculating the medium- and long-term power output of a hydropower station based on the water-electricity response relationship. This method includes: collecting historical operating data; eliminating unreasonable data based on the physical meaning and relationships between historical operating data to obtain a usable historical operating dataset of the hydropower station's overall operation; constructing a water-electricity response relationship data set containing the hydropower station's average power output, average power generation flow, and average gross head based on the usable historical operating dataset; fitting a water-electricity response relationship surface function based on the data set; and calculating the reservoir's gross head and power generation flow for the period to be predicted based on measured data, then substituting these values ​​into the water-electricity response relationship surface function to obtain the power output. However, the aforementioned patent does not fully consider the impact of the turbine generator unit's operating status on power generation efficiency. For example, vibration data of the turbine generator unit can reflect the unit's operational stability and thus affect its efficiency, but the aforementioned patent does not incorporate this into the model construction. Summary of the Invention

[0004] To address the problems existing in the prior art, this invention proposes a method and equipment for predicting the power generation of a hydropower station.

[0005] The technical solution of the present invention is as follows:

[0006] On the one hand, this invention proposes a method for predicting the power generation of a hydropower station, comprising the following steps:

[0007] Acquire meteorological data, hydrological data, and equipment operation data of the hydropower station, and calculate the inflow of the hydropower station based on the meteorological data;

[0008] Based on the inflow and hydrological data, a reservoir head model is constructed to output the gross head of the hydropower station.

[0009] The net head of the hydropower station is calculated based on the gross head and equipment operation data.

[0010] Vibration data of the hydro-turbine generator unit of the hydropower station is obtained, a unit vibration vector is constructed based on the vibration data, the unit vibration vector is input into the variational mode decomposition algorithm (VMD) to obtain vibration mode components, and the working efficiency of the hydro-turbine generator unit is determined based on the vibration mode components.

[0011] The effective head of the hydropower station is determined based on the downstream water level and the net head, and the power generation probability density of the hydropower station is obtained by calculating the effective head and the working efficiency of the turbine generator set.

[0012] The power generation of the hydropower station is predicted based on the meteorological data, hydrological data, equipment operation data, power generation probability density, and effective head.

[0013] Preferably, the specific steps for calculating and obtaining the inflow of the hydropower station based on the meteorological data are as follows:

[0014] Set the snowmelt attenuation coefficient;

[0015] The inflow of the hydropower station is calculated based on the snowmelt attenuation coefficient and meteorological data.

[0016] The meteorological data includes precipitation, watershed snowmelt, solar radiation, and temperature.

[0017] Preferably, the specific steps for constructing the reservoir capacity head model based on the inflow and hydrological data are as follows:

[0018] The water surface area of ​​the reservoir is obtained by constructing a water level area function based on the water level elevation of the corresponding reservoir of the hydropower station.

[0019] Determine the reservoir capacity, and construct a reservoir capacity head model based on the reservoir capacity, inflow, water surface area, and hydrological data;

[0020] The hydrological data includes outflow and dead water level.

[0021] Preferably, the step of calculating and obtaining the net head of the hydropower station based on the gross head and equipment operating data specifically involves:

[0022] Set the pipe friction coefficient, rotational loss coefficient, and water hammer loss coefficient;

[0023] The net head of the hydropower station is calculated based on the pipeline friction coefficient, rotational loss coefficient, water hammer loss coefficient, gross head, and equipment operation data.

[0024] Preferably, the operating efficiency of the hydro-generator unit is determined based on the vibration mode components, and the specific steps are as follows:

[0025] The vibration vector of the unit is input into the variational mode decomposition algorithm (VMD) to obtain at least two vibration mode components of order k, and a corresponding weight is set for each vibration mode component.

[0026] Determine the vibration gradient;

[0027] Determine the design water temperature, design head, and design efficiency of the hydropower station;

[0028] The operating efficiency of the hydro-generator unit is calculated based on the weights, vibration modal components, vibration gradient, design water temperature, design head, and design efficiency.

[0029] Preferably, the effective head of the hydropower station is determined based on the downstream water level and the net head, and the specific steps are as follows:

[0030] Determine the magnitude of the water level jump;

[0031] The effective head of the hydropower station is calculated based on the water level jump amplitude, the downstream water level of the hydropower station, and the net head.

