A method for monitoring dissolved oxygen in a biofilm, an optimized oxygen supply method, a system and a device

Abstract

The present application discloses a method for monitoring dissolved oxygen in a biofilm, an optimized oxygen supply method, a system and a device, relating to the technical field of wastewater treatment. The monitoring method includes: obtaining image data of a biofilm of a membrane aerated biofilm reactor (MABR) sewage treatment device during sewage treatment; extracting features from the image data to obtain image feature parameters; inputting the image feature parameters into a biofilm dissolved oxygen prediction model to obtain an effective concentration of dissolved oxygen in the biofilm output by the biofilm dissolved oxygen prediction model; the biofilm dissolved oxygen prediction model is obtained by training based on a machine learning model. The present application provides a method for monitoring dissolved oxygen in a biofilm using image recognition by a machine learning model, which overcomes the defects of high cost, easy damage and great maintenance difficulty of microelectrodes, and realizes effective monitoring of dissolved oxygen in the biofilm at low cost.

Description

Technical Field

[0001] The present application relates to the technical field of wastewater treatment, and in particular to a method for monitoring dissolved oxygen in a biofilm, a method for optimizing oxygen supply, a system and equipment. Background Art

[0002] Membrane Aerated Biofilm Reactor (MABR) is a new type of sewage treatment process that combines gas separation membrane technology with biofilm sewage treatment technology. This process uses MABR as a microbial carrier and provides bubble-free aeration for microorganisms, forming aerobic, anoxic, and anaerobic biological environments from close to the membrane layer to far away from the membrane layer, achieving the effect of simultaneous denitrification and carbon removal. Compared with traditional aeration processes, it has the advantages of low energy consumption, biofilm is not easy to fall off, and high oxygen utilization rate.

[0003] In MABR, oxygen is supplied from the lumen of the membrane fibers and diffuses through the membrane into the biofilm. Therefore, the DO (Dissolved Oxygen) concentration in the biofilm decreases from the inner layer of the biofilm (close to the membrane) along the biofilm thickness to the biofilm-liquid boundary layer; at the same time, nutrients and other pollutants diffuse into the biofilm from the bulk liquid. Compared with traditional biofilm reactors with co-diffusion biofilms, electron acceptors (such as nitrate and nitrite) and electron donors (ammonia nitrogen and chemical oxygen demand) diffuse into the MABR biofilm from opposite directions, forming a special counter-diffusion biofilm.

[0004] Since oxygen diffuses from the inside, it is difficult to monitor the dissolved oxygen in the solution to reflect the oxygen situation in the biofilm. Even if the dissolved oxygen in the solution is zero, the biofilm can still achieve good water purification due to the formation of an aerobic inner layer and an anaerobic outer layer biological environment. The dissolved oxygen situation in the biofilm can be monitored through microelectrodes and other technologies, but microelectrodes are expensive, easy to damage, and difficult to maintain, making them difficult to use in actual working conditions. Summary of the invention

[0005] The purpose of this application is to provide a method for monitoring dissolved oxygen in biofilms, a method, system and equipment for optimizing oxygen supply, so as to overcome the defects of microelectrodes such as high cost, easy damage and difficult maintenance, and to achieve low-cost and effective monitoring of dissolved oxygen in biofilms.

[0006] To achieve the above objectives, this application provides the following solutions.

[0007] In a first aspect, the present application provides a method for monitoring dissolved oxygen in a biofilm. The method for monitoring dissolved oxygen in the biofilm is applied to a membrane aeration biofilm reactor. The aeration biofilm reactor includes a biochemical reaction unit, and a heterogeneous mass transfer biofilm assembly is provided in the biochemical reaction unit. The heterogeneous mass transfer biofilm assembly includes a biofilm and an MABR membrane assembly. The method for monitoring dissolved oxygen in the biofilm includes: when using the membrane aeration biofilm reactor for sewage treatment, acquiring image data of the biofilm during the sewage treatment process; extracting features from the image data to obtain image feature parameters; inputting the image feature parameters into a biofilm dissolved oxygen prediction model to obtain the effective concentration of dissolved oxygen in the biofilm output by the biofilm dissolved oxygen prediction model; the biofilm dissolved oxygen prediction model is obtained by training based on a machine learning model.

