Automatic operation control method for low-dam hydropower station

Abstract

The invention provides an automatic operation control method for a low-dam hydropower station. The method comprises the following steps: preprocessing collected water level and incoming water flow data; a reservoir capacity dynamic calculation model is constructed in combination with the reservoir capacity curve graph and the water level flow data, and dynamic updating of reservoir capacity data is achieved; historical hydrological data, current water level flow and reservoir capacity data are fused to train a machine learning model, and the reliability of short-term inflow prediction is improved; based on the safe operation threshold value, the reservoir capacity data and the incoming water prediction result are input into a multi-objective optimization algorithm, a generator set power adjustment strategy and a flood discharge gate opening degree regulation strategy are automatically generated, and the generator set operation power and the flood discharge gate opening degree are automatically controlled, so that the problems that in the prior art, a low-dam hydropower station is low in automation degree and high in efficiency are solved. And manual adjustment is relied on.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic control of water conservancy projects, and in particular to an automatic operation control method for a low dam hydropower station. BACKGROUND

[0002] Under the demand for comprehensive utilization of water resources and clean energy development, low dam hydropower stations are widely used due to their low construction cost and small ecological impact.

[0003] However, the small reservoir capacity and sensitive response to incoming water of low dam hydropower stations require precise coordination of the dynamic relationship between water level, flow rate, and reservoir capacity. The operation control of low dam hydropower stations needs to adjust the power generation and flood discharge strategy through real-time data feedback to avoid water level exceeding the limit or wasting water, and rely on reliable incoming water prediction to plan the operation scheme in advance. Traditional control methods that rely on manual experience or simple logic cannot meet the needs of automation and refinement. SUMMARY

[0004] The present application provides an automatic operation control method for a low dam hydropower station to solve the problem of low automation and reliance on manual adjustment in the prior art.

[0005] In one aspect, the present application provides an automatic operation control method for a low dam hydropower station, comprising:

[0006] Collecting water level data and incoming water flow rate data at the entrance of the river of the low dam hydropower station, and preprocessing the water level data and the incoming water flow rate data to obtain water level flow rate data;

[0007] Retrieving reservoir capacity curve data of the low dam hydropower station, and constructing a reservoir capacity dynamic calculation model combining the water level flow rate data to obtain reservoir capacity data;

[0008] Combining historical hydrological data, the water level flow rate data, and the reservoir capacity data as training samples, inputting a machine learning model to perform short-term incoming water prediction, and obtaining incoming flow prediction results;

[0009] Based on a safe operation threshold, inputting the safe operation threshold, the reservoir capacity data, and the incoming flow prediction results into a multi-objective optimization algorithm to generate a generator power adjustment strategy and a flood discharge gate opening control strategy;

[0010] Transmitting the generator power adjustment strategy to a generator control system, dynamically adjusting the generator power, and combining the reservoir capacity data to obtain power output data that adapts to the incoming water flow rate data;

[0011] Transmitting the flood discharge gate opening control strategy to a gate control system, and using a fuzzy PID algorithm to optimize the adjustment logic to control the gate opening.

[0012] Optionally, the water level data of the low dam hydropower station and the inflow data of the river inlet are collected, and the water level data and the inflow data are preprocessed to obtain water level and flow data, including:

[0013] The water level data of the low dam hydropower station is collected by the water level sensor deployed on the low dam body;

[0014] The inflow data is collected by the Doppler ultrasonic flowmeter deployed at the river inlet;

[0015] The error correction operation is performed on the low dam hydropower station water level data in combination with the factory calibration parameters of the water level sensor and the low dam reservoir water level monitoring historical error record, to eliminate the accuracy deviation of the water level sensor and obtain corrected water level data;

[0016] According to the flow rate conversion formula of the Doppler ultrasonic flowmeter, in combination with the cross-sectional size parameters of the river inlet, the inflow data is calibrated twice to obtain corrected inflow data;

[0017] The corrected water level data and the corrected inflow data are filtered to form an anti-interference water level and flow intermediate data set;

[0018] The collection time stamp of the data points in the water level and flow intermediate data set is extracted, and the time stamp of the corrected inflow data is aligned and corrected based on the collection time of the water level sensor to obtain water level and flow data.

[0019] Optionally, the low dam hydropower station reservoir capacity curve data is retrieved, and a reservoir capacity dynamic calculation model is constructed in combination with the water level and flow data to obtain reservoir capacity data, including:

[0020] The pre-stored low dam hydropower station reservoir capacity curve data is obtained from the operation and maintenance records of the low dam hydropower station; the low dam hydropower station reservoir capacity curve data includes static reservoir capacity reference values corresponding to different water level values;

[0021] The water level value and the inflow value in the water level and flow data are extracted;

[0022] The water level value is taken as an input parameter, the water flow value is taken as a dynamic correction parameter, the static reservoir capacity reference value is associated and mapped with the water level value and the inflow value, and a reservoir capacity dynamic calculation model is constructed;

[0023] The water level value and the inflow value are input into the reservoir capacity dynamic calculation model to obtain reservoir capacity data.

[0024] Optionally, historical hydrological data, the water level and flow data, and the reservoir capacity data are combined as training samples and input into a machine learning model to perform short-term inflow prediction to obtain a reservoir inflow prediction result, including:

[0025] collecting historical hydrological data recorded in the operation process of the low dam hydropower station, the historical hydrological data including historical water level data, historical inflow data and historical rainfall correlation data;

[0026] screening the historical hydrological data, and arranging the structured historical data set after excluding abnormal fluctuation data;

[0027] correlating and integrating the structured historical data set with the water level and flow data and the reservoir capacity data according to the time dimension to form a training sample set meeting the model training format requirements;

[0028] inputting the training sample set into a preset machine learning model, and iteratively training the machine learning model using the historical data in the training sample set;

[0029] inputting the water level and flow data and the reservoir capacity data in the training sample set into the trained machine learning model, and outputting the reservoir inflow prediction result.