[0032] Preferably, the probability density of power generation of the hydropower station is obtained by calculating the effective head and the operating efficiency of the turbine generator set. The specific steps are as follows:

[0033] Construct the drift function and the diffusion function;

[0034] The power generation probability density of a hydropower station is calculated based on the effective head, the operating efficiency of the turbine generator set, the drift function, and the diffusion function.

[0035] Preferably, based on the meteorological data, hydrological data, equipment operation data, power generation probability density, and effective head, a Bayesian network is used to predict the power generation of the hydropower station.

[0036] In another aspect, the present invention also provides an electronic device having a computer program stored thereon, which, when executed by a processor, implements the hydropower generation prediction method as described in any embodiment of the present invention.

[0037] The present invention has the following beneficial effects:

[0038] 1. This invention comprehensively integrates multiple modal data, including meteorological data, hydrological data, equipment operation data, and vibration data from hydro-generator units. Meteorological data, encompassing precipitation, watershed snowmelt, solar radiation, and temperature, accurately reflects the impact of the external environment on the inflow to the hydropower station. Hydrological data, such as outflow and dead water level, reflects reservoir water level changes and flow conditions. Equipment operation data helps understand the actual operating status of the hydropower station equipment, while vibration data, after processing, can determine the unit's operating efficiency. Compared to traditional methods that rely solely on a single data type for prediction, integrating multimodal data enables power generation prediction to more comprehensively and accurately reflect the combined effects of various factors, thereby improving prediction accuracy.

[0039] 2. In calculating the inflow, this invention considers the characteristics of the watershed and sets the fractional derivative order and snowmelt attenuation coefficient to calculate the inflow, which is more scientific and accurate than relying solely on historical flow data or simple models to estimate the inflow. By using the Variational Mode Decomposition (VMD) algorithm to process the unit vibration data, the complex vibration vector can be decomposed into multiple vibration mode components. Combining the weights of each component and relevant design parameters, the operating efficiency of the hydro-generator unit can be determined more accurately, thereby improving the accuracy of subsequent power generation prediction.

[0040] 3. This invention constructs a water level area function based on the reservoir water level elevation to determine the reservoir water surface area. Then, it combines hydrological data such as reservoir capacity and inflow to construct a reservoir head model, which can output the gross head more accurately. This lays a good foundation for the subsequent calculation of net head and effective head, making the entire prediction model more consistent with the actual hydrological and operational conditions of the hydropower station.

[0041] 4. This invention constructs drift and diffusion functions, combined with effective head, turbine generator unit operating efficiency, etc., to accurately calculate the probability density of power generation of hydropower stations. This helps to understand the distribution and variation of power generation in more detail, providing more accurate and richer information input for subsequent power generation prediction based on Bayesian networks. This makes the power generation prediction results not only have deterministic values, but also reflect their probabilistic characteristics, providing decision-makers with more comprehensive risk assessment information.

[0042] 5. Based on meteorological data, hydrological data, equipment operation data, power generation probability density, and effective head, this invention uses Bayesian networks to predict power generation. It can comprehensively consider the complex correlations and mutual influences between various factors, and provide the predicted power generation results and their uncertainty range based on probabilistic reasoning. Compared with traditional deterministic prediction methods, it provides a more reliable and valuable decision-making basis for the operation and management of hydropower stations.

[0043] 6. This invention analyzes and processes vibration data of hydro-generator units, and uses the VMD algorithm and related parameters to determine the unit's operating efficiency. This not only allows for more accurate monitoring of the unit's real-time operating status, but also enables timely detection of potential problems or faults in the unit, providing strong support for equipment maintenance and operation optimization, and helping to improve the unit's operational stability and power generation efficiency. Attached Figure Description

[0044] Figure 1 This is a flowchart illustrating the implementation of the method of the present invention. Detailed Implementation

[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] It should be understood that the step numbers used in the text are for ease of description only and are not intended to limit the order in which the steps are performed.

