Sludge sedimentation detection method, system and device based on image intelligent analysis

Abstract

The invention relates to a sludge settlement detection method, system and device based on intelligent image analysis, and the method comprises the steps: regularly taking out uniform activated sludge, placing the sludge in a 1000mL measuring cylinder, and carrying out the stirring and uniform mixing through an adjustable magnetic stirrer according to preset parameters; the camera equipment collects image information and videos of the sludge sedimentation process in the measuring cylinder and transmits the image information and the videos to the local analysis system in real time, and the local analysis system processes and analyzes the image information and the videos to generate preliminary analysis data. The analysis cloud platform system performs calibration analysis by combining the preliminary analysis data and daily operation data of the sewage plant, generates a comprehensive analysis report and early warning information and feeds back the comprehensive analysis report and the early warning information to the local analysis system, and if the early warning information is abnormal early warning, the local analysis system triggers an equipment early warning mechanism after receiving the early warning information; and the abnormal state information is transmitted back to the analysis cloud platform system for recording and archiving.

Description

Technical Field

[0001] This application relates to the field of sludge treatment and detection technology, and in particular to a sludge settling detection method, system and device based on image intelligent analysis. Background Technology

[0002] In municipal wastewater treatment and industrial wastewater treatment, the settling performance of activated sludge is a key indicator reflecting the operational status of the wastewater treatment system, directly affecting wastewater treatment efficiency, effluent quality, and process stability. Among these, sludge settling ratio (SV) and sludge volume index (SVI) are the core parameters for evaluating sludge settling performance. Traditional testing methods mainly rely on manual operation, which can only obtain settling data at specific time points and cannot capture the dynamic changes throughout the entire settling process, making it difficult to predict the risk of sludge bulking or provide early warning of deterioration in settling performance. Summary of the Invention

[0003] To address the problems of traditional methods, this invention provides a sludge settling detection method based on intelligent image analysis, comprising the following steps: Periodically remove the uniform activated sludge and place it in a 1000mL graduated cylinder, then stir and mix it using the adjustable magnetic stirrer according to preset parameters. The camera device acquires image information and video of the sludge settling process inside the measuring cylinder, and transmits the image information and video to the local analysis system in real time; The local analysis system processes and analyzes the image information and video to generate preliminary analysis data. The analysis cloud platform system combines the preliminary analysis data with the daily operation data of the wastewater treatment plant for calibration analysis, generates a comprehensive analysis report and early warning information, and feeds the comprehensive analysis report and early warning information back to the local analysis system. If the warning information is an abnormal warning, the local analysis system will trigger the device warning mechanism upon receiving it and send the abnormal status information back to the analysis cloud platform system for recording and archiving.

[0004] In one possible implementation, the uniform activated sludge is periodically removed and placed in a 1000mL graduated cylinder, and stirred and mixed according to preset parameters using the adjustable magnetic stirrer, including: The preset parameters include stirring intensity and stirring duration, and the stirring intensity is dynamically adjusted according to the initial sludge concentration.

[0005] In one possible implementation, the camera device acquires image information and video of the sludge settling process inside the measuring cylinder, and transmits the image information and video to the local analysis system in real time, including: The video is periodically captured and the image information is processed in grayscale. The original image is then used for multiple calibrations of image recognition to identify the sludge settling ratio. The floating sludge and wastewater mixture is optimized and shielded, and the image is internally analyzed and the distortion is corrected through the local analysis system.

[0006] In one possible implementation, the local analysis system processes and analyzes the image information to generate preliminary analysis data, including: The limit for the proportion of floating sludge is set at 2%, and the limit for the proportion of sludge-water mixture is set at 5%. When the proportion exceeds the limit, an alert is issued and the monitoring is stopped.

[0007] One possible implementation includes: When the proportion is within the limit value, the sludge settling curve is obtained by analyzing the sludge settling proportion at different time periods. The curve is fitted, and the settling rate curve and settling acceleration curve are calculated by graphical differentiation. By comparing and analyzing the sludge settling curve, the sludge settling rate curve and the settling acceleration curve, the maximum value of the sludge settling rate is marked, and the sludge concentration and SVI value are predicted according to the settling model to determine the excellent settling performance and predict the risk of bulking. Calculate the settlement contribution ratio for each time period, predict settlement changes through big data simulation analysis, and guide process early warning and operation control.

