Hydroelectric generating set rotating speed fault monitoring system and method based on machine vision

Abstract

The invention discloses a hydroelectric generating set rotating speed fault monitoring system and method based on machine vision, and relates to the technical field of fault monitoring. Analyzing water flow abnormity of the upstream set area based on the water flow data of the upstream set area; analyzing water flow abnormity of the water inlet setting area based on the water flow data of the water inlet setting area; based on the water wheel blade rotating speed abnormity, the upstream set area water flow abnormity and the water inlet set area water flow abnormity, water wheel blade rotating speed abnormity caused when the upstream set area water flow flows through the water turbine is estimated; performing early warning on the hydroelectric generating set with the rotating speed fault according to the comparison result; water wheel blade abnormity and water flow abnormity are combined to analyze the influence of water flow on the rotating speed, whether the rotating speed fault is caused when upstream water flow flows through the water turbine or not is judged according to the current water flow data and the rotating speed condition, and the accuracy and timeliness of fault judgment of the hydroelectric generating set are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault monitoring, and more specifically to a system and method for monitoring the rotation speed fault of a hydraulic generator set based on machine vision. Background Art

[0002] A hydroelectric generating set is also called a "turbine generator set". Each turbine and its matching generator in a hydropower station form a power generation unit. It is the main power equipment for the hydropower station to produce electricity. When the water flow used by the hydropower station passes through the turbine, the water energy is converted into mechanical energy that drives the machinery to rotate. The turbine generator in the hydroelectric generating set is driven by the turbine, and the speed of the generator determines the frequency of the output AC power. Therefore, fault monitoring of the speed of the hydroelectric generating set is very important to ensure the stable operation of the hydroelectric generating set.

[0003] However, the existing technology for judging the speed fault of a hydroelectric generator set usually analyzes the speed fault risk based on real-time monitoring of turbine blade data, but cannot analyze the influence of water flow on the speed through abnormal turbine blades and water flow, and thus cannot judge whether the flow through the turbine in different time periods will cause speed faults based on water flow data and speed conditions, resulting in low efficiency in fault monitoring of hydroelectric generators. In summary, how to improve the fault monitoring efficiency of a hydroelectric generator is an urgent problem to be solved by those skilled in the art. In order to solve this problem, the present invention provides a system and method for monitoring the speed fault of a hydroelectric generator set based on machine vision. Summary of the invention

[0004] The purpose of the present invention is to provide a system and method for monitoring the speed fault of a hydroelectric generator set based on machine vision. The present invention combines the abnormality of turbine blades and the abnormality of water flow to analyze the influence of water flow on the speed, and judges whether the upstream water flow through the turbine will cause a speed fault based on the current water flow data and the speed condition, thereby improving the accuracy and timeliness of the fault judgment of the hydroelectric generator set.

[0005] To achieve the above object, the present invention provides the following technical solutions: The method for monitoring the speed fault of a hydroelectric generator set based on machine vision includes the following specific steps: S1. Collecting turbine blade data, and analyzing abnormal turbine blade speed based on the turbine blade data; S2, collecting water flow data of the upstream set area and the water flow data of the turbine water inlet set area, and analyzing the water flow abnormality of the upstream set area based on the water flow data of the upstream set area; analyzing the water flow abnormality of the water inlet set area based on the water flow data of the water inlet set area; S3, based on the abnormal water turbine blade speed, the abnormal water flow in the upstream set area and the abnormal water flow in the water inlet set area, it is estimated that the abnormal water turbine blade speed is caused by the water flow in the upstream set area flowing through the turbine; S4. Compare the estimated abnormal rotation speed of the water turbine blades with the set abnormal rotation speed threshold of the water turbine blades, and issue an early warning to the hydroelectric generating set determined to have a rotation speed failure according to the comparison result.

[0006] Preferably, S1 comprises the following specific steps: S101, collecting water turbine blade speed data; S102, collecting images of water turbine blades, and analyzing gap data based on the images of water turbine blades, wherein the gap data includes a gap area and a gap depth; S103, inputting the turbine blade speed data and the gap data into a turbine blade speed abnormal value calculation formula to calculate the turbine blade speed abnormal value, the turbine blade speed abnormal value calculation formula is: ; in, is an exponential function with real number e as base, is the number of gaps, is the area of ​​the qth gap, is the maximum safe area of ​​the gap, is the depth of the qth notch, is the maximum safe depth of the notch, is the acquisition time of the speed data, is the time integral, is the speed at time t, is the minimum value of the standard speed range, is the maximum value of the standard speed range, is the average speed.