[0047] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0048] The terms “comprising” and “including” indicate the presence of the described feature, whole, step, operation, element and / or component, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0049] The term “and / or” refers to any combination of one or more of the associated listed items, as well as all possible combinations, and includes these combinations.

[0050] Example 1:

[0051] See Figure 1 This embodiment provides a method for predicting the power generation of a hydropower station, including the following steps:

[0052] Acquire meteorological data, hydrological data, and equipment operation data of the hydropower station, and calculate the inflow of the hydropower station based on the meteorological data;

[0053] Based on the inflow and hydrological data, a reservoir head model is constructed to output the gross head of the hydropower station.

[0054] The net head of the hydropower station is calculated based on the gross head and equipment operation data.

[0055] Vibration data of the hydro-turbine generator unit of the hydropower station is obtained, a unit vibration vector is constructed based on the vibration data, the unit vibration vector is input into the variational mode decomposition algorithm (VMD) to obtain vibration mode components, and the working efficiency of the hydro-turbine generator unit is determined based on the vibration mode components.

[0056] The effective head of the hydropower station is determined based on the downstream water level and the net head, and the power generation probability density of the hydropower station is obtained by calculating the effective head and the working efficiency of the turbine generator set.

[0057] The power generation of the hydropower station is predicted based on the meteorological data, hydrological data, equipment operation data, power generation probability density, and effective head.

[0058] Preferably, the specific steps for calculating and obtaining the inflow of the hydropower station based on the meteorological data are as follows:

[0059] Set the fractional derivative order and the snowmelt attenuation coefficient;

[0060] The inflow rate of the hydropower station is calculated based on the fractional derivative order, snowmelt attenuation coefficient, and meteorological data, and is expressed by the following formula:

[0061]

[0062] In the formula, τ represents the time index, α represents the fractional derivative order, which is strongly correlated with watershed characteristics: glacier-charged type α≈0.3 (slow melting), rainstorm-dominated type α≈0.7 (rapid response), Q in Let S represent the inflow rate, t represent the time variable, k1 represent the snowmelt runoff coefficient, k2 represent the temperature coefficient, k3 represent the precipitation influence coefficient, λ represent the snowmelt attenuation coefficient, and S represent the snowmelt runoff coefficient. snow T represents the amount of snowmelt in the watershed. a R represents temperature. solar P represents solar radiation. rain Indicates precipitation;

[0063] The meteorological data includes precipitation, watershed snowmelt, solar radiation, and temperature.

[0064] Preferably, the specific steps for constructing the reservoir capacity head model based on the inflow and hydrological data are as follows:

[0065] The surface area of ​​the reservoir is obtained by constructing a water level-area function based on the water level elevation of the corresponding reservoir of the hydropower station, expressed by the formula:

[0066]

[0067] In the formula, H min β0 represents the dead water level, i.e., the lowest operating elevation of the reservoir; β1 represents the area scale coefficient; β2 represents the topographic index; and A represents the water level area function.

[0068] The reservoir capacity can be determined using the following formula:

[0069]

[0070] In the formula, h represents the elevation integral variable, and V A Indicates the reservoir's capacity;

[0071] Based on the reservoir capacity, inflow, water surface area, and hydrological data, a reservoir head model is constructed, expressed by the formula:

[0072]

[0073] In the formula, H gross Indicates the water head, Q out H represents the outflow rate, H represents the water level elevation of the reservoir, and β represents the curvature correction factor. Indicates the reservoir capacity curvature;

[0074] The hydrological data includes outflow and dead water level.

[0075] Preferably, the step of calculating and obtaining the net head of the hydropower station based on the gross head and equipment operating data specifically involves:

[0076] Set the pipe friction coefficient, rotational loss coefficient, and water hammer loss coefficient;

[0077] The net head of the hydropower station is calculated based on the pipeline friction coefficient, rotational loss coefficient, water hammer loss coefficient, gross head, and equipment operating data, and is expressed by the formula:

[0078]

[0079]

[0080] In the formula, H net denoted by _x_, x represents the horizontal coordinate of the pipe with the pipe inlet as the origin, g represents the acceleration due to gravity, v represents the water flow velocity in the pipe, f represents the pipe friction coefficient (preset based on the pipe material), D represents the pipe inner diameter, w represents the unit angular velocity vector, a represents the water hammer wave velocity, L represents the pipe length, ζ represents the rotational loss coefficient, and κ represents the water hammer loss coefficient.