[0008] In one possible implementation, the limit for the proportion of floating sludge is set at 2%, and the limit for the proportion of sludge-water mixture is set at 5%. When the proportion exceeds the limit, an alert is issued and the detection is stopped, including: If there is no floating sludge near the horizontal liquid surface, or if there is some sludge but its proportion is less than 2% of the total volume, the sludge settling is considered normal and normal testing is performed. If mud and water are mixed during the sludge settling process and the proportion is greater than 5% of the total volume, the sludge settling is judged to be abnormal, an early warning message is issued, and the detection is stopped. If there is no mud-water mixing during the sludge settling process, or if there is mud-water mixing but its proportion is less than 5% of the total volume, the sludge settling is considered normal and normal testing is performed.

[0009] In one possible implementation, by analyzing the proportion of sludge settling at different time periods, a sludge settling curve is obtained. The curve is then fitted, and the settling rate curve and settling acceleration curve are calculated by graphical differentiation, including: According to the preset parameters, the stirring time is set to 1, 2, 5, 10, 15, 20 and 30 minutes for detection time, and recorded as SV1, SV2, SV5, SV10, SV15, SV20 and SV30. The preset normal range of the sludge settling ratio is 10% to 70%. The sludge settling ratio within the detection period can be selected to generate a sludge settling ratio settling analysis report simultaneously. When the detected sludge settling is SV30, the detection data of sludge settling SV1, SV2, SV5, SV10, SV15 and SV20, as well as simulated sludge concentration and SVI value can be generated simultaneously.

[0010] A detection system for implementing the image-based intelligent analysis-based sludge settling detection method, comprising: The camera unit captures images and videos of the sludge settling process inside the measuring cylinder. The local analysis unit records the image information and the video, and generates preliminary analysis data; The cloud platform unit analyzes the preliminary analysis data and the daily operation data of the wastewater treatment plant for calibration analysis, and generates a comprehensive analysis report and early warning information.

[0011] A detection device, comprising: The main equipment, camera equipment, local analysis system, and analysis cloud platform system; The camera device is mounted on the main body of the device to record the image information and the video, and the camera device is communicatively connected to the local analysis system; The analysis cloud platform system interacts and connects with the local analysis system.

[0012] One possible implementation also includes: early warning equipment; The early warning device is communicatively connected to the local analysis system.

[0013] The beneficial effects of the sludge settling detection method, system, and device based on image intelligent analysis in this application are as follows: Magnetic stirring is used for simultaneous mixing, and the stirring degree can be adjusted according to the sludge concentration. Simultaneous reflection distortion correction ensures the accuracy of settling records, avoiding human and system errors. Through image recognition learning and online analysis, real-time analysis and early warning of activated sludge settling performance are performed. This can serve as an auxiliary means to predict changes in sludge settling performance, provide early warning of sludge bulking, and guide adjustments to municipal wastewater treatment processes. For users with online data, the prediction model can be corrected based on measured sludge concentration for system operation management and control, improving process operation stability. Cloud platform management is possible, forming an independent, lifelong analysis system with wastewater treatment plant users, enabling long-term real-time monitoring and analysis, and continuously optimizing the cloud system's analysis and management capabilities. It has universal applicability to the research and application of solid-liquid separation systems, assisting in process optimization and online detection, and improving process operation stability.

[0014] Other features and aspects of this application will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0015] The accompanying drawings, which are included in and form part of this specification, illustrate exemplary embodiments, features, and aspects of this application together with the specification and serve to explain the principles of this application.

[0016] Figure 1 The diagram illustrates the implementation process of the sludge settling detection method based on image intelligent analysis according to the present invention. Figure 2 The diagram shows the main structure of the device body of the present invention; Figure 3 The figure shown is a graph of the sludge settling detection method based on image intelligent analysis according to the present invention. Detailed Implementation

[0017] Various exemplary embodiments, features, and aspects of this application will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0018] It should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the present invention or simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the present invention.

[0019] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0020] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0021] Furthermore, to better illustrate this application, numerous specific details are provided in the following detailed embodiments. Those skilled in the art should understand that this application can be implemented without certain specific details. In some instances, methods, means, components, and circuits well-known to those skilled in the art have not been described in detail in order to highlight the main points of this application.

