A method for real-time monitoring of gate flow in hydropower stations based on big data

Abstract

This invention discloses a real-time monitoring method for hydropower station gate flow based on big data, belonging to the field of hydropower technology. The method includes the following steps: forming a flow state perception model; constructing a flow anomaly disturbance identification model to calculate the flow disturbance difference; constructing a gate self-feedback correction model based on deviation back mapping; constructing a gate group collaborative optimization mechanism; and constructing an adaptive model detection mechanism. This invention significantly improves the system's response capability to nonlinear disturbances and the security and reliability of monitoring data by innovatively introducing technologies such as a flow anomaly disturbance identification model, a gate self-feedback correction model, a time-series drift tracking model, and a structurally trusted blockchain mechanism. Compared with traditional methods, this invention not only possesses higher flow prediction accuracy and adaptive control capabilities but also constructs a multi-node asynchronous consensus verification mechanism for monitoring data, effectively supporting intelligent scheduling decisions and event tracing applications across departments and time periods.

Description

Technical Field

[0001] This invention relates to the field of hydropower technology, specifically to a method for real-time monitoring of gate flow in hydropower stations based on big data. Background Technology

[0002] As key execution units for regulating water flow and reservoir water levels, the operation of hydropower station gates directly impacts the overall scheduling efficiency and water resource utilization security of the power station. Currently, mainstream flow monitoring methods mainly rely on fixed sensor networks to collect data such as flow rate, water level, and gate opening, and then use static hydraulic formulas or empirical models to estimate and determine flow control.

[0003] However, in actual operation, the sources of water flow disturbance are complex and varied. Factors such as aquatic plants, sediment deposition, structural aging, and flow regime disturbances can all cause significant deviations between actual and theoretical flow rates. Traditional models struggle to dynamically detect these disturbances and track their evolution. Conventional models often employ fixed hydraulic formulas or threshold rules, lacking the ability to model multiple coupled disturbances, resulting in low prediction accuracy and delayed fault response. Current flow monitoring platforms mostly rely on centralized databases or log recording systems. In the event of scheduling errors, cross-departmental scheduling disputes, or the risk of historical data tampering, the lack of a reliable and traceable data archiving system impacts the security and audit compliance of the scheduling system. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a real-time monitoring method for the flow of gates in hydropower stations based on big data, in order to solve the problems mentioned in the background section.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] In a first aspect, embodiments of the present invention provide a method for real-time monitoring of gate flow in a hydropower station based on big data, comprising the following steps: S1. Model the key parameters of each gate to form a water flow state perception model; S2. Based on the parameters output by the model in S1, construct a traffic anomaly disturbance identification model, calculate the traffic disturbance difference, and determine whether there is an anomaly in the disturbance source identification. S3. To address the flow disturbance difference caused by disturbance sources, a gate self-feedback correction model based on deviation reverse mapping is constructed to perform real-time correction of individual gates. S4. Construct a gate group collaborative optimization mechanism to make the flow target of each gate of the hydropower station approach the optimal distribution of the system; S5. Construct an adaptive model detection mechanism to dynamically determine whether the model used in the current steps S1-S4 has failed.

[0007] To further optimize this technical solution, in step S1, the water flow state perception model is modeled based on the key parameters of the i-th gate, including relative opening, upstream water level, and downstream water level, as shown in the following model: ; in, The theoretical instantaneous flow rate of the i-th gate at time t; , : Empirical calibration coefficient; Gravitational acceleration constant; The relative opening of the gate; , These represent the upstream and downstream water levels, respectively.

[0008] To further optimize this technical solution, the traffic anomaly disturbance identification model in step S2 is as follows: ; in, : The measured instantaneous flow rate of the i-th gate at time t; : Flow disturbance difference; The perturbation function generated by the multi-channel anomaly source satisfies: ; in, : The weighting coefficient of the k-th type of disturbance source for the i-th gate; : The influence term of the k-th type of disturbance source; The total number of disturbance sources.

[0009] To further optimize this technical solution, in step S3, the gate self-feedback correction model quantizes the objective function to reduce the flow disturbance difference. To compress the opening size to an acceptable range as much as possible at the current moment, the following opening correction control strategy is proposed: ; in, Suggested opening degree for the next moment; : Control gain factor; When the system detects When the deviation is large, the opening is automatically adjusted. To correct flow errors and ensure the closed-loop performance of the real-time flow monitoring system.