[0030] Optionally, based on a safe operation threshold, inputting the safe operation threshold, the reservoir capacity data and the reservoir inflow prediction result into a multi-objective optimization algorithm to generate a generator power adjustment strategy and a flood discharge gate opening control strategy, comprising:

[0031] determining a safe operation threshold according to the low dam hydropower station design specification and historical safe operation records;

[0032] converting the safe operation threshold, the reservoir capacity data and the reservoir inflow prediction result into a structured data matrix recognizable by the multi-objective optimization algorithm;

[0033] inputting the structured data matrix into a preset multi-objective optimization algorithm, taking the reservoir capacity over-safety threshold and the water level over-limit threshold as the first constraint condition, and taking the maximum power generation efficiency threshold and the minimum water abandonment amount as the optimization target, to initialize the population generation of the structured data matrix;

[0034] iteratively calculating the generator power adjustment parameters and the flood discharge gate opening control parameters in each generation population through selection, crossover and mutation operations of the genetic algorithm, verifying whether the calculation result meets the safe operation threshold after each iteration, eliminating the parameter combinations that do not meet the constraint, and obtaining the initial generator power adjustment parameters and the flood discharge gate opening control parameters;

[0035] stopping iteration and screening the optimal parameter combination in the non-dominated solution set when the iteration number reaches the preset number or the calculation result converges to a stable range;

[0036] arranging the optimal parameter combination according to the operation logic to obtain an executable generator power adjustment strategy and a flood discharge gate opening control strategy.

[0037] Optionally, the generator set power adjustment strategy is transmitted to a generator set control system, the generator set power is dynamically adjusted, and the reservoir capacity data are combined to obtain power generation power output data adapted to the incoming water flow data, including:

[0038] The power adjustment starting value, the single adjustment amplitude, and the power generation timing parameter in the generator set power adjustment strategy are extracted to form a standardized control instruction set;

[0039] According to the standardized control instruction set, a power adjustment program is started according to the power generation timing parameter;

[0040] Taking the reservoir capacity data change rate as a reference benchmark, if the reservoir capacity data show an abnormal upward trend, it is determined that the power generation power is lower than the incoming water flow adaptation value, and the power generation power is adjusted upward by a preset percentage of the single adjustment amplitude; if the reservoir capacity data show an abnormal downward trend, it is determined that the power generation power is higher than the incoming water flow adaptation value, and the power generation power is adjusted downward by a preset percentage of the single adjustment amplitude.

[0041] Optionally, the flood discharge gate opening degree control strategy is transmitted to a gate control system, a fuzzy PID algorithm is used to optimize the adjustment logic, and the gate opening degree is controlled, including:

[0042] The opening degree target value, the adjustment step, and the gate timing parameter in the flood discharge gate opening degree control strategy are extracted to form a standardized gate control instruction set;

[0043] The opening degree value of the flood discharge gate is continuously collected at a fixed time interval, the difference between the opening degree target value and the opening degree value is calculated as a deviation value, and the deviation change rate is calculated according to the deviation value;

[0044] The initial values of the proportional coefficient, the integral coefficient, and the differential coefficient are calibrated based on the historical adjustment data of the gate to construct an initial parameter set of the fuzzy PID algorithm;

[0045] The deviation value and the deviation change rate are input into a preset fuzzy rule base, and the correction amount of the initial parameter set is calculated through fuzzy reasoning calculation;

[0046] The initial parameter set is updated by the correction amount to generate an optimized adjustment logic to drive the flood discharge gate to adjust the opening degree by the adjustment step.

[0047] Optionally, it further includes:

[0048] A cross-basin data interaction channel is established to obtain real-time flood discharge plan data of the upstream reservoir of the low dam hydropower station, monitoring data of the upstream tributary inflow, and meteorological warning data, and a cross-basin hydrological data set is formed;

[0049] Integrate the cross-basin hydrological data set with the water level flow data, reservoir capacity data of the low dam hydropower station, and construct a basin-reservoir coupling correlation model with the flood discharge plan data and the monitoring data as input variables and the reservoir capacity data as an output variable;

[0050] When the upstream reservoir issues a flood discharge warning, calculate the water level prediction value of the low dam hydropower station within a preset time in the future through the basin-reservoir coupling correlation model in combination with the flood discharge plan data, the flood discharge period and the reservoir capacity data;

[0051] If the difference between the water level prediction value and the upper limit of the reservoir capacity safe operation threshold is less than a preset value, adjust the generator set power adjustment strategy and the flood discharge gate opening control strategy.

[0052] Optionally, it further comprises:

[0053] Real-time collection of the operation state data of the water level sensor, the Doppler ultrasonic flowmeter, the generator set and the gate;

[0054] Comparison of the operation state data with a preset device normal operation parameter range, identification of abnormal data exceeding the range, division of abnormal levels according to the importance and deviation degree of the abnormal data corresponding to the devices;

[0055] Generation of emergency response instructions based on the abnormal levels, and recording of the abnormal data generation time, abnormal levels and emergency response instruction execution results to form an abnormality processing log.

[0056] Optionally, it further comprises:

[0057] Division of the intermediate reservoir capacity into a safe buffer section, a power generation priority section and an ecological guarantee section with the reservoir capacity corresponding to the low dam design flood control limit water level as the upper limit and the reservoir capacity corresponding to the dead water level as the lower limit;

[0058] Calculation of the deviation rate of the incoming flow prediction result from the incoming flow;

[0059] Adjustment of the generator set power adjustment strategy and the flood discharge gate opening control strategy based on the deviation rate and the intermediate reservoir capacity.

[0060] In another aspect, the present application also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the low dam hydropower station automatic operation control method of any of the above aspects when executing the program.

[0061] In another aspect, the present application also provides a non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the low dam hydropower station automatic operation control method of any of the above aspects.

[0062] In another aspect, the present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the low dam hydropower station automatic operation control method according to any one of the above.

[0063] The low dam hydropower station automatic operation control method provided by the present application realizes dynamic updating of reservoir capacity data by preprocessing the collected water level and inflow data, combining the reservoir capacity curve and water level and flow data to construct a reservoir capacity dynamic calculation model; then the machine learning model is trained by fusing historical hydrological data, current water level and flow and reservoir capacity data, so as to improve the short-term inflow prediction reliability; based on the safe operation threshold, the reservoir capacity data and the inflow prediction result are input into the multi-objective optimization algorithm to automatically generate the generator unit power adjustment strategy and the spillway gate opening control strategy, and to automatically control the operation power of the generator unit and the opening of the spillway gate, so as to solve the problem of low automation degree of the low dam hydropower station in the prior art and the dependence on manual adjustment. BRIEF DESCRIPTION OF DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative effort.

