Hydroelectric generating set speed regulator parameter monitoring method and system based on real-time data

Abstract

The invention discloses a hydroelectric generating set speed regulator parameter monitoring method and system based on real-time data, and relates to the technical field of power systems, and the method comprises the steps: arranging a sensor on a hydroelectric generating set speed regulator, and collecting operation data in real time; converting the operation data into a digital signal, filtering the received digital signal, removing invalid data, formatting the data into a standard format, and storing the data according to a time sequence; the formatted data are analyzed through a multiple linear regression algorithm, a parameter correlation model is established, and theoretical operation parameter values are calculated; a control signal is generated according to the data analysis result, and the hydraulic oil pressure and the valve opening are adjusted through an executing mechanism. According to the hydroelectric generating set speed regulator parameter monitoring method based on the real-time data, the hydraulic oil pressure and the opening degree of the water inlet valve are dynamically monitored and adjusted by collecting the operation data of the hydroelectric generating set in real time, the change of the power grid load can be rapidly responded, the rotating speed of the generating set is adjusted, and the power generation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power systems, and in particular to a method and system for monitoring parameters of a speed regulator of a hydroelectric generator set based on real-time data. Background Art

[0002] As one of the core control devices of a hydropower station, the main function of the hydropower generator speed governor is to adjust the operating status of the generator set and ensure the stability of the power grid output. Traditional hydropower generator speed governors rely on mechanical or simple automation equipment to monitor and adjust the operating parameters of the generator set, but with the dynamic changes in the power grid load and the increasing complexity of the generator set itself, traditional speed governor systems are difficult to adapt to changing working conditions.

[0003] Existing hydroelectric generator speed governor systems usually rely on manual or periodic inspections for fault detection and maintenance, making it difficult to obtain key operating parameters in real time, such as speed, hydraulic pressure, and water inlet flow. This approach is not only inefficient, but also prone to delays in fault handling due to untimely parameter acquisition, further affecting the stability of the power generation system. In addition, the means used to adjust operating parameters in existing systems are relatively simple, with low adjustment accuracy, and cannot accurately adjust for subtle changes under different load conditions.

[0004] With the expansion of hydropower station scale and the improvement of stability requirements of power system, the automation and intelligence of speed regulators have gradually become the key to improving system efficiency. However, most speed regulators on the market currently rely on simple feedback control systems and lack intelligent analysis and prediction functions for real-time operation data. In addition, fault detection and emergency handling capabilities are also relatively limited, making it difficult to achieve real-time prediction and response to faults.

[0005] Therefore, how to use intelligent algorithms based on real-time collected operating data to accurately control and adjust the operating status of the hydro-generator set and provide fault prediction and emergency operation functions has become a technical problem that needs to be urgently solved in the field of hydropower station speed regulators. Summary of the invention

[0006] In view of the above-mentioned problems, the present invention is proposed.

[0007] Therefore, the technical problem solved by the present invention is that the existing speed governor system of the hydroelectric generator set cannot accurately monitor and adjust the hydraulic oil pressure and the water inlet valve opening in real time during operation, resulting in a delayed response of the system to changes in the load of the power grid, making it difficult to accurately maintain the stable speed of the generator set. In addition, the fault detection and response mechanism in the existing system is relatively passive, relying on data feedback after the fault occurs, and cannot predict the fault in advance, so it is difficult to perform load transfer operations in time when the fault occurs, affecting the stability of the power grid and the power generation efficiency.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: A method for monitoring parameters of a speed governor of a hydroelectric generator set based on real-time data, comprising:

[0009] Arrange sensors on the speed governor of the hydroelectric generator set to collect operating data in real time;

[0010] Convert the operation data into digital signals, filter the received digital signals, remove invalid data, and format the data into a standard format and store them in chronological order;

[0011] The formatted data were analyzed using a multivariate linear regression algorithm to establish a parameter association model and calculate theoretical operating parameter values;

[0012] Based on the data analysis results, a control signal is generated to adjust the hydraulic oil pressure and valve opening through the actuator.

