System and method for detecting rotating speed of hydroelectric generating set based on machine vision

Abstract

The invention relates to the technical field of hydroelectric generation, in particular to a hydroelectric generating set rotating speed detection system and method based on machine vision, and the method comprises the steps: obtaining hydraulic time sequence data and power grid time sequence data, and obtaining marker position time sequence image data of a rotating part of a hydroelectric generating set; extracting a time sequence corner characteristic quantity of the marker in the marker position time sequence image by utilizing a machine vision technology, and calculating to obtain unit rotating speed time sequence data; based on the hydraulic time sequence data, the power grid time sequence data and the unit rotating speed time sequence data, evaluating the input fluctuation relevance and the output fluctuation relevance of the unit rotating speed; based on the input fluctuation relevance and the output fluctuation relevance, evaluating the fluctuation coordination of the hydraulic power and the power grid aiming at keeping the rotating speed of the unit stable; and performing unit rotating speed fluctuation early warning based on a fluctuation coordination evaluation result of the hydraulic power and the power grid. According to the method, the fluctuation coordination of the input side and the output side of the unit is quantified, so that the accuracy and the reliability of unit rotating speed fluctuation early warning are improved.

Description

Technical Field

[0001] This application relates to the technical field of hydropower generation, and particularly to a machine vision-based rotational speed detection system and method for hydropower generating units. Background Art

[0002] With the rapid development of renewable energy, hydropower generating units, as an important part of the power system, the stability of their operation and the coordination with the power grid are the keys to ensuring power supply. Variable-speed hydropower generating units have the advantages of high partial-load operation efficiency, good unit stability, fast power regulation speed, and no reverse regulation during the regulation process. Moreover, they have a strong fit with new energy with high randomness. Variable-speed hydropower generating units are playing an increasingly important role in promoting the consumption of new energy.

[0003] Compared with conventional hydropower generating units, the rotational speed of variable-speed hydropower generating units can vary continuously during operation, and this continuous change in rotational speed also brings new challenges to the detection of unit rotational speed. Traditional methods for detecting unit rotational speed mainly rely on sensors installed at the shaft end or inside the generator, such as magnetoelectric or optoelectronic rotational speed sensors, which are vulnerable to environmental interference and drift during long-term operation. The development of machine vision technology provides a new solution for non-contact rotational speed measurement. By performing image processing on the position changes of markers on the surface of the rotating components of the unit, rotational speed time-series data can be extracted with high precision, avoiding the complexity and maintenance problems brought by the installation of traditional sensors.

[0004] At the same time, the existing technology only focuses on the operating state of the unit itself when detecting the unit rotational speed. However, the unit rotational speed is affected by both the input power fluctuation on the hydraulic side and the load fluctuation on the grid side. For example, when a grid voltage dip fault occurs, the energy output from the unit to the grid is blocked, which is likely to cause the unit rotational speed to increase rapidly. However, the existing technology lacks a comprehensive analysis of the input-side fluctuation and the output-side fluctuation when detecting the unit rotational speed, resulting in insufficient accuracy and reliability of the unit rotational speed fluctuation warning. Summary of the Invention

[0005] In order to overcome the defects and deficiencies existing in the prior art, this application provides a machine vision-based rotational speed detection system and method for hydropower generating units, which improves the accuracy and reliability of the unit rotational speed fluctuation warning by quantifying the input-side fluctuation correlation and the output-side fluctuation correlation that affect the stability of the unit rotational speed and evaluating the fluctuation coordination between the input side and the output side.

[0006] To achieve the above object, this application adopts the following technical solutions: In the first aspect, this application provides a machine vision-based rotational speed detection method for hydropower generating units, including the following steps: Obtain hydraulic time - series data and grid time - series data related to the operation of a hydraulic generator set, and obtain time - series image data of the marker positions of the rotating components of the hydraulic generator set; Use machine vision technology to extract the time - series angular feature quantities of the markers in the time - series image of the marker positions and calculate the time - series data of the unit speed; Evaluate the input fluctuation correlation and output fluctuation correlation of the unit speed based on the hydraulic time - series data, grid time - series data, and unit speed time - series data; Evaluate the fluctuation coordination between the hydraulics and the grid with the goal of maintaining the stability of the unit speed based on the input fluctuation correlation and output fluctuation correlation; Perform early warning of unit speed fluctuations based on the evaluation results of the fluctuation coordination between the hydraulics and the grid.

