Liquid level monitoring system of flow battery based on machine vision

Abstract

The invention particularly relates to a liquid level monitoring system for a flow battery based on machine vision. The liquid level monitoring system comprises an image acquisition module; the liquid level detection module is used for analyzing based on the liquid level image of the flow battery to obtain an analyzed and evaluated liquid level of the flow battery; the display and interaction module is used for outputting and presenting the liquid level detection result; and a system control module. According to the method, the first evaluation liquid level preliminarily locates the liquid level contour in a rapid gradient calculation mode, the second evaluation liquid level accurately extracts the edge through multi-stage processing, and the two parts complement each other; in the comprehensive analysis stage, by means of unique mean value calculation, a method for constructing a geometric model based on liquid level deviation and calculating a difference coefficient, and in combination with a preset threshold value, an additional liquid level value is matched, errors of a single detection method can be effectively eliminated, and detection deviation caused by factors such as environment interference and image noise can be corrected.

Description

Technical Field

[0001] The present invention relates to the technical field of liquid flow battery monitoring, and in particular to a liquid level monitoring system of a liquid flow battery based on machine vision. Background Art

[0002] Accurately monitoring the liquid level inside flow batteries is crucial during their production, use, and maintenance. Excessively high levels can cause electrolyte overflow, corroding equipment and causing environmental pollution; while low levels can degrade battery performance and even lead to safety incidents.

[0003] Traditional liquid level monitoring methods, such as float, capacitive, and ultrasonic level sensors, have numerous limitations. Float-type level gauges rely on mechanical structures and are susceptible to electrolyte corrosion over time, leading to increased measurement errors. Mechanical wear can also cause failures. Capacitive level sensors are susceptible to changes in ambient temperature, humidity, and electrolyte conductivity, leading to inaccurate measurement results. Ultrasonic level gauges are susceptible to interference in complex electromagnetic environments, making measurement accuracy difficult to guarantee.

[0004] With the development of machine vision technology, liquid level monitoring methods based on image analysis are gradually applied in the industrial field.

[0005] Most existing machine vision-based liquid level monitoring solutions use a single detection algorithm or a simple image processing process.

[0006] For example, some solutions rely solely on simple edge detection algorithms such as the Sobel operator. These algorithms are sensitive to noise and, in the complex operating environment of flow batteries (e.g., image jitter caused by equipment vibration and image interference caused by electrolyte impurities), can easily generate a large number of false edges, leading to large errors in liquid level detection. Although some solutions use relatively advanced algorithms such as the Canny operator, they lack the fusion analysis of the results of different algorithms, cannot fully utilize the advantages of each algorithm, and are difficult to adapt to the needs of accurate liquid level measurement under different working conditions.

[0007] Therefore, there is an urgent need for a liquid flow battery level monitoring system with high reliability, high measurement accuracy, intelligent interaction and efficient control capabilities to address the above-mentioned problems. Summary of the Invention

[0008] The purpose of the present invention is to solve the above problems and to propose a liquid level monitoring system for a flow battery based on machine vision.

[0009] In order to achieve the above object, the present invention adopts the following technical solutions: The liquid level monitoring system of the flow battery based on machine vision includes: Image acquisition module: obtains the liquid surface image information of the flow battery and preprocesses it; Liquid level detection module: Analyzes the liquid level image of the flow battery to obtain the analytical evaluation liquid level of the flow battery; Display and interaction module: output and present the liquid level detection results; System control module: controls the equipment in the image acquisition module and coordinates the workflow of each module in the system.

[0010] Preferably, the obtaining of liquid surface image information of the flow battery includes: Capture images of the flow battery liquid level using an industrial camera; Choose the appropriate lens according to the camera model, shooting distance, and field of view requirements;

[0011] Provide ample light for shooting.

[0012] Preferably, the preprocessing of the acquired image includes: Remove noise from images; Enhance the features of the image by adjusting the contrast and brightness of the image; Convert a color image or grayscale image into a binary image and classify the pixels in the image into two categories, including foreground and background.