[0065] Figure 1 is a flowchart of the low dam hydropower station automatic operation control provided by the embodiment of the present application;

[0066] Figure 2 is a structural schematic diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0067] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort are within the scope of protection of the present application.

[0068] Figure 1 is one of the flowcharts of the low dam hydropower station automatic operation control method provided by the embodiment of the present application.

[0069] As shown in Figure 1 , the low dam hydropower station automatic operation control method provided by the embodiment of the present application mainly includes the following steps:

[0070] 101, Collect the water level data of the low dam hydropower station and the incoming water flow data of the river entrance, and preprocess the water level data and the incoming water flow data to obtain water level flow data.

[0071] The water level data is used to reflect the current water level condition of the low dam hydropower station, and the incoming water flow data represents the water flow intensity at the river entrance. By preprocessing the water level data and the incoming water flow data, noise and outliers in the data can be eliminated, thereby obtaining more accurate and reliable water level flow data.

[0072] Specifically, the water level data of the low dam hydropower station and the incoming water flow data of the river entrance are collected, and the water level data and the incoming water flow data are preprocessed to obtain water level flow data, including:

[0073] The water level data of the low dam hydropower station is collected by the water level sensor deployed on the low dam body;

[0074] The incoming water flow data is collected by the Doppler ultrasonic flowmeter deployed at the river entrance;

[0075] The error correction operation is performed on the water level data of the low dam hydropower station in combination with the factory calibration parameters of the water level sensor and the historical error records of the low dam reservoir water level monitoring, to eliminate the precision deviation of the water level sensor and obtain corrected water level data;

[0076] According to the flow rate flow conversion formula of the Doppler ultrasonic flowmeter, in combination with the cross-sectional size parameters of the river entrance, the incoming water flow data is calibrated twice to obtain corrected incoming water flow data;

[0077] The corrected water level data and the corrected incoming water flow data are filtered to form an anti-interference water level flow intermediate data set;

[0078] The collection time stamp of the data points in the water level flow intermediate data set is extracted, and the time stamp of the corrected incoming water flow data is aligned and corrected based on the collection time of the water level sensor to obtain water level flow data.

[0079] The water level sensor is deployed at a preset monitoring position of the low dam body, such as a water level observation hole in the middle of the dam body, to collect the water level data in the low dam hydropower station in real time. The water level data directly reflects the current water storage depth of the reservoir.

[0080] At the same time, the Doppler ultrasonic flowmeter is deployed at a preset cross section upstream of the river entrance to collect the incoming water flow data at the river entrance in real time. The incoming water flow data is preliminarily calculated based on the ultrasonic velocity measurement principle after obtaining the flow velocity.

[0081] To eliminate the impact of the water level sensor's own accuracy deviation on the data, an error correction calculation is performed on the collected water level data of the low-dam hydropower station, combining the calibration parameters of the water level sensor at the factory with error data recorded during historical water level monitoring of the low-dam reservoir. For example, the historical average error value is subtracted from the original water level data, and the sensitivity deviation is adjusted according to the calibration parameters to obtain the corrected water level data.

[0082] For the inflow data, the velocity-flow conversion formula built into the Doppler ultrasonic flow meter is used, where the velocity-flow conversion formula is flow rate = velocity × cross-sectional area of ​​the water passage. Combined with the pre-measured cross-sectional dimensions of the river inlet, the collected raw inflow data is calibrated a second time to obtain the corrected inflow data.

[0083] Then, considering the potential impact of factors such as electromagnetic interference and water flow fluctuations in the field environment on the data, the moving average filtering method was adopted to perform filtering processing on the corrected water level data and the corrected inflow flow data respectively, removing abnormal fluctuation components in the data and forming an anti-interference intermediate dataset of water level and flow.

[0084] Finally, the timestamps corresponding to each data point in the intermediate water level and flow rate dataset are extracted, including the acquisition times of the water level data and the inflow flow rate data. Using the acquisition time of the water level sensor as a unified benchmark, the timestamps of the later flow rate data are aligned and corrected through time interpolation or delay compensation. For example, timestamps in the future flow rate data that do not match the acquisition time of the water level data are adjusted to the closest water level data acquisition time, ensuring that the corresponding water level and flow rate data are available at the same time point. Ultimately, this yields water level and flow rate data that is time-synchronized, accurate, and highly resistant to interference.

[0085] 102. Retrieve the reservoir capacity curve data of the low-dam hydropower station, and construct a dynamic calculation model of the reservoir capacity by combining the water level and flow data to obtain the reservoir capacity data.

[0086] Among them, the reservoir capacity dynamic calculation model can convert water level and flow data into reservoir capacity data based on the correlation between water level data and inflow data, as well as the correspondence between reservoir capacity and water level in low-dam hydropower stations. The reservoir capacity dynamic technology model can reflect the reservoir's water storage status in real time.

[0087] Specifically, the reservoir capacity curve data of the low-dam hydropower station is retrieved, and a dynamic calculation model for the reservoir capacity is constructed by combining the water level and flow data to obtain the reservoir capacity data, including:

[0088] The reservoir capacity curve data of the low dam hydropower station is obtained from the operation and maintenance records of the low dam hydropower station; the reservoir capacity curve data of the low dam hydropower station includes the static reservoir capacity benchmark value corresponding to different water level values;

[0089] extracting the water level value and the inflow value from the water level-flow data;

[0090] mapping the static storage capacity reference value with the water level value and the inflow value by taking the water level value as an input parameter and the inflow value as a dynamic correction parameter, and constructing a dynamic storage capacity calculation model;

[0091] inputting the water level value and the inflow value into the dynamic storage capacity calculation model to obtain storage capacity data.

[0092] The low dam hydropower station storage capacity curve data can be retrieved from the historical database or operation record document of the low dam hydropower station operation management system, and the low dam hydropower station storage capacity curve data is generated based on the topographic survey and water volume calculation results in the low dam reservoir construction stage, including the mapping relationship between different water level values and corresponding static storage capacity reference values, and the static storage capacity reference value reflects the theoretical water storage volume of the reservoir at a specific water level.

[0093] Then, after obtaining the low dam hydropower station storage capacity curve data, the real-time water level value and the real-time inflow value in the current calculation period are extracted from the water level-flow data obtained by preprocessing, and the real-time water level value and the real-time inflow value are taken as the basic state parameter and the dynamic influence parameter of the storage capacity calculation respectively, to ensure that the dynamic storage capacity technology model can adjust the calculation results combined with real-time hydrological changes.