[0007] Preferably, S2 comprises the following specific steps: S201, collecting water volume data of a set upstream area; S202, collecting water flow pictures in the upstream set area, and analyzing water flow turbidity data in the upstream set area based on the water flow pictures in the upstream set area, wherein the water flow turbidity data in the upstream set area includes the volume of upstream water flow particles and the distance between particles; S203, inputting the water volume data of the upstream set area and the water flow turbidity data of the upstream set area into the upstream water flow abnormal value calculation formula to calculate the upstream water flow abnormal value, the upstream water flow abnormal value calculation formula is: ; in, is an exponential function with real number e as base, Set the regional water volume for the upstream, For the maximum safe water volume, Set the number of particles in the upstream area. is the volume of the i-th particle in the upstream setting area, is the maximum safe particle volume, is the distance between the ith particle in the upstream setting area and its closest particle, is the minimum safe particle distance; S204, collecting water volume data of a set area of ​​a turbine water inlet; S205, collecting a water flow picture of a set area of ​​a water turbine inlet, and analyzing water flow turbidity data of the set area of ​​the water inlet based on the water flow picture of the set area of ​​the water inlet, wherein the water flow turbidity data of the set area of ​​the water inlet includes a volume of particles in the water inlet and a distance between particles; S206, inputting the water volume data of the water inlet setting area and the water flow turbidity data of the water inlet setting area into the water inlet water flow abnormal value calculation formula to calculate the water inlet water flow abnormal value, the water inlet water flow abnormal value calculation formula is: ; in, Set the regional water volume for the turbine inlet, Set the number of regional particles for the water inlet, Set the volume of the g-th particle in the inlet area, Set the distance between the gth particle and its closest particle in the inlet area.

[0008] Preferably, S3 comprises the following specific steps: The abnormal value of the water turbine blade speed, the abnormal value of the upstream water flow and the abnormal value of the water inlet water flow are input into the abnormal value calculation formula of the speed in the next time period to calculate the abnormal value of the speed in the next time period. The abnormal value calculation formula of the speed in the next time period is: .

[0009] Preferably, S4 comprises the following specific steps: The speed abnormal value of the next time period is compared with the set turbine blade speed abnormal threshold. If the speed abnormal value of the next time period is less than the set turbine blade speed abnormal threshold, the speed is judged to be normal; if the speed abnormal value of the next time period is greater than or equal to the set turbine blade speed abnormal threshold, a speed fault is judged and an early warning is issued for the hydropower generator set.

[0010] A machine vision-based speed fault monitoring system for a hydroelectric generator set, which is used to implement a machine vision-based speed fault monitoring method for a hydroelectric generator set, including a data acquisition module, which is used to collect turbine blade data, upstream set area water flow data, and turbine water inlet set area water flow data; The image acquisition module is used to acquire images of turbine blades, water flow images in a set upstream area, and water flow images in a set turbine inlet area; The speed abnormality analysis module is used to input the water turbine blade speed data and the gap data into the water turbine blade speed abnormality value calculation formula to calculate the water turbine blade speed abnormality value; The water flow anomaly analysis module is used to input the water volume data of the upstream set area and the water flow turbidity data of the upstream set area into the upstream water flow anomaly value calculation formula to calculate the upstream water flow anomaly value; input the water volume data of the water inlet set area and the water flow turbidity data of the water inlet set area into the water inlet water flow anomaly value calculation formula to calculate the water inlet water flow anomaly value; The speed abnormality prediction module is used to input the speed abnormality value of the turbine blade, the upstream water flow abnormality value and the water inlet water flow abnormality value into the speed abnormality value calculation formula of the next time period to calculate the speed abnormality value of the next time period; The fault warning module is used to compare the speed abnormality value of the next time period with the set water turbine blade speed abnormality threshold. If the speed abnormality value of the next time period is less than the set water turbine blade speed abnormality threshold, the speed is judged to be normal; if the speed abnormality value of the next time period is greater than or equal to the set water turbine blade speed abnormality threshold, the speed fault is judged and the hydroelectric generator set is warned; The control module is used to control the operation of the data acquisition module, the image acquisition module, the speed abnormality analysis module, the water flow abnormality analysis module, the speed abnormality estimation module and the fault warning module.