[0007] Optionally, the extraction of the time - series angular feature quantities of the markers in the time - series image of the marker positions and the calculation of the time - series data of the unit speed include: Perform image pre - processing on the obtained time - series image data of the marker positions. The image pre - processing includes image background removal, image binarization, and image filtering; Extract the markers in the pre - processed time - series image of the marker positions through a feature extraction algorithm and track the extracted markers using a marker trajectory centroid localization method based on radial Gaussian fitting to obtain the time - series angular feature quantities of the markers; Calculate the angle difference through the first - order difference of adjacent time - series angular feature quantities, and obtain the time - series data of the unit speed by dividing the angle difference by the time interval between adjacent time - series angular feature quantities.

[0008] Optionally, the evaluation of the input fluctuation correlation and output fluctuation correlation of the unit speed includes: Perform detrending processing on the hydraulic time - series data, grid time - series data, and unit speed time - series data respectively and extract the fluctuation quantities to obtain hydraulic fluctuation time - series data, grid fluctuation time - series data, and unit speed fluctuation time - series data. The detrending processing includes any one of the HP filtering method and the moving average method; Perform correlation analysis on the hydraulic fluctuation time - series data and the grid fluctuation time - series data respectively with the corresponding unit speed fluctuation time - series data to obtain the input fluctuation correlation index and the output fluctuation correlation index, which are used to evaluate the input fluctuation correlation and output fluctuation correlation of the unit speed.

[0009] Optionally, the performing correlation analysis on the hydraulic fluctuation time - series data and the grid fluctuation time - series data respectively with the corresponding unit speed fluctuation time - series data includes: Using the time-domain analysis method, perform time-delay correlation analysis on the hydraulic fluctuation time-series data and the grid fluctuation time-series data respectively with the corresponding unit speed fluctuation time-series data. Take the maximum value of the cross-correlation coefficient between the hydraulic fluctuation time-series data and the unit speed fluctuation time-series data as the input time-delay correlation degree, and take the maximum value of the cross-correlation coefficient between the grid fluctuation time-series data and the unit speed fluctuation time-series data as the output time-delay correlation degree; Using the frequency-domain analysis method, perform coherence analysis on the hydraulic fluctuation time-series data and the grid fluctuation time-series data respectively with the corresponding unit speed fluctuation time-series data. Take the coherence coefficient between the hydraulic fluctuation time-series data and the unit speed fluctuation time-series data as the input coherence coefficient, and take the coherence coefficient between the grid fluctuation time-series data and the unit speed fluctuation time-series data as the output coherence coefficient; Take the product of the input time-delay correlation degree and the input coherence coefficient as the input fluctuation correlation index, and take the product of the output time-delay correlation degree and the output coherence coefficient as the output fluctuation correlation index.

[0010] Optionally, the evaluation of the fluctuation coordination of the hydraulic power and the grid with the goal of maintaining the stability of the unit speed includes: Obtain the input fluctuation correlation index and the output fluctuation correlation index of the unit speed; Calculate the fluctuation coordination index of the hydraulic power and the grid through the input fluctuation correlation index and the output fluctuation correlation index. The formula for calculating the fluctuation coordination index is: ; In the formula represents the input fluctuation correlation index, represents the output fluctuation correlation index, represents the fluctuation coordination index, which is used to evaluate the fluctuation coordination of the hydraulic power and the grid.

[0011] Optionally, the early warning of the unit speed fluctuation based on the evaluation result of the fluctuation coordination of the hydraulic power and the grid includes: Obtain the fluctuation coordination index of the hydraulic power and the grid. When the fluctuation coordination index is greater than or equal to the preset fluctuation coordination threshold, give an early warning of the unit speed fluctuation. When the fluctuation coordination index is less than the preset fluctuation coordination threshold, do not give an early warning of the unit speed fluctuation.

[0012] In a second aspect, the present application provides a machine vision-based hydraulic generator unit speed detection system, including: A data acquisition module, configured to acquire hydraulic time-series data and grid time-series data related to the operation of the hydraulic generator unit, and acquire the time-series image data of the position of the marker of the rotating component of the hydraulic generator unit; A speed calculation module, configured to use machine vision technology to extract the time-series rotation angle feature quantity of the marker in the time-series image of the marker position and calculate the unit speed time-series data; An association evaluation module, configured to evaluate the input fluctuation association and output fluctuation association of the unit speed based on hydraulic time-series data, power grid time-series data, and unit speed time-series data; A coordination evaluation module, configured to evaluate the fluctuation coordination between the hydraulics and the power grid with the goal of maintaining the stability of the unit speed based on the input fluctuation association and output fluctuation association; A speed fluctuation warning module, configured to perform warning of unit speed fluctuations based on the evaluation result of the fluctuation coordination between the hydraulics and the power grid.

