Intelligent operation method based on hydropower station equipment operation time and generating capacity statistics

Abstract

The invention discloses an intelligent operation method based on hydropower station equipment operation time and generating capacity statistics. The intelligent operation method comprises the following steps: step 1, determining an optimal data acquisition period; 2, calculating the planned generating capacity; generating capacity calculated by the 96-point power generation curve is used as expected output, through a power generation curve list of 96 data points, each data point represents the planned generating capacity of different time periods in one day, the data points which should be used are determined according to the current time, interpolation calculation is carried out, and the real-time planned generating capacity is obtained; step 3, real-time monitoring and error calculation: monitoring the actual generating capacity in real time, and calculating an error signal; step 4, closed-loop control adjustment is carried out; and Step 5, a customized operation management strategy is carried out. Through the measures of optimizing a control method of the AGC system, improving a generating capacity prediction technology, enhancing monitoring and adjusting of system operation parameters and the like, the difference value between machine end output and internet gateway output is reduced, so that the deviation between power generation control and planned generating capacity is reduced, and the power generation efficiency and stability of a hydropower station are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of hydropower station operation, and particularly relates to a smart operation method based on the statistics of the operation time and power generation of hydropower station equipment. Background Art

[0002] The operation time of equipment is one of the important factors in the operation of hydropower stations. However, its influencing factors are complex and diverse, including equipment wear, temperature changes, load fluctuations, etc., resulting in a certain degree of uncertainty in its impact on the power station operation. Although the operation time of equipment has an important impact on the power station operation, it is often ignored in power station management, lacking systematic analysis and countermeasures, resulting in low operation efficiency and stability of the power station.

[0003] In the operation management of large hydropower stations, achieving a closed-loop power quantity is a key goal. Traditional hydropower station operation management often relies on periodic data collection and manual processing, lacking real-time feedback and adjustment mechanisms. Therefore, in order to improve the operation efficiency, stability and response speed of hydropower stations, it is necessary to introduce a closed-loop power quantity control system. In traditional power systems, the closed-loop power quantity control system usually adjusts the operation parameters of hydropower station equipment by monitoring the difference between the actual power generation and the expected power generation, so that the actual power generation is as close as possible to the expected value. However, traditional closed-loop control methods often have problems such as unreasonable data collection periods and low accuracy of power generation statistics, and cannot meet the requirements of modern hydropower stations for efficient and precise operation. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a smart operation method based on the statistics of the operation time and power generation of hydropower station equipment. By optimizing the control method of the AGC system, improving the power generation prediction technology, strengthening the monitoring and adjustment of system operation parameters and other measures, the difference between the generator terminal output and the grid connection point output is reduced, thereby reducing the deviation between the power generation control and the planned power generation, and improving the power generation efficiency and stability of the hydropower station.

[0005] To solve the above technical problem, the technical solution adopted by the present invention is: A smart operation method based on the statistics of the operation time and power generation of hydropower station equipment, comprising the following steps: Step1, determination of the optimal data collection period; according to the equipment characteristics and actual requirements of the hydropower station, comprehensively considering factors such as equipment operation characteristics, data change frequency, and system response speed, and optimizing and adjusting through on-site testing and analysis to meet the actual requirements and performance requirements of the system; determining a reasonable data collection period to ensure accurate recording of the equipment operation time and power generation; Step 2. Calculate the planned power generation; Use the power generation calculated from the 96-point power generation curve as the expected output. Through the power generation curve list of 96 data points, each data point represents the planned power generation at different time periods of a day. Determine the data point to be used according to the current time and perform interpolation calculation to obtain the real-time planned power generation; Step 3. Real-time monitoring and error calculation: Real-time monitor the actual power generation and calculate the error signal in each acquisition period; Step 4. Closed-loop control adjustment; According to the error signal, feedback to the AGC to adjust the operating parameters of the system, reduce the error and make the system output gradually approach the expected value; Continuously monitor and adjust to form a closed-loop control system, make the output of the system stable near the expected value, and dynamically adjust the operating state of the system; Step 5. Determine the basis, control variables and execution logic for strategy adjustment based on the dynamic optimization strategy of equipment operation data and power generation statistics.

