Method and system for optimizing operation efficiency of unattended hydroelectric generating set

Abstract

This invention provides a method and system for optimizing the operating efficiency of unmanned hydropower units, relating to the field of hydropower station operation and maintenance optimization technology. First, it extracts the time-series evolution trajectory of the unmanned hydropower unit's operating state, encompassing data on mechanical, water flow drive, and power output state evolution. Next, it extracts the environmental load prediction characteristics of the operating environment, including predicted data on water flow, meteorological, and grid load correlation within a preset future time period. Then, it establishes a bidirectional adaptive correlation between the two and mines the inherent patterns, generating a bidirectional adaptive correlation result. Based on the bidirectional adaptive correlation result, it generates prediction-driven operation control parameters. Finally, it converts the prediction-driven operation control parameters into time-series drive commands to drive the coordinated action of various execution components, completing the optimized operation efficiency control. This invention can improve the unit's operating efficiency and stability.

Description

Technical Field

[0001] This invention relates to the field of hydropower station operation and maintenance optimization technology, and more specifically, to a method and system for optimizing the operating efficiency of unattended hydropower units. Background Technology

[0002] In the field of hydropower, the application of unmanned hydropower units is becoming increasingly widespread, and their efficient and stable operation is of great significance for ensuring power supply and improving energy utilization efficiency. However, existing methods for operating and controlling unmanned hydropower units have many limitations.

[0003] On the one hand, traditional operation and control mainly rely on real-time adjustments based on the current operating status of the unit, lacking the ability to predict future changes in environmental load. For example, if the unit operation is adjusted solely based on current mechanical operating parameters, water flow drive conditions, and power output data, the unit may not be able to adapt in time when there are significant changes in water flow load, weather conditions, or grid load in the future, leading to decreased operating efficiency or even malfunctions.

[0004] On the other hand, existing methods often employ a one-way analysis approach when dealing with the relationship between operating status and environmental factors. This means that they only consider the impact of environmental factors on operating status while ignoring the adaptability of operating status to environmental changes. This one-way analysis makes it difficult to fully explore the inherent adaptation patterns between operating status and environmental load, and it cannot generate operating control parameters that can effectively cope with future environmental changes, thus limiting further improvements in the operating efficiency of unattended hydropower units. Summary of the Invention

[0005] In view of the aforementioned problems, and in conjunction with the first aspect of the present invention, embodiments of the present invention provide a method for optimizing the operating efficiency of unattended hydropower units, the method comprising:

[0006] Extract the time-series evolution trajectory of the operating status of the unattended hydropower unit. The time-series evolution trajectory of the operating status includes the mechanical operating status evolution data, water flow drive status evolution data, and power output status evolution data of the unattended hydropower unit during continuous operation.

[0007] Extract the environmental load prediction features of the operating environment of the unattended hydropower unit. The environmental load prediction features include water flow load prediction data, meteorological impact prediction data and power grid load correlation prediction data for a future preset time period.

[0008] Establish a two-way adaptive correlation between the time-series evolution trajectory of the operating state and the predicted characteristics of the environmental load. Through the two-way adaptive correlation, explore the inherent adaptation rules between the evolution of the operating state and the changes in the environmental load, and generate the two-way adaptive correlation results.

[0009] Based on the bidirectional adaptation and correlation results, predictive driving operation control parameters for unattended hydropower units are generated. These predictive driving operation control parameters can adapt to future environmental load changes and continue the evolution trend of the optimal operating state.

[0010] Predictive driving operation control parameters are converted into timing drive commands for each execution component of the unmanned hydropower unit. These timing drive commands drive the coordinated action of each execution component, thereby optimizing and controlling the operating efficiency of the unmanned hydropower unit.

[0011] Furthermore, embodiments of the present invention also provide a system for optimizing the operating efficiency of unattended hydropower units, comprising:

[0012] A processor; a machine-readable storage medium for storing machine-executable instructions of the processor; wherein the processor is configured to execute the above-described method for optimizing the operating efficiency of unattended hydropower units by executing the machine-executable instructions.

[0013] In another aspect, embodiments of the present invention also provide a computer program product, the computer program product including machine-executable instructions stored in a computer-readable storage medium, a processor for an unattended hydropower unit operation efficiency optimization system reads the machine-executable instructions from the computer-readable storage medium, the processor executes the machine-executable instructions, causing the unattended hydropower unit operation efficiency optimization system to execute the above-described unattended hydropower unit operation efficiency optimization method.

[0014] Based on the above, by extracting the time-series evolution trajectory of the unmanned hydropower unit's operating status, encompassing various aspects such as mechanical, water flow drive, and power output state evolution data during continuous operation, and extracting the environmental load prediction characteristics of the operating environment, considering factors such as water flow load, meteorological influence, and grid load correlation in the future preset time period, a two-way adaptive correlation between the operating status time-series evolution trajectory and the environmental load prediction characteristics is established, and its inherent adaptation rules are explored, which can effectively understand the complex relationship between unit operation and environmental changes. The prediction-driven operation control parameters generated based on the two-way adaptive correlation results can accurately adapt to future environmental load changes and continue the optimal operating state evolution trend, effectively avoiding the problem of unit operating efficiency decline caused by environmental changes. Converting the prediction-driven operation control parameters into time-series drive commands and driving the coordinated action of various execution components, precise and efficient optimization and control of the unmanned hydropower unit's operating efficiency is achieved, significantly improving the unit's operating efficiency and stability. Attached Figure Description

[0015] Figure 1This is a schematic diagram of the execution flow of the method for optimizing the operating efficiency of unattended hydropower units provided in an embodiment of the present invention.

[0016] Figure 2 This is a schematic diagram of exemplary hardware and software components of an unattended hydropower unit operation efficiency optimization system provided in an embodiment of the present invention. Detailed Implementation

[0017] The present invention will now be described in detail with reference to the accompanying drawings. Figure 1 This is a flowchart illustrating a method for optimizing the operating efficiency of unattended hydropower units according to an embodiment of the present invention. The following is a detailed description of this method for optimizing the operating efficiency of unattended hydropower units.

[0018] Step S110: Extract the time-series evolution trajectory of the unattended hydropower unit's operating status. The time-series evolution trajectory of the operating status includes the mechanical operating status evolution data, water flow drive status evolution data, and power output status evolution data of the unattended hydropower unit during continuous operation.

[0019] This embodiment takes a mixed-flow unmanned hydropower unit of a conventional hydropower station in a certain river basin as the application object. The unit is in continuous operation all year round. By collecting, processing and integrating various status data during its continuous operation, a complete time-series evolution trajectory of the operating status is constructed.

[0020] Step S111: Deploy the timing data acquisition component group, which includes a mechanical status acquisition component, a water flow status acquisition component, and an electrical energy status acquisition component. The mechanical status acquisition component is deployed in the key mechanical parts of the unattended hydropower unit, including the impeller assembly, guide vane assembly, main shaft assembly, and bearing assembly. The water flow status acquisition component is deployed in the water flow areas of the inlet channel, impeller chamber, and outlet channel of the unattended hydropower unit. The electrical energy status acquisition component is deployed in the stator winding, rotor winding, and electrical energy conversion and transmission parts of the electrical energy output terminal of the unattended hydropower unit.

[0021] In the mechanical condition acquisition components, multiple vibration sensors are evenly arranged circumferentially at the hub of the impeller assembly to collect vibration signals during impeller rotation. Displacement sensors are installed at each guide vane operating mechanism of the guide vane assembly to monitor changes in the guide vane opening and closing angles. Torque and speed sensors are installed at the journals at both ends of the main shaft assembly to acquire the transmission torque and rotational speed of the main shaft. Temperature and vibration sensors are installed at the thrust bearing and guide bearing of the bearing assembly to monitor the bearing temperature and vibration. Regarding the water flow condition acquisition components, flow meters and pressure sensors are installed at the inlet and converging sections of the inlet channel to measure the inlet flow rate and pressure. Multiple pressure sensors are arranged circumferentially on the inner wall of the impeller chamber to monitor the impact pressure of the water flow on the impeller. A flow meter and pressure sensor are installed at the diffuser section of the outlet channel to collect the outlet flow rate and pressure data. In the power status acquisition component, current sensors and voltage sensors are installed on the stator winding and rotor winding respectively to collect the current and voltage signals of the windings; a three-phase power parameter acquisition device is installed at the power output terminal to collect parameters such as voltage, current, and power factor of the output power. The placement of all sensors has been precisely calculated to ensure that the collected data accurately reflects the operating status of each part of the hydropower unit, while avoiding interference with the normal operation of the unit.

[0022] Step S112: Start the timing data acquisition component group, set a uniform acquisition time interval, continuously acquire the raw mechanical operation data of key mechanical parts of the unattended hydropower unit through the mechanical status acquisition component, continuously acquire the raw water flow drive data of the area through which the water flows through the unattended hydropower unit through the water flow status acquisition component, and continuously acquire the raw electrical output data of the electrical energy conversion and transmission parts of the unattended hydropower unit through the electrical energy status acquisition component.

[0023] After activating the timing data acquisition component group, a unified acquisition time interval is set. This time interval is determined based on the changing characteristics of the hydropower unit's operating status, ensuring data continuity without generating excessive redundant data due to overly frequent acquisition. The mechanical status acquisition component continuously acquires raw mechanical operation data at set intervals, including vibration signals from the runner assembly, displacement signals from the guide vane assembly, torque and speed signals from the main shaft assembly, and temperature and vibration signals from the bearing assembly. The water flow status acquisition component simultaneously acquires raw water flow drive data, including flow rate and pressure in the inlet channel, impact pressure in the runner chamber, and flow velocity and pressure in the outlet channel. The electrical energy status acquisition component acquires raw electrical output data, including current and voltage signals from the stator and rotor windings, as well as various electrical parameters from the electrical output terminal. During acquisition, each component performs preliminary analog-to-digital conversion on the raw signals, converting analog signals into digital signals and temporarily storing them locally to ensure data is not lost in the event of transmission interruption.

[0024] Step S113: Transmit the raw mechanical operation data, raw water flow drive data, and raw electrical energy output data to the time-series data processing component. The time-series data processing component performs interference removal processing on the raw mechanical operation data, retaining the valid mechanical data that can reflect changes in the mechanical operation state, performs interference removal processing on the raw water flow drive data, retaining the valid water flow data that can reflect changes in the water flow drive state, and performs interference removal processing on the raw electrical energy output data, retaining the valid electrical energy data that can reflect changes in the electrical energy output state.

[0025] The raw data of mechanical operation, water flow drive, and power output are transmitted to the time-series data processing component via a dedicated data transmission line. For the raw mechanical operation data, a wavelet transform denoising algorithm is used to process the impeller vibration signal, removing interference components caused by power grid frequency and mechanical noise. The guide vane displacement signal uses a median filtering algorithm to remove jump interference caused by transmission clearance. The main shaft torque and speed signals use an adaptive filtering algorithm to eliminate the coupling interference between power grid voltage fluctuations and mechanical vibration. The bearing temperature and vibration signals use a threshold judgment method to remove abnormal data caused by poor sensor contact, thus obtaining valid mechanical data. In the raw water flow drive data, the flow rate and pressure data of the inlet channel use a moving average filtering algorithm to remove water flow pulsation interference. The impact pressure data of the impeller chamber is decomposed into multiple intrinsic mode functions using an empirical mode decomposition method, and after removing interfering modes, valid pressure data is reconstructed. The flow velocity and pressure data of the outlet channel are processed using a wavelet transform denoising algorithm to retain valid water flow data reflecting changes in water flow state. Regarding the raw data of power output, the current and voltage signals of the stator and rotor windings are subjected to Fourier transform to remove harmonic interference and retain the fundamental signal; the power parameters at the power output end are filtered digitally and verified to remove metering errors and instantaneous interference, thus obtaining valid power data.