[0013] Preferably, the analysis based on the liquid level image of the flow battery to obtain the analysis and evaluation liquid level of the flow battery specifically includes: respectively obtaining a first evaluation liquid level and a second evaluation liquid level of the flow battery; The first evaluation liquid level and the second evaluation liquid level are comprehensively analyzed to obtain the analysis evaluation liquid level.

[0014] Preferably, the process of obtaining the first evaluation liquid level includes: Use the image processing library to read the image file containing the liquid surface and convert it into a grayscale image; Perform a horizontal convolution operation on the grayscale image to obtain a horizontal convolution kernel: Perform a vertical convolution operation on the grayscale image to obtain a vertical convolution kernel: Calculate gradient magnitude and direction based on horizontal and vertical gradients; Including calculating the gradient amplitude based on the horizontal gradient and the vertical gradient; calculating the gradient direction through the inverse tangent function; A preset amplitude threshold is set, and the gradient amplitude is compared with the threshold to extract the liquid surface contour on the binary edge image: each contour is composed of a series of points; Filter out the contours related to the liquid surface according to the position, size and shape characteristics of the contours; Calculate contour features, including perimeter, area, and center of gravity; Obtain the cross-sectional area of the container, obtain the area enclosed by the liquid surface contour through contour extraction, obtain the liquid surface height data based on the proportional relationship, and record it as the first evaluation liquid level; The obtained liquid level height data is then subjected to difference calculation with the scale value in the image of the container to obtain a first liquid level deviation.

[0015] Preferably, the process of obtaining the second evaluation liquid level includes: Read the image and convert it to grayscale; Use a two-dimensional Gaussian function to construct a Gaussian kernel and perform convolution on the grayscale image to remove noise; Obtaining the gradient magnitude and direction obtained during the first evaluation liquid level calculation process; Traverse each pixel in the image, and for each pixel, determine the gradient magnitude of its adjacent pixels in the gradient direction according to its gradient direction; If the gradient magnitude of the pixel is not the local maximum, its value is set to 0, otherwise its original value is retained; Set high and low thresholds to process the image after non-maximum suppression, including: Pixels with gradient magnitudes greater than a high threshold are identified as strong edge pixels; Pixels with gradient magnitudes less than the low threshold are excluded; Pixels with gradient magnitudes between the high and low thresholds are retained as weak edge pixels if they are connected to strong edge pixels, otherwise they are excluded; Extract the contour of the image after double threshold processing; According to the liquid level height calculation process in the first evaluation liquid level acquisition process, the contour is screened, the contour features are calculated, and the liquid level height is calculated according to the shape of the container; the obtained liquid level height is recorded as the second evaluation liquid level, and the difference between the obtained liquid level height data and the scale value in the container image is calculated to obtain the second liquid level deviation.

[0016] Preferably, the step of comprehensively analyzing the first evaluation liquid level and the second evaluation liquid level to obtain the analysis evaluation liquid level comprises: Calculate the average of the first evaluation liquid level and the second evaluation liquid level as the base liquid level; After normalizing the first liquid level deviation and the second liquid level deviation, the first liquid level deviation and the second liquid level deviation are respectively used as the right angle sides of an isosceles right triangle, and the remaining sides are connected to obtain two isosceles right triangles. The areas of the two isosceles right triangles are calculated respectively, and the difference between their areas is calculated to obtain the difference coefficient; Three groups of threshold value ranges are preset, each group of threshold value ranges corresponds to an additional liquid level value, and the difference coefficient is matched with the three groups of threshold value ranges to obtain the additional liquid level value corresponding to the difference coefficient; The basic liquid level and the additional liquid level value are summed to obtain the analytical evaluation liquid level.