[0022] Example 1 like Figure 1 As shown, this application proposes a sludge settling detection method based on image intelligent analysis, comprising the following steps: S1. Periodically remove the uniform activated sludge and place it in a 1000mL graduated cylinder. Use an adjustable magnetic stirrer to stir and mix it according to the preset parameters. Periodically, uniform activated sludge is removed and placed in a 1000mL graduated cylinder. The sludge is then stirred and mixed using an adjustable magnetic stirrer according to preset parameters. This step ensures the uniformity of the sludge in its initial state for testing, preventing interference with subsequent sedimentation test results due to uneven initial distribution. Regular sampling allows for continuous monitoring of sludge sedimentation performance and timely understanding of its changes.

[0023] As an optional embodiment of this application, optionally, the uniform activated sludge is periodically removed and placed in a 1000mL graduated cylinder, and stirred and mixed according to preset parameters using the adjustable magnetic stirrer, including: The preset parameters include stirring intensity and stirring time, and the stirring intensity is dynamically adjusted according to the initial sludge concentration.

[0024] Specifically, the preset parameters include stirring intensity and stirring time. Stirring intensity can be represented by the rotation speed of the magnetic stirrer; different stirring intensities affect the degree of sludge mixing. Stirring time refers to the duration the stirrer operates; sufficient stirring time ensures thorough mixing of the sludge, avoiding deviations in test results due to insufficient mixing. The stirring intensity is dynamically adjusted based on the initial sludge concentration. Initial sludge concentration refers to the concentration of the activated sludge before stirring. The concentration affects the characteristics of the sludge; for example, higher-concentration sludge may require a higher stirring intensity to achieve good mixing, while lower-concentration sludge can have a lower stirring intensity. This dynamic adjustment ensures thorough mixing of the sludge at different initial concentrations, thereby guaranteeing the accuracy and reliability of subsequent test results.

[0025] S2. The camera equipment collects image information and video of the sludge settling process inside the measuring cylinder and transmits the image information and video to the local analysis system in real time; The camera equipment is used to capture the dynamic process of sludge settling, providing raw data for subsequent analysis and processing. Real-time transmission ensures that the local analysis system can obtain information and process it in a timely manner.

[0026] As an optional implementation of this application, optionally, the camera device acquires image information and video of the sludge settling process inside the measuring cylinder, and transmits the image information and video to the local analysis system in real time, including: The video is periodically captured and the image information is processed in grayscale. The original image is then used for multiple calibrations of image recognition to identify the sludge settling ratio. The floating sludge and wastewater mixture is optimized and shielded, and the image is internally analyzed and the distortion is corrected through the local analysis system.

[0027] Specifically, firstly, the video is periodically captured, and the image information is processed into grayscale. The time interval for periodically capturing images can be set according to actual needs, such as capturing one image per second, which can more accurately reflect the sludge settling process. Grayscale processing converts the color image to a grayscale image, reducing the amount of information in the image, facilitating subsequent image recognition and processing, and also improving processing speed. Secondly, multiple calibrations for image recognition are performed using the original images to identify the sludge settling ratio. The original images retain all the information, and by comparing and calibrating them with the processed images, the accuracy of image recognition can be improved. Identifying the sludge settling ratio refers to determining the proportion of sludge volume settling in the graduated cylinder to the total volume at a given moment; this is an important indicator for measuring sludge settling performance. In addition, optimized shielding is applied to the mixture of floating sludge and wastewater. The mixture of floating sludge and wastewater can interfere with the identification of settled sludge; optimized shielding eliminates these interfering factors, making the identification results more accurate. Simultaneously, the local analysis system corrects intrinsic parameter errors and distortions in the images. Due to the optical characteristics of the camera equipment and the shooting angle, the acquired images may contain intrinsic parameter errors and distortions. Correction eliminates these errors, ensuring the authenticity and accuracy of the images and providing reliable image data for subsequent analysis. S3. The local analysis system processes and analyzes image information and video to generate preliminary analysis data. The analysis cloud platform system combines the preliminary analysis data with the daily operation data of the sewage treatment plant for calibration analysis, generates a comprehensive analysis report and early warning information, and feeds the comprehensive analysis report and early warning information back to the local analysis system. The local analysis system is responsible for the initial processing of raw images and videos to obtain basic analytical data, while the analysis cloud platform system uses more operational data for calibration, which makes the analysis results more in line with the actual situation. The comprehensive analysis report and early warning information provide a comprehensive reference for subsequent decision-making.