[0013] Thirdly, the present application provides an electronic device, including: a processor and a memory, wherein, a computer program that can be called by the processor is stored in the memory, and the processor executes a method for detecting the speed of a hydraulic generator set using machine vision by calling the computer program stored in the memory.

[0014] Fourthly, the present application provides a computer-readable storage medium, storing instructions, when the instructions run on a computer, enabling the computer to execute a method for detecting the speed of a hydraulic generator set using machine vision.

[0015] Compared with the prior art, the present application has the following advantages and beneficial effects: The present application uses machine vision technology to extract the time-series rotation angle feature quantity of the marker in the time-series image of the marker position and calculates the unit speed time-series data, improving the robustness of the unit speed detection. By quantifying the fluctuation association on the hydraulic input side and the fluctuation association on the power grid output side that affect the stability of the unit speed and evaluating the fluctuation coordination between the input side and the output side, the accuracy and reliability of the unit speed fluctuation warning are effectively improved. Description of the Drawings

[0016] By reading the detailed description of the non-limiting embodiments with reference to the following drawings, other features, objectives, and advantages of the present application will become more obvious: Figure 1 is an overall flow schematic diagram of a method for detecting the speed of a hydraulic generator set using machine vision provided by an embodiment of the present application; Figure 2 is a structural schematic diagram of a system for detecting the speed of a hydraulic generator set using machine vision provided by an embodiment of the present application; Figure 3 is a structural schematic diagram of the electronic device provided by an embodiment of the present application. Detailed Embodiments

[0017] The technical solution of the present application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. Without conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other.

[0018] Please refer to Figure 1 , Figure 1 which is a schematic diagram of the overall process of a method for detecting the rotational speed of a hydraulic generator set using machine vision provided by an embodiment of the present application, specifically including the following steps: S110: Obtain hydraulic time-series data and power grid time-series data related to the operation of the hydraulic generator set, and obtain time-series image data of the marker positions of the rotating components of the hydraulic generator set.

[0019] S120: Use machine vision technology to extract the time-series rotation angle feature quantity of the marker in the time-series image of the marker position and calculate the time-series data of the unit rotational speed; Extracting the time-series rotation angle feature quantity of the marker in the time-series image of the marker position and calculating the time-series data of the unit rotational speed includes: Perform image preprocessing on the obtained time-series image data of the marker position. The image preprocessing includes image background removal, image binarization, and image filtering; In an embodiment of the present application, the acquired image contains both a rotating marker and background objects at the same time. Among them, the background objects are redundant information. According to the concept of pixel connectivity, it is judged whether a pixel is connected to an edge pixel, and then the background objects are removed. Among them, connectivity means that between any two pixels in a connected set, there exists a connected path entirely composed of the elements of this set. A connected path is a path that can move between adjacent pixels. There are two alternative criteria for connectivity, namely 4-connectivity and 8-connectivity; In an embodiment of the present application, in order to transform the time-series image of the marker position into a binary image, the image should first be transformed into a grayscale image, and then an appropriate threshold is selected to perform binarization processing on the image. The specific process of binarization processing is as follows: Set a certain threshold T. Binarization processing is to divide the image into two parts with T. The pixel group greater than T takes the value 1, and the pixel group less than T takes the value 0, so as to divide the image into two regions with only the target object and the black background left. Through binarization processing, the detection object is highlighted from the complex image background. The binary data matrix makes the detection algorithm simple and easy to implement; Extract the markers in the preprocessed time-series images of the marker positions through a feature extraction algorithm, and use the centroid positioning method of the marker trajectory based on radial Gaussian fitting to track the extracted markers, obtaining the time-series angular feature quantities of the markers; In an embodiment of the present application, when extracting the markers of the rotating component, a straight line is used to represent the position of the rotating marker. Since the shape of the marker is long and strip-shaped, it is reasonable that the straight line is near the midline of the rotating marker image, which is convenient for the implementation of the detection algorithm. The straight line representing the position of the rotating marker is represented by the regression line obtained by the least squares method; In an embodiment of the present application, for the centroid positioning method of the marker trajectory based on radial Gaussian fitting, an edge positioning method based on the local region effect is adopted to obtain the center of the least squares fitting circle of the marker motion trajectory, and then the centroid positioning method of the marker trajectory based on radial Gaussian fitting is used to obtain a more accurate marker motion trajectory. The specific steps include: Taking the initially detected marker position as the center, establish a local region of interest (ROI); taking the current marker center point as the origin within the ROI, sample the brightness values outward with different radii; calculate the average brightness corresponding to each radius to obtain the radial brightness distribution curve; use the radial Gaussian function to describe the brightness distribution of the marker; use the nonlinear least squares method (such as the Levenberg-Marquardt algorithm) to fit the radial Gaussian function; repeat the above steps to obtain the accurate centroid position of the marker in each frame of the image; Calculate the angle difference through the first-order difference of adjacent time-series angular feature quantities, and obtain the unit speed time-series data by dividing the angle difference by the time interval between adjacent time-series angular feature quantities.