[0008] Optionally, the image feature parameters include: the bubble density on the biofilm surface, the surface bubble size, the biofilm thickness, the biofilm color, and the biofilm temperature distribution.

[0009] In a second aspect, the present application provides an optimized oxygen supply method based on image recognition. The optimized oxygen supply method based on image recognition is applied to a membrane aeration biofilm reactor. The aeration biofilm reactor includes a biochemical reaction unit and a gas delivery unit. A heterogeneous mass transfer biofilm assembly is provided in the biochemical reaction unit. The heterogeneous mass transfer biofilm assembly includes a biofilm and an MABR membrane assembly. The gas delivery unit is connected to the heterogeneous mass transfer biofilm assembly. The optimized oxygen supply method based on image recognition includes: when using the membrane aeration biofilm reactor for sewage treatment, acquiring image data of the biofilm and water quality monitoring parameters in the biochemical reaction unit during the sewage treatment process; extracting features from the image data to obtain image feature parameters; inputting the image feature parameters into a biofilm dissolved oxygen prediction model to obtain the effective concentration of dissolved oxygen in the biofilm output by the biofilm dissolved oxygen prediction model; the biofilm dissolved oxygen prediction model is obtained by training based on a machine learning model; generating an oxygen supply control signal according to the effective concentration of dissolved oxygen in the biofilm and the water quality monitoring parameters, and adjusting the oxygen supply amount of the gas delivery unit.

[0010] Optionally, the water quality monitoring parameters include: influent ammonia nitrogen, effluent ammonia nitrogen, total nitrogen, COD (Chemical Oxygen Demand) concentration, and DO concentration in the biochemical reaction unit; the image feature parameters include: the bubble density on the biofilm surface, the surface bubble size, the biofilm thickness, the biofilm color, and the biofilm temperature distribution.

[0011] Optionally, the way to adjust the oxygen supply amount of the gas delivery unit includes: adjusting one or more of the aeration pressure, the gas flow rate, and the aeration mode.

[0012] In a third aspect, the present application provides an optimized oxygen supply system based on image recognition. The optimized oxygen supply system based on image recognition is applied to a membrane aeration biofilm reactor. The aeration biofilm reactor includes a biochemical reaction unit and a gas delivery unit. An interfacial mass transfer biofilm assembly is arranged in the biochemical reaction unit. The interfacial mass transfer biofilm assembly includes a biofilm and an MABR membrane assembly. The gas delivery unit is connected to the interfacial mass transfer biofilm assembly. The optimized oxygen supply system based on image recognition includes: an oxygen supply adjustment device, an image recognition unit, a dissolved oxygen monitoring device, and an intelligent terminal. The oxygen supply adjustment device is arranged between the gas delivery unit and the interfacial mass transfer biofilm assembly. The image recognition unit and the dissolved oxygen monitoring device are arranged in the biochemical reaction unit. Both the image recognition unit and the dissolved oxygen monitoring device are connected to the intelligent terminal, and the intelligent terminal is connected to the control end of the oxygen supply adjustment device. The image recognition unit is used to collect image data of the biofilm, and the dissolved oxygen monitoring device is used to obtain water quality monitoring parameters. The intelligent terminal is used to adopt the above-mentioned optimized oxygen supply method based on image recognition according to the image data and the water quality monitoring parameters to obtain an oxygen supply control signal, and control the oxygen supply adjustment device according to the oxygen supply control signal to adjust the oxygen distribution amount.

[0013] Optionally, the oxygen supply adjustment device includes one or both of a membrane gas supply pressure monitoring component and a flow rate adjustment component.

[0014] Optionally, the image recognition unit includes one or more of an underwater camera, a laser scanning imager, and an infrared camera.