[0006] The equipment operation characteristic factors in the above Step 1 include: Analysis of equipment operation characteristics: Distribution of equipment operation time: Analyze the statistical characteristics of the equipment operation duration to determine whether there are regular operation cycles, including daily cycles and weekly cycles; Change of operation state: The influence of different working conditions, including the active and reactive loads of the unit and the water head condition, on the data acquisition period.

[0007] The data change frequency factors in the above Step 1 include: Quantification of data change frequency: Statistically analyze the change rates Ri of different monitoring parameters, including unit output, water head change, and the angle change of the water guide mechanism, unit: % / minute; Calculate the average value Ravg of the data change rates of different parameters: ; where N is the total number of monitored parameters; Set the threshold , if It indicates that the data changes rapidly and the sampling interval should be shortened; otherwise, the sampling interval can be extended.

[0008] The system response speed factors in the above Step 1 include: Analysis of system response speed: System time delay : The time from the change of the monitoring signal to its influence on the system control, including the response delay of the AGC control signal; Control adjustment period : The shortest time interval for the system to perform one adjustment; Data acquisition period Calculation: ; where k and m are empirical coefficients used to adjust the sampling accuracy.

[0009] The optimization of the data acquisition period in the above Step1 includes: The final data acquisition period is determined by the following formula: ; where: α is an adjustment coefficient that controls the upper and lower limits of the sampling frequency; β is a weight factor for the influence of data changes on the sampling interval; The exponential function makes the sampling period shorten when the data change rate is high to improve data accuracy; when the data changes slowly, the sampling period is appropriately extended to reduce the computational burden.

[0010] The determination of a reasonable data acquisition period in the above Step1 includes: Initial value: Set the initial sampling period according to experience, which can be 15 seconds, 30 seconds, or 1 minute; Dynamic adjustment: Monitor the data change rate, update Ravg every once in a while, and adjust .

[0011] Model adaptive optimization: Train a machine learning model through historical data to optimize α and β to adapt to different power plant environments.

[0012] In the closed-loop control regulation in the above Step4, the system output approaches the expected value through error range quantification: Let the expected output power be Pset and the actual output power be Pact. The error between the two is defined as: e(t) = Pset(t) - Pact(t); Error qualified range: ∣e(t)∣ ≤ ε; where ε is the allowable error range; when the error e(t) is less than this threshold, the control is considered to meet the standard.

[0013] The structure of the closed-loop control regulation system in the above Step4 is: The closed-loop control system includes the following links: Error calculation: Calculate e(t) in real time and judge whether the current error exceeds the threshold; Error feedback: Transmit the error signal to the AGC control module to generate a regulation instruction; Control regulation: Correct the error by adjusting the unit output, including adjusting the opening of the guide vane mechanism and adjusting the load distribution; Real-time monitoring: Update the actual output Pact, continue to calculate the error, and ensure that the error converges gradually.

[0014] The process of determining the basis for policy adjustment in Step 5 above is as follows: Basis for operation management policy: Adjust according to equipment operation time, power generation error, system load level, and equipment health status. The goals include: Minimize the error between generator terminal output and grid connection point output: including reducing adjustment deviation and improving the plan achievement rate; Optimize the load distribution of unit operation: Based on equipment status and efficiency factor, improve the overall energy efficiency; Reduce equipment fatigue loss: Through balanced scheduling, avoid wear of individual units.

[0015] The dynamic optimization strategy for equipment operation data in Step 5 above includes: 1) Adjustment based on error feedback; 2) Dynamic adjustment based on optimized load distribution; 3) Adjustment based on equipment health status: Health status score D: D = αT + βV + γI T is the cumulative operation time, V is the vibration level, I is the generator current unbalance degree, and α, β, γ are empirical weight coefficients; When D > Dalarm, reduce the priority of this unit and arrange preventive maintenance.