[0020] S130: Evaluate the input fluctuation correlation and output fluctuation correlation of the unit speed based on the hydraulic time-series data, grid time-series data, and unit speed time-series data; Extract the fluctuation quantities corresponding to the hydraulic time series data, grid time series data, and unit speed time series data through detrending, and use time domain and frequency domain analysis methods to calculate the input fluctuation correlation index and output fluctuation correlation index. Quantify the impact of hydraulic fluctuations and grid fluctuations on the unit speed stability through the correlation index. Specifically, the input fluctuation correlation index reflects the degree of influence of fluctuations in hydraulic parameters (such as head, water flow rate, etc.) on the unit speed, while the output fluctuation correlation index measures the effect of load changes on the grid side on the unit speed. For example, when the grid load changes, the balance relationship between the original output power of the unit and the grid load is broken. If the hydraulic parameters on the input side of the unit do not change, the unit speed will be affected by the grid load change, resulting in an increase or decrease in the unit speed. Calculate the input fluctuation correlation index and output fluctuation correlation index to provide data support for evaluating the fluctuation coordination between hydraulics and the grid, thereby constructing a more accurate unit speed fluctuation early warning mechanism, discovering potential risks that may lead to unstable operation in advance, and evaluating the input fluctuation correlation and output fluctuation correlation of the unit speed, including: Perform detrending on the hydraulic time series data, grid time series data, and unit speed time series data respectively and extract the fluctuation quantities to obtain the hydraulic fluctuation time series data, grid fluctuation time series data, and unit speed fluctuation time series data. The detrending process includes any one of the HP filtering method and the moving average method; Perform correlation analysis on the hydraulic fluctuation time series data and grid fluctuation time series data respectively with the corresponding unit speed fluctuation time series data to obtain the input fluctuation correlation index and output fluctuation correlation index for evaluating the input fluctuation correlation and output fluctuation correlation of the unit speed; Perform correlation analysis on the hydraulic fluctuation time series data and grid fluctuation time series data respectively with the corresponding unit speed fluctuation time series data, including: Use the time domain analysis method to perform time-delay correlation analysis on the hydraulic fluctuation time series data and grid fluctuation time series data respectively with the corresponding unit speed fluctuation time series data. Take the maximum value of the cross-correlation coefficient between the hydraulic fluctuation time series data and the unit speed fluctuation time series data as the input time-delay correlation degree, and take the maximum value of the cross-correlation coefficient between the grid fluctuation time series data and the unit speed fluctuation time series data as the output time-delay correlation degree. Taking the input time-delay correlation degree as an example, the calculation process of the input time-delay correlation degree is: (1)Calculate the cross-correlation coefficients between the hydraulic fluctuation time series data and the unit speed fluctuation time series data at different time-delay values : ; In the formula represents the time node corresponding hydraulic fluctuation time series data, represents the time-delay value, represents the number of time nodes, represents the average value of the hydraulic fluctuation time series data, represents the unit speed fluctuation time series data at the moment represents the average value of the unit speed fluctuation time series data, represents the standard deviation of the hydraulic fluctuation time series data, represents the standard deviation of the unit speed fluctuation time series data, represents that the time delay value is the cross - correlation coefficient at this time; (2) Take the maximum value of the cross - correlation coefficient between the hydraulic fluctuation time series data and the unit speed fluctuation time series data as the input time - delay correlation degree; Use the frequency - domain analysis method to perform coherence analysis on the hydraulic fluctuation time series data and the power grid fluctuation time series data respectively with the corresponding unit speed fluctuation time series data. Take the coherence coefficient between the hydraulic fluctuation time series data and the unit speed fluctuation time series data as the input coherence coefficient, and take the coherence coefficient between the power grid fluctuation time series data and the unit speed fluctuation time series data as the output coherence coefficient; Take the product of the input time - delay correlation degree and the input coherence coefficient as the input fluctuation correlation index, and take the product of the output time - delay correlation degree and the output coherence coefficient as the output fluctuation correlation index.