[0011] An electronic device, comprising: a memory for storing a computer program; The processor is used to implement the steps of the above-mentioned method for monitoring the rotation speed fault of a hydroelectric generator set based on machine vision when executing the computer program.

[0012] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for monitoring speed faults of a hydraulic generator set based on machine vision.

[0013] Compared with the prior art, the present invention has the following beneficial effects: The present invention collects turbine blade data, and analyzes the abnormal rotation speed of the turbine blade based on the turbine blade data; collects water flow data of an upstream set area and water flow data of a turbine water inlet set area, and analyzes the abnormal water flow in the upstream set area based on the water flow data of the upstream set area; analyzes the abnormal water flow in the water inlet set area based on the water flow data of the water inlet set area; estimates the abnormal rotation speed of the turbine blade caused by the water flow in the upstream set area flowing through the turbine based on the abnormal rotation speed of the turbine blade, the abnormal water flow in the upstream set area and the abnormal water flow in the water inlet set area; compares the estimated abnormal rotation speed of the turbine blade with the set abnormal rotation speed threshold of the turbine blade, and issues an early warning to the hydroelectric generator set judged as having a rotation speed fault according to the comparison result; the present invention combines the abnormal rotation speed of the turbine blade and the abnormal water flow to analyze the influence of the water flow on the rotation speed, and judges whether the upstream water flow flowing through the turbine will cause a rotation speed fault according to the current water flow data and the rotation speed, thereby improving the accuracy and timeliness of fault judgment of the hydroelectric generator set. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0015] Figure 1 It is a flow chart of a method for monitoring speed failure of a hydroelectric generator set based on machine vision according to the present invention; Figure 2 It is a schematic diagram of the S1 process in the method for monitoring the speed fault of a hydroelectric generator set based on machine vision of the present invention; Figure 3 It is a schematic diagram of the S2 process in the method for monitoring the speed fault of a hydroelectric generator set based on machine vision of the present invention; Figure 4 It is a schematic diagram of the overall framework of the hydraulic generator set speed fault monitoring system based on machine vision of the present invention. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0017] See also Figure 1-Figure 4 , Figure 1 A schematic diagram of a flow chart of a method for monitoring speed failure of a hydroelectric generator set based on machine vision according to an embodiment of the present invention; The method for monitoring the speed fault of a hydroelectric generator set based on machine vision provided by the present invention comprises the following specific steps: S1. Collecting turbine blade data, and analyzing abnormal turbine blade speed based on the turbine blade data; Figure 2 A schematic diagram of the S1 process in the method for monitoring speed faults of a hydroelectric generator set based on machine vision provided in an embodiment of the present invention; In this embodiment, S1 includes the following specific steps: S101, collecting water turbine blade speed data; Specifically, according to the working environment of the hydroelectric generator set, a suitable photoelectric, Hall effect, magnetoelectric or other speed sensor is selected, and the sampling frequency and sampling time of the speed sensor are set to monitor the speed of the turbine blades in real time; The purpose of collecting speed data is that the rapid change of speed affects the stability of the hydroelectric generator set and increases the fatigue and noise of the turbine blades.

[0018] S102, collecting images of water turbine blades, and analyzing gap data based on the images of water turbine blades, where the gap data includes a gap area and a gap depth; Specifically, a high-resolution camera is used to take pictures of the water turbine blades from multiple angles, and the pictures are pre-processed by image processing software such as Photoshop, MATLAB, and ImageJ, and then the gaps of the water turbine blades are identified by using algorithms such as Canny and Sobel, and the area, depth, and position of the gaps are measured by using measuring tools such as rulers and measuring rectangles; The purpose of collecting notch data is that the notch area and depth affect the mechanical properties of the turbine blades. The larger the notch area, the less torque the turbine will output, and the deeper the notch, the more likely the turbine blades will break when rotating at high speeds.

