Hydropower station computer monitoring method based on domestic hardware

Abstract

The invention relates to the technical field of hydropower station intelligent monitoring and dispatching, and discloses a hydropower station computer monitoring method based on domestic hardware, which comprises the following steps: dynamic system modeling: establishing nonlinear dynamic models, including water pump and generator power models, of equipment in a hydropower station, and describing the operation state of the equipment; the multi-objective optimization scheduling is used for calculating load scheduling of equipment based on a multi-objective optimization model of power consumption, equipment loss and system energy efficiency; and the fault prediction and early warning module is used for carrying out real-time prediction on the equipment state through Kalman filtering, carrying out fault mode prediction based on historical data and sending out fault early warning in time. According to the invention, through dynamic system modeling, multi-objective optimization scheduling, Kalman filtering fault prediction and H-infinity robust control, efficient scheduling, accurate fault early warning and robust control strategy optimization of hydropower station equipment are realized, and the operation efficiency and stability of the system are significantly improved.

Description

Technical Field

[0001] The invention relates to the technical field of intelligent monitoring and dispatching of hydropower stations, and in particular to a computer monitoring method for hydropower stations based on domestic hardware. Background Art

[0002] In modern society, hydropower stations are an important source of energy supply, and their stable and efficient operation is crucial to ensuring power supply, reducing energy consumption and improving economic benefits. Hydropower stations not only involve a large number of complex equipment, but also face challenges such as environmental changes and equipment failures. In order to ensure that hydropower stations can continue to operate stably under various complex working conditions, it is particularly important to adopt advanced monitoring and control technologies.

[0003] At present, the monitoring systems of hydropower stations mostly use methods based on empirical rules or simple optimization models for equipment scheduling and load distribution. These methods usually focus on a single goal, such as optimizing equipment power consumption or equipment loss, which can improve efficiency and reduce losses to a certain extent. In addition, some hydropower stations have adopted a fault prediction mechanism based on historical data and experience settings, which issues alarms by monitoring the status changes of equipment, thereby avoiding the impact of partial equipment failures on the system. In the prior art, control methods are mostly based on traditional control theory, have a certain anti-interference ability, and can maintain the stable operation of the hydropower station system to a certain extent.

[0004] However, the existing technology still has some shortcomings; first, the existing equipment scheduling method fails to consider the balance between multiple objectives, and cannot comprehensively optimize the overall efficiency of the hydropower station, resulting in unbalanced equipment load and energy waste; second, the traditional fault prediction mechanism relies on simple threshold settings and cannot accurately detect tiny fault signals of the equipment, thereby reducing the reliability and timeliness of fault warnings; in addition, the existing control method shows poor adaptability when facing external disturbances and equipment failures, and cannot flexibly adjust the control strategy according to real-time changes, which may cause the system to become unstable in sudden situations, affecting the safe operation of the hydropower station. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a computer monitoring method for a hydropower station based on domestic hardware, which solves the problems of uneven scheduling of hydropower station equipment, inaccurate fault prediction and poor adaptability of control strategies in the prior art.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A computer monitoring method for a hydropower station based on domestic hardware, comprising the following steps:

[0007] Dynamic system modeling: used to establish nonlinear dynamic models of various equipment in the hydropower station, including pump and generator power models, to describe the operating status of each equipment;

[0008] Multi-objective optimization scheduling: used to calculate the load scheduling of equipment based on multi-objective optimization models of power consumption, equipment loss and system energy efficiency;

[0009] Fault prediction and early warning: used to predict the equipment status in real time through Kalman filtering, predict the fault mode based on historical data, and issue fault early warning in time;

[0010] Robust control: used to adaptively adjust the control strategy through the H∞ controller to ensure system stability when the system faces external disturbances and equipment failures;

[0011] Feedback and optimization: It is used to monitor the operating status of the hydropower station in real time, adjust the load scheduling through the feedback mechanism, and continuously optimize the equipment operation efficiency.

[0012] Preferably, the dynamic system modeling includes:

[0013] By establishing a power output model of the water pump, taking into account the water flow rate and head height, the power of the water pump is calculated using physical formulas;

[0014] By establishing a power output model of the generator, the pump power is related to the generator efficiency and the output power of the generator is calculated;

[0015] Combining the water flow, equipment power output and load scheduling of the hydropower station, nonlinear differential equations are used to model the equipment operation.

[0016] Preferably, the multi-objective optimization scheduling includes:

[0017] Construct a multi-objective optimization model based on the power consumption, system energy efficiency and equipment loss of each equipment in the hydropower station;

[0018] Use the weighted sum method to combine multiple optimization objectives into one objective function for solution;

[0019] Use genetic algorithm or particle swarm optimization algorithm to solve the objective function and calculate the optimal load scheduling solution;

[0020] By optimizing calculations and adjusting the load of each device, we can ensure that the equipment operates in the optimal state and reduce energy efficiency loss and equipment loss.

[0021] Preferably, the fault prediction and early warning include:

[0022] Use Kalman filtering to estimate the state of the equipment in real time and predict the future state based on current and historical data;

[0023] Using the Kalman filter algorithm, the health status of the equipment is dynamically updated and real-time prediction results are generated;

[0024] Based on fault history data and support vector machines, potential failure modes are predicted, and warnings are issued and measures are taken based on the prediction results.