[0081] Preferably, the operating efficiency of the hydro-generator unit is determined based on the vibration mode components, and the specific steps are as follows:

[0082] The vibration vector of the unit is input into the variational mode decomposition algorithm (VMD) to obtain at least two vibration mode components of order k, and a corresponding weight is set for each vibration mode component.

[0083] Determine the vibration gradient;

[0084] Determine the design water temperature, design head, and design efficiency of the hydropower station;

[0085] The operating efficiency of the hydro-generator unit is calculated based on the aforementioned weights, vibration modal components, vibration gradient, design water temperature, design head, and design efficiency, and is expressed by the following formula:

[0086]

[0087] In the formula, η represents the operating efficiency of the hydro-generator unit. ref Indicates design efficiency, α * T represents the water temperature decay coefficient. w Indicates water temperature, T ref Indicates the design water temperature, H ref Indicates the design head, β * κ1 represents the head index, and κ1 represents the turbulence coefficient. The vibration gradient is represented by V0, determined through head disturbance experiments or numerical simulation (using computer software ANSYS CFX and Mechanical). V0 represents the vibration reference, V represents the unit vibration vector, κ2 represents the thermo-coupling coefficient, K represents the order of the vibration modal components, and ψ... k The VMD represents the weight of the k-th vibrational modal component. k (V) represents the k-th vibration mode component, ΔT represents the water temperature change, which is the difference between the water temperature and the design water temperature, and ΔH represents the head change, which is the difference between the design head and the net head.

[0088] Preferably, the effective head of the hydropower station is determined based on the downstream water level and the net head, and the specific steps are as follows:

[0089] Determine the magnitude of the water level jump;

[0090] The effective head of the hydropower station is calculated based on the water level jump amplitude, the downstream water level of the hydropower station, and the net head, and is expressed by the formula:

[0091]

[0092] In the formula, H eff The effective head is represented by ρ, and the dissipation coefficient is represented by ρ. Z represents the geometric coefficient, t0 represents the time variable of the lower limit of integration, which is preset according to the actual situation. downLet ξ(τ) represent the downstream water level of the hydropower station, ξ(τ) represent the water level jump amplitude at time τ, and dN(τ) represent the binary variable at time τ, used to describe sudden water level jump events. If the value is 1, it means that a water level jump event has occurred; if it is 0, it means that it has not occurred.

[0093] The magnitude of the water level jump is expressed by the formula:

[0094]

[0095] In the formula, μ ξ This represents the average value of the basic water level jump, which is preset based on experience. ξ Does W represent the standard deviation of abrupt fluctuations, obtained from historical flood events? ξ Represents Gaussian white noise, α ξ G represents the rainfall sensitivity coefficient, G represents the reservoir gate opening, and γ represents the sluice gate opening. ξ This indicates the gate operation coefficient.

[0096] Preferably, the probability density of power generation of the hydropower station is obtained by calculating the effective head and the operating efficiency of the turbine generator set. The specific steps are as follows:

[0097] Construct a drift function and a diffusion function, wherein the drift function is expressed by the formula:

[0098]

[0099] The diffusion function is expressed by the formula:

[0100]

[0101] The power generation probability density of a hydropower station is calculated based on the effective head, the operating efficiency of the turbine-generator unit, the drift function, and the diffusion function, and is expressed by the following formula:

[0102]

[0103] In the formula, p represents the probability density of power generation, μ represents the drift function, P represents the power generation, σ represents the diffusion function, and k p L represents the power constant. p λ represents the propagation distance. p Memory decay coefficient;

[0104] The propagation distance is expressed by the formula:

[0105]

[0106] In the formula, β p This represents the vortex belt structure coefficient.

[0107] Preferably, based on the meteorological data, hydrological data, equipment operation data, power generation probability density, and effective head, a Bayesian network is used to predict the power generation of the hydropower station.

[0108] Example 2:

[0109] This embodiment provides an electronic device that stores a computer program, which, when executed by a processor, implements the hydropower generation prediction method as described in any embodiment of the present invention.