[0026] Step S114: After performing time-series alignment processing on the effective mechanical data, effective water flow data, and effective electrical energy data, extract the mechanical operating state features from the effective mechanical data, and generate mechanical operating state evolution data based on the time-series changes of each mechanical operating state feature. The mechanical operating state features include the rotational state features of the impeller assembly, the opening and closing state features of the guide vane assembly, the transmission state features of the main shaft assembly, and the support state features of the bearing assembly.

[0027] First, the three types of valid data undergo time-series alignment. Using the clock of the power status acquisition component as a reference, a timestamp calibration algorithm is used to correct the timestamps of the valid mechanical and water flow data, ensuring that the three types of data remain synchronized in the time dimension. Then, the mechanical operating status features are extracted from the valid mechanical data, as detailed below.

[0028] Step S1141: Classify and organize the effective mechanical data into wheel rotation data, guide vane opening and closing data, main shaft transmission data, and bearing support data. Each type of data contains characteristic values ​​corresponding to continuous time markers.

[0029] The time-aligned valid mechanical data are categorized according to their source and the mechanical parts they reflect. Runner rotation data includes characteristic values ​​of the runner vibration signal, such as the peak and effective values ​​of vibration acceleration; guide vane opening and closing data includes guide vane angle values ​​collected by guide vane displacement sensors; main shaft transmission data covers the torque and speed values ​​of the main shaft; and bearing support data includes the temperature and vibration characteristic values ​​of the bearing. Each type of data is indexed by a time stamp, forming continuous time-series data.

[0030] Step S1142: Extract the rotation state features of the rotor assembly from the rotor rotation data. The rotation state features reflect the rotation stability and rotation consistency of the rotor assembly under different time markers. By extracting the temporal change trend of the feature values ​​in the rotor rotation data, the change nodes of the rotor assembly rotation state are identified.

[0031] The rotational data of the impeller is analyzed, and the root mean square value of vibration acceleration at each time point is calculated to assess rotational smoothness. Characteristic frequency components are extracted through spectral analysis to assess rotational consistency. The temporal trends of these characteristic values ​​are tracked, and when the rate of change of the characteristic values ​​exceeds a set threshold, it is identified as a change node in the rotational state of the impeller assembly. This change node indicates that the rotational state of the impeller has changed significantly.

[0032] Step S1143: Extract the opening and closing state features of the guide vane assembly from the guide vane opening and closing data. The opening and closing state features reflect the changes in the opening and closing angles of the guide vane assembly under different time markers and the continuity of the opening and closing actions. By extracting the temporal change trend of the feature values ​​in the guide vane opening and closing data, the change nodes of the opening and closing state of the guide vane assembly are identified.

[0033] In the analysis of guide vane opening and closing data, the opening and closing angle values ​​and their rate of change are extracted as opening and closing state features. The angle value reflects the current opening degree of the guide vane, and the rate of change reflects the speed of the opening and closing action. By analyzing the temporal changes of these feature values, abrupt changes in the angle rate of change or the angle value itself are identified as nodes indicating changes in the opening and closing state of the guide vane assembly.

[0034] Step S1144: Extract the transmission state features of the spindle assembly from the spindle transmission data. The transmission state features reflect the transmission stability and transmission efficiency of the spindle assembly at different time markers. By extracting the temporal change trend of the feature values ​​in the spindle transmission data, the change nodes of the transmission state of the spindle assembly are identified.

[0035] Regarding spindle drive data, the instantaneous power is obtained by multiplying the spindle torque and speed, and the transmission efficiency is evaluated in conjunction with the spindle's rated power parameters. The standard deviation of torque and speed is calculated to assess transmission stability. When changes in these characteristic values ​​exceed set thresholds, the nodes indicating changes in the spindle assembly's transmission state are identified.

[0036] Step S1145: Extract the support state features of the bearing assembly from the bearing support data. The support state features reflect the support stability and friction-related state of the bearing assembly at different time markers. By extracting the time-series change trend of the feature values ​​in the bearing support data, the change nodes of the bearing assembly support state are identified.

[0037] In the analysis of bearing support data, the rate of change of bearing temperature and vibration amplitude are used as characteristics of the support state. The rate of temperature change reflects frictional heating, and the vibration amplitude reflects the support stability. When the temperature exceeds the set warning range or the vibration amplitude increases significantly, it is identified as a change point in the support state of the bearing assembly.

[0038] Step S1146: Associate the rotational state features of the impeller assembly, the opening and closing state features of the guide vane assembly, the transmission state features of the main shaft assembly, and the support state features of the bearing assembly under the same time mark to form mechanical state time node data.

[0039] The rotational state features of the runner assembly, the opening and closing state features of the guide vane assembly, the transmission state features of the main shaft assembly, and the support state features of the bearing assembly extracted at the same time mark are associated and combined to form a mechanical state time node data containing multi-dimensional information. This mechanical state time node data comprehensively reflects the overall operating status of the key mechanical parts of the hydropower unit at that time mark.

[0040] Step S1147: Arrange the mechanical state time node data in the order of time markers to form a mechanical state time sequence, wherein the mechanical state time sequence contains complete mechanical operating state information corresponding to consecutive time markers.

[0041] All mechanical state time point data are arranged sequentially according to the time stamps to form a mechanical state time series. This mechanical state time series is based on time, with each time point corresponding to a set of mechanical state time point data, completely recording the continuous change process of the mechanical operating state of the hydropower unit over time.

[0042] Step S1148: Analyze the differences in mechanical state time node data corresponding to adjacent time markers in the mechanical state time sequence, and extract the difference change features. The difference change features reflect the degree and direction of change of the mechanical operating state at adjacent times.

[0043] The mechanical state time series is analyzed, and the differences between the mechanical state time nodes corresponding to two adjacent time marks are calculated. For each state feature, the numerical difference at adjacent time marks is calculated. The direction of change is determined by the sign of the numerical difference, and the degree of change is determined by the magnitude of the absolute value of the numerical difference. The directions and degrees of change of all state features are integrated to extract the differential change features.

[0044] Step S1149: Divide the mechanical operation state evolution stages based on the difference change characteristics. The difference change characteristics within the same evolution stage remain stable, while the difference change characteristics of different evolution stages are significantly different.

[0045] Based on the extracted differential change characteristics, a clustering algorithm is used to segment the mechanical state time series. Continuous time nodes with similar differential change characteristics are divided into an evolution stage. The differential change characteristics within the same evolution stage remain relatively stable in terms of the degree and direction of change, while the differential change characteristics between different evolution stages are significantly different.

[0046] Step S11410: Summarize the core state characteristics of each mechanical operation state evolution stage, and record the start time marker and end time marker of each evolution stage.

[0047] For each defined mechanical operation state evolution stage, analyze the time node data of all mechanical states within that stage, and extract representative core state characteristics. For example, the core state characteristics of a certain stage might be high runner rotation stability and stable guide vane opening and closing angles. Simultaneously, record the start and end time markers for each evolution stage to clarify the time range of each stage.

[0048] Step S11411: Integrate the mechanical state time sequence, difference change characteristics and evolution stage division results to generate mechanical operation state evolution data. The mechanical operation state evolution data is used to present the evolution process of mechanical operation state from one stage to another and the core state attributes of each stage.

[0049] The mechanical state time sequence, difference change characteristics, and evolution stage division results are integrated. According to the time order, the start time mark, end time mark, core state characteristics, and difference change characteristics within each evolution stage are organized to form mechanical operation state evolution data. This mechanical operation state evolution data presents the complete evolution process of mechanical operation state from one stage to another and the core state attributes of each stage.

[0050] Step S115: Extract water flow driving state features from the effective water flow data. The water flow driving state features include water flow introduction state features of the inlet channel, water flow impact state features of the impeller chamber, and water flow discharge state features of the outlet channel. Based on the temporal changes of each water flow driving state feature, generate water flow driving state evolution data.

[0051] Water flow driving state characteristics are extracted from effective water flow data. The water flow inlet characteristics of the inlet channel include parameters such as inlet flow rate, inlet pressure, and their rate of change. The water flow impact characteristics of the impeller chamber are obtained by analyzing parameters such as impact pressure distribution and pressure pulsation frequency. The water flow discharge characteristics of the outlet channel include parameters such as outlet flow velocity, outlet pressure, and tailwater fluctuations. Based on the temporal changes of each water flow driving state characteristic, change nodes are identified, evolution stages are divided, the core state characteristics of each stage are summarized, and time stamps are recorded. These are then integrated to generate water flow driving state evolution data.

[0052] Step S116: Extract the power output state features from the effective power data. The power output state features include the power generation state features of the stator winding, the electromagnetic induction state features of the rotor winding, and the power transmission state features of the power output terminal. Power output state evolution data is generated based on the time-series changes of each power output state feature.

[0053] In the extraction of power output state characteristics, the power generation state characteristics of the stator winding are obtained by analyzing parameters such as current, voltage, and power of the winding and their changing trends; the electromagnetic induction state characteristics of the rotor winding are extracted based on the current, voltage, and excitation parameters of the rotor winding; and the power transmission state characteristics at the power output end include parameters such as output voltage, current, power factor, and power quality. Based on the temporal changes of each power output state characteristic, change nodes are identified, evolution stages are divided, core state characteristics are summarized and time stamps are recorded, and integrated to generate power output state evolution data.

[0054] Step S117: Construct a time-series evolution trajectory framework. The time-series evolution trajectory framework uses time markers as the horizontal axis and operating state characteristics as the vertical axis. The mechanical operating state evolution data, water flow drive state evolution data, and power output state evolution data are sequentially filled into the time-series evolution trajectory framework according to the time markers.

[0055] A time-series evolution trajectory framework is constructed, with the horizontal axis representing time markers and the vertical axis representing operational state characteristics, covering specific parameters in three categories of state characteristics: mechanical, water flow, and electrical energy. Mechanical operational state evolution data, water flow-driven state evolution data, and electrical energy output state evolution data are filled into the corresponding positions in the framework according to the time marker order, forming multi-dimensional operational state data points within the framework.

[0056] Step S118: Associate the mechanical operation status evolution data, water flow drive status evolution data, and power output status evolution data under the same time mark to form a time node associated data group. The time node associated data group reflects the collaborative relationship of different operation states at the same time. Connect adjacent time node associated data groups to form a continuous operation status time sequence evolution trajectory. The operation status time sequence evolution trajectory is used to present the change process and collaborative evolution characteristics of each operation state of the unattended hydropower unit during continuous operation.

[0057] The evolution data of three types of operating states—mechanical, water flow, and electrical energy—at the same time point are correlated to form a time-node correlated data group. This time-node correlated data group reflects the collaborative relationship between different operating states at the same moment. Connecting adjacent time-node correlated data groups forms a continuous time-series evolution trajectory of operating states. This trajectory presents the change process and collaborative evolution characteristics of each operating state of the unmanned hydropower unit during continuous operation.

[0058] Step S120: Extract the environmental load prediction features of the operating environment of the unattended hydropower unit. The environmental load prediction features include water flow load prediction data, meteorological impact prediction data and power grid load correlation prediction data within a preset future time period.

[0059] To optimize the operation efficiency of hydropower units, it is necessary to extract the environmental load prediction characteristics of their operating environment. These environmental load prediction characteristics include water flow load prediction data, meteorological impact prediction data, and power grid load correlation prediction data for a future preset time period.

[0060] Step S121: Collect historical environmental load data of the operating environment of the unattended hydropower unit. The historical environmental load data includes historical water flow load data, historical meteorological impact data, and historical power grid load correlation data. The historical water flow load data records the changes in water flow rate, water flow velocity, and water flow pressure in different historical periods. The historical meteorological impact data records the changes in precipitation, wind force, and temperature in different historical periods. The historical power grid load correlation data records the changes in power grid load demand and power transmission efficiency in different historical periods.