[0025] Preferably, the robust control includes:

[0026] Design an H∞ controller to reduce the impact of external disturbances on the system by minimizing the maximum gain of the system transfer function;

[0027] Robust control algorithms are used to enable the hydropower plant to maintain stability in the event of equipment failure or external disturbances;

[0028] Adaptively adjust control strategies to ensure that equipment can still operate efficiently in the event of sudden failures or uncertainties.

[0029] Preferably, the implementation feedback and optimization includes:

[0030] Collect equipment operation data through real-time monitoring system to evaluate current equipment status and load distribution;

[0031] Use feedback mechanism to transmit monitoring data to the dispatching system and adjust the load dispatching plan according to the feedback data;

[0032] Based on real-time monitoring data and optimization calculation results, the equipment operation strategy is continuously adjusted to achieve system self-optimization and continuously improve equipment operation efficiency.

[0033] Preferably, the dynamic system modeling further comprises:

[0034] Use physical models to establish the nonlinear relationship between the pump and the generator, and determine the relationship between power output and water flow and head height parameters;

[0035] Through system modeling, a comprehensive dynamic description of the working status of each equipment in the hydropower station is made, providing a basis for subsequent load scheduling and optimization.

[0036] Preferably, the multi-objective optimization scheduling further includes:

[0037] According to the operating constraints of each device, add constraints to the optimization model to ensure that the calculated load scheduling plan meets the requirements of safe operation of the equipment;

[0038] The optimization plan is updated through real-time data, and the scheduling plan is recalculated regularly to respond to changes in the system's operating status.

[0039] Preferably, the fault prediction and early warning further includes:

[0040] Monitor system sensor data in real time and identify abnormal patterns in equipment operation by comparing and analyzing historical fault data;

[0041] Combine abnormal patterns with fault prediction models, use machine learning algorithms to diagnose faults, and issue alarms through monitoring systems.

[0042] Preferably, the implementation feedback and optimization further includes:

[0043] The system automatically evaluates the operating status and dynamically adjusts the scheduling plan based on the equipment health status and external environment;

[0044] When equipment fails, the feedback mechanism can automatically adjust the operating strategy, reduce system downtime, and ensure the continuous operation of the hydropower station.

[0045] The present invention provides a computer monitoring method for a hydropower station based on domestic hardware. It has the following beneficial effects:

[0046] 1. The present invention uses a multi-objective optimization model to perform equipment scheduling, comprehensively considers multiple factors such as power consumption, equipment loss and energy efficiency, and accurately optimizes the load distribution of the hydropower station. Compared with traditional scheduling methods, the present invention can more efficiently balance the load of each device, reduce unnecessary energy waste, reduce equipment loss, and improve overall system efficiency.

[0047] 2. Use Kalman filtering technology to predict the operating status of equipment in real time, and combine historical data to predict failure modes and identify potential risks in advance. Compared with the common threshold-based early warning method, this invention can more accurately capture equipment anomalies, issue alarms in a timely manner, reduce downtime, and reduce maintenance costs.

[0048] 3. The H∞ robust control technology of the present invention can effectively cope with external disturbances and equipment failures, while ensuring system stability and improving the fault tolerance of the hydropower station. Compared with traditional control methods, the adaptive adjustment capability of the present invention enhances the stability of the system in complex environments, and can ensure efficient operation even in the case of partial equipment failure.

[0049] 4. Based on domestic hardware, the present invention realizes the high integration of the hydropower station monitoring system and reduces the dependence on external hardware. Different from the technical solution that relies on imported hardware, the present invention not only improves the security and stability of the system, but also supports localized technical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] Please refer to the attached Figure 1 The embodiment of the present invention provides a computer monitoring method for a hydropower station based on domestic hardware, comprising the following steps:

[0053] S1. Dynamic system modeling: used to establish nonlinear dynamic models of various equipment in the hydropower station, including pump and generator power models, to describe the operating status of each equipment;

[0054] Dynamic system modeling provides a scientific basis for subsequent multi-objective optimization scheduling, fault prediction and early warning, robust control, etc. by accurately describing the working status of various equipment in the hydropower station (such as pumps, generators, etc.). This step mainly includes the establishment of pump and generator power models, and also involves the operation constraints of the equipment to ensure that the equipment works within a safe and efficient operating range.

[0055] In this embodiment, the model of the water pump power output takes into account factors such as water flow, water head height and water pump efficiency. The power output formula of the water pump is:

[0056]

[0057] in: For the pump in time Power output at the moment (unit: Watt, W); is the efficiency of the water pump (dimensionless), which indicates the energy efficiency of the water pump and is usually between 0 and 1. The specific value depends on the design and working conditions of the water pump; is the density of water (unit: kilograms / cubic meter, kg / m 3 ). In hydropower stations, the value is usually 1000 kg / m 3 ; is the water flow rate (unit: cubic meters per second, m 3 / s), indicating the pump is The amount of water being processed at any given moment and the size of the flow rate affect the power output of the pump; is the acceleration due to gravity (unit: m / s 2 , m / s 2 ), which is usually taken as 9.81 m / s on the Earth's surface 2 ; It is the water head height (unit: meter, m), that is, the vertical height difference from the water inlet to the water outlet of the water pump, which affects the energy conversion efficiency of the water pump.