[0010] To further optimize this technical solution, in step S4, when the flow correction of a single gate cannot meet the overall drainage scheduling requirements, a gate group collaborative optimization mechanism is introduced to improve flow balance at the system level. A collaborative optimization model is constructed based on the gate group collaborative optimization mechanism to make the flow target of each gate approach the optimal distribution of the system, and the objective function is defined.

[0011] To further optimize this technical solution, the objective function of the collaborative optimization model is as follows: ; in, The system's flow balance deviation index at time t, with the overall goal of making... Minimum, through adjustment Let Gradually declining; Total number of gates; The system expects average flow rate to satisfy: ; This collaborative optimization model is used to minimize the flow balance deviation among the gates by adjusting their opening degrees. The distribution guides the coordinated operation of each gate to achieve overall balance in flow output.

[0012] To further optimize this technical solution, in step S5, the adaptive model detection mechanism is used to address the problem that the model may gradually fail due to the long-term evolution of the external environment or equipment performance degradation. The adaptive model detection mechanism dynamically judges whether the model has failed based on the model failure metric of error entropy.

[0013] To further optimize this technical solution, the gate flow error entropy is defined in the adaptive model detection mechanism as follows: ; in, : The flow error entropy of the i-th gate; Number of error interval divisions; : The frequency proportion within the m-th error interval, which represents the probability that the error falls into this interval over a period of time; If the system detects the error entropy of a certain gate If the value continues to rise and exceeds the allowable threshold, it is determined that the model is no longer adapted to the actual traffic flow patterns, and a model failure warning will be automatically triggered.

[0014] To further optimize this technical solution, the method also includes effectively capturing and predicting the long-term impact of slow-varying disturbances on flow, designing a time-series drift tracking model to identify and fit the impact of non-abrupt disturbances on the long-term trend of gate flow, using the model to determine whether there is a systematic slow deterioration or improvement trend, and issuing maintenance warnings or parameter recalibration signals accordingly.

[0015] To further optimize this technical solution, the method also introduces a structured trusted blockchain technology to construct an asynchronous storage and consensus verification mechanism for gate flow monitoring data. The mechanism encapsulates structured data, including gate number, opening degree, upstream and downstream water levels, and flow disturbance difference, into a multi-level sub-block structure using a lightweight hash chain. Each sub-block structure represents the independent data flow state of a gate.

[0016] In a second aspect, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the computer program instructions, when executed by the processor, implement the steps of a method for real-time monitoring of hydropower station gate flow based on big data as described in the first aspect of the present invention.

[0017] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, they implement the steps of a method for real-time monitoring of hydropower station gate flow based on big data as described in the first aspect of the present invention.

[0018] Compared with existing technologies, this invention provides a method for real-time monitoring of gate flow in hydropower stations based on big data, which has the following beneficial effects: This real-time monitoring method for hydropower station gate flow based on big data innovatively introduces technologies such as a flow anomaly disturbance identification model, a gate self-feedback correction model, a time-series drift tracking model, and a structurally trusted blockchain mechanism. This significantly improves the system's response to nonlinear disturbances and the security and reliability of monitoring data. Compared with traditional methods, this invention not only possesses higher flow prediction accuracy and adaptive control capabilities, but also constructs a multi-node asynchronous consensus verification mechanism for monitoring data. This effectively supports intelligent scheduling decisions and event tracing applications across departments and time periods, demonstrating significant engineering application prospects and promotional value.

[0019] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0020] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart illustrating a real-time monitoring method for hydropower station gate flow based on big data, as proposed in this invention. Detailed Implementation

[0021] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0022] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0023] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0024] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0025] Example 1: Reference Figure 1 This is the first embodiment of the present invention, which provides a method for real-time monitoring of gate flow in hydropower stations based on big data, including the following steps: S1. Model the key parameters of each gate to form a water flow state perception model.