[0017] Preferably, the display and interaction module specifically includes: Liquid level display unit: Display the specific height and capacity information of the current liquid level in real time in numerical form; By drawing graphs related to liquid level, the proportional relationship between liquid level and other parameters can be demonstrated; Display the change trend of liquid level over time in the form of a curve; Parameter setting unit: It is used by users to set the camera's resolution, frame rate, exposure time, and gain parameters; According to the actual working requirements of the flow battery, set the upper and lower limit alarm thresholds of the liquid level; Operation control unit: Users can effectively control the image acquisition, processing and analysis processes through the operation interface.

[0018] Preferably, the system control module specifically includes: Hardware control unit: By communicating with the interface of the hardware device, start and stop instructions are sent to the camera and light source. When the system starts working, the hardware control unit first sends a start signal to the camera and light source to put them into working state. When the system stops working, a stop signal is sent to turn off the camera and light source. According to the camera shooting parameters and light source brightness parameters set by the user in the parameter setting unit, the corresponding control instructions are sent to the hardware device; Process control unit: At preset time intervals, the system sends acquisition instructions to the image acquisition module to trigger the camera to acquire the liquid level image of the flow battery. Perform filtering, enhancement and binarization preprocessing operations on the collected image, then extract the liquid level edge and contour information from the preprocessed image, calculate the liquid level height, and finally store and analyze the liquid level data; During the entire process execution, the process control unit monitors the working status of each module in real time.

[0019] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention uses a rapid gradient calculation method to preliminarily locate the liquid level contour through the first evaluation liquid level, and a multi-stage processing method to accurately extract the edge of the second evaluation liquid level, and the two complement each other. In the comprehensive analysis stage, through a unique mean calculation, a geometric model is constructed based on the liquid level deviation and a difference coefficient is calculated, combined with a preset threshold to match the additional liquid level value, it can effectively eliminate the errors of a single detection method and correct the detection deviation caused by environmental interference, image noise and other factors.

[0020] 2. The present invention realizes high flexibility of human-computer interaction and intelligent system operation by integrating a complete display and interaction module and a system control module; the control module realizes precise control of hardware equipment and intelligent scheduling of the work flow of each module through the collaborative work of the hardware control unit and the process control unit. When an abnormality occurs, it can automatically adjust the working strategy and provide timely feedback. Compared with traditional monitoring systems, the response speed is improved, the manual maintenance cost is effectively reduced, and the automation and intelligence level of liquid flow battery monitoring is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Further details, features and advantages of the present application are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which: Figure 1 Flowchart of the present invention. DETAILED DESCRIPTION

[0022] Several embodiments of the present application will be described in more detail below with reference to the accompanying drawings so that those skilled in the art can implement the present application. The present application can be embodied in many different forms and for many different purposes and should not be limited to the embodiments described herein. These embodiments are provided to make the present application comprehensive and complete and to fully convey the scope of the present application to those skilled in the art. The embodiments do not limit the present application.

[0023] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the relevant art and / or the context of this specification, and will not be interpreted in an idealized or overly formal sense unless expressly defined as such herein.

