Secondary sedimentation tank control method, device and equipment and storage medium

Abstract

The invention discloses a secondary sedimentation tank control method, device and equipment and a storage medium. The method comprises the following steps: periodically collecting various parameter data in a secondary sedimentation tank area range; constructing a float sludge probability prediction model and carrying out model training; taking the various parameter data as input of a float sludge probability prediction model, and outputting a predicted float sludge probability value; establishing a corresponding relation between the predicted float sludge probability value and the concentration value of the upper-layer float sludge of the secondary sedimentation tank; and executing different control strategies on the secondary sedimentation tank according to the predicted float sludge probability value output by the float sludge probability prediction model. According to the technical scheme provided by the embodiment of the invention, the probability that the secondary sedimentation tank generates float sludge can be predicted, and the corresponding control decision is executed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of secondary sedimentation tank sewage treatment, and particularly relates to a secondary sedimentation tank control method, device, equipment and storage medium. BACKGROUND

[0002] Sewage treatment refers to measures taken to change the properties of sewage so as to pose no harm to the environment. Sewage treatment is generally divided into three levels, and the aeration tank and the secondary sedimentation tank are the main body of the secondary sewage treatment. Waste water and activated sludge are fully contacted in the aeration tank to form a mixed liquid, and the soluble organic pollutants in the waste water are adsorbed and degraded by the activated sludge. Then the mixed liquid enters the secondary sedimentation tank, the purified clean water is discharged from the upper layer of the secondary sedimentation tank, and the activated sludge settled in the lower layer is backflowed to the aeration tank to maintain the content of activated sludge in the aeration tank.

[0003] However, during the settling process in the secondary sedimentation tank, due to the loose structure of the sludge, or the untimely discharge of the sludge at the bottom, or the generation of a large amount of nitrogen gas in the denitrification reaction, and other reasons, the sludge floats in the upper layer of the secondary sedimentation tank to form floating sludge, which not only affects the stability of the sewage treatment system, but also carries a large amount of activated sludge particles into the water outlet, causing the concentration of suspended solids in the water outlet to rise sharply, and reducing the content of activated sludge in the entire sewage treatment system.

[0004] Therefore, it is urgent to propose a new sewage treatment scheme, which can predict the floating sludge risk in the secondary sedimentation tank in real time, and automatically execute the secondary sedimentation tank control decision when the floating sludge risk is predicted, to complete the settling of the floating sludge. SUMMARY

[0005] The present application provides a secondary sedimentation tank control method, device, equipment and storage medium, which can execute the secondary sedimentation tank control decision to settle the floating sludge when the floating sludge risk is predicted.

[0006] In a first aspect, the present application provides a secondary sedimentation tank control method, comprising:

[0007] periodically collecting various types of parameter data in the range of the secondary sedimentation tank area;

[0008] constructing a floating sludge probability prediction model and performing model training; inputting the various types of parameter data into the floating sludge probability prediction model as input, and outputting a predicted floating sludge probability value; the predicted floating sludge probability value and the floating sludge concentration in the upper layer of the secondary sedimentation tank establish a corresponding relationship;

[0009] According to the predicted floating sludge probability value output by the floating sludge probability prediction model, different control strategies are executed for the secondary sedimentation tank.

[0010] Further, the various types of parameter data include pressure change rate data, nitrate concentration data and sludge concentration gradient data;

[0011] After collecting the various types of parameter data, the various types of parameter data are preprocessed, specifically: the various types of parameter data of different collection frequencies are time-aligned; for parameter data that is continuously missing for less than a preset duration, linear interpolation is used for filling; for parameter data that is continuously missing for greater than or equal to a preset duration, historical same-period mean value filling is used; for the same type of parameter data, all numerical values are scaled to a unit interval through linear normalization.

[0012] Further, in the process of constructing the floating sludge probability prediction model, historical data of various types of parameter data and corresponding floating sludge concentration values are collected, and a training set and a test set are divided in proportion;

[0013] The test set is used to adjust the parameters in the floating sludge probability prediction model, and the test set is used to verify the accuracy of the floating sludge probability prediction model;

[0014] The historical data of various types of parameter data in the test set is input into the floating sludge probability prediction model, and the parameters in the floating sludge probability prediction model are adjusted, so that the error between the predicted floating sludge probability value output by the floating sludge probability prediction model and the floating sludge probability value converted from the floating sludge concentration value is within a preset range.

[0015] Further, after the floating sludge probability prediction model outputs the predicted floating sludge probability value, it further includes:

[0016] According to the predicted floating sludge probability value, different types of carbon sources are selected; according to the nitrate nitrogen deficiency and the influent flow, the dosage of the carbon source to be put is determined;

[0017] The carbon source types include: NMP wastewater, biogas and sodium acetate.

[0018] Further, a sludge distribution model is constructed based on the various types of parameter data;

[0019] In the sludge distribution model, the pressure change rate data, the nitrate concentration data, the sludge concentration gradient data, the sludge settling rate and the activated sludge concentration are input, and the sludge bulking index is output.