[0026] In existing technologies, the calculation of gate flow is usually based on the static head difference method, which simply takes the difference in water level before and after the gate as the only driving factor, while ignoring the influence of multiple factors such as the gate's own structural state, dynamic opening changes during operation, and spatial heterogeneity of the gate's location. This results in insufficient flow estimation accuracy and cannot meet the needs of high-frequency dynamic monitoring.

[0027] Step S1 breaks through the limitations of traditional single-dimensional static modeling and innovatively constructs a spatiotemporally distributed gate flow state perception model, organically integrating time t with dynamic factors such as gate number i and location-related parameters, providing theoretical support with spatiotemporal analytical power for the flow behavior of each gate.

[0028] The flow state perception model is based on key parameters of the i-th gate, including relative opening, upstream water level, and downstream water level. The model is shown below: ; in, : The theoretical instantaneous flow rate (m³ / s) of the i-th gate at time t; , : Empirical calibration coefficients, obtained based on historical regression data; Gravitational acceleration constant; : Relative opening of the gate (between 0 and 1); , : These are the upstream and downstream water levels (unit: m).

[0029] Opening the gate As a dynamic control variable, it is combined with the current upstream and downstream water level difference to form a square root term, while also introducing empirical coefficients. and To adapt to different gate types and watershed characteristics. By adjusting and Based on historical regression values, the model can automatically adapt to various structural parameters and operating environments, enabling customized modeling by gate and time period. It will calculate theoretical instantaneous flow in real time. This serves as the basis for subsequent perturbation analysis (i.e., step S2).

[0030] S2. Based on the parameters output by the model in S1, construct a traffic anomaly disturbance identification model, calculate the traffic disturbance difference, and determine whether there is an anomaly in the disturbance source identification.

[0031] This step introduces a disturbance function to construct a flow anomaly disturbance identification model. Because dam operation may involve latent factors such as sediment blockage, structural vibration, and underwater vegetation disturbance, the measured flow rate may vary. Deviation from theoretical value .

[0032] In traditional systems, when measured flow rates differ from predicted flow rates, responses are typically limited to threshold alarms or fuzzy judgments, lacking the ability to structurally identify the source of the deviation. This black-box approach fails to explain the specific causes of the problem or provide a reliable basis for subsequent control measures.

[0033] The traffic anomaly disturbance identification model is shown below: ; in, : The measured instantaneous flow rate of the i-th gate at time t; : Flow disturbance difference; The perturbation function generated by the multi-channel anomaly source satisfies: ; in, The weight coefficients of the k-th type of disturbance source for the i-th gate are estimated by fitting and optimization algorithms. The influence of the k-th type of disturbance source, such as sediment accumulation rate, structural vibration frequency, inflow fluctuation coefficient, and aquatic plant resistance. The total number of disturbance sources.

[0034] Decomposing the perturbation function into a linear combination of multiple specific perturbation sources reflects the "source structure" of the perturbation.

[0035] This model introduces an interpretable perturbation function between theoretical and measured flow rates. This method forms a double-equals model structure and decomposes the sources of disturbance into models. It effectively establishes a closed-loop modeling structure with physical logic for the entire system, linking "observation data—deviation calculation—disturbance interpretation." Compared to existing technologies, this transforms the causes of flow disturbance differences from an uncontrollable black box into a traceable combination of disturbance sources, thereby reducing false alarms.

[0036] S3. To address the flow disturbance difference caused by disturbance sources, a gate self-feedback correction model based on deviation reverse mapping is constructed to perform real-time correction of individual gates.

[0037] Traditional hydropower station flow control largely relies on static opening settings or preset rules, lacking the ability to dynamically respond to actual flow deviations. Especially when facing sudden disturbances (such as sudden increases in sediment or rapid changes in upstream head), the system often adjusts lagily, leading to control instability or even misjudgments. Step S3 proposes an opening correction mechanism based on disturbance deviation feedback, which... In the calculation of aperture, an analytical function is used to suggest the aperture at the next time step. This significantly enhances the system's real-time adaptive capabilities.

[0038] The gate self-feedback correction model quantifies the objective function to reduce the flow disturbance difference. To compress the opening size to an acceptable range as much as possible at the current moment, the following opening correction control strategy is proposed: ; in, Suggested opening degree for the next moment; : Control gain factor, set according to gate response sensitivity; When the system detects When the deviation is large, the opening is automatically adjusted. To correct flow errors and ensure the closed-loop performance of the real-time flow monitoring system.