[0021] S140: Evaluate the fluctuation coordination of the water power and the power grid with the goal of maintaining the unit speed stable based on the input fluctuation correlation and the output fluctuation correlation; The speed of the hydro - generator unit is affected by both hydraulic inputs (such as water head, water flow rate) and power grid outputs (such as load fluctuations, voltage changes). When the mechanical power provided by the hydraulic system and the electrical power consumed by the power grid load maintain dynamic balance, it is beneficial to maintain the stability of the unit speed. The input fluctuation correlation and the output fluctuation correlation respectively characterize the influence intensity and response characteristics of the fluctuations on the hydraulic side and the power grid side on the unit speed. By comprehensively analyzing the fluctuation relationship between the hydraulic side and the power grid side, the matching degree between the hydraulic system and the power grid can be quantified, that is, the fluctuation coordination of the water power and the power grid, and thus provides a key basis for the early warning of the unit speed fluctuation. Evaluating the fluctuation coordination of the water power and the power grid with the goal of maintaining the unit speed stable includes: Obtain the input fluctuation correlation index and the output fluctuation correlation index of the unit speed; Calculate the fluctuation coordination index of the water power and the power grid through the input fluctuation correlation index and the output fluctuation correlation index. The formula for the fluctuation coordination index is: ; where represents the input fluctuation correlation index, represents the output fluctuation correlation index, Indicates the combined action intensity of the fluctuations on the input side and the output side on the rotational speed. Indicates the total intensity of the fluctuations on the input side and the output side, which is used for normalization. Indicates the fluctuation coordination index, which is used to evaluate the fluctuation coordination between hydropower and the power grid.

[0022] S150: Conduct early warning of the unit rotational speed fluctuation based on the evaluation result of the fluctuation coordination between hydropower and the power grid; The fluctuation coordination index is used to quantify the matching degree between the hydropower side and the power grid side. When this index is greater than the preset threshold, it indicates that the hydropower unit is difficult to effectively coordinate the fluctuations between hydropower and the power grid, and the risk of rotational speed fluctuation increases. It is necessary to take adjustment measures in a timely manner, such as adjusting the guide vane opening to control the water flow rate, optimizing the load distribution, or enabling auxiliary frequency modulation means. When the fluctuation coordination index is lower than the threshold, it means that the unit has sufficient adjustment margin and the risk of rotational speed fluctuation is relatively low, and no additional intervention is required. By constructing a unit rotational speed early warning mechanism, it helps to detect abnormal unit operation in advance, prevent frequency oscillation, overspeed or low-speed faults, and improve the safety and reliability of the operation of hydropower units. Conducting early warning of the unit rotational speed fluctuation based on the evaluation result of the fluctuation coordination between hydropower and the power grid includes: Obtain the fluctuation coordination index between hydropower and the power grid. When the fluctuation coordination index is greater than or equal to the preset fluctuation coordination threshold, conduct early warning of the unit rotational speed fluctuation. When the fluctuation coordination index is less than the preset fluctuation coordination threshold, do not conduct early warning of the unit rotational speed fluctuation.

[0023] In an embodiment of the present application, the value-taking method of setting parameters such as the preset fluctuation coordination threshold can also be: construct a data set by obtaining hydropower time series data, power grid time series data, and marker position time series image data of the rotating components of the hydropower unit, substitute it into the evaluation of the fluctuation coordination index, and at the same time obtain the judgment result of the expert on the fluctuation coordination between hydropower and the power grid. Import the evaluated fluctuation coordination index and the judgment result into the fitting software, and output the preset fluctuation coordination threshold that meets the maximum judgment accuracy rate.

[0024] Please refer to Figure 2 , Figure 2 is a schematic structural diagram of a machine vision-based rotational speed detection system for a hydropower generating unit provided by an embodiment of the present application. This embodiment provides a machine vision-based rotational speed detection system for a hydropower generating unit, including: A data acquisition module 210, which is used to obtain hydropower time series data and power grid time series data related to the operation of the hydropower generating unit, and obtain marker position time series image data of the rotating components of the hydropower generating unit; A rotational speed calculation module 220, which is used to extract the time series angular feature quantity of the marker in the marker position time series image by using machine vision technology and calculate the unit rotational speed time series data; The relevance evaluation module 230 is configured to evaluate the input fluctuation relevance and output fluctuation relevance of the unit speed based on the hydraulic time series data, grid time series data, and unit speed time series data; The coordination evaluation module 240 is configured to evaluate the fluctuation coordination between the hydraulics and the grid aiming at maintaining the stability of the unit speed based on the input fluctuation relevance and output fluctuation relevance; The speed fluctuation warning module 250 is configured to perform warning on the unit speed fluctuation based on the evaluation result of the fluctuation coordination between the hydraulics and the grid.