[0016] A smart operation method based on the operation time and power generation statistics of hydropower station equipment provided by the present invention has the following beneficial effects: Accurate analysis of the impact of operation time: The present invention incorporates the equipment operation time factor into the consideration scope of power station operation management. Through accurate data collection and analysis, it deeply explores the actual impact of equipment operation time on power station operation, providing a more scientific and comprehensive basis for power station management.

[0017] Power generation calculation method based on the 96-point power generation curve: The present invention uses the power generation calculated from the 96-point power generation curve as the expected output, compares it with the actual power generation, and thus realizes the accurate statistics of power generation. Compared with the traditional simple calculation method, it can more accurately estimate the actual power generation and improve the accuracy of power generation statistics.

[0018] Application of closed-loop control system: The present invention forms a closed-loop control system by feeding back the error signal to the AGC system and adjusting the operation parameters of the system, so that the system output can be stabilized near the expected value. Compared with the traditional open-loop control system, it can more effectively control the operation of the system and improve the stability and reliability of the system.

[0019] Improving the operating efficiency and reliability of power stations: Through precise analysis and intelligent adjustment of the equipment operation time factor, the present invention can improve the operating efficiency and reliability of power stations, reduce energy losses and operating risks, and provide strong support for the long-term stable operation of power stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The present invention will be further described below in conjunction with the drawings and embodiments: Figure 1 is a schematic diagram of the overall operation process of the present invention; Figure 2 is a flowchart for determining the optimal data acquisition period of the present invention; Figure 3 is a schematic diagram of the real-time monitoring and error calculation process of the present invention; Figure 4 is a schematic diagram of the process of the closed-loop control and regulation system of the present invention; Figure 5 is a schematic diagram of the operation management strategy of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] The technical solution of the present invention will be described in detail below in conjunction with the drawings and embodiments.

[0022] Embodiment 1: As Figure 1 and 2 shown in, Step 1, determining the optimal data acquisition period; according to the equipment characteristics and actual requirements of the hydropower station, comprehensively considering factors such as equipment operation characteristics, data change frequency, and system response speed, and optimizing and adjusting through on-site testing and analysis to meet the actual needs and performance requirements of the system; determining a reasonable data acquisition period to ensure accurate recording of equipment operation time and power generation; The equipment operation characteristic factors include: Analysis of equipment operation characteristics: Distribution of equipment operation time: Analyze the statistical characteristics of equipment operation duration to determine whether there are regular operation cycles, including daily and weekly cycles; Change in operating state: The influence of different operating conditions, including active and reactive loads of the unit and water head conditions, on the data acquisition period; The data change frequency factors include: Quantification of data change frequency: Statistically analyze the change rates Ri of different monitoring parameters, including unit output, water head change, and guide vane mechanism angle, unit: % / minute; Calculate the average data change rate Ravg of different parameters: ; where N is the total number of monitored parameters; set a threshold , if It indicates that the data changes rapidly, and the sampling interval should be shortened; conversely, the sampling interval can be extended.

[0023] The factors of the system response speed include: Analysis of the system response speed: System time delay : The time from the change of the monitoring signal to its impact on the system control, including the response delay of the AGC control signal; Control adjustment period : The shortest time interval for the system to perform one adjustment; Data acquisition period Calculation: ; where k and m are empirical coefficients used to adjust the sampling accuracy.

[0024] The optimization of the data acquisition period includes: Final data acquisition period It is determined by the following formula: ; where: α is the adjustment coefficient, which controls the upper and lower limits of the sampling frequency; β is the weight factor of the impact of data change on the sampling interval; Exponential function makes the sampling period shorten when the data change rate is high to improve data accuracy; when the data changes slowly, the sampling period is appropriately extended to reduce the calculation burden.

[0025] Determining a reasonable data acquisition period includes: Initial value: Set the initial sampling period according to experience, which can be 15 seconds, 30 seconds or 1 minute; Dynamic adjustment: Monitor the data change rate, update Ravg every period of time (such as 24 hours), and adjust .

[0026] Model adaptive optimization: Train a machine learning model with historical data to optimize α and β to adapt to different power station environments.