[0028] As an optional implementation of this application, the local analysis system may optionally process and analyze the image information to generate preliminary analysis data, including: By analyzing the proportion of sludge settling at different time periods, sludge settling curves were obtained. The sludge settling curve is fitted, and the settling rate curve and settling acceleration curve are calculated by graphical differentiation.

[0029] Specifically, by analyzing the sludge settling percentage at different time periods, a sludge settling curve is obtained. Different time periods can be determined based on a pre-set detection duration, such as 1 minute, 2 minutes, or 5 minutes. The sludge settling curve is plotted with time on the x-axis and the sludge settling percentage on the y-axis. It visually reflects the sludge settling situation at different times, such as the settling speed and the stability of the settling. Based on this, the sludge settling curve was fitted, and the settling rate curve and settling acceleration curve were calculated using graphical differentiation. Curve fitting aims to obtain a smooth curve that more accurately reflects the sludge settling trend, eliminating curve fluctuations caused by factors such as detection errors. Graphical differentiation involves mathematically differentiating the fitted settling curve to obtain the settling rate curve, which reflects the change in sludge settling velocity at different times. Differentiating the settling rate curve again yields the settling acceleration curve, which reflects the rate of change of settling velocity, enabling a more in-depth analysis of the dynamic characteristics of sludge settling.

[0030] As an optional implementation of this application, the local analysis system may optionally process and analyze the image information to generate preliminary analysis data, including: By comparing and analyzing the sludge settling curve, the sludge settling rate curve and the settling acceleration curve, the maximum value of the sludge settling rate is marked, and the sludge concentration and SVI value are predicted according to the settling model to determine the excellent settling performance and predict the risk of bulking. Calculate the settlement contribution ratio for each time period, predict settlement changes through big data simulation analysis, and guide process early warning and operation control.

[0031] Specifically, the sedimentation model predicts sludge concentration and SVI (sludge volume index) to determine the quality of sedimentation and predict the risk of bulking. The sedimentation model is a mathematical model built upon extensive experimental data and theoretical analysis. By inputting relevant data such as sludge sedimentation curves, it can predict sludge concentration and SVI. The SVI is an important indicator of sludge sedimentation performance; a lower SVI indicates better sedimentation performance, while a higher SVI indicates poorer performance. Determining the quality of sedimentation performance allows for timely understanding of the sludge's condition, while predicting the risk of bulking enables early detection of potential sludge bulking problems, providing time for preventative measures. Simultaneously, the settling contribution ratio for each time period is calculated, and changes in settling performance are predicted through big data simulation analysis to guide process early warning and operational control. The settling contribution ratio refers to the degree to which sludge settling contributes to overall settling performance in different time periods. Calculating this ratio allows for a deeper understanding of sludge settling patterns. Big data simulation analysis utilizes computer technology to analyze and process large amounts of historical and real-time data to predict future trends in sludge settling performance. Based on these predictions, early warning and operational control of wastewater treatment processes can be implemented, process parameters can be optimized, and wastewater treatment efficiency can be improved.

[0032] Furthermore, as an optional embodiment of this application, optionally, by comparing and analyzing the sludge settling curve, the sludge settling rate curve, and the settling acceleration curve, the maximum value of the sludge settling rate is marked, and the sludge concentration and SVI value are predicted according to the settling model to determine the settling performance as excellent and predict the risk of bulking, including: According to the preset parameters, the stirring time is set to 1, 2, 5, 10, 15, 20 and 30 minutes for detection time, and recorded as SV1, SV2, SV5, SV10, SV15, SV20 and SV30. The preset normal range of the sludge settling ratio is 10% to 70%. The sludge settling ratio within the detection period can be selected to generate a sludge settling ratio settling analysis report simultaneously. When the detected sludge settling is SV30, the detection data of sludge settling SV1, SV2, SV5, SV10, SV15 and SV20, as well as simulated sludge concentration and SVI value can be generated simultaneously.