[0058] This formula reflects the relationship between the power output of the pump and parameters such as flow rate and head height. By measuring the flow rate and head height, the power output of the pump under specific working conditions can be calculated through this formula.

[0059] The power output of the generator is directly dependent on the power output of the water pump. Assuming there is no other energy loss between the generator and the water pump, the power output formula of the generator is:

[0060]

[0061] in: For the generator at time Power output at the moment (unit: Watt, W); is the efficiency of the generator (dimensionless), which indicates the efficiency of the generator in converting the mechanical work of the pump into electrical energy, usually between 0 and 1; is the power output of the pump (unit: Watt, W), and the calculation method is shown in the previous part.

[0062] The model assumes that the energy conversion between the pump and the generator is linear, and the power of the pump is directly converted into the electrical energy output of the generator. The actual conversion efficiency is determined by the efficiency parameter of the generator. Decide.

[0063] In order to ensure that the equipment operates within a safe range, constraints must be set on the power output of each device in the hydropower station. In this embodiment, the power output of all equipment (including pumps and generators) cannot exceed their designed maximum power to avoid equipment overload and damage.

[0064] Specifically, the power output of the pump and generator needs to meet the following constraints:

[0065]

[0066] in: For the generator at time Power output at the moment (unit: Watt, W); The maximum power output of the generator (unit: Watt, W), which is determined by the design specifications and operating conditions of the equipment.

[0067] In actual operation, if the power output of the generator exceeds the maximum power , which may cause damage to the device or system failure. Therefore, it is necessary to ensure that the device is always operating within its maximum power range.

[0068] In a hydropower station, the working conditions of pumps, generators and other related equipment are not only affected by their own physical parameters, but also by the complex coupling effects between systems. Therefore, the establishment of the model does not rely solely on simple linear relationships, but adopts a nonlinear dynamic model. Through this modeling method, the interaction between devices and how they affect the overall behavior of the system can be effectively described.

[0069] In general, the relationship between the power output of pumps and generators and multiple factors such as water flow, head, load, etc. is nonlinear. These nonlinear characteristics need to be described by solving ordinary differential equations (ODE). For example, the relationship between water flow, equipment load and power output can be modeled by nonlinear differential equations. These equations take into account the dynamic response of the equipment under different operating conditions and can accurately predict the operating behavior of the equipment.

[0070] In one possible implementation, the effect of the flow rate change and head height of the water pump on the power output can be described by a nonlinear equation. For example, the change of the power output of the water pump is not only affected by the head height, but also by factors such as flow rate change and equipment wear. By introducing these factors, the operating status of the equipment can be described more accurately.

[0071] In this embodiment, the dynamic relationship between multiple devices (such as water pumps, generators, etc.) in the hydropower station is highly coupled. In order to fully reflect the behavior of the overall system of the hydropower station, the present invention establishes an integrated dynamic system model by integrating the power models of various devices. This model can simultaneously consider the synergy between water pumps, generators and other equipment, and provide support for subsequent load scheduling, fault prediction and optimization.

[0072] In specific implementation, these nonlinear equations can be solved by numerical methods (such as Euler method, Runge-Kutta method, etc.) to obtain the operating status of each device in the hydropower station. These calculation results will provide accurate data support for subsequent optimization scheduling algorithms to ensure that the entire system can operate efficiently and stably.

[0073] The dynamic system modeling step provides accurate basic data and theoretical support for subsequent steps such as load scheduling, fault prediction and robust control of the hydropower station by establishing power models of pumps and generators and combining the maximum power constraints and nonlinear dynamic models of the equipment.

[0074] S2, Multi-objective optimization scheduling: used for load scheduling of computing equipment based on a multi-objective optimization model of power consumption, equipment loss and system energy efficiency;

[0075] Through the dynamic models established by S1, these models provide the necessary data support and theoretical basis for multi-objective optimization scheduling. By combining factors such as equipment power consumption, loss and system energy efficiency for comprehensive optimization, this step aims to improve the operating efficiency of the hydropower station by calculating the optimal load scheduling solution.

[0076] The key task of this step is to balance multiple objectives such as power consumption, equipment loss and system energy efficiency through a multi-objective optimization model to achieve the optimal operating state of the overall system. On this basis, this embodiment uses optimization methods such as genetic algorithm (GA) and particle swarm optimization (PSO) to solve the optimal solution, ensuring that the equipment of the hydropower station operates in the most appropriate load distribution mode while avoiding equipment overload and inefficient operation.