[0061] Historical environmental load data were collected. Historical water flow load data was obtained from hydrological stations in the river basins where the hydropower units are located, recording changes in water flow, velocity, and pressure over different historical periods. Historical meteorological impact data was obtained from local meteorological departments, including data on precipitation, wind speed, and temperature changes over different historical periods. Historical power grid load correlation data was provided by the power grid dispatching department, recording changes in power grid load demand and power transmission efficiency over different historical periods. The collected data were cleaned and formatted uniformly, removing outliers and missing values, and converted to a standardized format.

[0062] Step S122: Collect hydrological characteristic data of the watershed where the unmanned hydropower unit is located. The hydrological characteristic data includes the topographic features, river system distribution features, and water supply features of the watershed. The topographic features reflect the slope and elevation changes of the watershed. The river system distribution features reflect the distribution and confluence patterns of tributaries within the watershed. The water supply features reflect the proportion of precipitation and groundwater supply in the watershed. Collect meteorological forecast data of the area where the unmanned hydropower unit is located. The meteorological forecast data includes precipitation forecasts, wind forecasts, and temperature forecasts for a preset future period. Collect future load demand data for the unmanned hydropower unit's grid connection. The future load demand data includes the peak load period, valley load period, and stable load period of the grid within a preset future period.

[0063] Hydrological characteristic data of the watershed were collected, and digital elevation model data of the watershed was obtained through a geographic information system to extract topographic features, including slope distribution and elevation changes. River system distribution characteristics, including tributary distribution and confluence patterns, were obtained by analyzing remote sensing imagery and hydrological maps. Water supply characteristics were obtained by reviewing watershed hydrological research reports to clarify the proportions of precipitation and groundwater recharge. Meteorological forecast data was obtained from professional meteorological forecasting agencies and included precipitation, wind, and temperature forecasts for the preset future time period. Future load demand data was provided by the power grid dispatching department and included information on peak, valley, and stable load periods for the preset future time period.

[0064] Step S123: Divide the historical environmental load data into time series. Divide the historical environmental load data into multiple historical load time series units according to a fixed time period. Each historical load time series unit contains historical water flow load data, historical meteorological impact data and historical power grid load correlation data for the corresponding time period.

[0065] Historical environmental load data is divided into time series, with a fixed time period length. The historical data is divided into multiple historical load time series units according to the time period length. Each unit contains historical water flow load data, historical meteorological impact data, and historical power grid load correlation data for the corresponding time period, which facilitates subsequent feature extraction and correlation analysis.

[0066] Step S124: Extract the environmental load characteristics of each historical load time series unit and establish the correlation between the historical environmental load characteristics and the corresponding hydrological characteristics, meteorological characteristics and power grid load characteristics.

[0067] Environmental load characteristics for each historical load time series unit are extracted, including statistical characteristics of water flow, meteorological, and power grid load data, such as mean, variance, maximum, and minimum values. Simultaneously, hydrological, meteorological, and power grid load characteristics for the corresponding time period are extracted. Correlation analysis and other methods are used to establish the relationship between historical environmental load characteristics and these characteristics, clarifying the degree of influence of each characteristic on the environmental load.

[0068] Step S125: Based on meteorological forecast data, analyze the meteorological change trend within the future preset time period, combine historical meteorological impact data and the correlation between meteorological characteristics, predict the impact of meteorological changes on the operating environment load within the future preset time period, and generate meteorological impact prediction data.

[0069] Based on meteorological forecast data, we analyze the meteorological trends within a predetermined time period, such as the increase or decrease in precipitation, the change in wind force, and the rise or fall in temperature. By combining historical meteorological impact data with the correlation between meteorological characteristics, we predict the impact of these meteorological changes on the operational environment load, generating meteorological impact prediction data that includes the direction and extent of the impact of meteorological factors on the environmental load at different time markers.

[0070] Step S126: Based on hydrological characteristic data and meteorological impact prediction data, analyze the changes in water supply and confluence in the basin within the preset time period in the future. Combine the correlation between historical water load data and hydrological characteristics to predict the changes in water flow rate, water flow velocity and water flow pressure within the preset time period in the future, and generate water load prediction data.

[0071] Step S1261: Analyze the hydrological characteristic data and extract the topographic slope characteristics, water system confluence path characteristics, and water source replenishment ratio characteristics of the watershed. The topographic slope characteristics affect the change of water flow velocity, the water system confluence path characteristics affect the water flow confluence velocity and confluence volume, and the water source replenishment ratio characteristics affect the change of total water flow.

[0072] The hydrological characteristic data were analyzed, and the topographic slope features were extracted from the digital elevation model data to calculate the slope values ​​and distribution of different areas within the watershed. The river network was analyzed to extract the characteristics of the river system confluence path, including river length, direction, and confluence node location. The water source replenishment ratio characteristics were determined based on the water source replenishment characteristic data to clarify the proportion of each replenishment source.

[0073] Step S1262: Analyze meteorological impact prediction data and extract the precipitation period distribution, precipitation intensity change and temperature change trend within the future preset period. The precipitation period distribution and precipitation intensity change directly affect the water flow replenishment, and the temperature change trend affects the snowmelt water replenishment in the basin.

[0074] Analyze meteorological impact forecast data to extract the distribution of precipitation periods within the future preset time period, i.e., the specific time intervals in which precipitation occurs; precipitation intensity changes, reflecting the changes in the amount of precipitation per unit time; and temperature change trends, including the overall trend of temperature rise and fall and the distribution of high and low temperature periods. For watersheds with snow and ice cover, temperature changes affect the amount of snow and ice meltwater replenishment.

[0075] Step S1263: Correlate topographic slope characteristics with precipitation intensity changes, analyze the flow velocity changes of water under different precipitation intensities under the influence of topographic slope, and determine the comprehensive influence relationship between topographic slope and precipitation intensity on water flow velocity; correlate the characteristics of the river system confluence path with precipitation time distribution, analyze the confluence process of water along the confluence path under different precipitation time periods, and determine the comprehensive influence relationship between confluence path length, number of confluence nodes, and precipitation time distribution on the confluence volume; correlate the characteristics of water source replenishment ratio with temperature change trends, analyze the impact of temperature changes on snowmelt replenishment, and combine with precipitation replenishment to determine the change in the total water flow replenishment of the basin within the future preset time period.

[0076] By linking topographic slope characteristics with precipitation intensity variations, this study analyzes the changes in water flow velocity across different topographic slope regions under varying precipitation intensities, determining the comprehensive influence of both factors on water flow velocity. Furthermore, by linking river system confluence path characteristics with precipitation time distribution, this study analyzes the confluence process along the confluence path during different precipitation time periods, determining the comprehensive influence of confluence path length, number of nodes, and precipitation time distribution on the confluence volume. Finally, by linking water source replenishment ratio characteristics with temperature change trends, this study analyzes the impact of temperature changes on snowmelt replenishment, and, combined with precipitation replenishment, determines the changes in the total water flow replenishment of the basin within a predetermined time period.

[0077] Step S1264: Extract historical data segments from historical water load data that are similar to current hydrological characteristics and meteorological forecast characteristics. The similarity is reflected in the degree of matching of topographic slope, confluence path, water supply ratio and precipitation characteristics.

[0078] Historical data segments similar to current hydrological and meteorological forecast characteristics are extracted from historical water load data. By calculating the similarity between the topographic slope, confluence path, water supply ratio, and precipitation characteristics of each segment in the historical data and the current parameters, historical data segments with high similarity are extracted as references.

[0079] Step S1265: Analyze the changes in water flow rate, water flow velocity, and water flow pressure in similar historical data segments, and extract the core influencing factors and their weights in the historical changes.

[0080] Analyze the changes in water flow, velocity, and pressure in similar historical data segments, compare the relationship between these changes and the corresponding hydrological and meteorological characteristics, extract core influencing factors such as precipitation intensity and topographic slope, and determine the influence weight of each factor, that is, the magnitude of the role of each factor in the process of change.

[0081] Step S1266: Based on the comprehensive influence relationship, changes in total water supply and historical changes, establish a water flow load prediction model. The water flow load prediction model can integrate the influence of hydrological characteristics, meteorological prediction characteristics and historical changes on water flow load.

[0082] Based on the comprehensive influence relationships, changes in total water supply, and the core influencing factors and their weights in historical variations, a water load prediction model is established. This model is constructed using methods such as multiple regression analysis, taking hydrological characteristic parameters, meteorological forecast parameters, and changes in total water supply as inputs, and water flow rate, velocity, and pressure as outputs. The model is trained using historical data to accurately integrate the influence of various factors on water load.

[0083] Step S1267: Input the hydrological characteristic parameters and meteorological forecast parameters for the future preset time period into the water flow load prediction model, and output the predicted values ​​of water flow rate, water flow velocity and water flow pressure corresponding to different time marks in the future preset time period.

[0084] The hydrological characteristic parameters and meteorological forecast parameters for the future preset time period are input into the water flow load prediction model. Based on the input parameters and internal algorithms, the model outputs the predicted values ​​of water flow rate, velocity and pressure corresponding to different time markers within the future preset time period.

[0085] Step S1268: Arrange the predicted values ​​of water flow rate, water flow velocity, and water pressure in the order of time markers to form the predicted sequence of water flow rate, water flow velocity, and water pressure.

[0086] The predicted values ​​of water flow rate, velocity, and pressure output by the model are arranged in time sequence to form their respective prediction sequences, reflecting the continuous change trend of each water flow parameter over time.

[0087] Step S1269: Associate the predicted values ​​of water flow rate, water flow velocity, and water flow pressure under the same time marker to form water flow load prediction node data.

[0088] By associating and combining the predicted values ​​of water flow rate, flow velocity, and pressure at the same time mark, a water flow load prediction node data is formed, which comprehensively reflects the overall state of water flow load at that time mark.

[0089] Step S12610: Integrate all water flow load prediction node data and corresponding prediction sequences to generate water flow load prediction data. The water flow load prediction data is used to present the changing trends and synergistic relationships of various parameters of water flow load within a future preset time period.

[0090] By integrating all water flow load prediction node data and prediction sequences, water flow load prediction data is generated. This water flow load prediction data presents the changing trends of water flow rate, velocity, and pressure within a preset time period and the synergistic relationship between them.

[0091] Step S127: Based on the analysis of future load demand data, analyze the load change trend of the power grid within a preset time period, combine the correlation between historical power grid load correlation data and power grid load characteristics, predict the correlation impact of power grid load changes on the power output of unattended hydropower units within a preset time period, and generate power grid load correlation prediction data.

[0092] Analyze future load demand data to determine the load change trend of the power grid within a preset time period, such as the increase or decrease trend of load and the changes in peak and valley loads. Combine historical power grid load correlation data with the correlation between power grid load characteristics to predict the correlation impact of power grid load changes on the power output of hydropower units, and generate power grid load correlation prediction data, including information such as the power grid's requirements for unit power output and the impact of transmission efficiency at different time markers.

[0093] Step S128: Construct an environmental load prediction feature framework, wherein the environmental load prediction feature framework uses the time marker of a future preset period as the horizontal axis and the environmental load type as the vertical axis.

[0094] An environmental load prediction feature framework is constructed, with the horizontal axis representing the time marker of a future preset period and the vertical axis representing the environmental load type, including types such as water flow load, meteorological impact load, and power grid load correlation. The frame cells correspond to a specific combination of time marker and environmental load type.

[0095] Step S129: Fill the water flow load prediction data, meteorological impact prediction data, and power grid load correlation prediction data into the environmental load prediction feature framework in sequence according to the time marker of the future preset time period, and associate all prediction data under the same future time marker to form a future environmental load correlation data group.