[0033] Specifically, based on the preset stirring time settings, detection durations of 1, 2, 5, 10, 15, 20, and 30 minutes were determined and denoted as SV1, SV2, SV5, SV10, SV15, SV20, and SV30, respectively, where SV represents the sludge settling ratio. The sludge settling ratio refers to the percentage of settled sludge volume to the total volume at a given moment; it is a commonly used indicator for measuring sludge settling performance. Figure 3 The curve graph shows that the sludge settling ratio is within a preset normal range of 10% to 70%. When the detected sludge settling ratio is within this range, it indicates that the sludge settling performance is basically normal; if it exceeds this range, there may be an abnormal settling situation. During the sludge settling ratio testing within the specified testing period, a sludge settling ratio and settling analysis report can be generated simultaneously. When the sludge settling ratio is SV30, test data for sludge settling ratios SV1, SV2, SV5, SV10, SV15, and SV20, along with simulated sludge concentrations and SVI values, can be generated simultaneously. This setup aims to comprehensively understand the sludge performance at different settling times. By comparing the sludge settling ratio at different time points, the changing trend of sludge settling can be more clearly grasped. Simultaneously, generating simulated sludge concentrations and SVI values ​​further supplements the understanding of sludge characteristics, providing richer data support for accurately determining settling performance and predicting risks.

[0034] S4. If the warning information is an abnormal warning, the local analysis system will trigger the device warning mechanism after receiving it and send the abnormal status information back to the analysis cloud platform system for recording and archiving. Upon receiving the data, the local analysis system will trigger the device's early warning mechanism, such as issuing audible and visual alarms, sending SMS notifications to relevant personnel, and simultaneously transmitting abnormal status information back to the analysis cloud platform system for recording and archiving.

[0035] As an optional implementation of this application, the analysis cloud platform system may optionally perform calibration analysis by combining the preliminary analysis data and the daily operation data of the wastewater treatment plant, including: The limits for the proportion of floating sludge are set at 2% and the limit for the proportion of sludge-water mixture is set at 5%. When the proportion exceeds the limit, an alert is issued and the monitoring is stopped. If there is no floating sludge near the horizontal liquid surface, or if there is some sludge but its proportion is less than 2% of the total volume, the sludge settling is considered normal and normal testing is performed. If mud and water are mixed during the sludge settling process and the proportion is greater than 5% of the total volume, the sludge settling is judged to be abnormal, an early warning message is issued, and the detection is stopped. If there is no mud-water mixing during the sludge settling process, or if there is mud-water mixing but its proportion is less than 5% of the total volume, the sludge settling is considered normal and normal testing is performed.

[0036] Specifically, firstly, a limit of 2% is set for the proportion of floating sludge and 5% for the proportion of sludge mixed with water. These two limits are determined based on extensive experimental data and actual operational experience of wastewater treatment plants. When the proportion of floating sludge or the proportion of sludge mixed with water exceeds the corresponding limit, it indicates an abnormality in the sludge settling state. When the proportion exceeds the limit, the system will issue an early warning and stop monitoring. Issuing an early warning is to promptly remind staff to pay attention to the abnormality, and stopping monitoring is to avoid obtaining invalid or inaccurate data, and also to prevent damage to the equipment caused by the abnormality. If there is no floating sludge near the horizontal liquid surface, or if there is some sludge but its proportion is less than 2% of the total volume, the sludge settling is considered normal, and normal monitoring continues. In this case, the floating sludge has a small impact on sludge settling and will not interfere with the accuracy of the test results. If there is sludge mixed with water during the sludge settling process and its proportion is greater than 5% of the total volume, the sludge settling is considered abnormal, an early warning is issued, and monitoring stops. An excessively high proportion of sludge mixed with water indicates that the sludge and water are not well separated, resulting in poor settling. In this case, continuing monitoring is meaningless, and the abnormality needs to be addressed promptly. If there is no mud-water mixing during sludge settling, or if mud-water mixing exists but its proportion is less than 5% of the total volume, then the sludge settling is considered normal, and normal testing is performed. In this case, the impact of mud-water mixing on the test results is within an acceptable range, ensuring the validity of the test data.