[0077] In multi-objective optimization scheduling, the core is to build a comprehensive objective function, which not only integrates power consumption, equipment loss and system energy efficiency, but also considers the synergy between equipment. The form of the objective function is as follows:

[0078]

[0079] in: is the objective function (unit: dimensionless), which represents the comprehensive optimization goal of the whole system; For the The power consumption coefficient of a device (unit: watt, W), which indicates the energy consumed by the device per unit time; For the Devices at time The load at a certain moment (unit: watt, W), that is, the power output of the device at a certain moment; and are weighted coefficients (dimensionless), which are used to balance the relationship between power consumption, energy efficiency and equipment loss. By adjusting these weight coefficients, the focus of the optimization goal can be adjusted according to actual needs; For the system at time Energy efficiency (dimensionless), which indicates the energy efficiency of the entire system; It is the loss of the equipment (unit: Watt, W), which indicates the energy consumed by the equipment due to various reasons (such as friction, heat loss, etc.).

[0080] The objective function is set in such a way that the optimization problem can find a balance between power consumption, system energy efficiency and equipment loss. and The value of can make the objective function tend to optimize specific goals and meet different operating requirements.

[0081] In order to solve the multi-objective optimization problem, this embodiment uses intelligent optimization algorithms such as genetic algorithm (GA) and particle swarm optimization algorithm (PSO). These optimization methods have strong global search capabilities, can effectively avoid local optimal solutions and find the optimal load scheduling solution.

[0082] In some embodiments, the genetic algorithm optimizes the load scheduling scheme by simulating the evolution process of organisms. Specifically, the genetic algorithm evaluates the pros and cons of each scheduling scheme according to the fitness function, and continuously generates a new generation of better solutions through operations such as selection, crossover and mutation.

[0083] The particle swarm optimization algorithm (PSO) simulates the behavior of a flock of birds foraging. It assumes that each solution is a particle, and the particle searches for the optimal solution by exploring the solution space. In each generation, the particle adjusts its position and speed according to the individual optimal solution and the global optimal solution, thus gradually approaching the global optimal solution. The PSO algorithm is particularly suitable for optimization problems where the solution space is large and local optimization is not easy.

[0084] When optimizing scheduling, it is necessary to include the constraints of multiple devices in the calculation of the objective function. These constraints ensure the safe operation of the equipment and the stability of the system. In general, the constraints mainly include the following aspects:

[0085] Device power limit: The power output of a device cannot exceed its maximum carrying capacity.

[0086] Equipment minimum power limit: In addition to the maximum power limit, the minimum power output limit of the equipment also needs to be considered to ensure that the equipment does not lose efficiency due to running at too low a load.

[0087] System energy efficiency constraint: The overall energy efficiency of the system cannot be lower than a certain threshold. The lower limit of may be affected by many factors such as the working status of the equipment and the external environment, so it needs to be optimized as one of the constraints.

[0088] Equipment loss limit: Equipment loss It should be limited to a certain range to prevent the system from being inefficient due to excessive losses. This constraint usually needs to take into account factors such as the working time and load of the equipment.

[0089] In order to further improve the optimization effect, this embodiment introduces a real-time feedback mechanism in the optimization process. By continuously acquiring the real-time operation data of the equipment, the scheduling system can dynamically adjust the scheduling plan according to factors such as the health status and workload of the equipment. Real-time data includes but is not limited to parameters such as the power output, load, and temperature of the equipment.

[0090] In one possible implementation, the system obtains the operating status information of the equipment through sensors and monitoring systems, and feeds it back to the dispatch system. Based on this feedback data, the dispatch system adjusts the load distribution to avoid overloading or inefficient operation of the equipment. For example, when a certain equipment is overloaded and inefficient, the system automatically adjusts its load and gives priority to other equipment to share the workload.

[0091] Finally, the optimization algorithm will obtain the optimal load dispatching plan based on the calculation results. This plan not only takes into account factors such as power consumption, energy efficiency and equipment loss, but also meets the operating constraints of the equipment, ensuring the efficient and stable operation of the hydropower station under different working conditions.

[0092] Specifically, the optimization scheme will serve as the basis for load dispatching strategies in actual operation. The dispatching system will automatically update the load distribution according to the real-time status to ensure that each device always operates within the optimal load range. The optimization results will be continuously fed back to the system to form a closed-loop control process, further improving the operating efficiency of the hydropower station.

[0093] The multi-objective optimization scheduling step balances multiple aspects such as power consumption, equipment loss and system energy efficiency by constructing a comprehensive objective function, and realizes intelligent optimization of load scheduling while ensuring the safe operation of equipment.

[0094] S3, Fault prediction and early warning: used to predict the equipment status in real time through Kalman filtering, predict the fault mode based on historical data, and issue fault early warning in time;

[0095] This step aims to predict possible faults and issue early warnings by dynamically monitoring the operating status of the equipment, combining Kalman filtering and machine learning methods. This allows necessary preventive measures to be taken before a fault occurs, thereby improving the stability and safety of the hydropower station.

[0096] In fault prediction, Kalman filter algorithm is widely used for equipment state estimation. Kalman filter is a recursive algorithm that dynamically estimates the equipment state and predicts the future state based on the system model and measurement data. This process can effectively remove the uncertainty caused by measurement error or noise, thereby improving the accuracy of fault prediction.

[0097] In general, Kalman filtering is applied to continuous-time systems, usually to predict the health status of equipment or the behavior of equipment in the future. For hydropower station equipment, the Kalman filter algorithm can process multi-dimensional data such as current, power, temperature, vibration, etc. Based on these real-time data, the Kalman filter can dynamically update the equipment state estimate and predict possible failures.