[0015] Optionally, the spacing distance between the image recognition unit and the interfacial mass transfer biofilm assembly is: 30 mm - 1000 mm; the spacing distance between the dissolved oxygen monitoring device and the interfacial mass transfer biofilm assembly is: 10 mm - 30 mm.

[0016] In a fourth aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the computer program to implement the above-mentioned method for monitoring dissolved oxygen in a biofilm or the above-mentioned optimized oxygen supply method based on image recognition.

[0017] According to the specific embodiments provided by the present application, the present application has the following technical effects.

[0018] The present application provides a method for monitoring dissolved oxygen in biofilm, an optimized oxygen supply method, a system and a device. The monitoring method includes: obtaining image data of the biofilm during the sewage treatment process and water quality monitoring parameters in the biochemical reaction unit; extracting features from the image data to obtain image feature parameters; inputting the image feature parameters into a biofilm dissolved oxygen prediction model to obtain the effective concentration of dissolved oxygen in the biofilm output by the biofilm dissolved oxygen prediction model; the biofilm dissolved oxygen prediction model is obtained by training based on a machine learning model. The present application provides a method for monitoring dissolved oxygen in biofilm using image recognition based on a machine learning model, which overcomes the defects of high cost, easy damage and difficult maintenance of microelectrodes, and realizes the effective monitoring of dissolved oxygen in biofilm at low cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0020] Figure 1 It is a schematic flow chart of a method for monitoring dissolved oxygen in biofilm provided by an embodiment of the present application.

[0021] Figure 2 It is a schematic flow chart of an optimized oxygen supply method based on image recognition provided by an embodiment of the present application.

[0022] Figure 3 It is a schematic structural diagram of an optimized oxygen supply system based on image recognition provided by an embodiment of the present application.

[0023] Figure 4 It is a schematic structural diagram of a computer device provided by an embodiment of the present application.

[0024] Description of the reference numerals: 1, inlet tank; 2, gas delivery unit; 201, gas supply device; 202, gas flow meter; 203, pressure gauge; 3, biochemical reaction unit; 301, heterogeneous mass transfer biofilm assembly; 302, image recognition unit; 303, dissolved oxygen monitoring device; 4, intelligent terminal; 5, outlet tank; 6, peristaltic pump. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0026] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0027] The monitoring method, optimized oxygen supply method, system, and equipment for dissolved oxygen in the biofilm of the present application are all applied to a membrane aeration biofilm reactor, such as Figure 3 shown, the membrane aeration biofilm reactor includes: an influent tank 1, an effluent tank 5, a gas delivery unit 2, and a biochemical reaction unit 3.

[0028] The inlet of the biochemical reaction unit 3 is connected to the influent tank 1, and a peristaltic pump 6 is provided between the inlet of the biochemical reaction unit 3 and the influent tank 1; the outlet of the biochemical reaction unit 3 is connected to the effluent tank 5; an interfacial mass transfer biofilm assembly 301 is provided in the biochemical reaction unit 3, and the interfacial mass transfer biofilm assembly 301 is perpendicular to the water flow direction.

[0029] The gas delivery unit 2 is connected to the inlet of the interfacial mass transfer biofilm assembly 301 through a gas pipe. The gas delivery unit 2 includes a gas supply device 201, a gas flow meter 202, and a pressure gauge 203. Among them, the gas flow meter 202 is used to adjust and monitor the gas flow, and the pressure gauge 203 monitors the aeration pressure.

[0030] The working principle of the membrane aeration biofilm reactor is specifically as follows.

[0031] The wastewater to be treated containing organic matter and ammonia nitrogen in the influent tank 1 is introduced into the biochemical reaction unit 3 through the peristaltic pump 6 and discharged from the outlet to the effluent tank 5 after a certain residence time.

[0032] Before the formal operation of the gas delivery unit 2, membrane hanging needs to be completed. First, a certain amount of nitrifying sludge is added to the biochemical reaction unit 3, and at the same time, wastewater containing ammonia nitrogen is configured to form a nitrifying biofilm on the surface of the interfacial mass transfer biofilm assembly 301. When a thin layer of yellowish-brown biofilm appears on the surface, it is regarded as the completion of membrane hanging.