[0096] The predicted data on water flow load, meteorological impact, and power grid load are entered into the corresponding positions in the framework according to the time markers. All predicted data under the same time marker are linked to form a future environmental load correlation data group, which reflects the comprehensive situation of various environmental loads under that time marker.

[0097] Step S1210: Integrate all future environmental load related data groups to generate environmental load prediction features. The environmental load prediction features are used to present the changing trend of the operating environmental load and the correlation between various types of loads within a future preset time period.

[0098] By integrating all future environmental load related data sets, an environmental load prediction feature is generated. This environmental load prediction feature uses time as a clue to present the overall trend of changes in the operating environmental load and the correlation between various types of loads within a future preset period.

[0099] Step S130: Establish a two-way adaptive correlation between the time-series evolution trajectory of the operating state and the predicted characteristics of the environmental load. Through the two-way adaptive correlation, explore the inherent adaptation law between the evolution of the operating state and the change of the environmental load, and generate the two-way adaptive correlation results.

[0100] Establish a two-way adaptive correlation between the time-series evolution trajectory of the operating state and the predicted characteristics of the environmental load, and explore the inherent adaptation law between the two. This correlation takes into account the adaptation of the operating state to the environmental load and the requirements of the environmental load on the operating state.

[0101] Step S131: Analyze the time-series evolution trajectory of the operating state, extract the key nodes of the operating state in the trajectory and the combination of operating state parameters corresponding to each key node. The key nodes of the operating state are the time nodes when the change of the operating state is greater than the set change threshold. The combination of operating state parameters includes the mechanical operating state parameters, water flow drive state parameters and electrical energy output state parameters of the time node.

[0102] The system analyzes the time-series evolution trajectory of the operating state, sets a threshold for changes in the operating state, traverses the trajectory and compares the combinations of operating state parameters at adjacent time nodes. Time nodes with differences greater than the threshold are identified as key nodes in the operating state, and the mechanical, water flow, and electrical energy state parameter combinations of these nodes are extracted.

[0103] Step S132: Analyze the environmental load prediction features, extract the key environmental load nodes and the environmental load parameter combinations corresponding to each key node from the environmental load prediction features. The key environmental load nodes are future time nodes where the environmental load changes significantly. The environmental load parameter combinations include the water flow load parameters, meteorological influence parameters and power grid load correlation parameters of the key environmental load nodes.

[0104] The environmental load prediction characteristics are analyzed, an environmental load change threshold is set, and the prediction characteristics are traversed to compare the environmental load parameter combinations of adjacent time nodes. Future time nodes with differences greater than the threshold are identified as key environmental load nodes, and the associated parameter combinations of water flow load, meteorological influence, and power grid load at these nodes are extracted.

[0105] Step S133: Connect the time axis of the operational state time-series evolution trajectory with the time axis of the environmental load prediction characteristics, so that the end time node of the operational state time-series evolution trajectory and the start time node of the environmental load prediction characteristics remain continuous, forming a complete time series.

[0106] By connecting the timeline of the operational status evolution trajectory with the timeline of the environmental load prediction characteristics, the end time node of the trajectory is continuous with the start time node of the prediction characteristics, forming a complete time series from the past to the future.

[0107] Step S134: Construct a bidirectional adaptation and association framework, which includes an operating status input terminal, an environmental load input terminal, an association analysis unit, and a result output terminal. The operating status input terminal is connected to the operating status time-series evolution trajectory data, and the environmental load input terminal is connected to the environmental load prediction feature data.

[0108] A bidirectional adaptive correlation framework is constructed, which includes an input end for operating status and environmental load, a correlation analysis unit, and a result output end. The input end is respectively connected to the time-series evolution trajectory of operating status and the predictive feature data of environmental load. The correlation analysis unit processes the data, and the output end outputs the correlation results.

[0109] Step S135: Extract the adaptive environmental load requirements of each key node in the time-series evolution trajectory of the operating state through the correlation analysis unit. The adaptive environmental load requirements are the environmental load conditions required to keep the key node of the operating state stable. Extract the adaptive operating state requirements of each key node in the environmental load prediction features through the correlation analysis unit. The adaptive operating state requirements are the operating state conditions required to enable the unattended hydropower unit to adapt to the key node of the environmental load.

[0110] The correlation analysis unit extracts the adaptive environmental load requirements of key nodes in the operating status, analyzes the combination of node operating status parameters, and determines the environmental load conditions required to maintain stable operation; at the same time, it extracts the adaptive operating status requirements of key environmental load nodes, analyzes the combination of node environmental load parameters, and determines the operating status conditions required for the unit to adapt to the load.

[0111] Step S136: Identify key nodes of future environmental load that meet the requirements of adapting to environmental load from the combination of environmental load parameters in the environmental load prediction characteristics, and establish a positive adaptation association between key nodes of the operating status and key nodes of future environmental load.

[0112] Identify future key nodes of environmental load that meet the requirements of adapting to environmental load from the characteristics of environmental load prediction, establish a positive adaptation correlation between the two, and indicate that the current operating state can adapt to specific future environmental loads.

[0113] Step S137: Identify key nodes of historical operating states that meet the requirements of adapting to the operating state from the combination of operating state parameters in the operating state time-series evolution trajectory, and establish a reverse adaptation association between key nodes of environmental load and key nodes of historical operating states.

[0114] Identify key nodes of historical operating states from the time-series evolution trajectory of operating states that meet the requirements of adapting key nodes of environmental load to operating states, establish a reverse adaptation relationship between the two, and indicate that future environmental loads can be adapted by specific historical operating states.

[0115] Step S138: Integrate the forward adaptation association and the reverse adaptation association to form a bidirectional adaptation association network. Each node in the bidirectional adaptation association network is associated with both the historical operating status and the future environmental load.

[0116] By integrating forward and reverse adaptation associations, a bidirectional adaptation association network is formed. Each node in the network is simultaneously associated with its historical operating status and future environmental load, achieving bidirectional association between the two.

[0117] Step S139: Analyze the parameter correspondence of each associated node in the bidirectional adaptation association network, and explore the inherent adaptation law between the operating state parameters and the environmental load parameters. The inherent adaptation law is reflected in the optimal value range of the environmental load parameters under different operating states and the optimal value range of the operating state parameters under different environmental loads.

[0118] For example, step S1391: Extract parameter data of all associated nodes in the bidirectional adaptation association network to form an association parameter dataset, wherein the association parameter dataset includes the combination of operating status parameters and the combination of environmental load parameters corresponding to each associated node.

[0119] Extract parameter data from all associated nodes in the bidirectional adaptive association network, including combinations of operating status parameters and environmental load parameters, to form an association parameter dataset.

[0120] Step S1392: Classify and organize the associated parameter dataset, divide the operating state parameter combinations according to the operating state type, and form a subset of environmental load parameter combinations corresponding to different operating state types.

[0121] The associated parameter datasets are categorized and organized, and the operating state parameter combinations are divided according to the operating state type to form a subset of environmental load parameter combinations corresponding to different operating state types, which facilitates the analysis of environmental load parameters for different operating states.

[0122] Step S1393: For each subset of environmental load parameters corresponding to each operating state type, analyze the value distribution of each environmental load parameter in the subset of environmental load parameter combinations, and extract the concentrated area in the value distribution. The concentrated area is the common value range of the environmental load parameters under this operating state type.

[0123] Analyze the subset of environmental load parameter combinations corresponding to each operating state type, statistically analyze the value distribution of each environmental load parameter, and extract the region in the value set. This region represents the common value range of the environmental load parameters under this operating state type.

[0124] Step S1394: Associate common value ranges with the stable runtime of the operating state type, filter out the common value ranges that make the operating state type maintain the longest stable runtime, and determine the value range as the optimal value range of the environmental load parameter under the operating state type.

[0125] By associating common value ranges with the stable runtime of different operating states, comparing the stable runtime of different operating states within different common value ranges, and selecting the common value range corresponding to the longest stable runtime, we can determine the optimal value range for the environmental load parameter under that operating state type.

[0126] Step S1395: Divide the environmental load parameter combinations in the associated parameter dataset according to the environmental load type to form a subset of operating status parameter combinations corresponding to different environmental load types.

[0127] The environmental load parameter combinations in the associated parameter dataset are divided according to the environmental load type, forming a subset of operating status parameter combinations corresponding to different environmental load types, which facilitates the analysis of operating status parameters for different environmental loads.

[0128] Step S1396: For each environmental load type, analyze the value distribution of each operating state parameter in the operating state parameter combination subset, and extract the concentrated area in the value distribution. The concentrated area is the common value range of the operating state parameter under the environmental load type.

[0129] Analyze the subset of operating status parameter combinations corresponding to each environmental load type, statistically analyze the value distribution of each operating status parameter, and extract the region in the value set as the common value range of the operating status parameter under that environmental load type.

[0130] Step S1397: Associate common value ranges with the power output efficiency related states, filter out the common value ranges that keep the power output efficiency related states optimal, and determine the value range as the optimal value range of the operating state parameters under this environmental load type.

[0131] By associating common value ranges with power output efficiency-related states, comparing power output efficiency-related states within different common value ranges, and selecting the common value range corresponding to the optimal power output efficiency-related state as the optimal value range for the operating state parameters under this environmental load type.

[0132] Step S1398: Analyze the overlapping and difference regions of the optimal value range of environmental load parameters under different operating state types, and summarize the characteristics of the change of the optimal value range of environmental load parameters with operating state type; analyze the overlapping and difference regions of the optimal value range of operating state parameters under different environmental load types, and summarize the characteristics of the change of the optimal value range of operating state parameters with environmental load type.

[0133] This study analyzes the overlapping and difference regions of the optimal value range of environmental load parameters under different operating state types, and summarizes their characteristics of changing with the operating state type. At the same time, it analyzes the overlapping and difference regions of the optimal value range of operating state parameters under different environmental load types, summarizes their characteristics of changing with the environmental load type, and deepens the understanding of the adaptation relationship between the two.

[0134] Step S1399: Associate the optimal value range of the operating status parameter with the optimal value range of the environmental load parameter to form a one-to-one matching parameter pair. The matching parameter pair can reflect the optimal matching relationship between the operating status and the environmental load.

[0135] The optimal range of operating status parameters is associated with the optimal range of environmental load parameters to form a one-to-one matching parameter pair. Each matching parameter pair reflects an optimal matching relationship between an operating status and an environmental load.

[0136] Step S13910: Based on the characteristics of the variation of the adaptation parameter pairs and their value ranges, construct an intrinsic adaptation law model. The intrinsic adaptation law model is used to present the adaptation relationship and variation trend between different operating states and environmental loads.

[0137] Based on the characteristics of the adaptation parameter pairs and their value ranges, an intrinsic adaptation law model is constructed. This intrinsic adaptation law model can intuitively present the adaptation relationship between different operating states and environmental loads, as well as the trend of changes with type.

[0138] Step S13911: Verify the degree of matching between the optimal value range output by the intrinsic adaptation law model and the actual running data by using the non-modeling data in the associated parameter dataset, and adjust the parameter weights in the intrinsic adaptation law model according to the degree of matching, and output the adjusted intrinsic adaptation law.

[0139] The model's inherent adaptation rules are validated using data from the associated parameter dataset that were not involved in modeling. The optimal range of values ​​output by the model is compared with the degree of matching between the model and the actual running data. The model parameter weights are adjusted according to the degree of matching to optimize the model and output the adjusted inherent adaptation rules.

[0140] Step S1310: Divide the adaptation association level based on the inherent adaptation rules. Different adaptation association levels correspond to different degrees of matching between the operating state and the environmental load. Extract the operating state parameter range and environmental load parameter range corresponding to each adaptation association level to form the adaptation association rules.