[0039] In this model, the calculation from the previous step This yields the perturbation difference between the current theoretical and actual flow rates; Head difference acquisition: Measured by water level sensors upstream and downstream of the dam. , And send it to the system in real time; Calculate the opening correction amount: The system automatically calculates the required opening correction amount based on the opening correction control strategy; Implementation of control strategy: combining control gain factor Generate a new round of control commands The signal is transmitted to the execution device; Closed-loop verification: After the actual opening degree is adjusted, the deviation is recalculated in the next round to form a continuous feedback correction mechanism.

[0040] While short-term deviation feedback has enabled immediate correction in step S3, it cannot effectively capture and predict the long-term impact of slowly varying disturbances (such as riverbed evolution and aquatic biomass accumulation) on flow. Therefore, a time-series modeling mechanism is needed for trend identification. This method also designs a time-series drift tracking model to identify and fit the impact of slowly varying disturbances on the long-term trend of gate flow.

[0041] In this embodiment, the time-drift tracking model is as follows: ; in, : Drift rate index of the i-th gate (m³ / s²); : Time window width; : The disturbance residual value at time j; time j represents the historical sampling time within the time window, and t represents the latest time at which the drift index is being calculated; : Mean residual within the time window.

[0042] Using this model, the system rolls forward a time window at fixed intervals (e.g., 30 minutes); within this time window, it extracts... And calculate its centering value; linearly weight the residuals at each time point with time offset weights to obtain ;like If the value remains above the threshold, a structural maintenance recommendation will be issued.

[0043] This model can determine whether there is a systemic slow deterioration or improvement trend, and issue maintenance warnings or parameter recalibration signals accordingly, rather than simply relying on real-time feedback for passive responses. It is particularly suitable for identifying the evolution of "non-abrupt disturbances" such as siltation and underwater structure aging.

[0044] S4. Construct a gate group collaborative optimization mechanism to make the flow target of each gate of the hydropower station approach the optimal distribution of the system.

[0045] Based on the time-series drift tracking model, it has been determined that some gates may be affected by slow-varying disturbances. In this case, the flow correction of a single gate is no longer sufficient to meet the overall drainage scheduling requirements. Therefore, a gate group collaborative optimization mechanism is introduced to improve flow balance at the system level.

[0046] A collaborative optimization model is constructed based on the gate group collaborative optimization mechanism to make the flow target of each gate approach the optimal distribution of the system, and the objective function is defined.

[0047] The objective function of the collaborative optimization model is shown below: ; in, The system's flow balance deviation index at time t, with the overall goal of making... Minimum, through adjustment Let Gradually declining; Total number of gates; The system expects average flow rate to satisfy: ; This collaborative optimization model is used to minimize the flow balance deviation among the gates. It employs a real-time deployable evolutionary algorithm (such as a genetic algorithm) or a lightweight gradient descent method to solve the problem. The optimal opening distribution guides the coordinated operation of each gate, resulting in the optimized... The execution units of each gate are dispatched to complete a global control operation and achieve overall balance in flow output.

[0048] In this embodiment, the evolutionary algorithm searches for the optimal openness distribution by simulating natural selection and genetic mechanisms. Specifically, a set of randomly initialized gate opening combinations is first used as the initial population, and then based on the objective function... The fitness value is used to evaluate fitness, and selection, crossover, and mutation operations are performed sequentially, evolving generation by generation to gradually move towards a state where fitness is improved. Minimization-oriented optimization. The advantage of this method is that it can escape local optima, making it suitable for handling complex, nonlinear, and non-differentiable flow control scenarios. Furthermore, it does not rely on the specific gradient information of the flow equation, making it easy to deploy quickly in a near-optimal manner in real-time environments.

[0049] Lightweight gradient descent methods are directly based on the objective function. For each opening variable First derivative calculations are performed, and the aperture combinations are rapidly adjusted along the gradient direction to minimize the total system deviation. In each iteration, the system adjusts the aperture combinations for each aperture... Make minor updates. Since the gate flow rate and opening degree usually have a relatively monotonic relationship, lightweight gradient descent can quickly converge to a better solution within a finite number of steps. It has low computational cost and is suitable for deployment on resource-constrained edge computing nodes to achieve high-frequency, low-latency dynamic scheduling and adjustment.