[0027] Step2, Calculate the planned power generation; Use the power generation calculated from the 96-point power generation curve as the expected output. Through the power generation curve list of 96 data points, each data point represents the planned power generation at different time periods in a day. Determine the data point to be used according to the current time and perform interpolation calculation to obtain the real-time planned power generation; The specific function code for calculating the real-time planned power generation is: from datetime import datetime, timedelta import numpy as np def calculate_planned_generation(cur_time, generation_curve): """ Calculate the real-time planned power generation based on the current time and the power generation curve.

[0028] Parameters: cur_time (datetime): The current time.

[0029] generation_curve (list): A list of power generation curves containing 96 data points.

[0030] Returns: float: The real-time planned power generation.

[0031] """ # Calculate the minutes of the current time in a day cur_minutes = cur_time.hour * 60 + cur_time.minute # Calculate the index of the data point where the current time is located index = int(cur_minutes / (24 * 60 / len(generation_curve))) # Get the index and value of the current data point and the next data point current_index = index % len(generation_curve) next_index = (index + 1) % len(generation_curve) current_value = generation_curve[current_index] next_value = generation_curve[next_index] # Calculate the real-time planned power generation by linear interpolation time_ratio = (cur_minutes % (24 * 60 / len(generation_curve))) / (24* 60 / len(generation_curve)) planned_generation = current_value + (next_value - current_value) *time_ratio return planned_generation Principle of the function: The calculate_planned_generation function takes two parameters: cur_time: The current time, represented in the datetime type.

[0032] generation_curve: A list of generation curves containing 96 data points, representing the planned power generation for different time periods in a day.

[0033] First, the function calculates the number of minutes cur_minutes of the current time in a day. This value is the number of hours of the current time multiplied by 60 plus the number of minutes. Then, the function calculates the index index of the data point where the current time is located. This index is calculated based on the number of minutes of the current time in a day and the length of the generation curve. Next, the function determines the indices and corresponding values of the current data point and the next data point: current_index: The index of the current data point. next_index: The index of the next data point. current_value: The planned power generation corresponding to the current data point. next_value: The planned power generation corresponding to the next data point. Then, the function uses the method of linear interpolation to calculate the real-time planned power generation planned_generation according to the ratio of the current time between the current data point and the next data point. Linear interpolation is a simple interpolation method that assumes the change between two adjacent data points is linear. Finally, the function returns the calculated real-time planned power generation.

[0034] Step 3, as shown in Figure 3 below, real-time monitoring and error calculation: Real-time monitor the actual power generation and calculate the error signal; Step 4, as shown in Figure 4 below, closed-loop control regulation: According to the error signal, feedback to the AGC to adjust the operating parameters of the system, reduce the error and make the system output gradually approach the expected value; Continuously monitor and adjust to form a closed-loop control system, make the output of the system stable near the expected value, and dynamically adjust the operating state of the system; In the closed-loop control regulation, the system output approaches the expected value through error range quantization: Let the expected output power be \(P_{set}\) and the actual output power be \(P_{act}\). The error between the two is defined as: \(e(t)=P_{set}(t)-P_{act}(t)\); Error qualification range: \(\vert e(t)\vert\leq\varepsilon\); where \(\varepsilon\) is the allowable error range (such as 0.5 MW or 0.1% of the rated power). When the error \(e(t)\) is less than this threshold, the control is considered to meet the standard.

[0035] The structure of the closed-loop control and regulation system is as follows: The closed-loop control system mainly includes the following links: Error calculation: Calculate \(e(t)\) in real time and determine whether the current error exceeds the threshold; Error feedback: Transmit the error signal to the AGC control module to generate adjustment instructions; Control and regulation: Correct the error by adjusting the unit output, including adjusting the opening of the water guide mechanism and adjusting the load distribution; Real-time monitoring: Update the actual output \(P_{act}\), continue to calculate the error, and ensure that the error gradually converges.

[0036] Step5. As Figure 5 shown, a dynamic optimization strategy based on equipment operation data and power generation statistics, and clarify the basis, control variables, and execution logic for strategy adjustment.