[0141] Based on inherent adaptation rules, adaptation association levels are divided, with different levels corresponding to varying degrees of matching between operating states and environmental loads, such as high, medium, and low levels. The operating state parameter ranges and environmental load parameter ranges corresponding to each level are extracted to form adaptation association rules, clarifying the parameter range requirements under different matching degrees.

[0142] Step S1311: Integrate the bidirectional adaptation association network, the inherent adaptation rules and the adaptation association rules to generate bidirectional adaptation association results. The bidirectional adaptation association results include the adaptation relationship and adaptation requirements between the temporal evolution of the operating state and the changes in the environmental load.

[0143] Step S140: Generate predictive drive-type operation control parameters for unattended hydropower units based on the bidirectional adaptation association results. The predictive drive-type operation control parameters can adapt to future environmental load changes and continue the evolution trend of the optimal operating state.

[0144] Based on the bidirectional adaptation correlation results, predictive driving operation control parameters are generated. These predictive driving operation control parameters enable hydropower units to adapt to future environmental load changes and continue the evolution trend of optimal operating state, thereby optimizing operating efficiency.

[0145] Step S141: Analyze the bidirectional adaptation association results and extract the inherent adaptation patterns, adaptation association rules, and bidirectional adaptation association network data.

[0146] The bidirectional adaptation association results are analyzed to extract the inherent adaptation rules, including the optimal value range and variation characteristics of different operating states and environmental loads; adaptation association rules are extracted to clarify the parameter range of different adaptation association levels; and bidirectional adaptation association network data is extracted, including the parameter correspondence of each association node.

[0147] Step S142: Determine the optimal operating state parameter range and time series evolution trend of the unattended hydropower unit based on the inherent adaptation law. The optimal operating state parameter range is the range of operating state parameters that can adapt to future changes in environmental load, and the optimal operating state time series evolution trend is the operating state change trend that can maintain the optimal power output efficiency.

[0148] Based on the inherent adaptation law, the optimal operating state parameter range of the hydropower unit is determined. This optimal operating state parameter range is a parameter interval that can adapt to future changes in environmental load. At the same time, the time evolution trend of the optimal operating state is determined, so that the power output efficiency maintains the optimal operating state change trend.

[0149] Step S143: Extract the current running state parameters from the running state time-series evolution trajectory, compare the current running state parameters with the optimal running state parameter range, and determine the parameter differences between the current running state and the optimal running state.

[0150] Extract the current operating state parameters from the time-series evolution trajectory of the operating state, compare them with the optimal operating state parameter range, calculate the difference between the two, and clarify the direction and degree of adjustment that the current operating state needs to be made.

[0151] Step S144: Based on the adaptation association rules and bidirectional adaptation association network data, predict the direction and degree of impact of future environmental load changes on operating status parameters.

[0152] By combining adaptation association rules and bidirectional adaptation association network data, we can analyze the impact of future environmental load changes on operating status parameters and predict the direction of the impact (such as parameter increase or decrease) and the degree of impact (such as the size and range of the impact).

[0153] Step S145: Based on the parameter differences and the direction and degree of influence of future environmental load, determine the adjustment direction of the operating status parameters. The adjustment direction can bring the current operating status parameters closer to the optimal operating status parameter range and adapt to future environmental load changes.

[0154] Taking into account the parameter differences between the current operating state and the optimal state, as well as the direction and extent of the impact of future environmental load on the operating state parameters, the adjustment direction of the operating state parameters is determined so that the adjusted parameters can both approach the optimal range and adapt to future changes in environmental load.

[0155] Step S146: Divide the operating state control dimensions, which include mechanical operation control dimension, water flow drive control dimension and power output control dimension, and each control dimension corresponds to a different type of operating state parameter.

[0156] The operation status control dimensions are divided into mechanical operation, water flow drive, and power output control dimensions. The mechanical operation control dimension corresponds to the mechanical operation status parameters, the water flow drive control dimension corresponds to the water flow drive status parameters, and the power output control dimension corresponds to the power output status parameters, which facilitates the determination of control parameters by dimension.

[0157] Step S147: For the mechanical operation control dimension, based on the adaptation relationship between the mechanical operation state and the environmental load in the inherent adaptation law, and combined with the future environmental load prediction data, determine the control parameter types and preliminary control amplitudes of the impeller assembly, guide vane assembly, main shaft assembly, and bearing assembly; For the water flow drive control dimension, based on the adaptation relationship between the water flow drive state and the environmental load in the inherent adaptation law, and combined with the future water flow load prediction data, determine the control parameter types and preliminary control amplitudes of water inlet regulation, impeller impact adaptation, and water outlet guidance; For the power output control dimension, based on the adaptation relationship between the power output state and the environmental load in the inherent adaptation law, and combined with the future power grid load correlation prediction data, determine the control parameter types and preliminary control amplitudes of the stator winding, rotor winding, and power output terminal.

[0158] For the mechanical operation control dimension, based on the inherent adaptation law of the mechanical operating state and the environmental load, and combined with future environmental load prediction data, the types of control parameters and preliminary control amplitudes are determined for vibration control of the impeller assembly, angle adjustment of the guide vane assembly, torque and speed control of the main shaft assembly, and temperature and vibration control of the bearing assembly. For the water flow drive control dimension, based on the inherent adaptation law of the water flow drive state and the environmental load, and combined with future water flow load prediction data, the types of control parameters and preliminary control amplitudes are determined for flow and pressure control of inlet water regulation, impact pressure regulation of impeller impact adaptation, and flow velocity and pressure control of outlet water guidance. For the power output control dimension, based on the inherent adaptation law of the power output state and the environmental load, and combined with future grid load correlation prediction data, the types of control parameters and preliminary control amplitudes are determined for current and voltage regulation of the stator and rotor windings, and power and power quality control at the power output terminal.

[0159] Step S148: Construct a coordinated model of control parameters, which can coordinate control parameters of different control dimensions.

[0160] A collaborative model for control parameters is constructed. This model can analyze the mutual influence between control parameters of different control dimensions, coordinate the parameters, avoid conflicts between parameters, and achieve synergistic optimization of control effects.

[0161] Step S149: Normalize the initial control amplitudes of each control dimension, converting them into dimensionless relative amplitudes; input the normalized relative amplitudes and control parameter types into the control parameter coordination model; based on the adaptation association rules and bidirectional adaptation association network data, analyze the coordination relationship and conflict risk between different control parameters, and adjust the relative amplitudes of conflicting control parameters according to the analysis results; denormalize the adjusted relative amplitudes to obtain the optimized control amplitudes, optimize the coordination effect between control parameters, and enable the control parameters of each control dimension to work together to achieve the optimal operating state time-series evolution trend.

[0162] The initial control amplitudes for each control dimension are normalized and converted into dimensionless relative amplitudes to facilitate comparison and coordination of parameters across different dimensions. The normalized relative amplitudes and control parameter types are then input into a control parameter coordination model. Based on adaptive association rules and bidirectional adaptive association network data, the model analyzes the coordination relationships and conflict risks among parameters and adjusts the relative amplitudes of conflicting parameters. The adjusted relative amplitudes are then denormalized to obtain optimized control amplitudes, ensuring the coordinated action of all control parameters and guiding the operational state towards the optimal time-series evolution trend.

[0163] Step S1410: Based on the optimal operating state time-series evolution trend, plan the timing adjustment rhythm of each control parameter, and determine the adjustment start time, adjustment duration and adjustment interval of each control parameter.

[0164] For example, step S14101: Analyze the optimal operating state time sequence evolution trend, extract the evolution goals and stage transition time nodes of each stage in the optimal operating state time sequence evolution trend. Each stage evolution goal corresponds to a specific combination of operating state parameters, and the stage transition time node is the time point when one evolution stage transitions to another.

[0165] Analyze the evolution trend of the optimal operating state, extract the evolution goals of each stage, and each goal corresponds to a specific combination of operating state parameters; extract the stage transition time nodes, that is, the time points from one stage to another, and clarify the time range of each stage.

[0166] Step S14102: Associate each control parameter with the stage evolution target, and determine the core control parameter corresponding to each stage evolution target. The core control parameter is the control parameter that can directly affect the achievement of the stage evolution target.

[0167] By associating each control parameter with the stage evolution target, analyzing which control parameters have a direct impact on the achievement of the stage evolution target, and identifying the above parameters as core control parameters.

[0168] Step S14103: Based on the stage transition time node, determine the adjustment start time of each core control parameter. The adjustment start time of the core control parameter is earlier than the corresponding stage transition time node, so that the core control parameter can complete the adjustment and reach the target operating state parameter before the stage transition node.

[0169] Based on the phase transition time node, determine the start time for adjusting the core control parameters. This adjustment start time is earlier than the phase transition time node to ensure that the core control parameters are adjusted before the phase transition, so that the operating status parameters reach the values ​​required by the phase evolution target.

[0170] Step S14104: Analyze the adjustment process required for the core control parameters to be adjusted from the current value to the target value. Combine the response speed of the operating state to determine the adjustment duration of each core control parameter. The adjustment duration matches the smooth transition requirements of the operating state to avoid sudden changes in the operating state.

[0171] Analyze the adjustment process of the core control parameters from their current values ​​to the target values, considering the response speed of the operating state, and determine the duration of the adjustment. The duration should ensure a smooth transition of the operating state and avoid sudden changes in the operating state due to excessively rapid adjustments.

[0172] Step S14105: For multiple core control parameters within the same evolution stage, determine the adjustment interval for each parameter based on their synergistic relationship. The adjustment interval should ensure that the adjustment actions of each parameter are coordinated to form a synergistic control effect.

[0173] For multiple core control parameters within the same evolution stage, the adjustment interval of each parameter is determined based on their synergistic relationship, so that the adjustment actions of each parameter cooperate with each other to form a synergistic control effect and improve the overall control effect.

[0174] Step S14106: Identify non-core control parameters. Non-core control parameters are control parameters that assist core control parameters in achieving the stage evolution goals.

[0175] Identify non-core control parameters. These parameters do not directly affect the achievement of the stage evolution goals, but can help the core control parameters achieve their goals better, such as some auxiliary control parameters.

[0176] Step S14107: Associate non-core control parameters with core control parameters, determine the adjustment start time of non-core control parameters, and ensure that the adjustment start time of non-core control parameters is coordinated with the adjustment start time of the corresponding core control parameters so that the auxiliary role of non-core control parameters can be played synchronously.

[0177] By linking non-core control parameters with core control parameters, and determining the adjustment start time of non-core control parameters based on the adjustment start time of core control parameters, the adjustment start time of non-core control parameters is coordinated with that of core control parameters, ensuring that the auxiliary effects are exerted simultaneously.

[0178] Step S14108: Based on the adjustment duration of the core control parameters and the auxiliary role requirements of the non-core control parameters, determine the adjustment duration of the non-core control parameters. The adjustment duration of the non-core control parameters covers the adjustment process of the core control parameters and the subsequent stabilization phase.

[0179] Based on the duration of adjustment of the core control parameters and the auxiliary role requirements of the non-core control parameters, the duration of adjustment of the non-core control parameters is determined so that it covers the adjustment process and subsequent stabilization phase of the core control parameters, and continues to play an auxiliary role.

[0180] Step S14109: Plan the adjustment interval of non-core control parameters so that the adjustment action of non-core control parameters matches the adjustment rhythm of core control parameters.

[0181] Plan the adjustment intervals for non-core control parameters so that their adjustment actions match the adjustment rhythm of core control parameters, thereby avoiding interference with the adjustment effect of core control parameters.

[0182] Step S141010: Construct a timing adjustment rhythm framework. The timing adjustment rhythm framework uses time as the horizontal axis and the type of control parameter as the vertical axis, and fills in the adjustment start time, adjustment duration and adjustment interval of each control parameter into the framework.