[0019] S103, inputting the turbine blade speed data and the gap data into a turbine blade speed abnormal value calculation formula to calculate the turbine blade speed abnormal value, the turbine blade speed abnormal value calculation formula is: ; in, is an exponential function with real number e as base, is the number of gaps, is the area of ​​the qth gap, is the maximum safe area of ​​the gap, is the depth of the qth notch, is the maximum safe depth of the notch, is the acquisition time of the speed data, is the time integral, is the speed at time t, is the minimum value of the standard speed range, is the maximum value of the standard speed range, is the average speed, Used to calculate the stability of the turbine blade speed, if The larger the value, the more unstable the speed of the turbine blades.

[0020] Specifically, the maximum safe area of ​​the notch and the maximum safe depth of the notch are obtained by selecting a number of damaged turbine blades, measuring the notch area and depth of the damaged turbine blades, and taking the average of the measured data as the maximum safe area of ​​the notch and the maximum safe depth of the notch in this embodiment; The minimum value of the standard speed range and the maximum value of the standard speed range are determined as follows: A new hydroelectric generator set is selected, and the rotation speed of the turbine blades when the hydroelectric generator set is in operation is recorded. Based on the record analysis, the maximum and minimum values ​​of the rotation speed range of the turbine blades under normal use conditions are used as the maximum and minimum values ​​of the standard rotation speed range of this embodiment.

[0021] S2, collecting water flow data of the upstream set area and the water flow data of the turbine water inlet set area, and analyzing the water flow abnormality of the upstream set area based on the water flow data of the upstream set area; analyzing the water flow abnormality of the water inlet set area based on the water flow data of the water inlet set area; Figure 3 A schematic diagram of the S2 process in the method for monitoring speed faults of a hydroelectric generator set based on machine vision provided in an embodiment of the present invention; In this embodiment, S2 includes the following specific steps: S201, collecting water volume data of a set upstream area; Specifically, flow meters, water level sensors and other sensing devices are installed in the upstream set area, and the water volume is calculated using the formula: Get water volume data; where, is the cross-sectional area of ​​water flow, is the flow rate, For flow, is the flow time.

[0022] S202, collecting water flow images in the upstream set area, and analyzing water flow turbidity data in the upstream set area based on the water flow images in the upstream set area, where the water flow turbidity data in the upstream set area includes the volume of upstream water flow particles and the distance between particles; Specifically, a high-resolution camera is used to capture water flow images from multiple angles, and the water flow images are preprocessed by grayscale conversion, denoising, contrast enhancement, etc. According to the grayscale value of the particles, a suitable threshold is set to separate the particles from the background, and algorithms such as Canny and Sobel are used to detect the edges of the particles. The volume of the particles is obtained by measuring the ratio of the particle diameter and the image pixel size, and the distance between the particles is obtained by measuring the distance between the center points of the particles or the minimum distance between the edges.

[0023] S203, inputting the water volume data of the upstream set area and the water flow turbidity data of the upstream set area into the upstream water flow abnormal value calculation formula to calculate the upstream water flow abnormal value, the upstream water flow abnormal value calculation formula is: ; in, is an exponential function with real number e as base, Set the regional water volume for the upstream, For the maximum safe water volume, Set the number of particles in the upstream area. is the volume of the i-th particle in the upstream setting area, is the maximum safe particle volume, is the distance between the ith particle in the upstream setting area and its closest particle, is the minimum safe particle distance, Used to calculate the total volume of particles, Used to calculate the ratio of particles to water volume. The larger the ratio, the more turbid the water flow. Used to unify the units of particulate matter-cubic centimeters and water flow-cubic meters to facilitate calculations in this embodiment; Specifically, the maximum safe water volume is obtained by analyzing the maximum flow capacity of the turbine according to the design specifications of the turbine and the hydroelectric generator, that is, the maximum flow rate that the turbine water inlet can accept as the maximum safe water volume of this embodiment; The maximum safe particle volume and the minimum safe particle spacing are determined by selecting several damaged turbine blades, obtaining the most recent water flow data that caused the damage to the turbine blades, analyzing the particle volume and spacing of the water flow, and taking the average of the measured data as the maximum safe particle volume and the minimum safe particle spacing of this embodiment.