[0098] Specifically, the Kalman filtering process includes two main steps: prediction and update.

[0099] Prediction Steps:

[0100]

[0101] in: For the moment The state prediction of (unit: dimensionless). This term represents the state prediction of The equipment status previously predicted based on historical data; is the state transfer matrix (dimensionless), indicating the transition from Time has come The state change relationship at each moment is usually set according to the dynamic model of the device; is the control input matrix (dimensionless), which represents the impact of control input (such as load change, equipment adjustment, etc.) on the equipment state; is the control input (unit: dimensionless), such as device load, external disturbance, etc.

[0102] Through the prediction step, the Kalman filter can predict the future state of the device based on the system model and historical data.

[0103] Update steps:

[0104]

[0105]

[0106]

[0107] in: is the Kalman gain (dimensionless), which is used to adjust the prediction error and weigh the deviation between the predicted result and the actual measurement value; is the prediction covariance matrix (dimensionless), which represents the prediction error of the equipment state; is the actual measured value (unit: dimensionless), such as the actual current, temperature or other parameter of the device; is the measurement matrix (dimensionless), which represents the relationship between the equipment status and the measurement data; is the measurement noise covariance matrix (dimensionless), representing the uncertainty in the measurement process; It's time The updated state estimate (unit: dimensionless), which represents the device state corrected based on the predicted value and the actual measured data; is the predicted output obtained from the predicted state value and the measurement matrix (unit: dimensionless), which represents the measured value inferred from the predicted device state in the absence of measurement error; is the measurement residual (unit: dimensionless), which represents the difference between the actual measured value and the predicted measured value. This difference is used to adjust the predicted state estimate; It's time The updated covariance matrix (dimensionless) represents the updated state estimation error. It reflects the uncertainty of the updated device state; is the unit matrix (dimensionless), which is used to keep the dimensions of the matrix consistent; is the product of the Kalman gain and the measurement matrix (dimensionless), which is used to adjust the covariance matrix to reduce uncertainty.

[0108] Through the update step, the Kalman filter algorithm can adjust the predicted device state according to the actual measurement data, thereby improving the accuracy of the estimated device health state. The updated device state can serve as the basis for subsequent fault prediction.

[0109] In this embodiment, Kalman filtering is combined with machine learning (such as support vector machines (SVM) or deep learning networks) to improve the ability of fault prediction. Through machine learning, the system can learn the normal operation mode and failure mode of the equipment from historical data, and then classify and predict potential equipment failures.

[0110] As an option, support vector machines (SVM) can be applied to fault mode classification. By using the historical operating data of the equipment (such as temperature, pressure, vibration, current, etc.) as features and training the SVM model, the system can identify the normal and abnormal states of the equipment. The SVM algorithm achieves accurate classification of equipment failure modes by finding the optimal decision boundary between categories.

[0111] Specifically, SVM distinguishes different fault modes by constructing a hyperplane, making fault detection more accurate. For example, SVM can identify slight changes in equipment status, discover potential fault trends in advance, and provide timely warnings.

[0112] In one possible implementation, a hybrid method combining Kalman filtering and SVM can provide more accurate fault prediction. Kalman filtering is responsible for state estimation of real-time data, while SVM recognizes patterns of potential faults by learning from historical data. The combination of the two can greatly improve the accuracy and response speed of fault prediction.

[0113] The fault prediction and early warning step involves not only the prediction of faults, but also the system's emergency response mechanism. After the fault is predicted, the system will take appropriate measures based on the severity and urgency of the fault. For example, if it is predicted that the failure of a certain device will have a significant impact on the system, the system can automatically issue an alarm and dispatch backup equipment or take measures such as load transfer to prevent the fault from expanding.

[0114] Specifically, the system can transfer loads based on fault prediction, ensuring that other devices can share the load of the faulty device and reduce system downtime. The operator can promptly understand the location, type and severity of the fault through the monitoring interface, ensuring that countermeasures can be taken quickly.

[0115] As an option, in the event of an early warning, the system can automatically activate emergency plans, transfer the load to healthy equipment, or even automatically shut down or perform necessary repair operations in an emergency.

[0116] The realization of fault prediction and early warning depends on the support of real-time data acquisition system. The system continuously collects the operation data of the equipment through sensors installed on each device. The accuracy and comprehensiveness of real-time data are crucial to the accuracy of fault prediction.

[0117] Generally, the data acquisition system can obtain the key parameters of the equipment in real time, such as current, voltage, temperature, vibration, etc., and transmit these data to the central control platform through the industrial control system. By combining real-time data, Kalman filtering and machine learning models, the system can accurately determine the health status of the equipment before it fails.

[0118] By combining Kalman filtering and machine learning, the fault prediction and early warning steps can effectively improve the ability to predict equipment failures. Based on real-time monitoring and historical data, the system can dynamically evaluate the status of equipment and issue early warnings before potential failures occur, avoiding significant losses caused by equipment failures.