[0183] Construct a time-series adjustment rhythm framework, with time on the horizontal axis and the type of control parameter on the vertical axis. Fill in the start time, duration, and interval of each control parameter adjustment into the framework to intuitively present the time-series adjustment plan for each parameter.

[0184] Step S141011: Check whether there are conflicts in the adjustment time of each control parameter, whether the adjustment rhythm matches the evolution trend of the optimal operating state time sequence, and adjust the conflicting adjustment time and the adjustment rhythm that does not conform to the evolution trend. Output the time sequence adjustment rhythm of each control parameter to determine the adjustment start time, adjustment duration and adjustment interval of each control parameter and output them.

[0185] Check whether the adjustment times of each control parameter in the framework conflict, and whether the adjustment rhythm matches the evolution trend of the optimal operating state. Adjust the conflicting times and rhythms that do not conform to the trend, and finally output the timing adjustment rhythm of each control parameter, specifying the adjustment start time, duration and interval.

[0186] Step S1411: Correlate the timing adjustment rhythm of each control parameter with the key nodes of future environmental load, so that the adjustment action of the control parameter keeps synchronized with the nodes of environmental load change.

[0187] By linking the timing of adjustments to various control parameters with key future environmental load nodes, the adjustment actions of control parameters are synchronized with the environmental load change nodes in time, so that the unit can adjust to the appropriate state in a timely manner when the environmental load changes.

[0188] Step S1412: Integrate the control parameter types, optimized control amplitudes, and timing adjustment rhythms of each control dimension to form a set of predictive-driven operation control parameters.

[0189] By integrating the control parameter types, optimized control amplitudes, and timing adjustment rhythms of various control dimensions such as machinery, water flow, and electricity, a set of predictive-driven operation control parameters is formed, which includes all parameters that need to be adjusted and their adjustment requirements.

[0190] Step S1413: By simulating future environmental load changes and the execution process of control parameters, verify whether the control parameters can keep the unattended hydropower unit in the optimal operating state, correct the control parameters in the predictive drive-type operation control parameter set that do not match the requirements of the simulated operating state, and output the final predictive drive-type operation control parameters.

[0191] By simulating future environmental load changes and the execution process of control parameters, the system examines whether the control parameters can maintain the unit in its optimal operating state. Control parameters found in the simulation to be mismatched with the operating requirements are corrected, the parameter set is optimized, and the final predictive-driven operating control parameters are output.

[0192] Step S150: Convert the predicted driving operation control parameters into timing drive commands for each execution component of the unattended hydropower unit. Drive each execution component to work together through timing drive commands to optimize and control the operating efficiency of the unattended hydropower unit.

[0193] Predictive driving operation control parameters are converted into timing driving commands for each execution component, driving the components to work together and achieving optimized control of the hydropower unit's operating efficiency.

[0194] Step S151: Analyze the predictive driving operation control parameters, extract the control parameter type, control amplitude, and timing adjustment rhythm of each control dimension. The control parameter type corresponds to different execution components of the unattended hydropower unit, the control amplitude corresponds to the action range of the execution component, and the timing adjustment rhythm corresponds to the action time requirement of the execution component.

[0195] Analyze the predictive driving operation control parameters, extract the control parameter types of each control dimension, and identify the corresponding execution components; extract the control amplitude to determine the action range of the execution components; extract the timing adjustment rhythm to clarify the time requirements of the action, such as start time, duration, and interval.

[0196] Step S152: Establish the mapping relationship between control parameters and execution components, and determine the specific execution component corresponding to each control parameter type. The control parameters of the mechanical operation control dimension correspond to the impeller drive component, guide vane adjustment component, main shaft transmission component and bearing lubrication component. The control parameters of the water flow drive control dimension correspond to the inlet valve component, impeller chamber guide component and outlet valve component. The control parameters of the power output control dimension correspond to the excitation adjustment component, stator winding control component and power output adjustment component.

[0197] Establish a mapping relationship between control parameters and execution components. Mechanical operation control parameters correspond to the impeller drive component, guide vane adjustment component, main shaft transmission component, bearing lubrication component, etc.; water flow drive control parameters correspond to the inlet valve component, impeller chamber guide component, outlet valve component, etc.; electrical energy output control parameters correspond to the excitation adjustment component, stator winding control component, electrical energy output adjustment component, etc., and clarify which execution component executes each control parameter.

[0198] Step S153: Obtain motion characteristic data of each execution component. The motion characteristic data includes the motion response speed, motion accuracy requirements and maximum motion amplitude limit of the execution component. The motion characteristic data is used to determine the conversion rules of the control parameters into drive signals.

[0199] Acquire motion characteristic data for each execution component, including motion response speed, i.e., the time from receiving the command to starting the action; motion accuracy requirements, i.e., the allowable error range of the motion amplitude; and maximum motion amplitude limit, i.e., the maximum motion range that the component can achieve. The above data is used to determine the conversion rules of the control parameters into drive signals.

[0200] Step S154: Based on the motion characteristic data and the control amplitude, construct the conversion rules of the control parameters into the drive signal. The conversion rules of different execution components are determined according to their motion characteristics. The converted drive signal accurately reflects the control amplitude requirements.

[0201] Based on the motion characteristic data and control amplitude of the actuator, conversion rules are constructed. For example, for displacement-type actuators, the correspondence between the voltage or current of the drive signal and the displacement is determined according to the motion accuracy requirements and control amplitude; for velocity-type actuators, the correspondence between the drive signal and the velocity is determined to ensure that the converted drive signal accurately reflects the control amplitude requirements.

[0202] Step S155: According to the conversion rules, convert the control amplitude of each control parameter into the corresponding drive signal parameter. The drive signal parameter includes voltage parameter, current parameter or mechanical displacement parameter. The specific parameter type is determined according to the drive method of the execution component.

[0203] According to the established conversion rules, the control amplitude of each control parameter is converted into drive signal parameters, such as voltage, current or mechanical displacement parameters. The parameter type is determined according to the drive method of the actuator (such as electric, hydraulic or pneumatic).

[0204] Step S156: Based on the timing adjustment rhythm, determine the output start time, output duration and output interval of the drive signal corresponding to each execution component, so that the output rhythm of the drive signal is consistent with the timing adjustment rhythm of the control parameters.

[0205] Based on the timing adjustment rhythm, determine the start time, duration, and interval of the output of the drive signal for each execution component, ensuring that the output rhythm of the drive signal is consistent with the timing adjustment rhythm of the control parameters, and achieving planned adjustment.

[0206] Step S157: Construct a timing-driven instruction framework, which includes an execution component identifier, drive signal parameters, output start time, output duration, and output interval.

[0207] Construct a timing-driven instruction framework, including execution component identifiers to identify the components corresponding to the instructions; drive signal parameters to clarify the specific content of the drive signals; and output start time, duration, and interval to clarify the execution time requirements of the instructions.

[0208] Step S158: Fill the relevant information corresponding to each execution component into the timing drive instruction framework to generate the initial timing drive instructions for each execution component.

[0209] The initial timing drive instructions for each component are generated by filling the identification, drive signal parameters, output start time, duration, and interval of each execution component into the timing drive instruction framework.

[0210] Step S159: Associate the initial timing drive instructions of different execution components, and based on the coordination relationship in the predictive drive-type operation control parameters, verify the coordination of the timing drive instructions of each execution component, and identify timing drive instructions with action conflicts.

[0211] Associate the initial timing drive instructions of different execution components, verify the coordination of instructions based on the coordination relationship in the predicted drive-type operation control parameters, and check for action conflicts, such as the actions of two components overlapping in time and interfering with each other.

[0212] Step S1510: Adjust the output start time or output duration of timing-driven instructions with conflicting actions to eliminate the conflict and make the actions of each execution component work together.

[0213] Adjust the timing-driven instructions that have conflicting actions by modifying the output start time or duration to eliminate the conflict and ensure that the actions of each execution component can work together to achieve the overall control goal.

[0214] Step S1511: Perform signal integrity processing on the adjusted timing drive instructions, supplement auxiliary parameters of the drive signals, so that the timing drive instructions can be accurately identified and responded to by the execution components. Then, classify the processed timing drive instructions according to the execution components to form a set of exclusive timing drive instructions for each execution component.

[0215] The adjusted timing-driven instructions undergo signal integrity processing, supplementing auxiliary parameters of the drive signals, such as the rise and fall times, to ensure that the instructions can be accurately recognized and responded to by the execution components. The processed instructions, categorized by execution component, form a dedicated timing-driven instruction set for each component.

[0216] Step S1512: Send the dedicated timing drive instruction set of each execution component to the corresponding execution component through the signal transmission component.

[0217] A reliable signal transmission component is used to send the dedicated timing-driven instruction set of each execution component to the corresponding execution component, ensuring that the instructions are transmitted accurately.

[0218] Step S1513: Start the instruction execution module of the execution component. Each execution component executes actions sequentially according to its exclusive timing-driven instruction set to achieve timing adjustment of the running parameters.

[0219] The instruction execution module of the start-up execution component is activated, and each component executes actions sequentially according to the requirements of its dedicated timing-driven instruction set, adjusting operating parameters to ensure that the unit's operating status evolves as expected.

[0220] Step S1514: Collect operational feedback data during the operation of each execution component. The operational feedback data includes the actual action amplitude, action time, and corresponding changes in operational status parameters of the execution component.

[0221] During the execution of component actions, operational feedback data is collected through sensors, including the actual amplitude and duration of the component actions, as well as the changes in operational status parameters caused by these actions, in order to evaluate the effectiveness of instruction execution.

[0222] Step S1515: Based on the operation feedback data, confirm the compatibility between the actions of the execution components and the timing-driven instructions, so that the operation status parameters evolve according to the requirements of the prediction-driven operation control parameters, so as to complete the timing action execution of all execution components.

[0223] Based on operational feedback data, the alignment between the actions of the execution components and the timing-driven commands is analyzed, and it is checked whether the operating status parameters evolve according to the requirements of the predicted driving-type operation control parameters. If deviations are found, adjustments are made in a timely manner to ensure that the timing actions of all execution components are executed accurately, ultimately achieving optimized control of the operating efficiency of the unmanned hydropower unit.

[0224] In one exemplary embodiment, a system for optimizing the operating efficiency of unattended hydropower units is provided. This system can be a terminal, server, etc., and its internal structure diagram can be as follows: Figure 2 As shown, the system for optimizing the operating efficiency of unattended hydropower units includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, near-field communication, or other technologies. When the computer program is executed by the processor, it implements a method for optimizing the operating efficiency of unattended hydropower units. The display unit is used to generate a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device can be a touch layer covering the display screen, or a button, trackball, or touchpad set on the casing of the unattended hydropower unit operation efficiency optimization system, or an external keyboard, touchpad, or mouse, etc.

[0225] It should be noted that, in order to simplify the description of the present invention and thus help to understand one or more embodiments of the invention, multiple features may sometimes be grouped into one embodiment, drawing or description thereof in the foregoing description of the embodiments of the present invention.