[0037] Thus, through steps S1, S2, S3, and S4, magnetic stirring is used for simultaneous mixing, and the stirring intensity can be adjusted according to the sludge concentration. Simultaneously, reflective distortion correction ensures the accuracy of sedimentation records, avoiding human and systemic errors. Through image recognition learning and online analysis, the settling performance of activated sludge is analyzed and warned in real time. This can serve as an auxiliary means to predict changes in sludge settling performance, provide early warnings of sludge bulking, and guide adjustments to municipal wastewater treatment processes. For users with online data, the predictive model can be corrected based on measured sludge concentrations for system operation management and control, improving process stability. Cloud platform management is possible, forming an independent, lifelong analysis system with wastewater treatment plant users, enabling long-term real-time monitoring and analysis, and continuously optimizing the cloud system's analysis and management capabilities.

[0038] Example 2 Based on the implementation principle of Embodiment 1, in another aspect of this application, a detection system is provided for implementing an image-based intelligent analysis-based sludge settling detection method, comprising: The camera unit captures images and videos of the sludge settling process inside the measuring cylinder; The local analysis unit records image information and video, generating preliminary analysis data; The cloud platform unit is analyzed, and calibration analysis is performed by combining preliminary analysis data with daily operation data of the wastewater treatment plant to generate a comprehensive analysis report and early warning information.

[0039] In this specific embodiment, the camera unit records the sludge settling process within the graduated cylinder for different detection durations and transmits the video and real-time images to the local analysis unit. The local analysis unit communicates with the camera unit, acquires the video and real-time images, generates preliminary analysis data from the video and real-time images, and derives a sludge settling curve by analyzing the sludge settling percentage at different time periods. The sludge settling curve is then fitted, and graphical differentiation is performed to calculate the settling rate curve and settling acceleration curve. The analysis cloud platform unit communicates with the local analysis unit, combines the preliminary analysis data with the wastewater treatment plant's daily operation data for calibration analysis, generates a comprehensive analysis report and early warning information, and feeds the comprehensive analysis report and early warning information back to the local analysis system.

[0040] Example 3 A detection device includes: a main body, a camera device 7, a local analysis system, and an analysis cloud platform system; like Figure 2 The camera device 7 is installed on the main body of the device to record image information and video. The camera device 7 is also connected to the local analysis system, and the analysis cloud platform system is interactively connected to the local analysis system.

[0041] The main body of the equipment includes: a measuring chamber 1, an adjustable backlight 2, a measuring cylinder 4, a cleaning and maintenance door 9, an adjustable light reflector 3, and an adjustable magnetic stirrer 6. The measuring chamber 1 has an open top and a hollow interior. The adjustable magnetic stirrer 6 is located inside the measuring chamber 1. There are two measuring cylinders 4, both placed above the adjustable magnetic stirrer 6. The adjustable backlight 2 and the camera device 7 are respectively located on the front and rear sides of the measuring cylinder 4. The side wall of the measuring chamber 1 has through holes corresponding to the cleaning and maintenance door 9. The bottom of the measuring chamber 1 has a drainage and fixing groove 8, which corresponds to the adjustable magnetic stirrer 6.

[0042] In one specific embodiment, it further includes: an early warning device, which is communicatively connected to a local analysis system.

[0043] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A sludge settling detection method based on image intelligent analysis, characterized in that, Includes the following steps: Periodically remove the uniform activated sludge and place it in a 1000mL graduated cylinder. Use an adjustable magnetic stirrer to stir and mix it according to the preset parameters. The image information and video of the sludge settling process inside the measuring cylinder are collected by a camera device, and the image information and video are transmitted to the local analysis system in real time. The local analysis system processes and analyzes the image information and video to generate preliminary analysis data. The analysis cloud platform system combines the preliminary analysis data with the daily operation data of the wastewater treatment plant for calibration analysis, generates a comprehensive analysis report and early warning information, and feeds the comprehensive analysis report and early warning information back to the local analysis system. If the warning information is an abnormal warning, the local analysis system will trigger the device warning mechanism upon receiving it and send the abnormal status information back to the analysis cloud platform system for recording and archiving.