[0013] As a preferred solution of the method for monitoring parameters of a speed governor of a hydroelectric generator set based on real-time data described in the present invention, the sensors include a speed sensor, a pressure sensor and a flow sensor.

[0014] As a preferred solution of the method for monitoring parameters of a hydroelectric generator set governor based on real-time data described in the present invention, the operating data includes the rotation speed of the hydroelectric generator set, the oil pressure of the hydraulic system and the water inlet flow of the turbine.

[0015] As a preferred solution of the method for monitoring parameters of a speed governor of a hydroelectric generator set based on real-time data according to the present invention, the storage in chronological order includes converting analog signals of the rotation speed, oil pressure of the hydraulic system and water inlet flow into digital signals through an analog-to-digital conversion unit, the accuracy of the analog-to-digital conversion is set to 10 bits, and the sampling frequency is 1kHz;

[0016] After analog-to-digital conversion, a logic comparator is used to perform preliminary verification on the converted digital signal to determine whether the data is within the preset physical range and set upper and lower thresholds. If the data exceeds the threshold range, the data is discarded and marked as abnormal data. If the data does not exceed the threshold range, the data is marked as qualified data.

[0017] The qualified data enters the low-pass filter process, and the cut-off frequency is set to 50Hz. The data is filtered through a digital filter to filter out high-frequency noise above 50Hz and retain the valid signal;

[0018] The filtered data is checked according to the change rate, and the maximum change threshold Δ per second is set. By calculating the difference between adjacent sampling points, it is determined whether the data change rate exceeds the preset threshold. If the change rate exceeds the threshold, the data is marked as abnormal and excluded;

[0019] If the data changes normally, Kalman filtering is performed. In the Kalman filtering process, the prediction error threshold is set to ±2%. The current value is predicted based on the data at the previous moment, and the prediction error of each data point is calculated in real time. If the error exceeds the set threshold, the filtering process is continued until the error value drops within the set range.

[0020] The data after Kalman filtering enters the formatting process, and a timestamp accurate to milliseconds is attached. According to the set format, each set of data is organized into structured data containing timestamp, speed, oil pressure of the hydraulic system, and water inlet flow.

[0021] As a preferred solution of the method for monitoring parameters of a hydroelectric generator set speed governor based on real-time data described in the present invention, wherein: the theoretical operating parameter value is expressed as,

[0022] Y calc =α+β 1 X 1 +β 2 X 2

[0023] Among them, Y calc represents the theoretical speed, α represents the intercept of the model, β 1 represents the regression coefficient in the regression model, X 1 Indicates the actual oil pressure of the hydraulic system currently monitored in real time, β 2 represents the regression coefficient in the regression model, X 2 Indicates the current real-time monitored water inflow rate.

[0024] As a preferred solution of the method for monitoring parameters of a hydroelectric generator set speed governor based on real-time data described in the present invention, wherein: the generation of a control signal includes real-time monitoring of the actual pressure of the hydraulic system and comparing it with the optimal hydraulic oil pressure required for the theoretical speed. If the actual pressure of the hydraulic system is less than a first pressure threshold, a control signal is generated to instruct the hydraulic pump to adjust the output pressure of the hydraulic oil according to a first preset pressure adjustment standard; if the actual pressure of the hydraulic system is greater than or equal to the first pressure threshold and less than or equal to the second pressure threshold, a control signal is generated to instruct the hydraulic pump to adjust the hydraulic oil pressure according to a second preset pressure adjustment standard; if the actual pressure of the hydraulic system is greater than the second pressure threshold, a control signal is generated to instruct the hydraulic pump to adjust the hydraulic oil output according to a third preset pressure adjustment standard.