Claims

1. A method for optimizing the operating efficiency of unattended hydropower units, characterized in that, The method includes: Extract the time-series evolution trajectory of the operating status of the unattended hydropower unit. The time-series evolution trajectory of the operating status includes the mechanical operating status evolution data, water flow drive status evolution data, and power output status evolution data of the unattended hydropower unit during continuous operation. Extract the environmental load prediction features of the operating environment of the unattended hydropower unit. The environmental load prediction features include water flow load prediction data, meteorological impact prediction data and power grid load correlation prediction data for a future preset time period. Establish a two-way adaptive correlation between the time-series evolution trajectory of the operating state and the predicted characteristics of the environmental load. Through the two-way adaptive correlation, explore the inherent adaptation rules between the evolution of the operating state and the changes in the environmental load, and generate the two-way adaptive correlation results. Based on the bidirectional adaptation and correlation results, predictive driving operation control parameters for unattended hydropower units are generated. These predictive driving operation control parameters can adapt to future environmental load changes and continue the evolution trend of the optimal operating state. The predicted driving operation control parameters are converted into timing drive commands for each execution component of the unattended hydropower unit. The timing drive commands drive the execution components to work together, thereby optimizing and controlling the operating efficiency of the unattended hydropower unit. The establishment of a two-way adaptive correlation between the time-series evolution trajectory of the operational state and the predicted characteristics of the environmental load, and the mining of the inherent adaptation rules between the operational state evolution and environmental load changes through the two-way adaptive correlation, generates two-way adaptive correlation results, including: The time-series evolution trajectory of the operating state is analyzed, and the key nodes of the operating state and the combination of operating state parameters corresponding to each key node are extracted from the trajectory. The key nodes of the operating state are the time nodes when the change of the operating state is greater than a set change threshold. The combination of operating state parameters includes the mechanical operating state parameters, water flow drive state parameters and electrical energy output state parameters of the time node. The environmental load prediction features are analyzed, and the key nodes of environmental load and the combination of environmental load parameters corresponding to each key node are extracted from the environmental load prediction features. The key nodes of environmental load are future time nodes in which the environmental load changes significantly. The combination of environmental load parameters includes the water flow load parameters, meteorological influence parameters and power grid load correlation parameters of the key nodes of environmental load. Connect the time axis of the operational status time-series evolution trajectory with the time axis of the environmental load prediction characteristics to ensure that the end time node of the operational status time-series evolution trajectory is continuous with the start time node of the environmental load prediction characteristics, thus forming a complete time series. A bidirectional adaptive association framework is constructed, which includes an operation status input terminal, an environmental load input terminal, an association analysis unit, and a result output terminal. The operation status input terminal is connected to the operation status time-series evolution trajectory data, and the environmental load input terminal is connected to the environmental load prediction feature data. The adaptive environmental load requirements of each key node in the time-series evolution trajectory of the operating state are extracted by the correlation analysis unit. The adaptive environmental load requirements are the environmental load conditions required to keep the key node in the operating state stable. The adaptive operating state requirements of each key node in the environmental load prediction features are extracted by the correlation analysis unit. The adaptive operating state requirements are the operating state conditions required to enable the unattended hydropower unit to adapt to the key node in the environmental load. Identify key nodes of future environmental load that meet the requirements of adapting to environmental load from the combination of environmental load parameters in the characteristics of environmental load prediction, and establish a positive adaptation correlation between key nodes of the operating status and key nodes of future environmental load. Identify key historical operating state nodes that meet the requirements for adapting to the operating state from the combination of operating state parameters in the operating state time-series evolution trajectory, and establish a reverse adaptation association between key environmental load nodes and key historical operating state nodes. Integrating forward and reverse adaptation associations to form a bidirectional adaptation association network, in which each node is associated with both historical operating status and future environmental load; The parameter correspondence of each associated node in the bidirectional adaptive association network is analyzed to explore the inherent adaptation attributes between the operating status parameters and the environmental load parameters. The inherent adaptation attributes are reflected in the optimal value range of the environmental load parameters under different operating states and the optimal value range of the operating status parameters under different environmental loads. The adaptation association levels are divided based on the inherent adaptation rules. Different adaptation association levels correspond to different degrees of matching between the operating state and the environmental load. The range of operating state parameters and the range of environmental load parameters corresponding to each adaptation association level are extracted to form adaptation association rules. Integrate the bidirectional adaptation association network, intrinsic adaptation attributes, and adaptation association rules to generate bidirectional adaptation association results. The bidirectional adaptation association results include the adaptation relationship and adaptation requirements between the temporal evolution of the operating state and changes in environmental load. The generation of predictive drive-type operation and control parameters for unattended hydropower units based on bidirectional adaptation and correlation results includes: Analyze the bidirectional adaptation association results and extract the inherent adaptation attributes, adaptation association rules, and bidirectional adaptation association network data. The optimal operating state parameter range and time-series evolution trend of unmanned hydropower units are determined based on their inherent adaptability attributes. The optimal operating state parameter range is the range of operating state parameters that can adapt to future changes in environmental load, and the optimal operating state time-series evolution trend is the operating state change trend that can maintain the optimal power output efficiency. Extract the current running state parameters from the time-series evolution trajectory of the running state, compare the current running state parameters with the range of optimal running state parameters, and determine the parameter differences between the current running state and the optimal running state. Based on the adaptation association rules and bidirectional adaptation association network data, the direction and degree of impact of future environmental load changes on operating status parameters are predicted. By combining the parameter differences and the direction and degree of influence of future environmental load, the adjustment direction of the operating status parameters is determined. The adjustment direction can bring the current operating status parameters closer to the optimal operating status parameter range and adapt to future environmental load changes. The operation status control dimensions are divided into mechanical operation control dimensions, water flow drive control dimensions, and electrical energy output control dimensions, each of which corresponds to different types of operation status parameters. For the mechanical operation control dimension, based on the adaptation relationship between mechanical operating state and environmental load in the inherent adaptation law, and combined with future environmental load prediction data, the control parameter types and preliminary control amplitudes of the impeller assembly, guide vane assembly, main shaft assembly, and bearing assembly are determined. For the water flow drive control dimension, based on the adaptation relationship between water flow drive state and environmental load in the inherent adaptation law, and combined with future water flow load prediction data, the control parameter types and preliminary control amplitudes of inlet water regulation, impeller impact adaptation, and outlet water guidance are determined. For the power output control dimension, based on the adaptation relationship between power output state and environmental load in the inherent adaptation law, and combined with future grid load correlation prediction data, the control parameter types and preliminary control amplitudes of the stator winding, rotor winding, and power output terminal are determined. A control parameter coordination model is constructed, which can coordinate control parameters of different control dimensions. The initial control amplitudes of each control dimension are normalized and converted into dimensionless relative amplitudes. The normalized relative amplitudes and control parameter types are input into the control parameter coordination model. Based on the adaptation association rules and bidirectional adaptation association network data, the coordination relationship and conflict risk between different control parameters are analyzed, and the relative amplitudes of conflicting control parameters are adjusted according to the analysis results. The adjusted relative amplitudes are then denormalized to obtain the optimized control amplitudes, thereby optimizing the coordination effect between control parameters and enabling the control parameters of each control dimension to work together to achieve the optimal operating state time-series evolution trend. Based on the optimal operating state time-series evolution trend, the timing adjustment rhythm of each control parameter is planned, and the adjustment start time, adjustment duration and adjustment interval of each control parameter are determined. The timing of adjustments to various control parameters is correlated with key future environmental load milestones, ensuring that adjustments to control parameters are synchronized with changes in environmental load. By integrating the types of control parameters from various control dimensions, the optimized control amplitude, and the timing adjustment rhythm, a set of predictive-driven operation control parameters is formed. By simulating future environmental load changes and the execution process of control parameters, the study verifies whether the control parameters can keep the unattended hydropower unit in the optimal operating state, corrects the control parameters in the predictive-driven operation control parameter set that do not match the requirements of the simulated operating state, and outputs the final predictive-driven operation control parameters.

2. The method for optimizing the operating efficiency of unattended hydropower units according to claim 1, characterized in that, The extraction of the time-series evolution trajectory of the operating status of unattended hydropower units includes: A time-series data acquisition component group is deployed, which includes a mechanical status acquisition component, a water flow status acquisition component, and an electrical energy status acquisition component. The mechanical status acquisition component is deployed in key mechanical parts of the unattended hydropower unit, such as the impeller assembly, guide vane assembly, main shaft assembly, and bearing assembly. The water flow status acquisition component is deployed in the water flow areas of the inlet channel, impeller chamber, and outlet channel of the unattended hydropower unit. The electrical energy status acquisition component is deployed in the stator winding, rotor winding, and electrical energy conversion and transmission parts at the electrical energy output end of the unattended hydropower unit. Start the timing data acquisition component group, set a uniform acquisition time interval, continuously acquire the raw mechanical operation data of key mechanical parts of the unattended hydropower unit through the mechanical status acquisition component, continuously acquire the raw water flow drive data of the area through which the water flows through the unattended hydropower unit through the water flow status acquisition component, and continuously acquire the raw electrical output data of the electrical energy conversion and transmission parts of the unattended hydropower unit through the electrical energy status acquisition component. The system transmits raw mechanical operation data, raw water flow drive data, and raw electrical energy output data to the time-series data processing component. The time-series data processing component performs interference removal processing on the raw mechanical operation data, retaining the valid mechanical data that can reflect changes in the mechanical operation state; it also performs interference removal processing on the raw water flow drive data, retaining the valid water flow data that can reflect changes in the water flow drive state; and it performs interference removal processing on the raw electrical energy output data, retaining the valid electrical energy data that can reflect changes in the electrical energy output state. After performing time-series alignment processing on the effective mechanical data, effective water flow data, and effective electrical energy data, the mechanical operating state features in the effective mechanical data are extracted. Based on the time-series changes of each mechanical operating state feature, mechanical operating state evolution data is generated. The mechanical operating state features include the rotational state features of the impeller assembly, the opening and closing state features of the guide vane assembly, the transmission state features of the main shaft assembly, and the support state features of the bearing assembly. Extract water flow driving state features from effective water flow data. These features include water flow introduction state features in the inlet channel, water flow impact state features in the impeller chamber, and water flow discharge state features in the outlet channel. Based on the temporal changes of each water flow driving state feature, generate water flow driving state evolution data. Extract the power output state features from the effective power data. The power output state features include the power generation state features of the stator winding, the electromagnetic induction state features of the rotor winding, and the power transmission state features of the power output terminal. Power output state evolution data is generated based on the time-series changes of each power output state feature. A time-series evolution trajectory framework is constructed, with time markers as the horizontal axis and operating state characteristics as the vertical axis. Mechanical operating state evolution data, water flow drive state evolution data, and power output state evolution data are sequentially filled into the time-series evolution trajectory framework according to time markers. By associating mechanical operation status evolution data, water flow drive status evolution data, and power output status evolution data under the same time marker, a time node associated data group is formed. The time node associated data group reflects the collaborative relationship of different operation states at the same moment. Connecting adjacent time node associated data groups forms a continuous operation state time sequence evolution trajectory. The operation state time sequence evolution trajectory is used to present the change process and collaborative evolution characteristics of each operation state of the unattended hydropower unit during continuous operation.