[0094] Then, the static storage capacity reference value is mapped with the water level value and the inflow value by mathematical modeling, taking the water level value as an input parameter and the inflow value as a dynamic correction parameter. For example, first, the corresponding static storage capacity reference value is matched from the storage capacity curve data according to the real-time water level value, and then the storage capacity correction coefficient is calculated based on the inflow value. When the inflow is greater than the current outflow, the correction coefficient is set to 1.02-1.05, representing that the storage capacity shows a growth trend due to the inflow; when the inflow is less than the current outflow, the correction coefficient is set to 0.95-0.98, representing that the storage capacity shows a downward trend due to the outflow, and finally a dynamic storage capacity calculation model is constructed.

[0095] Finally, the extracted water level value and inflow value are substituted into the constructed dynamic storage capacity calculation model, the static storage capacity reference value is matched through the water level value, and the dynamic correction coefficient and the water level fluctuation compensation are calculated through the inflow value. After superposition operation, the actual storage capacity data at the current time is obtained, which not only retains the basic accuracy of the static storage capacity, but also integrates the dynamic influence of the inflow, and can accurately reflect the real-time water storage state of the low dam reservoir.

[0096] 103、Combine historical hydrological data, water level-flow data and storage capacity data as training samples, input machine learning model to perform short-term inflow prediction, and obtain inflow prediction results.

[0097] The short-term inflow prediction can be performed according to the periodicity, seasonality and trend characteristics of the historical data, and a machine learning algorithm can be used to learn and train the input training samples, so as to establish a short-term inflow prediction model. The short-term inflow prediction model can consider factors such as rainfall, evaporation, upstream inflow conditions and seasonal changes to improve the accuracy and reliability of the prediction results. Through short-term inflow prediction, the inflow conditions in the future period can be known in advance, providing data support for the scheduling and operation of the hydropower station.

[0098] Specifically, historical hydrological data, water level and flow data, and reservoir capacity data are used as training samples to input a machine learning model to perform short-term inflow prediction and obtain inflow prediction results, including:

[0099] Collecting historical hydrological data recorded during the operation of the low dam hydropower station, the historical hydrological data including historical water level data, historical inflow flow data and historical rainfall correlation data;

[0100] Filtering the historical hydrological data to remove abnormal fluctuation data and arranging the filtered data into a structured historical data set;

[0101] Integrating the structured historical data set with water level and flow data and reservoir capacity data according to the time dimension to form a training sample set meeting the model training format requirements;

[0102] Inputting the training sample set into a pre-set machine learning model and iteratively training the machine learning model using the historical data in the training sample set;

[0103] Inputting the water level and flow data and reservoir capacity data in the training sample set into the trained machine learning model to output inflow prediction results.

[0104] 104、Based on the safety operation threshold, inputting the safety operation threshold, reservoir capacity data and inflow prediction results into a multi-objective optimization algorithm to generate a generator power adjustment strategy and a flood discharge gate opening control strategy.

[0105] The generator power adjustment strategy is to dynamically adjust the output power of the generator set according to the current operation state of the reservoir and the future possible inflow conditions, so as to ensure that the hydropower station can meet the power demand and will not cause safety risks due to overload operation. The flood discharge gate opening adjustment strategy is used to automatically adjust the opening of the flood discharge gate when the predicted inflow exceeds the reservoir capacity, so as to safely release the excess water and prevent the reservoir from overflowing, thereby ensuring the safety of the dam and the downstream area.

[0106] Specifically, based on the safety operation threshold, inputting the safety operation threshold, reservoir capacity data and inflow prediction results into a multi-objective optimization algorithm to generate a generator power adjustment strategy and a flood discharge gate opening control strategy, including:

[0107] According to the design specification of low dam hydropower station and the historical safe operation record, the safe operation threshold is determined;

[0108] The safe operation threshold, reservoir capacity data and inflow prediction results are converted into a structured data matrix recognizable by a multi-objective optimization algorithm.

[0109] The structured data matrix is input into the preset multi-objective optimization algorithm, the reservoir capacity exceeds the safe threshold and the water level exceeds the threshold are taken as the first constraint condition, the maximum power generation efficiency threshold and the minimum water abandonment are taken as the optimization objective, and the structured data matrix is initialized to generate a population.

[0110] Through selection, crossover and mutation operations of genetic algorithm, the generator power adjustment parameters and the flood discharge gate opening control parameters in each generation population are iteratively calculated, and the calculation results are verified whether they meet the safe operation threshold each time the iteration is performed. The parameter combination that does not meet the constraint is eliminated, and the initial generator power adjustment parameters and the flood discharge gate opening control parameters are obtained.

[0111] When the number of iterations reaches the preset number or the calculation result converges to a stable range, the iteration is stopped and the optimal parameter combination in the non-dominated solution set is selected.

[0112] The optimal parameter combination is arranged according to the operation logic to obtain executable generator power adjustment strategy and flood discharge gate opening control strategy.

[0113] According to the index requirements of reservoir capacity safety and water level control in the design specification of low dam hydropower station and the historical safe operation record, the safe operation threshold is determined, wherein the safe operation threshold specifically includes reservoir capacity safety threshold, water level safety threshold and power generation efficiency threshold, to ensure that the safe operation threshold setting meets the engineering standard and adapts to the actual operation condition of the power station.

[0114] Then, the determined safe operation threshold, real-time reservoir capacity data and inflow prediction results are arranged according to the dimensions of threshold type, real-time data and prediction data, converted into a structured data matrix recognizable by a multi-objective optimization algorithm, for example, the row represents the parameter categories of reservoir capacity, water level and inflow, the list represents the safe threshold, current value and prediction value, and all data are standardized to a unified order of magnitude to avoid affecting the calculation accuracy of the algorithm due to the difference in data units.