[0025] As a preferred solution of the method for monitoring parameters of a hydroelectric generator set speed governor based on real-time data described in the present invention, wherein: after the hydraulic oil pressure is adjusted to the theoretical required range, the actual opening of the water inlet valve is monitored and compared with the opening required for the theoretical speed. If the actual opening of the valve is less than the first valve opening threshold, a control signal is generated, and the actuator is instructed to adjust the valve opening according to the first preset opening adjustment standard to increase the water inlet; if the valve opening is greater than or equal to the first valve opening threshold and less than or equal to the second valve opening threshold, a control signal is generated, and the actuator is instructed to adjust the opening according to the second preset opening adjustment standard; if the actual opening of the valve is greater than the second valve opening threshold, a control signal is generated, and the actuator is instructed to adjust the valve according to the third preset opening adjustment standard to reduce the water inlet until the theoretical opening requirement is reached.

[0026] Another object of the present invention is to provide a hydraulic generator set speed governor parameter monitoring system based on real-time data, which can solve the problems in the existing hydraulic generator set speed governor system that cannot accurately adjust the hydraulic oil pressure and the water inlet valve opening in real time, and cannot perform fault prediction and load transfer, improve the adjustment accuracy and response speed, and enhance the fault prediction and processing capabilities.

[0027] To solve the above technical problems, the present invention provides the following technical solutions: a real-time data-based parameter monitoring system for a hydroelectric generator set speed governor, comprising: a data acquisition module, a data processing module, a parameter analysis module and a control and adjustment module; the data acquisition module is used to arrange sensors in the hydroelectric generator set speed governor to collect operating data in real time; the data processing module is used to convert the operating data into a digital signal, filter the received digital signal, remove invalid data, and format the data into a standard format, and store it in chronological order; the parameter analysis module is used to analyze the formatted data using a multivariate linear regression algorithm, establish a parameter association model and calculate theoretical operating parameter values; the control and adjustment module is used to generate a control signal according to the data analysis results, and adjust the hydraulic oil pressure and valve opening through an actuator.

[0028] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for monitoring parameters of a speed governor of a hydroelectric generator set based on real-time data as described above are implemented.

[0029] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for monitoring parameters of a speed governor of a hydroelectric generator set based on real-time data as described above.

[0030] Beneficial effects of the present invention: The method for monitoring parameters of a speed governor of a hydroelectric generator set based on real-time data provided by the present invention collects operating data of the hydroelectric generator set in real time, dynamically monitors and adjusts the hydraulic oil pressure and the opening of the water inlet valve, can quickly respond to changes in the load of the power grid, accurately adjust the speed of the generator set, and ensure the improvement of power generation efficiency.

[0031] After the fault prediction signal is generated, the hydraulic system and water inlet valve are automatically adjusted, and the standby generator set is started to realize load transfer operation, ensure the continuous and stable power supply of the power grid, and reduce the impact of the fault on power output.

[0032] The accuracy and reliability of the collected data are ensured through signal filtering, data formatting and redundancy checking mechanisms, thus providing high-quality data support for the calculation of regression models and fault mode libraries. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0034] Figure 1 An overall flow chart of a method for monitoring parameters of a hydroelectric generator set speed governor based on real-time data provided by one embodiment of the present invention.

[0035] Figure 2 This is an overall structural diagram of a hydroelectric generator set speed governor parameter monitoring system based on real-time data provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0036] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0037] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0038] Example 1

[0039] Reference Figure 1, is an embodiment of the present invention, and provides a method for monitoring parameters of a speed governor of a hydroelectric generator set based on real-time data, comprising:

[0040] Arrange sensors on the speed governor of the hydroelectric generator set to collect operating data in real time;

[0041] Convert the operation data into digital signals, filter the received digital signals, remove invalid data, and format the data into a standard format and store them in chronological order;

[0042] The formatted data were analyzed using a multivariate linear regression algorithm to establish a parameter association model and calculate theoretical operating parameter values;

[0043] Based on the data analysis results, a control signal is generated to adjust the hydraulic oil pressure and valve opening through the actuator.

[0044] The sensors include a rotation speed sensor, a pressure sensor and a flow sensor.

[0045] The operating data includes the rotation speed of the hydro-generator set, the oil pressure of the hydraulic system and the water inlet flow of the turbine.