[0033] During wastewater treatment, the wastewater flows from the inlet tank 1 into the biochemical reaction unit 3, and a pollutant monitor is used to monitor the concentration of pollutants in the influent. After the wastewater to be treated enters the biochemical reaction unit 3, the gas delivery unit 2 supplies gas to the heterogeneous mass transfer biofilm module 301 through a pipeline. The gas is transferred to the biofilm through the membrane filaments. Due to the attenuation of oxygen concentration during the gas transfer process, microorganisms at different distances from the surface of the heterogeneous mass transfer biofilm module 301 exhibit different pollutant removal characteristics. For example, aerobic bacteria (nitrifying bacteria) are in the inner layer, and anaerobic (facultative anaerobic) bacteria (denitrifying bacteria) are in the outer layer, realizing the purification of wastewater. The purified water is discharged from the outlet to the outlet tank 5. A detector for detecting the pollutant concentration is provided in the outlet tank 5.

[0034] The heterogeneous mass transfer biofilm module 301 includes a biofilm and an MABR membrane module, and the biofilm is attached to the MABR membrane module.

[0035] Due to changes in pollutant levels and biofilm states, the dissolved oxygen level in the biofilm will change accordingly. The characteristics of the biofilm can be obtained by image recognition, and the oxygen level can be regulated accordingly. Thereby, a method, an optimized oxygen supply method, a system and equipment for monitoring the dissolved oxygen in the biofilm are provided.

[0036] In an exemplary embodiment, as Figure 1 shown, a method for monitoring the dissolved oxygen in a biofilm is provided, including the following steps 101 to 103.

[0037] Step 101, when treating wastewater using a membrane aeration biofilm reactor, obtain image data of the biofilm during the wastewater treatment process.

[0038] Step 102, extract features from the image data to obtain image feature parameters.

[0039] Step 103, input the image feature parameters into a biofilm dissolved oxygen prediction model to obtain the effective concentration of dissolved oxygen in the biofilm output by the biofilm dissolved oxygen prediction model; the biofilm dissolved oxygen prediction model is obtained by training based on a machine learning model.

[0040] Implementing the above steps 101 - 103 can achieve effective monitoring of the dissolved oxygen in the biofilm at low cost.

[0041] In another exemplary embodiment, in the above step 102, a deep learning algorithm is used to extract image feature parameters. The extracted image feature parameters are used for machine learning model training with the measured concentration of dissolved oxygen in the biofilm to obtain a biofilm dissolved oxygen prediction model. The image feature parameters include: the bubble density on the biofilm surface, the surface bubble size, the biofilm thickness, the biofilm color, and the biofilm temperature distribution, etc. The machine learning model is constructed based on the Open CV library.

[0042] In another exemplary embodiment, the biofilm dissolved oxygen prediction model in step 103 above is obtained by training and optimizing a machine learning model according to a predetermined evaluation index. The machine learning model includes an ACO-BP (Ant Colony Optimization-BackPropagation, a multi-layer feedforward neural network pre-trained based on the ant colony algorithm) neural network.

[0043] In another exemplary embodiment, the prediction accuracy of the biofilm dissolved oxygen prediction model in step 103 above needs to be verified regularly based on the evaluation index.

[0044] In one exemplary embodiment, as Figure 2 shown, an optimized oxygen supply method based on image recognition is provided, which includes the following steps 201-step 204.

[0045] Step 201, when treating sewage using a membrane aeration biofilm reactor, obtain the image data of the biofilm during the sewage treatment process and the water quality monitoring parameters in the biochemical reaction unit.

[0046] Step 202, extract features from the image data to obtain image feature parameters.

[0047] Step 203, input the image feature parameters into the biofilm dissolved oxygen prediction model to obtain the effective concentration of dissolved oxygen in the biofilm output by the biofilm dissolved oxygen prediction model; the biofilm dissolved oxygen prediction model is obtained by training based on a machine learning model.