[0037] The process of determining the basis for strategy adjustment is as follows: Basis for operation management strategy: Adjust according to equipment operation time, power generation error, system load level, and equipment health status. The main objectives include: Minimize the error between the generator terminal output and the grid connection point output: including reducing the adjustment deviation and improving the plan achievement rate; Optimize the unit operation load distribution: Based on the equipment status and efficiency factor, improve the overall energy efficiency; Reduce equipment fatigue loss: Through balanced scheduling, avoid excessive wear of individual units.

[0038] The dynamic optimization strategy for equipment operation data includes: 1) Adjustment based on error feedback; 2) Dynamic adjustment based on load distribution optimization; 3) Adjustment based on equipment health status: Health status score D: \(D = \alpha T+\beta V+\gamma I\) where \(T\) is the cumulative operation time, \(V\) is the vibration level, \(I\) is the generator current unbalance degree, and \(\alpha,\beta,\gamma\) are empirical weight coefficients; When D > Dalarm (e.g., the equipment has run for 20,000 hours or the vibration exceeds the limit), reduce the priority of this unit and arrange for preventive maintenance.

[0039] The core of this strategy lies in making refined and personalized adjustments to operation management according to actual situations and requirements to achieve the best operation effect.

[0040] Optimization of equipment inspection and maintenance plans: Based on factors such as the running time, workload, and wear condition of the equipment, formulate inspection and maintenance plans, reasonably arrange the maintenance time and methods to ensure the long-term stable operation of the equipment.

[0041] Intelligent operation monitoring and early warning system: Establish an intelligent operation monitoring and early warning system to continuously monitor the operation status and parameter changes of the equipment, promptly detect potential problems and take corresponding measures to prevent accidents.

[0042] Optimized operation parameter adjustment plan: According to real-time data and operation conditions, optimize the operation parameter adjustment plan, including power generation, water level control, flow regulation, etc., to achieve the best operation state of the equipment.

Claims

1. A smart operation method based on the statistics of the operation time and power generation of hydropower station equipment, characterized in that, It includes the following steps: Step 1. Determine the optimal data acquisition period: Based on the characteristics of hydropower station equipment and actual requirements, comprehensively consider equipment operation characteristics, data change frequency, and system response speed factors, and optimize and adjust through on-site testing and analysis to meet the actual requirements and performance requirements of the system; determine a reasonable data acquisition period to ensure accurate recording of equipment operation time and power generation. Step 2. Calculate the planned power generation: Use the power generation calculated from the 96-point power generation curve as the expected output. Through the power generation curve list of 96 data points, each data point represents the planned power generation in different time periods of a day. Determine the data point to be used according to the current time and perform interpolation calculation to obtain the real-time planned power generation. Step 3. Real-time monitoring and error calculation: Real-time monitor the actual power generation and calculate the error signal in each acquisition period. Step 4. Closed-loop control regulation: According to the error signal, feedback to the AGC to adjust the operation parameters of the system, reduce the error and make the system output gradually approach the expected value; continuously monitor and adjust to form a closed-loop control system, make the output of the system stable near the expected value, and dynamically adjust the operation state of the system. Step 5. Determine the basis, control variables, and execution logic of the dynamic optimization strategy based on equipment operation data and power generation statistics.

2. The intelligent operation method based on the statistics of the operation time and power generation of hydropower station equipment according to claim 1, characterized in that In Step 1, the equipment operation characteristic factors include: Equipment operation characteristic analysis: Distribution of equipment operation time: Analyze the statistical characteristics of equipment operation duration to determine whether there are regular operation cycles, including daily and weekly cycles. Change of operation state: The influence of different working conditions, including active and reactive loads of the unit and water head conditions, on the data acquisition period.