3. The method for optimizing the operating efficiency of unattended hydropower units according to claim 2, characterized in that, The extraction of mechanical operating state features from valid mechanical data, and the generation of mechanical operating state evolution data based on the temporal changes of each mechanical operating state feature, includes: The effective mechanical data is categorized and organized into wheel rotation data, guide vane opening and closing data, main shaft transmission data, and bearing support data. Each type of data contains characteristic values ​​corresponding to continuous time markers. The rotational state features of the rotor assembly are extracted from the rotor rotation data. These rotational state features reflect the rotational stability and consistency of the rotor assembly at different time markers. By extracting the temporal variation trend of the feature values ​​in the rotor rotation data, the change nodes of the rotor assembly's rotational state are identified. The opening and closing state features of the guide vane assembly are extracted from the guide vane opening and closing data. These features reflect the changes in the opening and closing angles of the guide vane assembly under different time markers and the continuity of the opening and closing actions. By extracting the temporal variation trend of the feature values ​​in the guide vane opening and closing data, the change nodes of the guide vane assembly's opening and closing state are identified. The transmission state characteristics of the spindle assembly are extracted from the spindle transmission data. These characteristics reflect the transmission stability and transmission efficiency of the spindle assembly at different time markers. By extracting the temporal variation trend of the characteristic values ​​in the spindle transmission data, the change nodes of the spindle assembly's transmission state are identified. The support state features of the bearing assembly are extracted from the bearing support data. These support state features reflect the support stability and friction-related state of the bearing assembly at different time markers. By extracting the time-series variation trend of the feature values ​​in the bearing support data, the change nodes of the bearing assembly support state are identified. By associating the rotational state characteristics of the impeller assembly, the opening and closing state characteristics of the guide vane assembly, the transmission state characteristics of the main shaft assembly, and the support state characteristics of the bearing assembly under the same time mark, mechanical state time node data is formed. The mechanical state time node data are arranged in the order of time markers to form a mechanical state time sequence, which contains complete mechanical operating state information corresponding to consecutive time markers. The differences in mechanical state time node data corresponding to adjacent time markers in the mechanical state time sequence are analyzed, and the difference change features are extracted. The difference change features reflect the degree and direction of change of the mechanical operating state at adjacent time points. The mechanical operating state evolution stages are divided based on the characteristics of difference changes. The characteristics of difference changes within the same evolution stage remain stable, while the characteristics of difference changes in different evolution stages are significantly different. Summarize the core state characteristics of each mechanical operation state evolution stage, and record the start and end time markers of each evolution stage; By integrating the time sequence of mechanical states, the characteristics of differences and changes, and the results of the division of evolution stages, mechanical operating state evolution data is generated. The mechanical operating state evolution data is used to present the evolution process of mechanical operating states from one stage to another and the core state attributes of each stage.

4. The method for optimizing the operating efficiency of unattended hydropower units according to claim 1, characterized in that, The extraction of environmental load prediction characteristics of the operating environment of unattended hydropower units includes: Historical environmental load data of the operating environment of unattended hydropower units is collected. The historical environmental load data includes historical water flow load data, historical meteorological impact data, and historical power grid load correlation data. The historical water flow load data records the changes in water flow rate, water flow velocity, and water flow pressure in different historical periods. The historical meteorological impact data records the changes in precipitation, wind force, and temperature in different historical periods. The historical power grid load correlation data records the changes in power grid load demand and power transmission efficiency in different historical periods. Hydrological characteristic data of the watershed where the unmanned hydropower unit is located are collected. The hydrological characteristic data includes the topographic features, river system distribution features and water source recharge features of the watershed. The topographic features reflect the slope and elevation changes of the watershed. The river system distribution features reflect the distribution and confluence patterns of tributaries in the watershed. The water source recharge features reflect the proportion of precipitation recharge and groundwater recharge in the watershed. Collect meteorological forecast data for the area where the unmanned hydropower unit is located. The meteorological forecast data includes precipitation forecast, wind forecast and temperature forecast for a preset period in the future. Collect future load demand data for unattended hydropower units connected to the power grid. The future load demand data includes the peak load period, the valley load period, and the stable load period of the power grid within a preset future time period. Historical environmental load data is divided into time series, and the historical environmental load data is divided into multiple historical load time series units according to a fixed time period. Each historical load time series unit contains historical water flow load data, historical meteorological impact data and historical power grid load correlation data for the corresponding time period. Extract the environmental load characteristics of each historical load time series unit, and establish the correlation between the historical environmental load characteristics and the corresponding hydrological, meteorological and power grid load characteristics; Based on the analysis of meteorological forecast data, the trend of meteorological changes in the future within a preset period is analyzed. Combined with the correlation between historical meteorological impact data and meteorological characteristics, the impact of meteorological changes on the operating environment load in the future preset period is predicted, and meteorological impact prediction data is generated. Based on hydrological characteristic data and meteorological impact prediction data, we analyze the changes in water supply and confluence in the basin within a preset time period. Combining the correlation between historical water load data and hydrological characteristics, we predict the changes in water flow rate, water flow velocity, and water flow pressure within a preset time period, and generate water load prediction data. Based on the analysis of future load demand data, the load change trend of the power grid within a preset period is analyzed. Combined with the correlation between historical power grid load correlation data and power grid load characteristics, the correlation impact of power grid load changes on the power output of unattended hydropower units within a preset period is predicted, and power grid load correlation prediction data is generated. An environmental load prediction feature framework is constructed, wherein the environmental load prediction feature framework uses the time marker of a future preset period as the horizontal axis and the environmental load type as the vertical axis; Water flow load prediction data, meteorological impact prediction data and power grid load correlation prediction data are sequentially filled into the environmental load prediction feature framework according to the time marker of the future preset time period, and all prediction data under the same future time marker are associated to form a future environmental load correlation data group. All future environmental load related data groups are integrated to generate environmental load prediction features. These features are used to present the changing trend of the operating environmental load and the correlation between various types of loads within a preset future time period.

5. The method for optimizing the operating efficiency of unattended hydropower units according to claim 4, characterized in that, Based on hydrological characteristic data and meteorological impact prediction data, the system analyzes changes in water supply and confluence within a predetermined time period. Combining historical water load data with hydrological characteristics, it predicts changes in water flow rate, velocity, and pressure within the predetermined time period, generating water load prediction data, including: Analyze hydrological characteristic data to extract the topographic slope characteristics, river system confluence path characteristics, and water source replenishment ratio characteristics of the watershed. The topographic slope characteristics affect the change of water flow velocity, the river system confluence path characteristics affect the water flow confluence velocity and confluence volume, and the water source replenishment ratio characteristics affect the change of total water flow. Analyze meteorological impact prediction data to extract the precipitation period distribution, precipitation intensity changes, and temperature change trends within a future preset time period. The precipitation period distribution and precipitation intensity changes directly affect the water flow replenishment, and the temperature change trends affect the snowmelt replenishment within the watershed. By linking topographic slope characteristics with precipitation intensity variations, this study analyzes the changes in water flow velocity under different precipitation intensities under the influence of topographic slope, determining the comprehensive influence of topographic slope and precipitation intensity on water flow velocity. Furthermore, by linking river system confluence path characteristics with precipitation time distribution, this study analyzes the confluence process of water flow along the confluence path during different precipitation time periods, determining the comprehensive influence of confluence path length, number of confluence nodes, and precipitation time distribution on the confluence volume. Finally, by linking water source replenishment ratio characteristics with temperature change trends, this study analyzes the impact of temperature changes on snowmelt replenishment, and, combined with precipitation replenishment, determines the changes in the total water flow replenishment of the basin within a predetermined time period. Historical data segments similar to current hydrological and meteorological forecast characteristics are extracted from historical water load data. The similarity is reflected in the degree of matching of topographic slope, confluence path, water supply ratio and precipitation characteristics. Analyze the changes in water flow rate, water flow velocity, and water flow pressure in similar historical data segments, and extract the core influencing factors and their weights in the historical changes. Based on comprehensive influence relationships, changes in total water supply and historical changes, a water flow load prediction model is established. The water flow load prediction model can integrate the influence of hydrological characteristics, meteorological prediction characteristics and historical changes on water flow load. Input the hydrological characteristic parameters and meteorological forecast parameters for a future preset period into the water flow load prediction model, and output the predicted values ​​of water flow rate, water flow velocity and water flow pressure corresponding to different time markers in the future preset period. The predicted values ​​of water flow rate, water flow velocity, and water pressure are arranged in chronological order to form the predicted sequences of water flow rate, water flow velocity, and water pressure. By associating the predicted values ​​of water flow rate, water flow velocity, and water flow pressure under the same time marker, water flow load prediction node data is formed. By integrating all water flow load prediction node data and corresponding prediction sequences, water flow load prediction data is generated. This water flow load prediction data is used to present the changing trends and synergistic relationships of various parameters of water flow load within a preset future time period.

6. The method for optimizing the operating efficiency of unattended hydropower units according to claim 1, characterized in that, The process of converting predicted drive-type operation control parameters into timing drive commands for each execution component of the unmanned hydropower unit, and driving the coordinated action of each execution component through timing drive commands to achieve optimized control of the operating efficiency of the unmanned hydropower unit, includes: The predictive driving operation control parameters are analyzed, and the control parameter types, control amplitudes, and timing adjustment rhythms of each control dimension are extracted. The control parameter types correspond to different execution components of the unattended hydropower unit, the control amplitudes correspond to the action range of the execution components, and the timing adjustment rhythms correspond to the action time requirements of the execution components. Establish a mapping relationship between control parameters and execution components, and determine the specific execution components corresponding to each control parameter type. Control parameters in the mechanical operation control dimension correspond to the impeller drive component, guide vane adjustment component, main shaft transmission component, and bearing lubrication component. Control parameters in the water flow drive control dimension correspond to the inlet valve component, impeller chamber guide component, and outlet valve component. Control parameters in the power output control dimension correspond to the excitation adjustment component, stator winding control component, and power output adjustment component. Acquire motion characteristic data of each execution component. The motion characteristic data includes the motion response speed, motion accuracy requirements and maximum motion amplitude limit of the execution component. The motion characteristic data is used to determine the conversion rules of the control parameters into drive signals. Based on motion characteristic data and control amplitude, a conversion rule for control parameters to drive signals is constructed. The conversion rule for different execution components is determined according to their motion characteristics. The converted drive signals accurately reflect the control amplitude requirements. According to the conversion rules, the control amplitude of each control parameter is converted into the corresponding drive signal parameter. The drive signal parameter includes voltage parameter, current parameter or mechanical displacement parameter. The specific parameter type is determined according to the drive method of the execution component. Based on the timing adjustment rhythm, the output start time, output duration and output interval of the drive signal corresponding to each execution component are determined so that the output rhythm of the drive signal is consistent with the timing adjustment rhythm of the control parameter. Construct a timing-driven instruction framework, which includes an execution component identifier, drive signal parameters, output start time, output duration, and output interval; Fill the relevant information corresponding to each execution component into the timing-driven instruction framework to generate the initial timing-driven instructions for each execution component; Associate the initial timing drive instructions of different execution components, and based on the coordination relationship in the predictive drive-type operation control parameters, verify the coordination of the timing drive instructions of each execution component and identify timing drive instructions with action conflicts. Adjust the start time or duration of output for timing-driven instructions that have conflicting actions to eliminate the conflict and make the actions of each execution component work together. The adjusted timing drive instructions are processed for signal integrity, and auxiliary parameters of the drive signals are added to ensure that the timing drive instructions can be accurately identified and responded to by the execution components. The processed timing drive instructions are then classified according to the execution components to form a set of dedicated timing drive instructions for each execution component. The dedicated timing drive instruction set of each execution component is sent to the corresponding execution component through the signal transmission component; The instruction execution module of the startup execution component is activated, and each execution component executes actions sequentially according to its dedicated timing-driven instruction set to achieve timing adjustment of running parameters; Collect operational feedback data during the operation of each execution component. The operational feedback data includes the actual action amplitude, action time, and corresponding changes in operational status parameters of the execution component. Based on the operational feedback data, the degree of fit between the actions of the execution components and the timing-driven instructions is confirmed, so that the operational status parameters evolve according to the requirements of the predictive-driven operational control parameters, in order to complete the timing actions of all execution components.

7. A system for optimizing the operating efficiency of unattended hydropower units, characterized in that, include: processor; A machine-readable storage medium for storing machine-executable instructions of the processor; The processor is configured to execute the method for optimizing the operating efficiency of unattended hydropower units according to any one of claims 1 to 6 by executing the machine-executable instructions.

8. A computer program product, characterized in that, The computer program product includes machine-executable instructions stored in a computer-readable storage medium. The processor of the unattended hydropower unit operation efficiency optimization system reads the machine-executable instructions from the computer-readable storage medium and executes the machine-executable instructions, causing the unattended hydropower unit operation efficiency optimization system to perform the operation efficiency optimization method for unattended hydropower units as described in any one of claims 1 to 6.

Images