[0115] Then, the structured data matrix is ​​input into a preset multi-objective optimization algorithm. For example, with the first constraint being that the reservoir capacity does not exceed the upper limit of the flood control limit and is not lower than the lower limit of the dead storage capacity, and the water level does not exceed the high flood control level and is not lower than the dead storage level, and with the optimization objectives being the minimum rated efficiency of the generator set and the minimum amount of flood discharge water, the structured data matrix is ​​initialized to generate a population. Each individual in the population corresponds to a combination of generator set power adjustment parameters and flood discharge gate opening control parameters. The population size is set to 50-100 individuals to ensure population diversity. Subsequently, the selection operation adopted the roulette wheel method to select high-quality individuals based on their fitness; the crossover operation used a single-point crossover method to exchange and recombine the parameters of two groups of high-quality individuals, such as crossing the power adjustment range of individual A with the gate opening change value of individual B; the mutation operation randomly adjusted the individual parameters with a mutation probability of 0.01-0.05. After each generation of iteration, the calculated parameter combination was substituted into the safe operation threshold for verification, and parameter combinations that exceeded the threshold for reservoir capacity or water level were eliminated, while the initial generator power adjustment parameters and flood discharge gate opening control parameters that met the constraints were retained.

[0116] When the number of iterations reaches a preset number, or after a preset number of consecutive iterations, and the deviation of the optimization objective converges to a stable range, the iteration stops. The final retained parameter combinations are then sorted using a non-dominated sorting method to select the optimal parameter combination from the non-dominated solution set. For example, a combination with a power generation efficiency of 89.5% and a water wastage of only 50,000 m³ is selected. 3 And the parameter combination satisfies the reservoir capacity and water level constraints.

[0117] Finally, the optimal parameter combinations are organized into executable strategies according to the actual operational logic. For example, the generator power adjustment strategy specifies the initial power value, the hourly adjustment range, and the upper limit of the adjusted power; the floodgate opening control strategy specifies the initial opening value, the adjustment step size each time, the upper limit of the opening, and the adjustment sequence.

[0118] 105. Transmit the generator set power adjustment strategy to the generator set control system, dynamically adjust the generator set power and combine it with reservoir capacity data to obtain power output data that is adapted to the inflow water flow data.

[0119] The generator power adjustment strategy intelligently adjusts the generator output power based on real-time inflow and reservoir capacity, ensuring that power generation efficiency is maximized while maintaining a safe reservoir operating level during the operation of the low-dam hydropower station. During the dynamic adjustment process, reservoir capacity data is continuously monitored to achieve the optimal match between power generation and inflow, thereby optimizing energy utilization efficiency and avoiding the risks of excessive flood discharge or insufficient reservoir capacity.

[0120] Specifically, the generator set power adjustment strategy is transmitted to the generator set control system, the generator set power is dynamically adjusted, and the reservoir capacity data is combined to obtain the power generation power output data adapted to the inflow data, including:

[0121] The power adjustment starting value, single adjustment amplitude and power generation timing parameter in the generator set power adjustment strategy are extracted to form a standardized control instruction set.

[0122] According to the standardized control instruction set, the power adjustment program is started according to the power generation timing parameter.

[0123] Taking the reservoir capacity data change rate as a reference benchmark, if the reservoir capacity data shows an abnormal upward trend, it is determined that the power generation power is lower than the inflow flow adaptation value, and the power generation power is adjusted upward by a preset percentage of the single adjustment amplitude; if the reservoir capacity data shows an abnormal downward trend, it is determined that the power generation power is higher than the inflow flow adaptation value, and the power generation power is adjusted downward by a preset percentage of the single adjustment amplitude.

[0124] Among the generator set power adjustment strategy generated from the multi-objective optimization algorithm, the power adjustment starting value, single adjustment amplitude and power generation timing parameter are accurately extracted and arranged into a control instruction set to ensure that the parameters in the control instruction set can be directly recognized and analyzed by the generator set control system.

[0125] Then, after receiving the standardized control instruction set, the instruction parameters in the standardized control instruction set are checked for legality, and the power adjustment program is started according to the power generation timing parameter in the standardized control instruction set after the check is passed.

[0126] If the power generation timing parameter is set to adjust every 30 minutes, the power adjustment is triggered according to the fixed period; if the setting is to start when the inflow flow change exceeds 5%, the current inflow flow is compared with the flow in the last adjustment period in real time, and the program is started immediately when the trigger condition is met, ensuring that the power adjustment matches the rhythm of the inflow flow change.

[0127] Finally, in the power adjustment process, the reservoir capacity data change rate is taken as the real-time feedback benchmark. If the reservoir capacity data shows an abnormal upward trend, it is determined that the current power generation power is lower than the inflow flow adaptation value, and the power generation power is adjusted upward by a preset percentage of the single adjustment amplitude at this time to increase water consumption to suppress the abnormal rise of reservoir capacity. If the reservoir capacity data shows an abnormal downward trend, it is determined that the current power generation power is higher than the inflow flow adaptation value, and the power generation power is adjusted downward by a preset percentage of the single adjustment amplitude at this time to reduce water consumption to alleviate the abnormal decline of reservoir capacity. Through dynamic feedback adjustment, the power generation power adapted to the real-time inflow flow is finally obtained.

[0128] 106、The flood discharge gate opening control strategy is transmitted to the gate control system, and the fuzzy PID algorithm is used to optimize the adjustment logic to control the gate opening.

[0129] The fuzzy PID algorithm establishes fuzzy control rules according to the relationship between the preset flood discharge gate opening range and the current water level, the inflow and the outflow, takes the real-time collected water level, inflow and outflow data as the input of the fuzzy controller, obtains the adjustment amount of the flood discharge gate opening through fuzzy reasoning, and then combines the traditional PID control algorithm to accurately calculate the adjustment amount and output the final control signal to the gate control system, so as to realize the regulation and control of the flood discharge gate opening.

[0130] Specifically, the flood discharge gate opening regulation and control strategy is transmitted to the gate control system, the fuzzy PID algorithm is used to optimize the adjustment logic, and the gate opening is controlled, including:

[0131] The opening target value, adjustment step and gate timing parameter in the flood discharge gate opening regulation and control strategy are extracted to form a standardized gate control instruction set;

[0132] The opening value of the flood discharge gate is continuously collected at fixed time intervals, the difference between the opening target value and the opening value is calculated as the deviation value, and the deviation change rate is calculated according to the deviation value;

[0133] The initial values of the proportional coefficient, integral coefficient and differential coefficient are calibrated based on the historical adjustment data of the gate to construct an initial parameter set of the fuzzy PID algorithm;

[0134] The deviation value and the deviation change rate are input into the preset fuzzy rule base, and the correction amount of the initial parameter set is calculated through fuzzy reasoning;

[0135] The initial parameter set is updated with the correction amount to generate an optimized adjustment logic to drive the flood discharge gate to adjust the opening by the adjustment step.