[0020] Further, after obtaining the predicted floating sludge probability value output by the floating sludge probability prediction model and the sludge bulking index output by the sludge distribution model, according to the first preset threshold and the second preset threshold set in advance, different control strategies are executed for the secondary sedimentation tank;

[0021] If the floating sludge probability value exceeds the first preset threshold, the hydraulic flushing system in the secondary sedimentation tank is started;

[0022] If the sludge bulking index exceeds the second preset threshold, the influent load of the secondary sedimentation tank is reduced and the mud scraping speed of the mud scraper in the secondary sedimentation tank is increased;

[0023] If the floating sludge probability value exceeds the first preset threshold value, and the sludge bulking index exceeds the second preset threshold value, a defoaming agent is automatically added to the secondary sedimentation tank and the reflux ratio is adjusted.

[0024] Further, according to the size of the predicted floating sludge probability value, a low-risk preset range, a medium-risk preset range and a high-risk preset range are divided.

[0025] When the predicted floating sludge probability value output by the model is in the low-risk preset range, data recording is performed.

[0026] When the predicted floating sludge probability value output by the model is in the medium-risk preset range, the sludge discharge frequency is increased.

[0027] When the predicted floating sludge probability value output by the model is in the high-risk preset range, aeration is performed at the bottom of the secondary sedimentation tank and the sludge scraping speed is increased.

[0028] In a second aspect, the present application provides a secondary sedimentation tank control device, comprising:

[0029] A data acquisition module is configured to periodically acquire various types of parameter data in the range of the secondary sedimentation tank.

[0030] A model construction module is configured to construct a floating sludge probability prediction model and perform model training; the various types of parameter data are used as input of the floating sludge probability prediction model, and a predicted floating sludge probability value is output; the predicted floating sludge probability value is in a corresponding relationship with the upper-layer floating sludge concentration of the secondary sedimentation tank.

[0031] A decision execution module is configured to execute different control strategies for the secondary sedimentation tank according to the predicted floating sludge probability value output by the floating sludge probability prediction model.

[0032] In a third aspect, the present application provides an electronic device, comprising:

[0033] At least one processor; and a memory connected in communication with the at least one processor;

[0034] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the steps of the secondary sedimentation tank control method of any embodiment of the present application.

[0035] In a fourth aspect, the present application provides a computer readable storage medium, which stores computer instructions for enabling a processor to execute the steps of the secondary sedimentation tank control method of any embodiment of the present application.

[0036] Compared with the prior art, the present application has the following beneficial effects:

[0037] The technical solution in this embodiment of the invention first periodically collects various parameter data within the secondary sedimentation tank area; then, it constructs a sludge probability prediction model and trains the model; finally, based on the predicted sludge probability value output by the sludge probability prediction model, it implements different control strategies for the secondary sedimentation tank. Through the solution in this embodiment of the invention, the sludge situation in the secondary sedimentation tank can be predicted, and based on the prediction results, the secondary sedimentation tank can be systematically controlled to reduce the risk of sludge floating. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only preferred embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 A schematic flowchart of a secondary sedimentation tank control method provided in an embodiment of the present invention;

[0040] Figure 2 A schematic diagram of the framework of the sludge distribution model provided in an embodiment of the present invention;

[0041] Figure 3 A schematic diagram of the sludge treatment process provided in an embodiment of the present invention;

[0042] Figure 4 This is a schematic diagram of a secondary sedimentation tank control device provided in an embodiment of the present invention;

[0043] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] Figure 1 This is a flowchart illustrating a secondary sedimentation tank control method provided in an embodiment of the present invention. This embodiment is applicable to situations where risk warnings are issued for floating sludge in a secondary sedimentation tank. The method can be executed by a secondary sedimentation tank control device, which can be implemented in software and / or hardware and can be configured in an electronic device.

[0046] like Figure 1 As shown, the method specifically includes:

[0047] S1, periodically collecting various types of parameter data in the area of the secondary sedimentation tank.

[0048] The various types of parameter data include pressure rate of change data, nitrate concentration data, and sludge concentration gradient data, etc.

[0049] It should be noted that the pressure rate of change data can be collected by a pressure transmitter, the nitrate concentration data can be collected by a nitrate analyzer, and the sludge concentration gradient data can be collected by a sludge concentration meter. The pressure transmitter is deployed at the bottom of the secondary sedimentation tank to collect the bottom pressure, which reflects the accumulation rate of the gas (ammonia and nitrogen) at the bottom. The nitrate analyzer is deployed at a depth of 2-3 meters in the secondary sedimentation tank to collect the concentration of nitrate, which reflects the activity of denitrification reaction. The sludge concentration meter is deployed at different depths in the secondary sedimentation tank to collect the sludge concentration of each layer, which reflects the settlement and suspension of sludge.

[0050] During the collection of various types of parameter data, it is necessary to construct a time sequence. Preferably, the time steps and time intervals of the time sequence are set, for example, 60 time steps are set as a group of time sequence, and the time interval between adjacent time steps is 10 minutes. The data corresponding to different time steps are assigned weights, for example, the weight of the parameter data corresponding to 1 hour before the floating sludge floats is increased to 0.35, and the baseline weight is 0.05. According to the weight of each time step, the same type of parameter data is weighted and summed as the actual input of the floating sludge probability prediction model.