[0048] Step 204, generate an oxygen supply control signal according to the effective concentration of dissolved oxygen in the biofilm and the water quality monitoring parameters, and adjust the oxygen supply amount of the gas delivery unit.

[0049] In another exemplary embodiment, the water quality monitoring parameters in step 201 above include: influent ammonia nitrogen, effluent ammonia nitrogen, total nitrogen, COD concentration, and DO concentration in the biochemical reaction unit.

[0050] In another exemplary embodiment, in step 201 above, the image data is also screened and the clearly photographed area is cropped, and the image size, contrast, and brightness are unified.

[0051] In another exemplary embodiment, the specific method for extracting image feature parameters in step 202 is as follows: Install the Open CV library in a Python environment. First, use cv2.imread() to read the image, perform preprocessing such as Gaussian image filtering and edge detection, calculate the number of pixels to obtain the biofilm color information; fit the edge contours, calculate the biofilm thickness based on the circumscribed rectangle of the biofilm contour; perform secondary processing on the preprocessed image, such as grayscaling, binarization, and background removal, and use distance transformation or erosion and dilation to separate and count the microbubbles that may appear on the biofilm surface.

[0052] Obtain the biofilm thermal image data through an infrared detector, use the Open CV library to visualize the temperature distribution characteristics, and normalize the thermal point values to obtain the biofilm thermodynamic parameters.

[0053] In another exemplary embodiment, the machine learning model training process in step 203 is as follows:

[0054] Use the obtained image feature parameters and their corresponding measured dissolved oxygen concentrations in the biofilm (exemplarily, the measured concentration is obtained through microelectrode testing) to construct a model data set, and divide the model data set into a training set and a test set. The model data set can be constructed not only using the measured data of the laboratory system, but also using the data of network open source databases and paper collections, or can be constructed by combining multiple methods, which is not limited here. Use the training set and the test set to train and test the ACO-BP neural network. Further, evaluate the performance of the model through the mean square error, mean absolute error, and determination coefficient, and adjust the hyperparameters to optimize the model fitting effect.

[0055] In another exemplary embodiment, the specific implementation method of step 203 is as follows: Input the intermittently obtained image feature parameters into the biofilm dissolved oxygen prediction model to output the effective dissolved oxygen concentration in the biofilm. The obtained effective dissolved oxygen concentration in the biofilm and the water quality monitoring parameters (including: ammonia nitrogen, total nitrogen, COD, and DO concentration in the biochemical reaction unit measured in the inlet and outlet pools) are transmitted to the intelligent terminal through a data line. The intelligent terminal selects an adjustment mode according to the dissolved oxygen guidance value of a specific biochemical reaction, mainly including two schemes: adjusting the output power and adjusting the aeration mode, so as to control the aeration volume of the blower and correct the current biofilm dissolved oxygen level.

[0056] In another exemplary embodiment, in step 204, according to the effective dissolved oxygen concentration in the biofilm and the collected and measured water quality monitoring parameters, adjust the control measures of the gas delivery unit to complete the entire optimized oxygen distribution process. Among them, the methods for adjusting the oxygen supply amount of the gas delivery unit include: adjusting one or more of the aeration pressure, gas flow rate, and aeration mode.

[0057] The optimized oxygen supply method based on image recognition in the above embodiments of the present application introduces an image recognition and machine learning module to predict the dissolved oxygen level of the heterogeneous mass transfer biofilm, providing a new optimization method for the regulation of dissolved oxygen in biofilm treatment, and having the following beneficial effects compared with the prior art.

[0058] 1. Improve treatment efficiency or economy: In a membrane aeration biofilm reactor, the dissolved oxygen monitoring is transferred from the solution to the biofilm, and the obtained results are beneficial to guiding the fine control of the aeration volume, and to a certain extent, avoiding insufficient aeration or over-aeration.

[0059] 2. Provide intelligent decision-making support for the dissolved oxygen monitoring of the biofilm. By inputting the real-time monitoring data into the artificial intelligence model, decision-making parameters can be obtained, the water treatment process is more accurate, and at the same time, it can make a quick response according to the real-time changes of the water quality.