[0136] Among the flood discharge gate opening regulation and control strategy generated from the multi-objective optimization algorithm, the opening target value, adjustment step and gate timing parameter are extracted to generate a gate control instruction set.

[0137] After generating the standardized control instruction set, the real-time opening value of the flood discharge gate is continuously collected at fixed time intervals through the gate displacement sensor, the difference between the collected real-time opening value and the opening target value is calculated to obtain the deviation value. For example, when the target opening is 60% and the real-time opening is 52%, the deviation value is 8%.

[0138] At the same time, based on the deviation values and time intervals of adjacent two times, the deviation change rate is calculated. For example, when the previous deviation value is 10% and the current deviation value is 8%, the deviation change rate is -0.2% / second. Then, the parameters are calibrated based on the historical adjustment data of the gate, the proportional coefficient, integral coefficient and differential coefficient are counted when the deviation value is small, and the initial parameter set is determined. The initial parameter set can guarantee the basic adjustment accuracy of the gate under normal working conditions.

[0139] Subsequently, the calculated deviation value and the deviation change rate are input into a preset fuzzy rule base. The fuzzy rule base includes fuzzy rules such as increasing the proportional coefficient and decreasing the integral coefficient if the deviation value is large and the deviation change rate is small, and the correction amount of the initial parameter set is calculated through fuzzy reasoning. For example, for a deviation value of 8% and a deviation change rate of -0.2% / second, the reasoning obtains a P correction amount of +0.3, an I correction amount of -0.1, and a D correction amount of +0.2.

[0140] Finally, the initial parameter set is updated using the calculated correction amount to generate an optimized fuzzy PID adjustment logic. The fuzzy PID adjustment logic can dynamically adapt the PID parameters according to the real-time deviation and the deviation change rate.

[0141] According to the optimized adjustment logic, the opening degree is gradually adjusted by the adjustment step size until the deviation between the real-time opening degree value and the target opening degree value is less than the preset threshold, achieving precise control of the flood discharge gate opening degree, ensuring flood control safety, and avoiding water resource waste caused by excessive opening degree adjustment.

[0142] In some embodiments, the low dam hydropower station automatic operation control method further comprises:

[0143] A cross-basin data interaction channel is established to obtain real-time flood discharge plan data of an upstream reservoir of the low dam hydropower station, monitoring data of upstream tributary inflow, and meteorological warning data, and to organize and form a cross-basin hydrological data set.

[0144] The cross-basin hydrological data set is integrated with the water level-flow data and the reservoir capacity data of the low dam hydropower station, and a basin-reservoir coupling correlation model is constructed with the flood discharge plan data and the monitoring data as input variables and the reservoir capacity data as output variables.

[0145] When the upstream reservoir issues a flood discharge warning, the water level prediction value of the low dam hydropower station within a preset time in the future is calculated through the basin-reservoir coupling correlation model, combined with the flood discharge plan data, the flood discharge period, and the reservoir capacity data.

[0146] If the difference between the water level prediction value and the upper limit of the safe operation threshold of the reservoir capacity is less than a preset value, the generator power adjustment strategy and the flood discharge gate opening degree control strategy are adjusted.

[0147] Specifically, by establishing a cross-basin data interaction channel, real-time communication connections are established with the upstream reservoir management system, the basin hydrological monitoring station, and the meteorological department data platform to obtain the flood discharge plan data of the upstream reservoir, including the flood discharge start time, the expected duration, the hourly flood discharge flow, the monitoring data of the upstream tributary inflow, and the meteorological warning data, to form a structured cross-basin hydrological data set, ensuring the timeliness and completeness of the data.

[0148] Next, the cross-basin hydrological dataset was integrated with the local water level and flow rate data and reservoir capacity data of the low-dam hydropower station through temporal correlation. Using the flood discharge flow and tributary inflow monitoring data from the upstream reservoir's flood discharge plan data as input variables and the reservoir capacity data of the low-dam hydropower station as output variables, a basin-wide reservoir coupling correlation model was constructed using multiple linear regression. This model was trained by mapping historical cross-basin data to changes in local reservoir capacity. For example, when the upstream flood discharge flow increased by 10 m³ / s, the hourly growth coefficient of the local reservoir capacity was calibrated to ensure that the model accurately reflects the impact of upstream hydrological changes on local reservoir capacity.

[0149] Then, when the upstream reservoir management system issues a flood discharge warning, the warning trigger signal, the corresponding flood discharge plan data, the flood discharge period, and the current reservoir capacity data of the low dam are immediately input into the basin reservoir coupling correlation model. The prediction period is set, and the hourly water level prediction value of the low dam hydropower station within the prediction period is output through the calculation of the basin reservoir coupling correlation model. At the same time, a water level change trend curve is generated to intuitively show the impact of upstream flood discharge on the local water level.

[0150] Finally, the difference between the predicted water level and the preset safe operating threshold of the reservoir is calculated. If the difference is less than the preset value, the strategy adjustment mechanism is triggered to increase the single power adjustment amplitude and shorten the adjustment interval. Water consumption is increased by increasing power generation to reserve reservoir capacity. The target value of the gate opening is increased, the single adjustment step size is increased, and the pre-discharge operation is initiated in advance. At the same time, the gate regulation logic is optimized by the fuzzy PID algorithm to ensure that the gate opening adjustment is stable and responds quickly, avoids the local water level from exceeding the limit due to upstream flood discharge, and ensures the safe operation of the low dam hydropower station.

[0151] In some embodiments, the automatic operation control method for low-dam hydropower stations further includes:

[0152] Real-time acquisition of operating status data from water level sensors, Doppler ultrasonic flow meters, generator sets, and gates.

[0153] The system compares the operating status data with the preset normal operating parameter range of the equipment, identifies abnormal data that exceeds the range, and classifies the abnormality level according to the importance of the equipment and the degree of deviation corresponding to the abnormal data.

[0154] Emergency response instructions are generated based on the anomaly level, and the time of anomaly data generation, anomaly level, and execution results of emergency response instructions are recorded to form an anomaly handling log.