[0025] In the embodiment of the present application, the speed calculation module 220 is configured to use machine vision technology to extract the time series rotation angle feature quantity of the marker in the time series image of the marker position and calculate the unit speed time series data. Extracting the time series rotation angle feature quantity of the marker in the time series image of the marker position and calculating the unit speed time series data includes: Perform image preprocessing on the obtained time series image data of the marker position. The image preprocessing includes image background removal, image binarization, and image filtering; Extract the marker in the preprocessed time series image of the marker position through a feature extraction algorithm and track the extracted marker by using the centroid positioning method of the marker trajectory based on radial Gaussian fitting to obtain the time series rotation angle feature quantity of the marker; Calculate the angle difference through the first-order difference of adjacent time series rotation angle feature quantities, and obtain the unit speed time series data by dividing the angle difference by the time interval between adjacent time series rotation angle feature quantities.

[0026] In the embodiment of the present application, the relevance evaluation module 230 is configured to evaluate the input fluctuation relevance and output fluctuation relevance of the unit speed based on the hydraulic time series data, grid time series data, and unit speed time series data. Evaluating the input fluctuation relevance and output fluctuation relevance of the unit speed includes: Perform detrending processing on the hydraulic time series data, grid time series data, and unit speed time series data respectively and extract the fluctuation quantity to obtain the hydraulic fluctuation time series data, grid fluctuation time series data, and unit speed fluctuation time series data. The detrending processing includes any one of the HP filtering method and the moving average method; Perform correlation analysis on the hydraulic fluctuation time series data and the grid fluctuation time series data respectively with the corresponding unit speed fluctuation time series data to obtain the input fluctuation relevance index and output fluctuation relevance index, which are used to evaluate the input fluctuation relevance and output fluctuation relevance of the unit speed; Performing correlation analysis on the hydraulic fluctuation time series data and the grid fluctuation time series data respectively with the corresponding unit speed fluctuation time series data includes: Using the time-domain analysis method, the time-delay correlation analysis is performed on the hydraulic fluctuation time-series data and the power grid fluctuation time-series data respectively with the corresponding unit speed fluctuation time-series data. The maximum value of the cross-correlation coefficient between the hydraulic fluctuation time-series data and the unit speed fluctuation time-series data is used as the input time-delay correlation degree, and the maximum value of the cross-correlation coefficient between the power grid fluctuation time-series data and the unit speed fluctuation time-series data is used as the output time-delay correlation degree; Using the frequency-domain analysis method, the coherence analysis is performed on the hydraulic fluctuation time-series data and the power grid fluctuation time-series data respectively with the corresponding unit speed fluctuation time-series data. The coherence coefficient between the hydraulic fluctuation time-series data and the unit speed fluctuation time-series data is used as the input coherence coefficient, and the coherence coefficient between the power grid fluctuation time-series data and the unit speed fluctuation time-series data is used as the output coherence coefficient; The product of the input time-delay correlation degree and the input coherence coefficient is used as the input fluctuation correlation index, and the product of the output time-delay correlation degree and the output coherence coefficient is used as the output fluctuation correlation index.

[0027] In the embodiment of the present application, the coordination evaluation module 240 is used to evaluate the fluctuation coordination of the hydraulic power and the power grid with the goal of maintaining the unit speed stable based on the input fluctuation correlation and the output fluctuation correlation. Evaluating the fluctuation coordination of the hydraulic power and the power grid with the goal of maintaining the unit speed stable includes: Obtain the input fluctuation correlation index and the output fluctuation correlation index of the unit speed; Calculate the fluctuation coordination index of the hydraulic power and the power grid through the input fluctuation correlation index and the output fluctuation correlation index. The calculation formula of the fluctuation coordination index is: ; In the formula represents the input fluctuation correlation index, represents the output fluctuation correlation index, represents the fluctuation coordination index, which is used to evaluate the fluctuation coordination of the hydraulic power and the power grid.

[0028] In the embodiment of the present application, the speed fluctuation warning module 250 is used to perform unit speed fluctuation warning based on the evaluation result of the fluctuation coordination of the hydraulic power and the power grid. Performing unit speed fluctuation warning based on the evaluation result of the fluctuation coordination of the hydraulic power and the power grid includes: Obtain the fluctuation coordination index of the hydraulic power and the power grid. When the fluctuation coordination index is greater than or equal to the preset fluctuation coordination threshold, perform unit speed fluctuation warning. When the fluctuation coordination index is less than the preset fluctuation coordination threshold, do not perform unit speed fluctuation warning.