[0024] See also Figure 1 As shown, the present invention provides a technical solution: The liquid level monitoring system of the flow battery based on machine vision includes: Image acquisition module: obtains the liquid surface image information of the flow battery and preprocesses it; include: Capture images of the flow battery liquid level using an industrial camera; Choose the right camera based on the specific application scenario and requirements, such as resolution, frame rate, sensitivity and other parameters; For example, for liquid level measurement with high precision requirements, a high-resolution camera can be selected; for fast-flowing flow batteries, a high-frame-rate camera is required to capture the instantaneous liquid level status; Choose an appropriate lens, such as a fixed-focus lens or a zoom lens, based on the camera model, shooting distance, and field of view requirements. For example, when monitoring the liquid level of flow batteries at different locations, a zoom lens can be used to flexibly adjust the shooting range. Provide sufficient light for shooting to ensure image quality; There are many types of light sources, such as white light sources and infrared light sources. For flow battery liquid level monitoring, white light sources are usually used to provide clear images. At the same time, it is also necessary to select an appropriate light source arrangement method based on the shooting environment and the surface characteristics of the object, such as backlighting and frontlighting. Backlighting is suitable for highlighting the outline of the liquid level, facilitating liquid level detection and analysis. Preprocess the acquired images, including: Remove noise from images and improve image quality; Common filtering methods include mean filtering, median filtering, Gaussian filtering, etc. For example, Gaussian filtering can effectively remove Gaussian noise in an image and make the image smoother. By adjusting the contrast and brightness of the image, the image features can be enhanced to facilitate subsequent processing and analysis. For example, the histogram equalization method can enhance the contrast of the image and make the difference between the liquid level and the background more obvious. Convert a color image or grayscale image into a binary image, which means dividing the pixels in the image into two categories, including foreground and background. Common binarization methods include thresholding, including global thresholding and local thresholding. Global thresholding is suitable for situations where the grayscale difference between the liquid level and background in the image is large and relatively uniform; local thresholding is suitable for situations where the grayscale difference between the liquid level and background varies in different areas. Liquid level detection module: Analyzes the liquid level image of the flow battery to obtain the analytical evaluation liquid level of the flow battery; Specifically include: respectively obtaining a first evaluation liquid level and a second evaluation liquid level of the flow battery; and comprehensively analyzing the first evaluation liquid level and the second evaluation liquid level to obtain an analysis evaluation liquid level; The process of obtaining the first evaluation liquid level includes: Use the image processing library to read the image file containing the liquid surface and convert it into a grayscale image; A color image consists of three channels: red (R), green (G), and blue (B). When converted to a grayscale image, the formula used is: ; Perform a horizontal convolution operation on the grayscale image to obtain a horizontal convolution kernel: Let the image be , the convolution result is:

[0025] in is the element at the corresponding position in the horizontal convolution kernel; Perform a vertical convolution operation on the grayscale image to obtain a vertical convolution kernel: The convolution result is: ; in is the element at the corresponding position in the vertical convolution kernel; Calculate gradient magnitude and direction based on horizontal and vertical gradients; Including calculating the gradient amplitude based on the horizontal gradient and the vertical gradient; calculating the gradient direction through the inverse tangent function; The horizontal gradient is ; The vertical gradient is ; The gradient amplitude is: ; Gradient direction ; A preset amplitude threshold is set, and the gradient amplitude is compared with the threshold to extract the liquid surface contour on the binary edge image: each contour is composed of a series of points; Compare the gradient magnitude to a threshold: ; in It is the edge image after binarization, 255 represents edge pixels and 0 represents non-edge pixels; Filter out the contours related to the liquid surface according to the position, size and shape characteristics of the contours; For example, screening can be performed by judging whether the center of gravity position of the contour and the contour area are within a reasonable range; Calculate contour features, including perimeter, area, and center of gravity; Obtain the cross-sectional area of the container, obtain the area enclosed by the liquid surface contour through contour extraction, obtain the liquid surface height data based on the proportional relationship, and record it as the first evaluation liquid level; and performing a difference calculation between the obtained liquid level height data and the scale value in the image of the container to obtain a first liquid level deviation; The process of obtaining the second evaluation liquid level includes: Read the image and convert it to grayscale; Use a two-dimensional Gaussian function to construct a Gaussian kernel and perform convolution on the grayscale image to remove noise; Obtaining the gradient magnitude and direction obtained during the first evaluation liquid level calculation process; Traverse each pixel in the image, and for each pixel, determine the gradient magnitude of its adjacent pixels in the gradient direction according to its gradient direction; If the gradient magnitude of the pixel is not the local maximum, its value is set to 0, otherwise its original value is retained; Set high and low thresholds to process the image after non-maximum suppression, including: Pixels with gradient magnitudes greater than a high threshold are identified as strong edge pixels; Pixels with gradient magnitudes less than the low threshold are excluded; Pixels with gradient magnitudes between the high and low thresholds are retained as weak edge pixels if they are connected to strong edge pixels, otherwise they are excluded; Extract the contour of the image after double threshold processing; Based on the liquid level calculation process during the first evaluation liquid level acquisition process, the contour is screened, the contour features are calculated, and the liquid level is calculated based on the shape of the container; the obtained liquid level is recorded as the second evaluation liquid level, and the difference between the obtained liquid level data and the scale value in the container image is calculated to obtain a second liquid level deviation; The first evaluation liquid level and the second evaluation liquid level are comprehensively analyzed to obtain the analysis evaluation liquid level, including: Calculate the average of the first evaluation liquid level and the second evaluation liquid level as the base liquid level; After normalizing the first liquid level deviation and the second liquid level deviation, the first liquid level deviation and the second liquid level deviation are respectively used as the right angle sides of an isosceles right triangle, and the remaining sides are connected to obtain two isosceles right triangles. The areas of the two isosceles right triangles are calculated respectively, and the difference between their areas is calculated to obtain the difference coefficient; Three groups of threshold value ranges are preset, each group of threshold value ranges corresponds to an additional liquid level value, and the difference coefficient is matched with the three groups of threshold value ranges to obtain the additional liquid level value corresponding to the difference coefficient; The basic liquid level and the additional liquid level value are calculated and the analytical evaluation liquid level is obtained; Display and interaction module: output and present the liquid level detection results; Specifically include: Liquid level display unit: The specific height and capacity of the current liquid level are displayed in real time in numerical form; the numerical display is clear and accurate, allowing users to quickly obtain the actual situation of the current liquid level; By drawing graphs related to liquid level, the proportional relationship between liquid level and other parameters can be demonstrated; For example, in bar charts and pie charts, the color, size and other attributes of the graph can be dynamically changed according to the different states of the liquid level, so that users can more intuitively judge whether the liquid level is within the normal range; Display the change trend of liquid level over time in the form of a curve; Users can analyze the changing patterns of the liquid level by observing the curve trend and promptly detect abnormal fluctuations in the liquid level. For example, when the curve rises or falls sharply, it may indicate that there is leakage or abnormal filling of the flow battery. Parameter setting unit: It is used by users to set the camera's resolution, frame rate, exposure time, and gain parameters; For example, when the flow battery is located in a dark environment, the user can appropriately increase the camera's exposure time and gain to obtain a clear liquid level image. In scenarios where rapid capture of liquid level changes is required, the camera's frame rate can be increased. According to the actual working requirements of the flow battery, set the upper and lower limit alarm thresholds of the liquid level; When the liquid level exceeds the set threshold range, the system will automatically trigger the alarm mechanism and promptly notify the user to take appropriate measures; Operation control unit: Users can effectively control the image acquisition, processing and analysis process through the operation interface; Start acquisition: When the user needs to start the liquid level monitoring system, click the "Start Acquisition" button on the operation interface. The system will trigger the image acquisition module to start working and collect the liquid level image of the flow battery according to the set parameters and time intervals.

[0026] Stop acquisition: When liquid level monitoring is no longer needed, the user can click the "Stop Acquisition" button, and the system will immediately stop image acquisition, and also stop subsequent image preprocessing, liquid level detection, and data processing to save system resources.