[0060] 3. Easy to expand and applicable to different scenarios. In the present application, for different scenarios, corresponding sample data is set to train and update the machine learning model, and its application in different scenarios can be realized.

[0061] In an exemplary embodiment, an optimized oxygen supply system based on image recognition is provided, as Figure 3 shown, including an oxygen supply regulating device, an image recognition unit 302, a dissolved oxygen monitoring device 303, and an intelligent terminal 4. Among them, the oxygen supply regulating device is arranged between the gas delivery unit 2 and the heterogeneous mass transfer biofilm assembly 301; the image recognition unit 302 and the dissolved oxygen monitoring device 303 are arranged in the biochemical reaction unit 3; both the image recognition unit 302 and the dissolved oxygen monitoring device 303 are connected to the intelligent terminal 4, and the intelligent terminal 4 is connected to the control end of the oxygen supply regulating device; the image recognition unit 302 is used to collect the image data of the biofilm, and the dissolved oxygen monitoring device 303 is used to obtain the water quality monitoring parameters; the intelligent terminal 4 is used to adopt the optimized oxygen supply method based on image recognition in the above embodiments according to the image data and the water quality monitoring parameters, obtain an oxygen supply control signal, and control the oxygen supply regulating device according to the oxygen supply control signal to adjust the oxygen distribution amount.

[0062] In another exemplary embodiment, the above image recognition unit 302 is one or a combination of an underwater camera, a laser scanning imager, and an infrared camera. The above image recognition unit 302 is located at 30 mm - 1000 mm from the heterogeneous mass transfer biofilm assembly; the above dissolved oxygen monitoring device 303 is located at 10 mm - 30 mm from the above heterogeneous mass transfer biofilm assembly. The above heterogeneous mass transfer biofilm assembly 301 includes a biofilm and a MABR membrane assembly, the biofilm is attached to the MABR membrane assembly, and the biofilm thickness is greater than 100 microns. The gas in the gas delivery unit 2 is air or oxygen.

[0063] In another exemplary embodiment, the above oxygen supply regulating device includes a membrane gas supply pressure monitoring component and a flow rate regulating component, which are used to adjust the aeration pressure, adjust the gas flow rate, and adjust the aeration mode, so as to further regulate the oxygen distribution amount.

[0064] In the optimized oxygen supply system according to the embodiments of the present application, during the treatment process, the real-time image of the biofilm is recorded by the image recognition unit, and the image features are extracted by using the deep learning algorithm. The extracted image feature parameters and the dissolved oxygen parameter of the biofilm (i.e., the measured concentration of dissolved oxygen in the biofilm) are input into the machine learning model, and the machine learning model is trained and optimized according to the predetermined evaluation index to obtain the dissolved oxygen prediction model of the biofilm. Further, according to the effective concentration of dissolved oxygen in the biofilm and the collected water quality data, the control measures of the gas delivery unit are adjusted to complete the entire optimized oxygen distribution process.

[0065] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 4 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes the above method for monitoring the dissolved oxygen in the biofilm or the above optimized oxygen supply method based on image recognition.

[0066] Those skilled in the art can understand that Figure 4 the structure shown in

[0067] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are realized.

[0068] Configure simulated wastewater with an ammonia nitrogen concentration of 50 mg / L in the inlet sump 1 as the water source. This simulated wastewater contains 1 g / L of sodium bicarbonate, 0.2 g / L of glucose, and 1 mL / L of trace elements, and the pH value of this simulated wastewater is between 7 and 7.5.

[0069] Select two identical biochemical reaction units for comparison. One uses the optimized oxygen supply method of this application (hereinafter referred to as R1), and the other uses the traditional dissolved oxygen control method (hereinafter referred to as R2). Introduce nitrifying sludge from the aerobic tank of the sewage treatment plant with an MLVSS of 10 g / L into the two biochemical reaction units, maintain the hydraulic retention time at 24 h, and the dissolved oxygen at 1 - 2 mg / L until the nitrifying biofilm is initially formed. The pollutant indexes of the effluent should be stable at this stage. In this example, the ammonia nitrogen removal rate is 80 - 90%, and the total nitrogen removal rate is stable at 40%.