[0110] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, A and B simultaneously, or B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0111] Those skilled in the art will recognize that the units and algorithm steps described in the embodiments disclosed herein can be implemented using electronic hardware, computer software, or a combination of electronic hardware and software. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0112] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0113] In the several embodiments provided in this application, any function, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0114] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for predicting the power generation of a hydropower station, characterized in that, Includes the following steps: Acquire meteorological data, hydrological data, and equipment operation data of the hydropower station, and calculate the inflow of the hydropower station based on the meteorological data; Based on the inflow and hydrological data, a reservoir head model is constructed to output the gross head of the hydropower station. The net head of the hydropower station is calculated based on the gross head and equipment operation data. Vibration data of the hydro-turbine generator unit of the hydropower station is obtained, a unit vibration vector is constructed based on the vibration data, the unit vibration vector is input into the variational mode decomposition algorithm (VMD) to obtain vibration mode components, and the working efficiency of the hydro-turbine generator unit is determined based on the vibration mode components. The effective head of the hydropower station is determined based on the downstream water level and the net head, and the power generation probability density of the hydropower station is obtained by calculating the effective head and the working efficiency of the turbine generator set. The power generation of the hydropower station is predicted based on the meteorological data, hydrological data, equipment operation data, power generation probability density, and effective head.

2. The method for predicting hydropower generation according to claim 1, characterized in that, The specific steps for calculating and obtaining the inflow of the hydropower station based on the meteorological data are as follows: Set the snowmelt attenuation coefficient; The inflow of the hydropower station is calculated based on the snowmelt attenuation coefficient and meteorological data. The meteorological data includes precipitation, watershed snowmelt, solar radiation, and temperature.

3. The method for predicting hydropower generation according to claim 2, characterized in that, The specific steps for constructing the reservoir capacity head model based on the inflow and hydrological data are as follows: The water surface area of ​​the reservoir is obtained by constructing a water level area function based on the water level elevation of the corresponding reservoir of the hydropower station. Determine the reservoir capacity, and construct a reservoir capacity head model based on the reservoir capacity, inflow, water surface area, and hydrological data; The hydrological data includes outflow and dead water level.

4. The method for predicting hydropower generation according to claim 3, characterized in that, The calculation of the net head of the hydropower station based on the gross head and equipment operation data specifically involves: Set the pipe friction coefficient, rotational loss coefficient, and water hammer loss coefficient; The net head of the hydropower station is calculated based on the pipeline friction coefficient, rotational loss coefficient, water hammer loss coefficient, gross head, and equipment operation data.

5. The method for predicting hydropower generation according to claim 4, characterized in that, The operating efficiency of the hydro-generator unit is determined based on the vibration modal components. The specific steps are as follows: The vibration vector of the unit is input into the variational mode decomposition algorithm (VMD) to obtain at least two vibration mode components of order k, and a corresponding weight is set for each vibration mode component. Determine the vibration gradient; Determine the design water temperature, design head, and design efficiency of the hydropower station; The operating efficiency of the hydro-generator unit is calculated based on the weights, vibration modal components, vibration gradient, design water temperature, design head, and design efficiency.

6. The method for predicting hydropower generation according to claim 5, characterized in that, The effective head of the hydropower station is determined based on the downstream water level and the net head, and the specific steps are as follows: Determine the magnitude of the water level jump; The effective head of the hydropower station is calculated based on the water level jump amplitude, the downstream water level of the hydropower station, and the net head.

7. The method for predicting hydropower generation according to claim 6, characterized in that, The probability density of power generation of the hydropower station is obtained by calculating the effective head and the operating efficiency of the turbine generator set. The specific steps are as follows: Construct the drift function and the diffusion function; The power generation probability density of a hydropower station is calculated based on the effective head, the operating efficiency of the turbine generator set, the drift function, and the diffusion function.

8. The method for predicting hydropower generation according to claim 7, characterized in that, Based on the meteorological data, hydrological data, equipment operation data, power generation probability density, and effective head, a Bayesian network is used to predict the power generation of the hydropower station.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the hydropower generation prediction method as described in any one of claims 1 to 8.

Images