[0050] It is not only suitable for the balanced scheduling of a fixed number of gates in the current system, but also has good scalability, adapting to possible future hydraulic expansion or modular gate unit access. Its optimization objective focuses on the consistency of gate flow output rather than the absolute flow size. This paradigm shift avoids the extreme value bias problem common in traditional algorithms, making system scheduling more flexible and robust.

[0051] S5. Construct an adaptive model detection mechanism to dynamically determine whether the model used in the current steps S1-S4 has failed.

[0052] The adaptive model detection mechanism is used to address the problem that models may gradually fail due to long-term evolution caused by the degradation of external environment or equipment performance. The adaptive model detection mechanism dynamically determines whether the model has failed based on the model failure metric of error entropy.

[0053] In the adaptive model detection mechanism, the gate flow error entropy is defined as follows: ; in, : The flow error entropy of the i-th gate; Number of error interval divisions; : The frequency proportion within the m-th error interval, that is, the probability (frequency) of the flow error of the i-th gate falling into the m-th interval within a preset time window. If the system detects the error entropy of a certain gate If the value continues to rise and exceeds the allowable threshold, it is determined that the model is no longer adapted to the actual traffic flow patterns, and a model failure warning will be automatically triggered.

[0054] This model no longer uses the mean or standard deviation of errors as the sole evaluation criterion, but instead introduces entropy, a statistical indicator reflecting the "disorderliness" of the system. When the system faces sudden disturbances or evolutionary systemic degradation, although the mean changes slowly, the distribution of errors may change from concentrated to divergent, at which point the entropy value will increase significantly. This design allows the system to identify model degradation before the "qualitative change in error pattern" occurs, thus achieving truly proactive modeling management.

[0055] In scenarios such as cross-regional collaboration in power dispatching, higher-level regulatory audits, and post-accident traceability, relying solely on a central database may face problems such as data tampering, isolated nodes, and weak fault tracing capabilities. Therefore, it is necessary to further introduce a reliable assurance mechanism.

[0056] Therefore, this method also introduces structured trusted blockchain technology to construct an asynchronous storage and consensus verification mechanism for gate flow monitoring data. This mechanism encapsulates structured data, including gate number, opening degree, upstream and downstream water levels, and flow disturbance difference, into a multi-level sub-block structure using a lightweight hash chain. Each sub-block represents an independent data flow state for a gate, and these sub-blocks are aggregated every set time window (e.g., 10 minutes). The multi-level sub-block structure encoded in the lightweight hash chain acts as lightweight nodes, verifying the validity of their corresponding fields and signing hash digests without requiring full synchronization. Only when more than a set percentage (e.g., 75%) of modules reach consensus can the current snapshot block be written into the chain and used as a trusted basis for future scheduling actions, incident reviews, or audit checks.

[0057] Example 2: This embodiment also provides a computer device applicable to a real-time monitoring method for hydropower station gate flow based on big data, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the real-time monitoring method for hydropower station gate flow based on big data proposed in the above embodiment.

[0058] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements a real-time monitoring method for the flow of gates in a hydropower station based on big data, as proposed in the above embodiment.

[0059] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0060] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, 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 of the various embodiments of this invention. 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.

[0061] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0062] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0063] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0064] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for real-time monitoring of gate flow in a hydropower station based on big data, characterized in that, Includes the following steps: S1. Model the key parameters of each gate to form a water flow state perception model; S2. Based on the parameters output by the model in S1, construct a traffic anomaly disturbance identification model, calculate the traffic disturbance difference, and determine whether there is an anomaly in the disturbance source identification. S3. To address the flow disturbance difference caused by disturbance sources, a gate self-feedback correction model based on deviation reverse mapping is constructed to perform real-time correction of individual gates. S4. Construct a gate group collaborative optimization mechanism to make the flow target of each gate of the hydropower station approach the optimal distribution of the system; S5. Construct an adaptive model detection mechanism to dynamically determine whether the model used in the current steps S1-S4 has failed.