[0119] S4, robust control: used to adaptively adjust the control strategy through the H∞ controller to ensure system stability when the system faces external disturbances and equipment failures;

[0120] In actual operation, hydropower stations may face external disturbances, equipment failures or other unforeseen factors, which may affect the stability and performance of the system. In order to deal with these uncertainties, this step introduces robust control, especially the H∞ control method, which ensures that the hydropower station system can still operate stably in complex environments through adaptive adjustment of control strategies.

[0121] The core goal of robust control is to ensure that the system can still maintain the predetermined performance and stability in the event of equipment failure or external disturbance. Specifically, the H∞ control method is adopted in this embodiment to minimize the system's sensitivity to disturbances by optimizing the control input, thereby ensuring efficient and safe operation of the equipment. Unlike traditional control methods, H∞ control can automatically adjust the control strategy when the system is affected by uncertain factors, thereby enhancing the robustness of the system.

[0122] In general, robust control improves the system's anti-disturbance capability by minimizing the system's H∞ norm. The H∞ norm measures the maximum gain of the system under external disturbances. Minimizing this norm can reduce the impact of disturbances on the system output, thereby achieving system stability.

[0123] The design of H∞ controller is based on the transfer function of the system , which describes the disturbance input of the system and output The goal of H∞ control is to solve the control input , which minimizes the H∞ norm of the system and reduces the impact of disturbances on the system output.

[0124] Specifically, the goal of H∞ control is to adjust the system output by controlling the input to achieve the following optimization goals:

[0125]

[0126] in: is the transfer function of the system (dimensionless), representing the disturbance input and output The transfer function describes how a disturbance affects the output of a system; It represents the H∞ norm, which measures the worst response or maximum gain of the system. By minimizing the H∞ norm, the system can maintain the minimum response under the action of disturbance.

[0127] The purpose of minimizing the H∞ norm is to make the system stable in the face of various uncertainties and disturbances and reduce unnecessary performance fluctuations.

[0128] The implementation of H∞ control involves building a dynamic model of the hydropower station and adjusting the control strategy in real time through a feedback mechanism. When designing an H∞ controller, it is first necessary to build a complete state space model based on the hydropower station equipment (such as pumps, generators, etc.). The model includes parameters such as the dynamic behavior of the equipment, disturbance input, and load distribution.

[0129] Generally, the H∞ controller needs to dynamically adjust the control input according to the real-time operating status of the equipment and external disturbances. For example, when the system faces external load fluctuations, the H∞ controller can automatically adjust the load distribution of the pump and generator to ensure that the equipment operates at the optimal operating point and avoid equipment overload or poor performance.

[0130] In one possible implementation, the H∞ controller collects the power output, temperature, vibration and other parameters of the equipment in real time, and dynamically adjusts the control strategy to ensure that the hydropower station can remain stable under different operating conditions. For example, when a certain device is in an abnormal state, the H∞ controller will adjust the load to avoid the impact of the device on the entire system, thereby ensuring the stability and efficiency of the hydropower station.

[0131] The H∞ controller in this embodiment combines a real-time feedback mechanism to continuously monitor the operating status of the device and adjust the control strategy in real time. The feedback mechanism can help the system automatically optimize the control input according to the health status of the device, load changes, and external environmental changes. Real-time feedback enables the H∞ controller to adaptively adjust the operating status of the device to ensure that the system is always in the optimal state.

[0132] As an option, the feedback mechanism not only focuses on the power output of the equipment, but also monitors key parameters such as temperature, vibration, efficiency, etc. These feedback signals are transmitted to the control system to help the system make real-time decisions, thereby further improving the robustness and stability of the hydropower station.

[0133] In one possible implementation, the system collects equipment status data through sensors and feeds this data back to the controller. Based on real-time data, the H∞ controller can dynamically adjust the load and optimize equipment operation to avoid equipment overload or efficiency loss.

[0134] External disturbances and system uncertainties are key factors affecting the stability of hydropower station operation. In actual operation, external disturbances (such as grid load fluctuations, changes in environmental conditions) and equipment failures (such as mechanical losses, performance degradation) will have an impact on the system. The H∞ controller reduces the impact of these disturbances by minimizing the H∞ norm of the system, ensuring that the hydropower station can cope with various complex operating conditions.

[0135] Specifically, disturbances may include external load fluctuations, load imbalances between devices, etc. Through real-time feedback and adaptive adjustment, the H∞ controller can automatically adjust the system control strategy when disturbances occur. For example, if the grid load fluctuates, the H∞ controller can quickly balance the load by adjusting the operating status of the pump and generator to avoid overload or unstable operation of the equipment.

[0136] In general, H∞ control is more robust than traditional control methods and can effectively cope with external disturbances and equipment failures. By optimizing the control input, the H∞ controller ensures the stability of the system, whether in the face of load fluctuations or equipment failures, the system can maintain optimal performance.

[0137] Specifically, H∞ control can adaptively adjust the control strategy according to the actual operating status of the equipment and the changes in external disturbances. This adaptive adjustment not only improves the operating efficiency of the hydropower station, but also improves its anti-interference ability, ensuring the reliability and safety of the hydropower station in complex environments.

[0138] The robust control step introduces the H∞ control method to ensure that the hydropower station can adjust the control strategy in real time when facing external disturbances and equipment failures to ensure the stability and efficient operation of the system. By minimizing the H∞ norm of the system, the H∞ controller effectively reduces the impact of external disturbances on the system, enhances the robustness of the system, and can improve the stability, reliability and efficiency of the hydropower station.