[0070] Comparative Example 1: Configure synthetic wastewater with an ammonia nitrogen concentration of approximately 30 mg / L and a COD concentration of approximately 100 mg / L in the inlet sump. The aeration pressure of the gas delivery unit is 5 kPa. The effluent indexes are an ammonia nitrogen concentration of approximately 0 and a total nitrogen concentration of approximately 15 mg / L. The dissolved oxygen concentration in the biochemical reaction unit is approximately 2 mg / L. According to the oxygen demand value of the nitrification reaction, do not adjust the gas delivery method of the heterogeneous mass transfer biofilm component of R2; while in R1, according to the predicted effective dissolved oxygen concentration in the biofilm by the optimized ACO - BP model, it is 4.5 mg / L, and the optimized aeration pressure is 1 kPa. After optimization, the ammonia nitrogen concentration of the effluent of R1 is approximately 0, and the total nitrogen concentration is approximately 8 mg / L, while saving 80% of the gas generation energy consumption.

[0071] Comparative Example 2: Configure synthetic wastewater with an ammonia nitrogen concentration of approximately 100 mg / L and a COD concentration of approximately 200 mg / L in the inlet sump. The aeration pressure of the gas delivery unit is 2 kPa. The effluent indexes are an ammonia nitrogen concentration of approximately 30 mg / L and a total nitrogen concentration of approximately 70 mg / L. The dissolved oxygen concentration in the biochemical reaction unit is approximately 0 mg / L. According to the oxygen demand value of the nitrification reaction, adjust the aeration pressure to 4 kPa until the dissolved oxygen concentration in R2 is 2 mg / L. After adjustment, the ammonia nitrogen concentration of the effluent is 5 mg / L, and the total nitrogen concentration of the effluent is approximately 70 mg / L; while in R1, according to the predicted effective dissolved oxygen concentration in the biofilm by the optimized ACO - BP model, it is 1.5 mg / L, and the optimized aeration pressure is 3 kPa. After optimization, the ammonia nitrogen concentration of the effluent of R1 is approximately 10 mg / L, and the total nitrogen concentration is approximately 60 mg / L, while saving 25% of the gas generation energy consumption.

[0072] It should be noted that during use, the ACO-BP model embedded in the intelligent terminal can be replaced later, and the artificial neural network model built into the platform also needs to be calibrated regularly. That is, after the artificial neural network model has been simulated and verified, its reliability during use needs to be regularly checked. If the accuracy decreases, the model needs to be replaced or retrained.

[0073] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties.

[0074] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, database, or other medium used in the various embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0075] The databases involved in the various embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the various embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0076] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0077] Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for monitoring dissolved oxygen in a biofilm, characterized in that, The method for monitoring dissolved oxygen in the biofilm is applied to a membrane aeration biofilm reactor, which includes a biochemical reaction unit. An interfacial mass transfer biofilm assembly is arranged in the biochemical reaction unit. The interfacial mass transfer biofilm assembly includes a biofilm and an MABR membrane assembly. The method for monitoring dissolved oxygen in the biofilm includes: When using the membrane aeration biofilm reactor for sewage treatment, acquiring image data of the biofilm during the sewage treatment process; Performing feature extraction on the image data to obtain image feature parameters. Specifically, using a deep learning algorithm to extract the image feature parameters, which include: the bubble density on the biofilm surface, the surface bubble size, the biofilm thickness, the biofilm color, and the biofilm temperature distribution; Inputting the image feature parameters into a biofilm dissolved oxygen prediction model to obtain the effective concentration of dissolved oxygen in the biofilm output by the biofilm dissolved oxygen prediction model. The biofilm dissolved oxygen prediction model is obtained by training based on a machine learning model.