[0027] Manually trigger liquid level detection: In addition to automatic liquid level detection at predetermined time intervals, users can also manually trigger liquid level detection operations based on actual conditions. For example, after performing certain special operations, users can manually trigger a liquid level detection immediately to obtain the latest liquid level information; System control module: controls the equipment in the image acquisition module and coordinates the workflow of each module in the system; Specifically include: Hardware control unit: By communicating with the interface of the hardware device, start and stop instructions are sent to the camera and light source. When the system starts working, the hardware control unit first sends a start signal to the camera and light source to put them into working state. When the system stops working, a stop signal is sent to turn off the camera and light source. According to the camera shooting parameters and light source brightness parameters set by the user in the parameter setting unit, the corresponding control instructions are sent to the hardware device; For example, the camera resolution, exposure time and other parameters set by the user are transmitted to the camera through the communication interface, so that it can capture images according to the new parameters; according to the requirements of ambient light and liquid level detection, the brightness and color of the light source and other parameters are adjusted; Process control unit: At preset time intervals, the system sends acquisition instructions to the image acquisition module to trigger the camera to acquire the liquid level image of the flow battery. For example, an image is collected every 1 minute to monitor the changes in liquid level in real time; Perform filtering, enhancement and binarization preprocessing operations on the collected image, then extract the liquid level edge and contour information from the preprocessed image, calculate the liquid level height, and finally store and analyze the liquid level data; During the entire process execution, the process control unit monitors the working status of each module in real time; If an abnormal situation occurs in a module, such as camera acquisition failure or abnormal liquid level detection results, the process control unit will take corresponding processing measures in a timely manner, such as re-triggering image acquisition, adjusting preprocessing parameters, etc., and feedback the abnormal information to the user so that the user can handle it in time.

[0028] The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The influencing weight factors and specific coefficient values in the formula are set by technical personnel in this field according to actual conditions, and can be adjusted and modified later.

[0029] The above description of the embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. The liquid level monitoring system of the flow battery based on machine vision is characterized by: include: Image acquisition module: obtains the liquid surface image information of the flow battery and preprocesses it; Liquid level detection module: Analyzes the liquid level image of the flow battery to obtain the analytical evaluation liquid level of the flow battery; Display and interaction module: output and present the liquid level detection results; System control module: controls the equipment in the image acquisition module and coordinates the workflow of each module in the system.

2. The liquid level monitoring system of a flow battery based on machine vision according to claim 1, characterized in that: The obtaining of liquid surface image information of the flow battery includes: Capture images of the flow battery liquid level using an industrial camera; Choose the appropriate lens according to the camera model, shooting distance, and field of view requirements; Provide ample light for shooting.

3. The liquid level monitoring system of a flow battery based on machine vision according to claim 2, characterized in that: Preprocess the acquired images, including: Remove noise from images; Enhance the features of the image by adjusting the contrast and brightness of the image; Convert a color image or grayscale image into a binary image and classify the pixels in the image into two categories, including foreground and background.

4. The liquid level monitoring system of a flow battery based on machine vision according to claim 1, characterized in that: The analysis based on the liquid level image of the flow battery to obtain the analysis and evaluation liquid level of the flow battery specifically includes: respectively obtaining a first evaluation liquid level and a second evaluation liquid level of the flow battery; The first evaluation liquid level and the second evaluation liquid level are comprehensively analyzed to obtain the analysis evaluation liquid level.

5. The liquid level monitoring system of a flow battery based on machine vision according to claim 4, characterized in that: The process of obtaining the first evaluation liquid level includes: Use the image processing library to read the image file containing the liquid surface and convert it into a grayscale image; Perform a horizontal convolution operation on the grayscale image to obtain a horizontal convolution kernel: Perform a vertical convolution operation on the grayscale image to obtain a vertical convolution kernel: Calculate gradient magnitude and direction based on horizontal and vertical gradients; Including calculating the gradient magnitude based on the horizontal gradient and the vertical gradient; calculating the gradient direction through the inverse tangent function Preset the amplitude threshold, compare the gradient amplitude with the threshold, and extract the liquid surface contour on the binary edge image: each contour consists of a series of points Filter out the contours related to the liquid surface according to the position, size and shape characteristics of the contours; Calculate contour features, including perimeter, area, and center of gravity; Obtain the cross-sectional area of the container, obtain the area enclosed by the liquid surface contour through contour extraction, obtain the liquid surface height data based on the proportional relationship, and record it as the first evaluation liquid level; The obtained liquid level height data is then subjected to difference calculation with the scale value in the image of the container to obtain a first liquid level deviation.