[0046] The storage in chronological order includes converting analog signals of the rotation speed, oil pressure of the hydraulic system and water inlet flow into digital signals through an analog-to-digital conversion unit, the accuracy of the analog-to-digital conversion is set to 10 bits and the sampling frequency is 1kHz;

[0047] After analog-to-digital conversion, a logic comparator is used to perform preliminary verification on the converted digital signal to determine whether the data is within the preset physical range and set upper and lower thresholds. If the data exceeds the threshold range, the data is discarded and marked as abnormal data. If the data does not exceed the threshold range, the data is marked as qualified data.

[0048] The qualified data enters the low-pass filter process, and the cut-off frequency is set to 50Hz. The data is filtered through a digital filter to filter out high-frequency noise above 50Hz and retain the valid signal;

[0049] The filtered data is checked according to the change rate, and the maximum change threshold Δ per second is set. By calculating the difference between adjacent sampling points, it is determined whether the data change rate exceeds the preset threshold. If the change rate exceeds the threshold, the data is marked as abnormal and excluded;

[0050] If the data changes normally, Kalman filtering is performed. In the Kalman filtering process, the prediction error threshold is set to ±2%. The current value is predicted based on the data at the previous moment, and the prediction error of each data point is calculated in real time. If the error exceeds the set threshold, the filtering process is continued until the error value drops within the set range.

[0051] The data after Kalman filtering enters the formatting process, and a timestamp accurate to milliseconds is attached. According to the set format, each set of data is organized into structured data containing timestamp, speed, oil pressure of the hydraulic system, and water inlet flow.

[0052] The formatted data is checked for timestamp continuity. The time interval between adjacent data is calculated to determine whether the timestamp of the data is within the allowable error range of ±0.5 milliseconds. If the time interval exceeds the range, the data is marked as discontinuous and the data with abnormal timestamp is supplemented using linear interpolation. The supplemented data is marked as valid data.

[0053] The valid data is checked by CRC32, and the check code is calculated and added. After the check is passed, the data is written into the main storage unit and simultaneously written into the redundant storage unit to form a redundant backup;

[0054] During the storage process, a periodic verification mechanism is set to perform verification on the stored data at a predetermined period. If the data in the main storage unit is inconsistent with the verification code, the backup data is extracted from the redundant storage unit and the erroneous data in the main storage unit is overwritten;

[0055] After the redundant data is recovered, the CRC32 check is performed again to ensure the integrity of the redundant data. After the check passes, the data recovery is completed;

[0056] If the verification still fails, the alarm mechanism is triggered, the error log is recorded and the operator is notified to intervene manually. The data anomaly records are stored in the log file for subsequent analysis and processing.

[0057] The oil pressure and water flow rate in the formatted data were extracted as independent variables, and the speed was taken as the dependent variable. The extracted data were used as input for the multiple linear regression model.

[0058] The multivariate linear regression algorithm is expressed as,

[0059] Y=α+β 1 X 1 +β 2 X 2 +∈

[0060] Among them, Y represents the speed, X 1 Indicates oil pressure, X 2 represents the inlet flow rate, α is the intercept of the model, β 1 is the regression coefficient of oil pressure, β 2 is the regression coefficient of the inlet flow rate, ∈ is the error term;

[0061] Use the input data to fit the multivariate linear regression model, input the extracted time series data into the regression model, and use the least squares method to fit α, β 1 and β 2Perform optimization calculations.

[0062] By fitting historical data and real-time data, the linear relationship between the independent variables (oil pressure and water inlet flow) and the dependent variable (speed), that is, the optimal value of the regression coefficient, is obtained.

[0063] Use the fitted regression model to calculate the theoretical speed value under the current working conditions in real time:

[0064] The theoretical operating parameter value is expressed as,

[0065] Y calc =α+β 1 X 1 +β 2 X 2

[0066] Among them, Y calc represents the theoretical speed, α represents the intercept of the model, β 1 represents the regression coefficient in the regression model, X 1 Indicates the actual oil pressure of the hydraulic system currently monitored in real time, β 2 represents the regression coefficient in the regression model, X 2 Indicates the current real-time monitored water inflow rate.