2. The method for real-time monitoring of hydropower station gate flow based on big data according to claim 1, characterized in that, In step S1, the water flow state perception model is modeled based on the key parameters of the i-th gate, including relative opening, upstream water level, and downstream water level, as shown in the following model: ； in, The theoretical instantaneous flow rate of the i-th gate at time t; , Empirical calibration coefficient; Gravitational acceleration constant; The relative opening of the gate; , These refer to the upstream water level and the downstream water level, respectively.

3. The method for real-time monitoring of gate flow in a hydropower station based on big data, as described in claim 1, is characterized in that... In step S2, the traffic anomaly disturbance identification model is as follows: ； in, : The measured instantaneous flow rate of the i-th gate at time t; : Flow disturbance difference; The perturbation function generated by the multi-channel anomaly source satisfies: ； in, : The weighting coefficient of the k-th type of disturbance source for the i-th gate; : The influence term of the k-th type of disturbance source; The total number of disturbance sources.

4. The method for real-time monitoring of gate flow in a hydropower station based on big data, as described in claim 1, is characterized in that... In step S3, the gate self-feedback correction model quantizes the objective function to reduce the flow disturbance difference. To compress the opening size to an acceptable range as much as possible at the current moment, the following opening correction control strategy is proposed: ； in, Suggested opening degree for the next moment; : Control gain factor; : Gravitational acceleration; When the system detects When the deviation is large, the opening is automatically adjusted. To correct flow errors and ensure the closed-loop performance of the real-time flow monitoring system.

5. The method for real-time monitoring of gate flow in a hydropower station based on big data, as described in claim 1, is characterized in that... In step S4, when the flow correction of a single gate cannot meet the overall drainage scheduling requirements, a gate group collaborative optimization mechanism is introduced to improve flow balance at the system level. A collaborative optimization model is constructed based on the gate group collaborative optimization mechanism to make the flow target of each gate approach the optimal distribution of the system, and the objective function is defined.

6. The method for real-time monitoring of gate flow in a hydropower station based on big data, as described in claim 5, is characterized in that... The objective function of the collaborative optimization model is shown below: ； in, The system's flow balance deviation index at time t, with the overall goal of making... Minimum, through adjustment Let Gradually declining Total number of gates; The system expects average flow rate to satisfy: ； This collaborative optimization model is used to minimize the flow balance deviation among the gates by adjusting their opening degrees. The distribution guides the coordinated operation of each gate to achieve overall balance in flow output.

7. The method for real-time monitoring of gate flow in a hydropower station based on big data, as described in claim 1, is characterized in that... In step S5, the adaptive model detection mechanism is used to address the problem that the model may gradually fail due to the long-term evolution of the external environment or equipment performance degradation. The adaptive model detection mechanism dynamically judges whether the model has failed based on the model failure metric of error entropy.

8. The method for real-time monitoring of gate flow in a hydropower station based on big data, as described in claim 7, is characterized in that... In the adaptive model detection mechanism, the gate flow error entropy is defined as follows: ； in, : The flow error entropy of the i-th gate; Number of error interval divisions; : The frequency proportion within the m-th error interval, which represents the probability that the error falls into this interval over a period of time; If the system detects the error entropy of a certain gate If the value continues to rise and exceeds the allowable threshold, it is determined that the model is no longer adapted to the actual traffic flow patterns, and a model failure warning will be automatically triggered.

9. A method for real-time monitoring of gate flow in a hydropower station based on big data, as described in claim 1, is characterized in that... The method also includes effectively capturing and predicting the long-term impact of slow-varying disturbances on flow, designing a time-series drift tracking model to identify and fit the impact of non-abrupt disturbances on the long-term trend of gate flow, using the model to determine whether there is a systematic slow deterioration or improvement trend, and issuing maintenance warnings or parameter recalibration signals accordingly.

10. A method for real-time monitoring of gate flow in a hydropower station based on big data, as described in claim 1, is characterized in that... This method also introduces the structured trusted blockchain technology to build an asynchronous storage and consensus verification mechanism for gate flow monitoring data. The mechanism encapsulates structured data, including gate number, opening degree, upstream and downstream water levels, and flow disturbance difference, into a multi-level sub-block structure using a lightweight hash chain. Each sub-block structure represents the independent data flow state of a gate.

Images