[0155] Specifically, the system uses sensors to collect real-time operational status data from water level sensors, Doppler ultrasonic flow meters, generator sets, and gates.

[0156] Next, the collected data is compared with the preset normal operating parameter range of the equipment to identify abnormal data that exceeds the range; then, according to the importance of the equipment and the degree of deviation, the abnormality level is divided into the first level, the second level, and the third level.

[0157] Finally, emergency commands are generated based on the anomaly level. Level 1 triggers shutdown and / or power outage and notifies operations and maintenance; Level 2 triggers load reduction and / or operation limitation and issues an early warning; Level 3 only issues an alarm and is continuously monitored.

[0158] Finally, the time, level, and command execution results of the anomaly are recorded to form an anomaly handling log, which is then stored and archived to provide a basis for troubleshooting and parameter optimization, ensuring stable equipment operation.

[0159] In some embodiments, the automatic operation control method for low-dam hydropower stations further includes:

[0160] Using the reservoir capacity corresponding to the flood control limit water level of the low dam design as the upper limit and the reservoir capacity corresponding to the dead water level as the lower limit, the intermediate reservoir capacity is divided into a safety buffer zone, a power generation priority zone, and an ecological protection zone.

[0161] Calculate the deviation rate between the predicted inflow and the actual inflow.

[0162] Based on the deviation rate and intermediate reservoir capacity, adjust the generator power adjustment strategy and the floodgate opening control strategy.

[0163] Specifically, the reservoir capacity corresponding to the flood control limit water level of the low dam design is taken as the upper limit, and the reservoir capacity corresponding to the dead water level is taken as the lower limit. The intermediate reservoir capacity between the upper and lower limits is divided into a safety buffer zone, a power generation priority zone, and an ecological protection zone.

[0164] Next, the predicted inflow rate obtained from the short-term inflow forecast is compared with the actual inflow rate, and the deviation rate between the two is calculated to determine the accuracy of the inflow forecast.

[0165] Finally, the adjustment strategy is based on the deviation rate and the current reservoir capacity. If the deviation rate is positive and the reservoir capacity is in the safe buffer zone, the adjustment range of the flood discharge gate opening can be increased and the adjustment range of power generation can be decreased to release reservoir capacity. If the deviation rate is negative and the reservoir capacity is in the power generation priority zone, the adjustment range of power generation can be increased and flood discharge can be suspended to make full use of the incoming water and ensure that the reservoir capacity is matched with the incoming water.

[0166] Figure 2 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention.

[0167] like Figure 2As shown, the electronic device may include a processor 210, a communications interface 220, a memory 230, and a communication bus 240. The processor 210, communications interface 220, and memory 230 communicate with each other via the communication bus 240. The processor 210 can call logical instructions from the memory 230 to execute the automatic operation control method for the low-dam hydropower station.

[0168] Furthermore, the logical instructions in the aforementioned memory 230 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0169] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the automatic operation control method for low-dam hydropower stations provided by the above methods.

[0170] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the automatic operation control method for low-dam hydropower stations provided by the methods described above.

[0171] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0172] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0173] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automatic operation control method for a low-dam hydropower station, characterized in that, include: Collect water level data of the low-dam hydropower station and inflow data of the river inlet, and preprocess the water level data and inflow data to obtain water level-flow data; Retrieve the reservoir capacity curve data of the low-dam hydropower station, and construct a dynamic calculation model of the reservoir capacity by combining the water level and flow data to obtain the reservoir capacity data; By combining historical hydrological data, water level and flow data, and reservoir capacity data as training samples, and inputting them into a machine learning model to perform short-term inflow prediction, the inflow prediction result is obtained. Based on the safe operation threshold, the safe operation threshold, the reservoir capacity data, and the inflow prediction results are input into a multi-objective optimization algorithm to generate a generator power adjustment strategy and a flood discharge gate opening control strategy. The generator set power adjustment strategy is transmitted to the generator set control system, and the generator set power is dynamically adjusted and combined with the reservoir capacity data to obtain power output data that is adapted to the inflow water data. The floodgate opening control strategy is transmitted to the gate control system, and the fuzzy PID algorithm is used to optimize the adjustment logic and control the gate opening.

2. The automatic operation control method for low-dam hydropower stations according to claim 1, characterized in that, Collect water level data of the low-dam hydropower station and inflow data of the river inlet, and preprocess the water level data and inflow data to obtain water level-flow data, including: Water level data of the low-dam hydropower station is collected by water level sensors deployed on the low-dam body; Water flow data were collected using Doppler ultrasonic flow meters deployed at the river inlet. By combining the factory calibration parameters of the water level sensor with the historical error records of water level monitoring in the low dam reservoir, an error correction operation is performed on the water level data of the low dam hydropower station to eliminate the accuracy deviation of the water level sensor and obtain the corrected water level data. Based on the velocity-flow conversion formula of the Doppler ultrasonic flow meter and combined with the cross-sectional dimensions of the river inlet, the inflow flow data is calibrated a second time to obtain corrected inflow flow data. Filtering is performed on the corrected water level data and the corrected inflow data to form an anti-interference intermediate water level and flow data dataset. Extract the collection timestamps of the data points in the intermediate data set of water level and flow rate, and align and correct the timestamps of the corrected inflow flow rate data based on the collection time of the water level sensor to obtain the water level and flow rate data.

3. The automatic operation control method for a low-dam hydropower station according to claim 1, characterized in that, Retrieve reservoir capacity curve data from the low-dam hydropower station, and combine it with the water level and flow rate data to construct a dynamic reservoir capacity calculation model, obtaining reservoir capacity data, including: The reservoir capacity curve data of the low dam hydropower station is obtained from the operation and maintenance records of the low dam hydropower station; the reservoir capacity curve data of the low dam hydropower station includes the static reservoir capacity benchmark value corresponding to different water level values; Extract the water level value and the inflow rate value from the water level and flow rate data; Using the water level value as an input parameter and the water flow rate value as a dynamic correction parameter, the static reservoir capacity benchmark value is correlated and mapped with the water level value and the inflow water flow rate value to construct a dynamic reservoir capacity calculation model. The water level value and the inflow rate value are input into the reservoir capacity dynamic calculation model to obtain reservoir capacity data.