[0067] The generating of the control signal comprises real-time monitoring of the actual pressure of the hydraulic system and comparing it with the optimal hydraulic oil pressure required for the theoretical speed; if the actual pressure of the hydraulic system is less than a first pressure threshold, a control signal is generated to instruct the hydraulic pump to adjust the output pressure of the hydraulic oil according to a first preset pressure adjustment standard; if the actual pressure of the hydraulic system is greater than or equal to the first pressure threshold and less than or equal to the second pressure threshold, a control signal is generated to instruct the hydraulic pump to adjust the hydraulic oil pressure according to a second preset pressure adjustment standard; if the actual pressure of the hydraulic system is greater than the second pressure threshold, a control signal is generated to instruct the hydraulic pump to adjust the hydraulic oil output according to a third preset pressure adjustment standard.

[0068] After the hydraulic oil pressure is adjusted to the theoretical required range, the actual opening of the water inlet valve is monitored and compared with the opening required for the theoretical speed. If the actual opening of the valve is less than the first valve opening threshold, a control signal is generated to instruct the actuator to adjust the valve opening according to the first preset opening adjustment standard to increase the water inlet; if the valve opening is greater than or equal to the first valve opening threshold and less than or equal to the second valve opening threshold, a control signal is generated to instruct the actuator to adjust the opening according to the second preset opening adjustment standard; if the actual opening of the valve is greater than the second valve opening threshold, a control signal is generated to instruct the actuator to adjust the valve according to the third preset opening adjustment standard to reduce the water inlet until the theoretical opening requirement is reached.

[0069] After completing the initial adjustment of pressure and valve opening, monitor the hydraulic pressure and water inlet valve opening in real time, record the current status and compare it with the theoretical value again. If any deviation is found (for example, the deviation between the hydraulic pressure or valve opening and the theoretical value exceeds the allowable range), a fine-tuning control signal is generated for detailed adjustment. The system will adjust the pressure first, then adjust the valve, and make corrections step by step until both the pressure and opening reach the theoretical state to ensure the operating stability of the generator set.

[0070] Through this dynamic adjustment mechanism, the system can effectively control the hydraulic oil pressure and valve opening, ensuring that the operating state of the generator set speed governor is always consistent with the calculated theoretical speed, thereby maintaining efficient and stable operation of the generator set.

[0071] After the pressure regulation and valve opening adjustment are completed, the hydraulic pressure, water inlet valve opening, generator speed and other parameters are monitored in real time. These monitored data are not only used to control and adjust the operating status of the equipment, but also used as input data for comparison with the fault mode library.

[0072] The established fault mode library contains typical fault characteristics based on previously collected historical data and adjusted operating data. Each fault mode corresponds to a specific set of operating parameter ranges or characteristics (such as a sudden abnormal increase in hydraulic pressure or a large fluctuation in speed).

[0073] The real-time collected data will be continuously compared with various fault characteristics in the fault mode library. By comparing the adjusted hydraulic pressure, valve opening and other data, it is determined whether there is a situation that deviates from the normal range and meets a certain fault mode. If the monitored data matches a pattern in the fault mode library, the system generates a fault prediction signal. The generation of this fault signal is based on the real-time monitoring and adjustment results of pressure and valve opening in the previous steps to ensure the accuracy of fault prediction.

[0074] When the system generates a fault prediction signal, it starts to perform corresponding emergency operations according to the type and severity of the signal. At this time, the fault signal is not only judged by parameter deviation, but also further confirmed by the actual operating status after adjustment. If the system confirms that the fault cannot be alleviated by adjusting the hydraulic pressure and valve opening, it will automatically enter the fault handling mode.

[0075] First, according to the fault signal, continue to adjust the opening of the water inlet valve and the hydraulic system pressure to ensure basic stability under fault conditions. If the fault signal indicates that the fault is serious, the system will gradually close the water inlet valve of the faulty unit and start the backup generator set to gradually transfer the grid load from the faulty unit to the backup unit. This load transfer operation is based on the results of real-time monitoring and adjustment of pressure and opening in the previous steps to ensure smooth load transfer operation.