[0024] S204, collecting water volume data of a set area of ​​a turbine water inlet; S205, collecting water flow images of the turbine water inlet setting area, and analyzing water flow turbidity data of the water inlet setting area based on the water flow images of the water inlet setting area, wherein the water flow turbidity data of the water inlet setting area includes the volume of water inlet water flow particles and the distance between particles; S206, inputting the water volume data of the set area of ​​the water inlet and the water flow turbidity data of the set area of ​​the water inlet into the water flow abnormal value calculation formula of the water inlet to calculate the water flow abnormal value of the water inlet. The water flow abnormal value calculation formula of the water inlet is: ; in, Set the regional water volume for the turbine inlet, Set the number of regional particles for the water inlet, Set the volume of the g-th particle in the inlet area, Set the distance between the gth particle and its closest particle in the inlet area.

[0025] S3, based on the abnormal water turbine blade speed, the abnormal water flow in the upstream set area and the abnormal water flow in the water inlet set area, it is estimated that the abnormal water turbine blade speed is caused by the water flow in the upstream set area flowing through the turbine; In this embodiment, S3 includes the following specific steps: The abnormal value of the turbine blade speed, the abnormal value of the upstream water flow and the abnormal value of the water inlet flow are input into the abnormal value calculation formula of the speed in the next time period to calculate the abnormal value of the speed in the next time period. The abnormal value calculation formula of the speed in the next time period is: .

[0026] S4. Compare the estimated abnormal rotation speed of the water turbine blades with the set abnormal rotation speed threshold of the water turbine blades, and issue an early warning to the hydroelectric generating set determined to have a rotation speed failure according to the comparison result.

[0027] In this embodiment, S4 includes the following specific steps: The speed abnormal value of the next time period is compared with the set turbine blade speed abnormal threshold. If the speed abnormal value of the next time period is less than the set turbine blade speed abnormal threshold, the speed is judged to be normal; if the speed abnormal value of the next time period is greater than or equal to the set turbine blade speed abnormal threshold, a speed fault is judged and an early warning is issued for the hydropower generator set.

[0028] See also Figure 4 , Figure 4 A schematic diagram of the overall framework of a hydraulic generator speed fault monitoring system based on machine vision provided by an embodiment of the present invention; The machine vision-based speed fault monitoring system for a hydroelectric generator set provided by the present invention is used to implement a machine vision-based speed fault monitoring method for a hydroelectric generator set, and includes a data acquisition module for acquiring turbine blade data, upstream set area water flow data, and turbine water inlet set area water flow data; The image acquisition module is used to acquire images of turbine blades, water flow images in a set upstream area, and water flow images in a set turbine inlet area; The speed abnormality analysis module is used to input the water turbine blade speed data and the gap data into the water turbine blade speed abnormality value calculation formula to calculate the water turbine blade speed abnormality value; The water flow anomaly analysis module is used to input the water volume data of the upstream set area and the water flow turbidity data of the upstream set area into the upstream water flow anomaly value calculation formula to calculate the upstream water flow anomaly value; input the water volume data of the water inlet set area and the water flow turbidity data of the water inlet set area into the water inlet water flow anomaly value calculation formula to calculate the water inlet water flow anomaly value; The speed abnormality prediction module is used to input the speed abnormality value of the turbine blade, the upstream water flow abnormality value and the water inlet water flow abnormality value into the speed abnormality value calculation formula of the next time period to calculate the speed abnormality value of the next time period; The fault warning module is used to compare the speed abnormality value of the next time period with the set water turbine blade speed abnormality threshold. If the speed abnormality value of the next time period is less than the set water turbine blade speed abnormality threshold, the speed is judged to be normal; if the speed abnormality value of the next time period is greater than or equal to the set water turbine blade speed abnormality threshold, the speed fault is judged and the hydroelectric generator set is warned; The control module is used to control the operation of the data acquisition module, the image acquisition module, the speed abnormality analysis module, the water flow abnormality analysis module, the speed abnormality estimation module and the fault warning module.

[0029] The present invention provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor calls the computer program stored in the memory to implement the above-mentioned machine vision-based hydraulic generator set speed fault monitoring method when executing.