4. The automatic operation control method for a low-dam hydropower station according to claim 1, characterized in that, By combining historical hydrological data, water level and flow rate data, and reservoir capacity data as training samples, and inputting them into a machine learning model to perform short-term inflow prediction, the inflow prediction results are obtained, including: Collect historical hydrological data recorded during the operation of the low-dam hydropower station, including historical water level data, historical inflow data, and historical rainfall-related data; Historical hydrological data were filtered, and abnormal fluctuation data were removed before being organized into a structured historical dataset. The structured historical dataset is linked and integrated with the water level and flow data and the reservoir capacity data according to the time dimension to form a training sample set that meets the requirements of the model training format; The training sample set is input into a preset machine learning model, and the machine learning model is iteratively trained using historical data from the training sample set. The water level and flow rate data and the reservoir capacity data in the training sample set are input into the trained machine learning model, and the inflow prediction result is output.

5. The automatic operation control method for a low-dam hydropower station according to claim 1, characterized in that, Based on a safe operating threshold, the safe operating threshold, along with the reservoir capacity data and the inflow prediction results, are input into a multi-objective optimization algorithm to generate a generator power adjustment strategy and a floodgate opening control strategy, including: Based on the design specifications for low-dam hydropower stations and historical safe operation records, the safe operation thresholds were determined. The safe operation threshold, the storage capacity data, and the inflow prediction results are converted into a structured data matrix that can be recognized by a multi-objective optimization algorithm. The structured data matrix is ​​input into a preset multi-objective optimization algorithm. The first constraints are reservoir capacity exceeding the safety threshold and water level exceeding the limit threshold. The optimization objectives are to maximize the power generation efficiency threshold and minimize the amount of water wasted. The structured data matrix is ​​then initialized to generate a population. Through selection, crossover, and mutation operations using a genetic algorithm, the generator power adjustment parameters and floodgate opening control parameters in each generation of the population are iteratively calculated. Each iteration verifies whether the calculation results meet the safe operation threshold, and parameter combinations that do not meet the constraints are eliminated to obtain the initial generator power adjustment parameters and floodgate opening control parameters. When the number of iterations reaches the preset number or the calculation results converge to a stable range, the iteration stops and the optimal parameter combination in the non-dominated solution set is selected. The optimal parameter combination is organized into an executable generator power adjustment strategy and a floodgate opening control strategy according to the operation logic.

6. The automatic operation control method for a low-dam hydropower station according to claim 1, characterized in that, The generator set power adjustment strategy is transmitted to the generator set control system to dynamically adjust the generator set power and combine it with the reservoir capacity data to obtain power output data adapted to the inflow water data, including: Extract the initial power adjustment value, single adjustment range, and power generation timing parameters from the generator set power adjustment strategy to form a standardized control instruction set; According to the standardized control instruction set, the power adjustment program is initiated according to the power generation timing parameters; Using the reservoir capacity data change rate as a reference, if the reservoir capacity data shows an abnormal upward trend, it is determined that the power generation is lower than the inflow rate adaptation value, and the power generation is adjusted upward by a preset percentage of the single adjustment range; if the reservoir capacity data shows an abnormal downward trend, it is determined that the power generation is higher than the inflow rate adaptation value, and the power generation is adjusted downward by a preset percentage of the single adjustment range.

7. The automatic operation control method for a low-dam hydropower station according to claim 1, characterized in that, The floodgate opening control strategy is transmitted to the gate control system, and the fuzzy PID algorithm is used to optimize the adjustment logic to control the gate opening, including: Extract the target opening value, adjustment step size, and gate timing parameters from the floodgate opening control strategy to form a standardized gate control instruction set; The opening value of the flood discharge gate is continuously collected at fixed time intervals, and the difference between the target opening value and the opening value is calculated as the deviation value. The deviation change rate is calculated based on the deviation value. Based on the historical regulation data of the gate, the initial values ​​of the proportional coefficient, integral coefficient, and derivative coefficient are calibrated, and the initial parameter set of the fuzzy PID algorithm is constructed. The deviation value and the deviation change rate are input into a preset fuzzy rule base, and the correction amount of the initial parameter set is obtained through fuzzy inference calculation. The initial parameter set is updated with the correction amount to generate optimized adjustment logic, which drives the floodgate to adjust its opening according to the adjustment step size.

8. The automatic operation control method for a low-dam hydropower station according to any one of claims 6-7, characterized in that, Also includes: Establish cross-basin data exchange channels to obtain real-time data on flood discharge plans of upstream reservoirs of low-dam hydropower stations, monitoring data on inflows from upstream tributaries, and meteorological early warning data, and compile them into a cross-basin hydrological dataset. The cross-basin hydrological dataset is integrated with the water level and flow data and reservoir capacity data of the low-dam hydropower station. The flood discharge plan data and the monitoring data are used as input variables, and the reservoir capacity data is used as the output variable to construct a basin reservoir coupling and correlation model. When an upstream reservoir issues a flood discharge warning, the water level prediction of the low-dam hydropower station within a preset time is calculated by using the basin reservoir coupling correlation model, combined with the flood discharge plan data, the flood discharge period and the reservoir capacity data. If the difference between the predicted water level and the upper limit of the safe operation threshold of the reservoir is less than the preset value, the power adjustment strategy of the generator set and the opening control strategy of the flood discharge gate will be adjusted.

9. The automatic operation control method for a low-dam hydropower station according to claim 2, characterized in that, Also includes: Real-time acquisition of operating status data from the water level sensor, the Doppler ultrasonic flow meter, the generator set, and the gate; The operating status data is compared with the preset normal operating parameter range of the equipment to identify abnormal data that exceeds the range, and the abnormality level is classified according to the importance of the equipment and the degree of deviation corresponding to the abnormal data. An emergency response command is generated based on the anomaly level, and the time of anomaly data generation, anomaly level, and execution result of the emergency response command are recorded to form an anomaly handling log.

10. The automatic operation control method for a low-dam hydropower station according to claim 1, characterized in that, Also includes: The reservoir capacity is divided into a safety buffer zone, a power generation priority zone, and an ecological protection zone, with the upper limit being the reservoir capacity corresponding to the flood control limit water level of the low dam design and the lower limit being the reservoir capacity corresponding to the dead water level. Calculate the deviation rate between the predicted inbound flow rate and the actual inbound flow rate; Based on the deviation rate and the intermediate reservoir capacity, the power adjustment strategy of the generator set and the flood discharge gate opening control strategy are adjusted.

Images