[0139] S5. Feedback and optimization: It is used to monitor the operation status of the hydropower station in real time, adjust the load scheduling through the feedback mechanism, and continuously optimize the equipment operation efficiency;

[0140] In actual operation, the system often faces problems such as dynamically changing working conditions, fluctuations in equipment health, interference from the external environment, etc. Therefore, step S5 of the present invention - implementing feedback and optimization, focuses on dynamically adjusting and optimizing the system through a real-time feedback mechanism to ensure that the hydropower station always maintains the best operating efficiency and stability under different operating conditions.

[0141] The main purpose of implementing feedback and optimization is to continuously adjust load distribution and equipment scheduling based on real-time data of equipment, environmental changes and system operating status, so that the entire hydropower station system can maintain efficient, safe and sustainable operation in a changing operating environment.

[0142] In general, in order to ensure that the system can respond to changes in the status of the equipment in real time, this embodiment adopts a comprehensive real-time data acquisition system. The system deploys sensors on key equipment to monitor various parameters of the equipment in real time, including power output, voltage, current, temperature, vibration, efficiency, etc. These data provide necessary input for the subsequent feedback mechanism.

[0143] Specifically, the key operating data of each device will be collected in real time through sensors and transmitted to the central control system. These data include parameters such as power, load, current, temperature, vibration, etc. The collection of real-time data can help the system to grasp the operating status of the equipment in a timely manner so as to adjust the equipment operation strategy when necessary.

[0144] As an option, the control system will also perform data preprocessing based on real-time data to remove sensor noise and eliminate abnormal data to ensure the accuracy of input data. After filtering and correction, the data will be used to adjust the scheduling plan and control strategy to avoid the system making wrong decisions due to inaccurate data.

[0145] Through real-time feedback, the system can dynamically adjust the load scheduling when the equipment status and environment change, ensuring that the equipment always operates at the optimal working point. Load scheduling optimization is not only performed during the initial scheduling of the equipment, but is continuously optimized during the operation of the equipment to ensure the operating efficiency of the system.

[0146] Specifically, the load scheduling optimization process dynamically adjusts the equipment load based on real-time data. It is related to its working status, including power consumption, efficiency and other factors. In order to ensure the efficient operation of the system, the dispatching system adjusts the load of each device according to the operating data of the device.

[0147] The optimization adjustment formula is as follows:

[0148]

[0149] in: Yes Equipment At the present moment Load (unit: Watt, W); Yes Equipment At the previous moment Load (unit: Watt, W); is the load adjustment, indicating the change from time To time The change in device load during a period (unit: watt, W).

[0150] It is calculated through real-time monitoring and feedback systems, and is usually related to factors such as the health status of the equipment, external environmental factors, and overall system performance. The load adjustment can be calculated according to the following formula:

[0151]

[0152] in: Yes Equipment At the moment The target load (unit: watt, W), that is, the load that the device should bear under ideal conditions; Yes Equipment At the moment The actual load (unit: watt, W), that is, the load actually carried by the equipment; Yes Equipment At the moment The power change rate (unit: watt / second, W / s) reflects the speed of change of the power output of the device; and is the adjustment coefficient, and different values ​​can be selected according to the device type and feedback mechanism.

[0153] Real-time feedback and optimization not only responds to the current operating status by simply adjusting the equipment load, but also achieves global optimization of the system by integrating multiple optimization goals. By introducing the objective function, we can balance the relationship between various goals, such as power consumption, equipment loss and system energy efficiency.

[0154] As an option, in addition to traditional load scheduling optimization, real-time feedback and optimization can also be combined with machine learning algorithms for adaptive optimization. By combining historical data with real-time data, machine learning models can predict future load demand and equipment status, and further optimize scheduling strategies.

[0155] For example, a regression model or neural network trained based on historical data can predict the load demand of the equipment and adjust the load in advance. This adaptive optimization method can improve the accuracy of load scheduling over a larger range and enable the hydropower station to maintain efficient operation under future operating conditions.

[0156] Specifically, the machine learning model generates a prediction model for load scheduling by analyzing historical operating data (such as equipment power consumption, load distribution, etc.). The prediction model can estimate the possible load change trend of the equipment in a certain period of time in the future, thereby helping the scheduling system to prepare load allocation in advance.

[0157] Real-time optimization and load scheduling is not a single process, but a continuous feedback loop. Each scheduling adjustment and feedback will play a role in the next adjustment, thus forming a closed-loop control system. Through continuous cycle optimization, hydropower stations can gradually improve the efficiency and stability of their systems.

[0158] Generally, the feedback loop includes data obtained from changes in equipment status, the results of load scheduling optimization, and updates on equipment health status. Each time the system is adjusted through the feedback mechanism, it can be optimized again based on the latest equipment status and external environmental conditions to ensure that the system operates in the best state.

[0159] As an option, this closed-loop feedback process is not limited to real-time load adjustment, but can also be extended to the adjustment of other control strategies, such as further improving system robustness by adjusting the parameters of the H∞ controller, or extending equipment life by adjusting the equipment operation mode.