[0076] In the specific load transfer process, the operating power of the faulty unit is first reduced to alleviate the further expansion of the fault by reducing the water inlet flow, and the standby unit is started to supplement the power output of the power grid. The entire load transfer operation is based on the type and severity of the fault signal, and the water inlet valve and hydraulic pressure are precisely adjusted to ensure a smooth load transition.

[0077] Example 2

[0078] Reference Figure 2 , is an embodiment of the present invention, providing a hydroelectric generator set speed governor parameter monitoring system based on real-time data, comprising:

[0079] Data acquisition module 100, data processing module 200, parameter analysis module 300 and control and adjustment module 400;

[0080] The data acquisition module 100 is used to arrange sensors on the speed governor of the hydroelectric generator set to collect operation data in real time;

[0081] The data processing module 200 is used to convert the operation data into digital signals, filter the received digital signals, remove invalid data, and format the data into a standard format and store them in chronological order;

[0082] The parameter analysis module 300 is used to analyze the formatted data using a multivariate linear regression algorithm, establish a parameter association model and calculate theoretical operating parameter values;

[0083] The control and regulation module 400 is used to generate a control signal according to the data analysis result, and regulate the hydraulic oil pressure and valve opening through the actuator.

[0084] Example 3

[0085] An embodiment of the present invention is different from the first two embodiments in that:

[0086] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0087] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0088] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0089] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0090] Example 4

[0091] As an embodiment of the present invention, a method for monitoring parameters of a speed governor of a hydroelectric generator set based on real-time data is provided. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0092] Simulation experiments were carried out using a traditional SCADA system, a PLC system and the method of the present invention, using the same type of hydroelectric generating units, and each system operated independently.

[0093] The grid load varies from 10% to 50% of the rated power of the generator set, and a hydraulic system pressure abnormality fault is randomly introduced.

[0094] Each system monitors speed, hydraulic system pressure, water inlet valve opening, fault response time and load transfer.

[0095] The SCADA system evaluates the current operating status by regularly collecting and monitoring the operating parameters of the generator set (such as speed, hydraulic pressure, and water inlet flow). The collection frequency of each parameter is usually 1 second. When the grid load changes, the SCADA system performs feedback control on the hydraulic oil pressure and the water inlet valve opening according to the set threshold rules. The adjustment process depends on the pre-set control logic, and the adjustment frequency is once every 3-5 seconds. If the hydraulic system pressure is detected to be abnormal, the SCADA system will make adjustments according to preset rules. The system will gradually reduce the hydraulic oil pressure, reduce the water inlet valve opening manually or through rules, and reduce power output. Usually manual intervention is required for fault handling and manual start of the standby generator set. The SCADA system records and processes data regularly, but there may be certain delays or collection failures. Data processing is mainly used for load reporting.

[0096] The PLC system is based on the high-speed acquisition module of the logic controller, and usually collects the real-time parameters of the generator set (such as speed, oil pressure, and water inlet flow) in milliseconds. The PLC system implements closed-loop control according to the set control program. Whenever the load changes, the system adjusts the hydraulic oil pressure and the water inlet valve opening according to the set control model. The adjustment frequency is higher than that of the SCADA system, and usually several adjustments can be performed per second. When the hydraulic system pressure is abnormal, the PLC system automatically performs simple load reduction operations through preset logic, but lacks intelligent fault prediction. The system still needs to rely on manual or preset programs to handle serious faults and start standby generator sets. The PLC system has good data acquisition and processing capabilities and less delays, but due to frequent data acquisition, data loss may occur.