[0030] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement the machine vision-based hydropower generator speed fault monitoring method provided in the above method embodiment. The electronic device may also include other components for realizing the functions of the device. For example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data, which will not be described in detail in this embodiment.

[0031] The present invention provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: collecting turbine blade data, and analyzing the abnormal rotation speed of the turbine blade based on the turbine blade data; collecting water flow data of an upstream set area and water flow data of a turbine water inlet set area, and analyzing the abnormal rotation speed of the upstream set area based on the water flow data of the upstream set area; analyzing the abnormal rotation speed of the water inlet set area based on the water flow data of the water inlet set area; estimating the abnormal rotation speed of the turbine blade caused by the water flow in the upstream set area flowing through the turbine based on the abnormal rotation speed of the turbine blade, the abnormal rotation speed of the upstream set area and the abnormal rotation speed of the water inlet set area; comparing the estimated abnormal rotation speed of the turbine blade with a set abnormal rotation speed threshold of the turbine blade, and issuing an early warning to a hydroelectric generator set judged to have a rotation speed fault according to the comparison result.

[0032] The computer-readable storage medium involved in the present invention includes random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, register, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the technical field.

[0033] It should also be noted that, in the present invention, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or apparatus that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or apparatus; in the absence of further restrictions, the elements defined by the sentence "comprises one..." does not exclude the presence of other identical elements in the process, method, article or apparatus that includes the elements.

[0034] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0035] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined in the present invention can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown in the present invention, but will conform to the widest scope consistent with the principles and novel features disclosed in the present invention.

Claims

1. A method for monitoring the speed fault of a hydroelectric generator set based on machine vision, characterized in that: The specific steps include: S1. Collecting turbine blade data, and analyzing abnormal turbine blade speed based on the turbine blade data; S2, collecting water flow data of the upstream set area and the water flow data of the turbine water inlet set area, and analyzing the water flow abnormality of the upstream set area based on the water flow data of the upstream set area; analyzing the water flow abnormality of the water inlet set area based on the water flow data of the water inlet set area; S3, based on the abnormal water turbine blade speed, the abnormal water flow in the upstream set area and the abnormal water flow in the water inlet set area, it is estimated that the abnormal water turbine blade speed is caused by the water flow in the upstream set area flowing through the turbine; S4. Compare the estimated abnormal rotation speed of the water turbine blades with the set abnormal rotation speed threshold of the water turbine blades, and issue an early warning to the hydroelectric generating set determined to have a rotation speed failure according to the comparison result.

2. The method for monitoring the speed fault of a hydroelectric generator set based on machine vision according to claim 1, characterized in that: The S1 comprises the following specific steps: S101, collecting water turbine blade speed data; S102, collecting images of water turbine blades, and analyzing gap data based on the images of water turbine blades, wherein the gap data includes a gap area and a gap depth; S103, inputting the turbine blade speed data and the gap data into a turbine blade speed abnormal value calculation formula to calculate the turbine blade speed abnormal value, the turbine blade speed abnormal value calculation formula is: ； in, is an exponential function with real number e as base, is the number of gaps, is the area of ​​the qth gap, is the maximum safe area of ​​the gap, is the depth of the qth notch, is the maximum safe depth of the notch, is the acquisition time of the speed data, is the time integral, is the speed at time t, is the minimum value of the standard speed range, is the maximum value of the standard speed range, is the average speed.

3. The method for monitoring the speed fault of a hydroelectric generator set based on machine vision according to claim 2, characterized in that: The S2 comprises the following specific steps: S201, collecting water volume data of a set upstream area; S202, collecting water flow pictures in the upstream set area, and analyzing water flow turbidity data in the upstream set area based on the water flow pictures in the upstream set area, wherein the water flow turbidity data in the upstream set area includes the volume of upstream water flow particles and the distance between particles; S203, inputting the water volume data of the upstream set area and the water flow turbidity data of the upstream set area into the upstream water flow abnormal value calculation formula to calculate the upstream water flow abnormal value, the upstream water flow abnormal value calculation formula is: ； in, is an exponential function with real number e as base, Set the regional water volume for the upstream, For the maximum safe water volume, Set the number of particles in the upstream area. is the volume of the i-th particle in the upstream setting area, is the maximum safe particle volume, is the distance between the ith particle in the upstream setting area and its closest particle, is the minimum safe particle distance.