3. The intelligent operation method based on the operation time and power generation statistics of hydropower station equipment according to claim 1, characterized in that, In Step 1, the data change frequency factors include: Quantification of data change frequency: Statistically calculate the change rate Ri of different monitoring parameters, including unit output, water head change, and guide vane mechanism angle, unit: % / minute. Calculate the average value Ravg of the data change rates of different parameters. ； where N is the total number of monitored parameters; set the threshold , if it indicates that the data changes rapidly, and the sampling interval should be shortened; otherwise, the sampling interval can be extended.

4. The intelligent operation method based on the operation time and power generation statistics of hydropower station equipment according to claim 1, characterized in that In Step 1, the system response speed factors include: System response speed analysis: System time delay : The time from the change of the monitoring signal to its impact on system control, including the response delay of the AGC control signal; Control adjustment period : The shortest time interval for the system to perform one adjustment; Data acquisition cycle Calculation: ; Among them, k and m are empirical coefficients used to adjust the sampling accuracy.

5. The intelligent operation method based on the operation time and power generation statistics of hydropower station equipment according to claim 1, characterized in that, In Step 1, the optimization of the data acquisition period includes: Final data acquisition period is determined by the following formula: ； Where: α is an adjustment coefficient that controls the upper and lower limits of the sampling frequency. β is a weight factor for the influence of data change on the sampling interval. Exponential function When the data change rate is high, the sampling period is shortened to improve data accuracy; when the data changes slowly, the sampling period is appropriately extended to reduce the computational burden.

6. The intelligent operation method based on the operation time and power generation statistics of hydropower station equipment according to claim 1, characterized in that, In Step 1, determining a reasonable data acquisition period includes: Initial value: Set the initial sampling period according to experience, and 15 seconds, 30 seconds, or 1 minute can be used. Dynamic adjustment: Monitor the data change rate, update Ravg every once in a while, and adjust ; Model adaptive optimization: Train a machine learning model through historical data to optimize α and β to adapt to different power station environments.

7. The intelligent operation method based on the statistics of the operation time and power generation of hydropower station equipment according to claim 1, characterized in that, In the closed-loop control regulation in Step 4, the system output approaching the expected value is quantified by the error range: Let the expected output power be Pset and the actual output power be Pact, and the error between the two is defined as: e(t) = Pset(t) - Pact(t); Error qualified range: ∣e(t)∣ ≤ ε; Among them, ε is the allowable error range; when the error e(t) is less than this threshold, the control is considered to meet the standard.

8. The intelligent operation method based on the operation time and power generation statistics of hydropower station equipment according to claim 7, characterized in that, The structure of the closed-loop control and regulation system in Step 4 is as follows: The closed-loop control system includes the following links: Error calculation: Calculate e(t) in real time and determine whether the current error exceeds the threshold; Error feedback: Transmit the error signal to the AGC control module to generate a regulation instruction; Control and regulation: Correct the error by adjusting the output of the unit, including adjusting the opening of the wicket gate mechanism and adjusting the load distribution; Real-time monitoring: Update the actual output Pact and continue to calculate the error to ensure that the error gradually converges.

9. The intelligent operation method based on the statistics of the operation time and power generation of hydropower station equipment according to claim 1, characterized in that, The process of determining the basis for policy adjustment in Step 5 is as follows: Basis for operation management policy: Adjust according to the equipment operation time, power generation error, system load level, and equipment health status. The goals include: Minimize the error between the generator terminal output and the grid connection point output: including reducing the regulation deviation and improving the plan achievement rate; Optimize the load distribution of unit operation: Based on the equipment status and efficiency factor, improve the overall energy efficiency; Reduce the fatigue loss of equipment: Avoid the wear of individual units through balanced scheduling.

10. The intelligent operation method based on the statistics of the operation time and power generation of hydropower station equipment according to claim 1, characterized in that, The dynamic optimization strategy for equipment operation data in Step 5 includes: 1) Adjustment based on error feedback; 2) Dynamic adjustment based on load distribution optimization; 3) Adjustment based on equipment health status: Health status score D: D = αT + βV + γI T is the cumulative operation time, V is the vibration level, I is the generator current unbalance degree, and α, β, γ are empirical weight coefficients; When D > Dalarm, reduce the priority of this unit and arrange preventive maintenance.

Images