2. An optimized oxygen supply method based on image recognition, characterized in that, The optimized oxygen supply method based on image recognition is applied to a membrane aeration biofilm reactor, which includes a biochemical reaction unit and a gas delivery unit. An interfacial mass transfer biofilm assembly is arranged in the biochemical reaction unit. The interfacial mass transfer biofilm assembly includes a biofilm and an MABR membrane assembly. The gas delivery unit is connected to the interfacial mass transfer biofilm assembly. The optimized oxygen supply method based on image recognition includes: When using the membrane aeration biofilm reactor for sewage treatment, acquiring image data of the biofilm and water quality monitoring parameters in the biochemical reaction unit during the sewage treatment process; Performing feature extraction on the image data to obtain image feature parameters. Specifically, using a deep learning algorithm to extract the image feature parameters, which include: the bubble density on the biofilm surface, the surface bubble size, the biofilm thickness, the biofilm color, and the biofilm temperature distribution; Inputting the image feature parameters into a biofilm dissolved oxygen prediction model to obtain the effective concentration of dissolved oxygen in the biofilm output by the biofilm dissolved oxygen prediction model. The biofilm dissolved oxygen prediction model is obtained by training based on a machine learning model; Generating an oxygen supply control signal according to the effective concentration of dissolved oxygen in the biofilm and the water quality monitoring parameters, and adjusting the oxygen supply amount of the gas delivery unit.

3. The optimized oxygen supply method based on image recognition according to claim 2, characterized in that The water quality monitoring parameters include: influent ammonia nitrogen, effluent ammonia nitrogen, total nitrogen, COD concentration, and DO concentration in the biochemical reaction unit.

4. The optimized oxygen supply method based on image recognition according to claim 2, wherein, The ways to adjust the oxygen supply amount of the gas delivery unit include: adjusting one or more of the aeration pressure, the gas flow rate, and the aeration mode.

5. An optimized oxygen supply system based on image recognition, characterized in that, The optimized oxygen supply system based on image recognition is applied to a membrane aeration biofilm reactor, which includes a biochemical reaction unit and a gas delivery unit. An interfacial mass transfer biofilm assembly is arranged in the biochemical reaction unit. The interfacial mass transfer biofilm assembly includes a biofilm and an MABR membrane assembly. The gas delivery unit is connected to the interfacial mass transfer biofilm assembly; The optimized oxygen supply system based on image recognition includes: an oxygen supply adjustment device, an image recognition unit, a dissolved oxygen monitoring device, and an intelligent terminal; The oxygen supply regulating device is arranged between the gas delivery unit and the heterogeneous mass transfer biofilm assembly; The image recognition unit and the dissolved oxygen monitoring device are arranged in the biochemical reaction unit; both the image recognition unit and the dissolved oxygen monitoring device are connected to the intelligent terminal, and the intelligent terminal is connected to the control end of the oxygen supply regulating device; The image recognition unit is used to collect the image data of the biofilm, and the dissolved oxygen monitoring device is used to obtain the water quality monitoring parameters; The intelligent terminal is used to adopt the optimized oxygen supply method based on image recognition according to any one of claims 2-4 by using the image data and the water quality monitoring parameters, obtain an oxygen supply control signal, and control the oxygen supply regulating device according to the oxygen supply control signal to adjust the oxygen distribution amount.

6. The optimized oxygen supply system based on image recognition according to claim 5, wherein, The oxygen supply regulating device includes one or both of a membrane gas supply pressure monitoring component and a flow rate regulating component.

7. The optimized oxygen supply system based on image recognition according to claim 5, wherein The image recognition unit includes one or more of an underwater camera, a laser scanning imager, and an infrared camera.

8. The optimized oxygen supply system based on image recognition according to claim 5, characterized in that, The distance between the image recognition unit and the heterogeneous mass transfer biofilm assembly is 30 mm - 1000 mm; the distance between the dissolved oxygen monitoring device and the heterogeneous mass transfer biofilm assembly is 10 mm - 30 mm.

9. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the method for monitoring the dissolved oxygen in the biofilm according to any one of claim 1 or the optimized oxygen supply method based on image recognition according to any one of claims 2-4.

Images