[0097] Based on the real-time data acquisition system of the present invention, the speed regulator continuously monitors the operating parameters of the generator set (such as speed, hydraulic oil pressure and water inlet flow), and the acquisition frequency is milliseconds, ensuring that the current state of the equipment can be obtained in real time. The method of the present invention dynamically adjusts the hydraulic pressure and the opening of the water inlet valve through a regression model. When the load changes, the system immediately calculates the theoretical speed based on the collected data, and generates a control signal based on the error, automatically adjusts the hydraulic oil pressure and the valve opening, and ensures that the generator set responds quickly to the change of the grid load, and the adjustment frequency is milliseconds. In the event of a fault, the present invention automatically predicts and generates a fault signal based on the fault mode library. Before the fault occurs, by predicting the system abnormality in advance, the hydraulic oil pressure and valve opening are automatically adjusted, and the standby generator set is started to complete the load transfer operation without manual intervention. Through signal filtering, data formatting, redundancy checking and other technologies, the present invention ensures the integrity and accuracy of the data and avoids data loss or delay problems. The experimental results are shown in Table 1.

[0098] Table 1 Comparison of experimental results

[0099]

[0100] SCADA and PLC systems rely on simple feedback control for load regulation and fault handling, cannot predict faults in real time, and have a long load response time. Especially in the process of load transfer, these systems mostly rely on preset rules or manual operations, and have low response efficiency. In terms of data processing, these two systems have certain delays or data loss problems, which affect the accuracy of system regulation.

[0101] By real-time monitoring of the operating data of the hydro-generator set, the method of the present invention can quickly respond to load changes, adjust the hydraulic oil pressure and the water inlet valve opening, significantly improve the adjustment accuracy, and control the error within ±0.5%. This is of great help to the load stability and power generation efficiency of the power grid.

[0102] The present invention realizes automatic fault prediction through the fault mode library, can accurately generate fault prediction signals before the fault occurs, and quickly start the backup generator set to achieve load transfer within 1 second. This not only avoids the risk of grid instability, but also improves the efficiency of fault handling.

[0103] Through signal filtering, data formatting and redundancy checking, the method of the present invention ensures the accuracy and integrity of the data, avoids the possible delay or data loss problems in traditional systems, and provides high-quality data support for model calculation and system adjustment. The present invention achieves more efficient load response and fault handling capabilities through real-time data acquisition and adjustment technology.

[0104] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for monitoring parameters of a speed governor of a hydroelectric generator set based on real-time data, characterized in that: include: Arrange sensors on the speed governor of the hydroelectric generator set to collect operating data in real time; Convert the operation data into digital signals, filter the received digital signals, remove invalid data, and format the data into a standard format and store them in chronological order; The formatted data were analyzed using a multivariate linear regression algorithm to establish a parameter association model and calculate theoretical operating parameter values; Based on the data analysis results, a control signal is generated to adjust the hydraulic oil pressure and valve opening through the actuator.

2. The method for monitoring parameters of a speed governor of a hydroelectric generator set based on real-time data according to claim 1, characterized in that: The sensors include a rotation speed sensor, a pressure sensor and a flow sensor.

3. The method for monitoring parameters of a speed governor of a hydroelectric generator set based on real-time data according to claim 2, characterized in that: The operating data includes the rotation speed of the hydro-generator set, the oil pressure of the hydraulic system and the water inlet flow of the turbine.

4. The method for monitoring parameters of a speed governor of a hydroelectric generator set based on real-time data as claimed in claim 3, characterized in that: The storage in chronological order includes converting analog signals of the rotation speed, oil pressure of the hydraulic system and water inlet flow into digital signals through an analog-to-digital conversion unit, the accuracy of the analog-to-digital conversion is set to 10 bits and the sampling frequency is 1kHz; After analog-to-digital conversion, a logic comparator is used to perform preliminary verification on the converted digital signal to determine whether the data is within the preset physical range and set upper and lower thresholds. If the data exceeds the threshold range, the data is discarded and marked as abnormal data. If the data does not exceed the threshold range, the data is marked as qualified data. The qualified data enters the low-pass filter process, and the cut-off frequency is set to 50Hz. The data is filtered through a digital filter to filter out high-frequency noise above 50Hz and retain the valid signal; The filtered data is checked according to the change rate, and the maximum change threshold Δ per second is set. By calculating the difference between adjacent sampling points, it is determined whether the data change rate exceeds the preset threshold. If the change rate exceeds the threshold, the data is marked as abnormal and excluded; If the data changes normally, Kalman filtering is performed. In the Kalman filtering process, the prediction error threshold is set to ±2%. The current value is predicted based on the data at the previous moment, and the prediction error of each data point is calculated in real time. If the error exceeds the set threshold, the filtering process is continued until the error value drops within the set range. The data after Kalman filtering enters the formatting process, and a timestamp accurate to milliseconds is attached. According to the set format, each set of data is organized into structured data containing timestamp, speed, oil pressure of the hydraulic system, and water inlet flow.