4. The method for monitoring the speed fault of a hydroelectric generator set based on machine vision according to claim 3, characterized in that: The S2 further comprises the following specific steps: S204, collecting water volume data of a set area of ​​a turbine water inlet; S205, collecting a water flow picture of a set area of ​​a water turbine inlet, and analyzing water flow turbidity data of the set area of ​​the water inlet based on the water flow picture of the set area of ​​the water inlet, wherein the water flow turbidity data of the set area of ​​the water inlet includes a volume of particles in the water inlet and a distance between particles; S206, inputting the water volume data of the water inlet setting area and the water flow turbidity data of the water inlet setting area into the water inlet water flow abnormal value calculation formula to calculate the water inlet water flow abnormal value, the water inlet water flow abnormal value calculation formula is: ； in, Set the regional water volume for the turbine inlet, Set the number of regional particles for the water inlet, Set the volume of the g-th particle in the inlet area, Set the distance between the gth particle and its closest particle in the inlet area.

5. The method for monitoring speed fault of a hydroelectric generator set based on machine vision according to claim 4, characterized in that: The S3 comprises the following specific steps: The abnormal value of the water turbine blade speed, the abnormal value of the upstream water flow and the abnormal value of the water inlet water flow are input into the abnormal value calculation formula of the speed in the next time period to calculate the abnormal value of the speed in the next time period. The abnormal value calculation formula of the speed in the next time period is: 。 6. The method for monitoring the speed fault of a hydroelectric generator set based on machine vision according to claim 5, characterized in that: The S4 comprises the following specific steps: The speed abnormality value in the next time period is compared with the set water turbine blade speed abnormality threshold value. If the speed abnormality value in the next time period is less than the set water turbine blade speed abnormality threshold value, the speed is judged to be normal. If the speed abnormal value in the next time period is greater than or equal to the set turbine blade speed abnormal threshold, a speed fault is determined and an early warning is issued to the hydroelectric generator set.

7. A machine vision-based speed fault monitoring system for a hydroelectric generator set, used to implement the machine vision-based speed fault monitoring method for a hydroelectric generator set as claimed in any one of claims 1 to 6, characterized in that: It includes a data acquisition module, which is used to collect water turbine blade data, upstream set area water flow data and water turbine inlet set area water flow data; The image acquisition module is used to acquire images of turbine blades, water flow images in a set upstream area, and water flow images in a set turbine inlet area; The speed abnormality analysis module is used to input the water turbine blade speed data and the gap data into the water turbine blade speed abnormality value calculation formula to calculate the water turbine blade speed abnormality value; The water flow anomaly analysis module is used to input the water volume data of the upstream set area and the water flow turbidity data of the upstream set area into the upstream water flow anomaly value calculation formula to calculate the upstream water flow anomaly value; input the water volume data of the water inlet set area and the water flow turbidity data of the water inlet set area into the water inlet water flow anomaly value calculation formula to calculate the water inlet water flow anomaly value; The speed abnormality prediction module is used to input the speed abnormality value of the turbine blade, the upstream water flow abnormality value and the water inlet water flow abnormality value into the speed abnormality value calculation formula of the next time period to calculate the speed abnormality value of the next time period; The fault warning module is used to compare the speed abnormality value in the next time period with the set water turbine blade speed abnormality threshold value. If the speed abnormality value in the next time period is less than the set water turbine blade speed abnormality threshold value, the speed is judged to be normal. If the speed abnormal value in the next time period is greater than or equal to the set turbine blade speed abnormal threshold, a speed fault is determined and an early warning is issued to the hydroelectric generator set; The control module is used to control the operation of the data acquisition module, the image acquisition module, the speed abnormality analysis module, the water flow abnormality analysis module, the speed abnormality estimation module and the fault warning module.

8. An electronic device, characterized in that: include: Memory for storing computer programs; A processor is used to implement the steps of the method for monitoring the speed fault of a hydroelectric generator set based on machine vision as described in any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for monitoring speed faults of a hydroelectric generator set based on machine vision are implemented as described in any one of claims 1 to 6.

Images