[0160] Implementing feedback and optimization steps ensures that hydropower station equipment operates under optimal working conditions through real-time monitoring, data collection and feedback mechanisms. By dynamically adjusting load scheduling and control strategies, the system can optimize operating efficiency in real time based on equipment health status, external environment and load demand changes.

[0161] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A computer monitoring method for a hydropower station based on domestic hardware, characterized in that: The following steps are involved: Dynamic system modeling: used to establish nonlinear dynamic models of various equipment in the hydropower station, including pump and generator power models, to describe the operating status of each equipment; Multi-objective optimization scheduling: used to calculate the load scheduling of equipment based on multi-objective optimization models of power consumption, equipment loss and system energy efficiency; Fault prediction and early warning: used to predict the equipment status in real time through Kalman filtering, predict the fault mode based on historical data, and issue fault early warning in time; Robust control: used to adaptively adjust the control strategy through the H∞ controller to ensure system stability when the system faces external disturbances and equipment failures; Feedback and optimization: It is used to monitor the operating status of the hydropower station in real time, adjust the load scheduling through the feedback mechanism, and continuously optimize the equipment operation efficiency.

2. A method for computer monitoring of a hydropower station based on domestic hardware according to claim 1, characterized in that: The dynamic system modeling includes: By establishing a power output model of the water pump, taking into account the water flow rate and head height, the power of the water pump is calculated using physical formulas; By establishing a power output model of the generator, the pump power is related to the generator efficiency and the output power of the generator is calculated; Combining the water flow, equipment power output and load scheduling of the hydropower station, nonlinear differential equations are used to model the equipment operation.

3. The method for computer monitoring of a hydropower station based on domestic hardware according to claim 1, characterized in that: The multi-objective optimization scheduling includes: Construct a multi-objective optimization model based on the power consumption, system energy efficiency and equipment loss of each equipment in the hydropower station; Use the weighted sum method to combine multiple optimization objectives into one objective function for solution; Use genetic algorithm or particle swarm optimization algorithm to solve the objective function and calculate the optimal load scheduling solution; By optimizing calculations and adjusting the load of each device, we can ensure that the equipment operates in the optimal state and reduce energy efficiency loss and equipment loss.

4. A method for computer monitoring of a hydropower station based on domestic hardware according to claim 1, characterized in that: The fault prediction and early warning include: Use Kalman filtering to estimate the state of the equipment in real time and predict the future state based on current and historical data; Using the Kalman filter algorithm, the health status of the equipment is dynamically updated and real-time prediction results are generated; Based on fault history data and support vector machines, potential failure modes are predicted, and warnings are issued and measures are taken based on the prediction results.

5. The method for computer monitoring of a hydropower station based on domestic hardware according to claim 1 is characterized in that: The robust control includes: Design an H∞ controller to reduce the impact of external disturbances on the system by minimizing the maximum gain of the system transfer function; Robust control algorithms are used to enable the hydropower plant to maintain stability in the event of equipment failure or external disturbances; Adaptively adjust control strategies to ensure that equipment can still operate efficiently in the event of sudden failures or uncertainties.

6. A method for computer monitoring of a hydropower station based on domestic hardware according to claim 1, characterized in that: The implementation feedback and optimization include: Collect equipment operation data through real-time monitoring system to evaluate current equipment status and load distribution; Use feedback mechanism to transmit monitoring data to the dispatching system and adjust the load dispatching plan according to the feedback data; Based on real-time monitoring data and optimization calculation results, the equipment operation strategy is continuously adjusted to achieve system self-optimization and continuously improve equipment operation efficiency.

7. A computer monitoring method for a hydropower station based on domestic hardware according to claim 2, characterized in that: The dynamic system modeling further includes: Use physical models to establish the nonlinear relationship between the pump and the generator, and determine the relationship between power output and water flow and head height parameters; Through system modeling, a comprehensive dynamic description of the working status of each equipment in the hydropower station is made, providing a basis for subsequent load scheduling and optimization.

8. A computer monitoring method for a hydropower station based on domestic hardware according to claim 3, characterized in that: The multi-objective optimization scheduling further includes: According to the operating constraints of each device, add constraints to the optimization model to ensure that the calculated load scheduling plan meets the requirements of safe operation of the equipment; The optimization plan is updated through real-time data, and the scheduling plan is recalculated regularly to respond to changes in the system's operating status.

9. A method for computer monitoring of a hydropower station based on domestic hardware according to claim 4, characterized in that: The fault prediction and early warning further include: Monitor system sensor data in real time and identify abnormal patterns in equipment operation by comparing and analyzing historical fault data; Combine abnormal patterns with fault prediction models, use machine learning algorithms to diagnose faults, and issue alarms through monitoring systems.

10. A method for computer monitoring of a hydropower station based on domestic hardware according to claim 6, characterized in that: The implementation feedback and optimization further includes: The system automatically evaluates the operating status and dynamically adjusts the scheduling plan based on the equipment health status and external environment; When equipment fails, the feedback mechanism can automatically adjust the operating strategy, reduce system downtime, and ensure the continuous operation of the hydropower station.

Images