[0029] For the steps of the above-mentioned parameters and each unit module in a machine vision-based hydraulic generator set speed detection system of the present application to implement corresponding functions, reference can be made to the parameters and steps in the embodiments of a machine vision-based hydraulic generator set speed detection method in the foregoing text, which will not be elaborated herein.

[0030] Please refer to Figure 3 , an embodiment of the present invention further provides an electronic device 300, including a memory 310, a processor 320, and a communication bus 330; the memory 310 and the processor 320 are connected through the communication bus 330. The memory 310 stores instructions that can be loaded and executed by the processor 320 to perform a machine vision-based hydraulic generator set speed detection method provided in the above-mentioned embodiment.

[0031] The memory 310 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 310 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing a machine vision-based hydraulic generator set speed detection method provided in the above-mentioned embodiment, etc.; the data storage area can store data involved in a machine vision-based hydraulic generator set speed detection method provided in the above-mentioned embodiment, etc.

[0032] The processor 320 may include one or more processing cores. The processor 320 runs or executes instructions, programs, code sets, or instruction sets stored in the memory 310, calls data stored in the memory 310, and performs various functions of the present application and processes data. The processor 320 may be at least one of an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, and a microprocessor. It can be understood that for different devices, the electronic devices for implementing the functions of the above-mentioned processor 320 may be others, and the embodiments of the present application do not make specific limitations.

[0033] The communication bus 330 may include a path for transmitting information between the above components. The communication bus 330 may be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The communication bus 330 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 only a double arrow is used in Figure 3 , but it does not mean that there is only one bus or one type of bus.

[0034] An embodiment of the present application provides a computer-readable storage medium storing a computer program that can be loaded and executed by a processor to perform a method for detecting the rotational speed of a hydraulic generator unit using machine vision as provided in the above embodiment.

[0035] In an embodiment of the present application, the computer-readable storage medium may be a tangible device that holds and stores instructions used by an instruction execution device. The computer-readable storage medium may be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination of the above. Specifically, the computer-readable storage medium may be a portable computer disk, a hard disk, a USB flash drive, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, an optical disk, a magnetic disk, a mechanical encoding device, and any combination of the above.

[0036] The term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0037] The above description is only a preferred embodiment of the present application and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the application involved in the present application is not limited to the technical solution formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the foregoing application concept. For example, a technical solution formed by mutually replacing the above features with (but not limited to) technical features having similar functions applied in the present application.

Claims

1. A method for detecting the rotational speed of a hydraulic generator set by machine vision, characterized in that, It includes the following steps: Obtain hydraulic time-series data and power grid time-series data related to the operation of a hydraulic generator set, and obtain time-series image data of the marker positions of the rotating components of the hydraulic generator set; Use machine vision technology to extract the time-series rotation angle feature quantities of the markers in the time-series image of the marker positions and calculate the time-series data of the unit speed; Evaluate the input fluctuation correlation and output fluctuation correlation of the unit speed based on the hydraulic time-series data, power grid time-series data, and unit speed time-series data; Evaluate the fluctuation coordination between the hydraulics and the power grid with the goal of maintaining the stability of the unit speed based on the input fluctuation correlation and output fluctuation correlation; Conduct early warning of the unit speed fluctuation based on the evaluation results of the fluctuation coordination between the hydraulics and the power grid.

2. A method for detecting the rotational speed of a hydraulic generator set by machine vision according to claim 1, characterized in that, The extraction of the time-series rotation angle feature quantities of the markers in the time-series image of the marker positions and the calculation of the time-series data of the unit speed include: Perform image preprocessing on the obtained time-series image data of the marker positions. The image preprocessing includes image background removal, image binarization, and image filtering; Extract the markers in the preprocessed time-series image of the marker positions through a feature extraction algorithm and track the extracted markers using a marker trajectory centroid positioning method based on radial Gaussian fitting to obtain the time-series rotation angle feature quantities of the markers; Calculate the angle difference through the first-order difference of adjacent time-series rotation angle feature quantities, and obtain the time-series data of the unit speed by dividing the angle difference by the time interval between adjacent time-series rotation angle feature quantities.