6. The liquid level monitoring system of a flow battery based on machine vision according to claim 5, characterized in that: The process of obtaining the second evaluation liquid level includes: Read the image and convert it to grayscale; Use a two-dimensional Gaussian function to construct a Gaussian kernel and perform convolution on the grayscale image to remove noise; Obtaining the gradient magnitude and direction obtained during the first evaluation liquid level calculation process; Traverse each pixel in the image, and for each pixel, determine the gradient magnitude of its adjacent pixels in the gradient direction according to its gradient direction; If the gradient magnitude of the pixel is not the local maximum, its value is set to 0, otherwise its original value is retained; Set high and low thresholds to process the image after non-maximum suppression, including: Pixels with gradient magnitudes greater than a high threshold are identified as strong edge pixels; Pixels with gradient magnitudes less than the low threshold are excluded; Pixels with gradient magnitudes between the high and low thresholds are retained as weak edge pixels if they are connected to strong edge pixels, otherwise they are excluded; Extract the contour of the image after double threshold processing; According to the liquid level height calculation process in the first evaluation liquid level acquisition process, the contour is screened, the contour features are calculated, and the liquid level height is calculated according to the shape of the container; the obtained liquid level height is recorded as the second evaluation liquid level, and the difference between the obtained liquid level height data and the scale value in the container image is calculated to obtain the second liquid level deviation.

7. The liquid level monitoring system of a flow battery based on machine vision according to claim 6, characterized in that: The first evaluation liquid level and the second evaluation liquid level are comprehensively analyzed to obtain the analysis evaluation liquid level, including: Calculate the average of the first evaluation liquid level and the second evaluation liquid level as the base liquid level; After normalizing the first liquid level deviation and the second liquid level deviation, the first liquid level deviation and the second liquid level deviation are respectively used as the right angle sides of an isosceles right triangle, and the remaining sides are connected to obtain two isosceles right triangles. The areas of the two isosceles right triangles are calculated respectively, and the difference between their areas is calculated to obtain the difference coefficient; Three groups of threshold value ranges are preset, each group of threshold value ranges corresponds to an additional liquid level value, and the difference coefficient is matched with the three groups of threshold value ranges to obtain the additional liquid level value corresponding to the difference coefficient; The basic liquid level and the additional liquid level value are summed to obtain the analytical evaluation liquid level.

8. The liquid level monitoring system of a flow battery based on machine vision according to claim 1, characterized in that: Display and interaction module, specifically including: Liquid level display unit: Display the specific height and capacity information of the current liquid level in real time in numerical form; By drawing graphs related to liquid level, the proportional relationship between liquid level and other parameters can be demonstrated; Display the change trend of liquid level over time in the form of a curve; Parameter setting unit: It is used by users to set the camera's resolution, frame rate, exposure time, and gain parameters; According to the actual working requirements of the flow battery, set the upper and lower limit alarm thresholds of the liquid level; Operation control unit: Users can effectively control the image acquisition, processing and analysis processes through the operation interface.

9. The liquid level monitoring system of a flow battery based on machine vision according to claim 1, characterized in that: System control module, specifically including: Hardware control unit: By communicating with the interface of the hardware device, start and stop instructions are sent to the camera and light source. When the system starts working, the hardware control unit first sends a start signal to the camera and light source to put them into working state. When the system stops working, a stop signal is sent to turn off the camera and light source. According to the camera shooting parameters and light source brightness parameters set by the user in the parameter setting unit, the corresponding control instructions are sent to the hardware device; Process control unit: At preset time intervals, the system sends acquisition instructions to the image acquisition module to trigger the camera to acquire the liquid level image of the flow battery. Perform filtering, enhancement and binarization preprocessing operations on the collected image, then extract the liquid level edge and contour information from the preprocessed image, calculate the liquid level height, and finally store and analyze the liquid level data; During the entire process execution, the process control unit monitors the working status of each module in real time.

Images