5. The method for monitoring parameters of a speed governor of a hydroelectric generator set based on real-time data according to claim 4, characterized in that: The theoretical operating parameter value is expressed as, Y calc =α+β1X1+β2X2 Among them, Y calc Represents the theoretical speed, α represents the intercept of the model, β1 represents the regression coefficient in the regression model, X1 represents the actual oil pressure of the hydraulic system currently monitored in real time, β2: represents the regression coefficient in the regression model, and X2 represents the water inlet flow currently monitored in real time.

6. The method for monitoring parameters of a speed governor of a hydroelectric generator set based on real-time data according to claim 5, characterized in that: The generating of the control signal comprises real-time monitoring of the actual pressure of the hydraulic system and comparing it with the optimal hydraulic oil pressure required for the theoretical speed; if the actual pressure of the hydraulic system is less than a first pressure threshold, a control signal is generated to instruct the hydraulic pump to adjust the output pressure of the hydraulic oil according to a first preset pressure adjustment standard; if the actual pressure of the hydraulic system is greater than or equal to the first pressure threshold and less than or equal to the second pressure threshold, a control signal is generated to instruct the hydraulic pump to adjust the hydraulic oil pressure according to a second preset pressure adjustment standard; if the actual pressure of the hydraulic system is greater than the second pressure threshold, a control signal is generated to instruct the hydraulic pump to adjust the hydraulic oil output according to a third preset pressure adjustment standard.

7. The method for monitoring parameters of a speed governor of a hydroelectric generator set based on real-time data according to claim 6, characterized in that: After the hydraulic oil pressure is adjusted to the theoretical required range, the actual opening of the water inlet valve is monitored and compared with the opening required for the theoretical speed. If the actual opening of the valve is less than the first valve opening threshold, a control signal is generated to instruct the actuator to adjust the valve opening according to the first preset opening adjustment standard to increase the water inlet; if the valve opening is greater than or equal to the first valve opening threshold and less than or equal to the second valve opening threshold, a control signal is generated to instruct the actuator to adjust the opening according to the second preset opening adjustment standard; if the actual opening of the valve is greater than the second valve opening threshold, a control signal is generated to instruct the actuator to adjust the valve according to the third preset opening adjustment standard to reduce the water inlet until the theoretical opening requirement is reached.

8. A system using the method for monitoring parameters of a hydroelectric generator speed governor based on real-time data as claimed in any one of claims 1 to 7, characterized in that: include: A data acquisition module (100), a data processing module (200), a parameter analysis module (300) and a control and adjustment module (400); The data acquisition module (100) is used to arrange sensors on the speed governor of the hydroelectric generator set to collect operating data in real time; The data processing module (200) is used to convert the operation data into digital signals, filter the received digital signals, remove invalid data, format the data into a standard format, and store them in chronological order; The parameter analysis module (300) is used to analyze the formatted data using a multivariate linear regression algorithm, establish a parameter association model and calculate theoretical operating parameter values; The control and adjustment module (400) is used to generate a control signal according to the data analysis result, and adjust the hydraulic oil pressure and valve opening through the actuator.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for monitoring parameters of a hydroelectric generator set speed governor based on real-time data as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for monitoring parameters of a hydroelectric generator set speed governor based on real-time data described in any one of claims 1 to 7 are implemented.

Images