3. A method for detecting the rotational speed of a hydraulic generator set by machine vision according to claim 1, characterized in that, The evaluation of the input fluctuation correlation and output fluctuation correlation of the unit speed includes: Perform detrending processing on the hydraulic time-series data, power grid time-series data, and unit speed time-series data respectively and extract the fluctuation quantities to obtain hydraulic fluctuation time-series data, power grid fluctuation time-series data, and unit speed fluctuation time-series data. The detrending processing includes any one of the HP filtering method and the moving average method; Conduct correlation analysis on the hydraulic fluctuation time-series data and the power grid fluctuation time-series data respectively with the corresponding unit speed fluctuation time-series data to obtain the input fluctuation correlation index and output fluctuation correlation index for evaluating the input fluctuation correlation and output fluctuation correlation of the unit speed.

4. A method for detecting the rotational speed of a hydraulic generator unit by machine vision according to claim 3, characterized in that, The conduct of correlation analysis on the hydraulic fluctuation time-series data and the power grid fluctuation time-series data respectively with the corresponding unit speed fluctuation time-series data includes: Use the time-domain analysis method to conduct time-delay correlation analysis on the hydraulic fluctuation time-series data and the power grid fluctuation time-series data respectively with the corresponding unit speed fluctuation time-series data. Take the maximum value of the cross-correlation coefficient between the hydraulic fluctuation time-series data and the unit speed fluctuation time-series data as the input time-delay correlation degree, and take the maximum value of the cross-correlation coefficient between the power grid fluctuation time-series data and the unit speed fluctuation time-series data as the output time-delay correlation degree; Use the frequency-domain analysis method to conduct coherence analysis on the hydraulic fluctuation time-series data and the power grid fluctuation time-series data respectively with the corresponding unit speed fluctuation time-series data. Take the coherence coefficient between the hydraulic fluctuation time-series data and the unit speed fluctuation time-series data as the input coherence coefficient, and take the coherence coefficient between the power grid fluctuation time-series data and the unit speed fluctuation time-series data as the output coherence coefficient; The product of the input time-delay correlation degree and the input coherence coefficient is used as the input fluctuation correlation index, and the product of the output time-delay correlation degree and the output coherence coefficient is used as the output fluctuation correlation index.

5. A method for detecting the rotational speed of a hydraulic generator unit by machine vision according to claim 1, characterized in that, The evaluation of the fluctuation coordination between the hydropower and the power grid with the goal of maintaining the stable speed of the unit includes: Obtaining the input fluctuation correlation index and the output fluctuation correlation index of the unit speed; Calculating the fluctuation coordination index between the hydropower and the power grid through the input fluctuation correlation index and the output fluctuation correlation index. The formula for calculating the fluctuation coordination index is: ； In the formula represents the input fluctuation correlation index, represents the output fluctuation correlation index, represents the fluctuation coordination index, which is used to evaluate the fluctuation coordination between hydropower and the power grid.

6. A method for detecting the rotational speed of a hydraulic generator set by machine vision according to claim 1, characterized in that, The early warning of the unit speed fluctuation based on the evaluation result of the fluctuation coordination between the hydropower and the power grid includes: Obtaining the fluctuation coordination index between the hydropower and the power grid. When the fluctuation coordination index is greater than or equal to the preset fluctuation coordination threshold, an early warning of the unit speed fluctuation is given. When the fluctuation coordination index is less than the preset fluctuation coordination threshold, no early warning of the unit speed fluctuation is given.

7. A rotational speed detection system for a hydraulic generator set using machine vision, which is applied to the rotational speed detection method for a hydraulic generator set using machine vision according to any one of claims 1-6, characterized in that, The system includes: A data acquisition module, which is used to acquire the hydropower time-series data and the power grid time-series data related to the operation of the hydropower generating unit, and acquire the time-series image data of the position of the marker of the rotating components of the hydropower generating unit; A speed calculation module, which is used to extract the time-series rotation angle feature quantity of the marker in the time-series image of the marker position by using machine vision technology and calculate the time-series data of the unit speed; A correlation evaluation module, which is used to evaluate the input fluctuation correlation and the output fluctuation correlation of the unit speed based on the hydropower time-series data, the power grid time-series data and the time-series data of the unit speed; A coordination evaluation module, which is used to evaluate the fluctuation coordination between the hydropower and the power grid with the goal of maintaining the stable speed of the unit based on the input fluctuation correlation and the output fluctuation correlation; A speed fluctuation early warning module, which is used to give an early warning of the unit speed fluctuation based on the evaluation result of the fluctuation coordination between the hydropower and the power grid.

8. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor. It is characterized in that the processor executes a method for detecting the speed of a hydropower generating unit by machine vision according to any one of claims 1-6 by calling the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that, Stored with instructions, when the instructions run on a computer, the computer is made to execute a method for detecting the speed of a hydropower generating unit by machine vision according to any one of claims 1-6.

Images