2. The sludge settling detection method based on image intelligent analysis according to claim 1, characterized in that, The local analysis system processes and analyzes the image information to generate preliminary analysis data, including: The video is periodically captured and the image information is processed in grayscale. The original image is then used for multiple calibrations of image recognition to identify the sludge settling ratio. The floating sludge and wastewater mixture is optimized and shielded, and the image is internally analyzed and the distortion is corrected through the local analysis system.

3. The sludge settling detection method based on image intelligent analysis according to claim 2, characterized in that, The video is periodically captured, and the image information is processed into grayscale. Multiple calibrations are then performed using the original images to identify the sludge settling percentage, including: By analyzing the proportion of sludge settling at different time periods, sludge settling curves were obtained. The sludge settling curve is fitted, and the settling rate curve and settling acceleration curve are calculated by graphical differentiation.

4. The sludge settling detection method based on image intelligent analysis according to claim 3, characterized in that, Also includes: By comparing and analyzing the sludge settling curve, the sludge settling rate curve and the settling acceleration curve, the maximum value of the sludge settling rate is marked, and the sludge concentration and SVI value are predicted according to the settling model to determine the excellent settling performance and predict the risk of bulking. Calculate the settlement contribution ratio for each time period, predict settlement changes through big data simulation analysis, and guide process early warning and operation control.

5. The sludge settling detection method based on image intelligent analysis according to claim 4, characterized in that, By comparing and analyzing the sludge settling curve, the sludge settling rate curve, and the settling acceleration curve, the maximum sludge settling rate is marked. Based on the settling model, the sludge concentration and SVI value are predicted to determine excellent settling performance and predict the risk of bulking, including: According to the preset parameters, the stirring time is set to 1, 2, 5, 10, 15, 20 and 30 minutes for detection time, and recorded as SV1, SV2, SV5, SV10, SV15, SV20 and SV30. The preset normal range of the sludge settling ratio is 10% to 70%. The sludge settling ratio within the detection period can be selected to generate a sludge settling ratio settling analysis report simultaneously. When the detected sludge settling is SV30, the detection data of sludge settling SV1, SV2, SV5, SV10, SV15 and SV20, as well as simulated sludge concentration and SVI value can be generated simultaneously.

6. The sludge settling detection method based on image intelligent analysis according to claim 1, characterized in that, The analysis cloud platform system combines the preliminary analysis data and the wastewater treatment plant's daily operation data to perform calibration analysis, including: The limits for the proportion of floating sludge are set at 2% and the limit for the proportion of sludge-water mixture is set at 5%. When the proportion exceeds the limit, an alert is issued and the monitoring is stopped. If there is no floating sludge near the horizontal liquid surface, or if there is some sludge but its proportion is less than 2% of the total volume, the sludge settling is considered normal and normal testing is performed. If mud and water are mixed during the sludge settling process and the proportion is greater than 5% of the total volume, the sludge settling is judged to be abnormal, an early warning message is issued, and the detection is stopped. If there is no mud-water mixing during the sludge settling process, or if there is mud-water mixing but its proportion is less than 5% of the total volume, the sludge settling is considered normal and normal testing is performed.

7. The sludge settling detection method based on image intelligent analysis according to claim 1, characterized in that, The uniform activated sludge is periodically removed and placed in a 1000mL graduated cylinder, and stirred and mixed according to preset parameters using the adjustable magnetic stirrer, including: The preset parameters include stirring intensity and stirring duration, and the stirring intensity is dynamically adjusted according to the initial sludge concentration.

8. A detection system for implementing the sludge settling detection method based on image intelligent analysis as described in claim 1, characterized in that, include: The camera unit captures images and videos of the sludge settling process inside the measuring cylinder; The local analysis unit records the image information and the video, and generates preliminary analysis data; The cloud platform unit analyzes the preliminary analysis data and the daily operation data of the wastewater treatment plant for calibration analysis, and generates a comprehensive analysis report and early warning information.

9. A detection device, characterized in that, include: The main equipment, camera equipment, local analysis system, and analysis cloud platform system; The camera device is mounted on the main body of the device to record the image information and the video, and the camera device is communicatively connected to the local analysis system; The analysis cloud platform system interacts and connects with the local analysis system.

10. The detection device according to claim 9, characterized in that, Also includes: Early warning equipment; The early warning device is communicatively connected to the local analysis system.

Images