[0051] Since the data collection frequencies of different sensors are not consistent, the parameter data cannot be completely aligned in time sequence. Therefore, it is necessary to perform interpolation processing on the collected data.

[0052] Preferably, after collecting various types of parameter data, data preprocessing is performed on the various types of parameter data.

[0053] The data preprocessing process includes: aligning the various types of parameter data with different collection frequencies in time sequence; for parameter data that is continuously missing for less than a preset duration, performing linear interpolation filling; for parameter data that is continuously missing for greater than or equal to a preset duration, performing historical same period mean filling; for the same type of parameter data, all numerical values are scaled to the unit interval by linear normalization.

[0054] For example, the acquisition frequency of the pressure transmitter collecting the pressure change rate data is set to 10 min / time, the acquisition frequency of the nitrate analyzer collecting the nitrate concentration data is set to 30 min / time, and the acquisition frequency of the sludge concentration meter collecting the sludge concentration gradient data is set to 1 h / time. If 10 min / time is taken as the unified acquisition frequency, the nitrate concentration data and the sludge concentration gradient data need to be supplemented, and at this time, the nitrate concentration data and the sludge concentration gradient data both have data missing. If the preset time length is 30 min, the nitrate concentration data needs to be linearly interpolated and filled, and the sludge concentration gradient data needs to be filled with the historical same period mean value.

[0055] In addition, for the abnormal value in the parameter data, it needs to be replaced by the median of the adjacent time data first, and then linear normalization processing is completed.

[0056] S2, a floating sludge probability prediction model is constructed and model training is performed; various types of parameter data are taken as inputs of the floating sludge probability prediction model, and a predicted floating sludge probability value is output; the predicted floating sludge probability value and the upper layer floating sludge concentration of the secondary sedimentation tank establish a corresponding relationship.

[0057] In the construction process of the floating sludge probability prediction model, historical data of various types of parameter data and corresponding floating sludge concentration values are collected, the floating sludge concentration values are converted into floating sludge probability values, and a training set and a test set are divided in proportion; the test set is used to adjust the parameters in the floating sludge probability prediction model, and the test set is used to verify the accuracy of the floating sludge probability prediction model.

[0058] The historical data of various types of parameter data in the test set are input into the floating sludge probability prediction model, the parameters in the floating sludge probability prediction model are adjusted, so that the error between the predicted floating sludge probability value output by the floating sludge probability prediction model and the floating sludge probability value converted from the floating sludge concentration value is within a preset range.

[0059] After a large amount of data training, the parameters in the floating sludge probability prediction model are obtained, which are represented as follows:

[0060]

[0061] In the formula, P represents the predicted floating sludge probability output by the floating sludge probability prediction model, P represents the pressure change rate data, N represents the nitrate concentration data, and X represents the sludge concentration gradient data.

[0062] For example, when the pressure transmitter collects the pressure change rate data of 0.82 kilopascal per minute, the nitrate analyzer collects the nitrate concentration data of 4.3 milligrams per liter, and the sludge concentration meter collects the sludge concentration gradient data of 0.73 grams per liter per centimeter. Substituted into the floating sludge probability calculation formula, the floating sludge probability is about 0.91, at this time, the control aeration system is started, and the sludge scraper is controlled to increase the sludge scraping speed.

[0063] In some embodiments, the sludge distribution model is constructed based on various parameter data.

[0064] Figure 2 A schematic diagram of the framework of the sludge distribution model provided by the embodiments of the present application is shown in FIG. 1. Figure 2 As shown in FIG. 1, in the sludge distribution model, the input is the rate of change of pressure data, nitrate concentration data, sludge concentration gradient data, sludge settling rate and activated sludge concentration, and the output is the sludge bulking index.

[0065] Optionally, in the process of constructing the sludge distribution model, historical data of various parameter data and corresponding sludge bulking index are collected, and a training set and a test set are divided in proportion; the historical data of various parameter data in the test set is input into the sludge distribution model, and the parameters in the sludge distribution model are adjusted so that the error between the sludge bulking index output by the sludge distribution model and the collected sludge bulking index is within a preset range; or, the historical data of various parameter data and the corresponding sludge bulking index are collected, and a mapping relationship between various parameter data and the sludge bulking index is constructed.

[0066] Sludge bulking is a common maladaptive phenomenon in activated sludge process, which is manifested as lightening, swelling and deterioration of sludge settling performance, leading to difficulty in separating sludge and water in the secondary sedimentation tank, and loss of sludge with effluent. Sludge bulking index (SVI) is one of the core indicators for judging sludge bulking, which is defined as the volume occupied by 1 gram of dry sludge after 30 minutes of precipitation of the mixed liquor in the aeration tank. When the SVI value exceeds 150, it indicates that the sludge is about to or has been in a bulking state, and control measures need to be taken immediately.

[0067] Further, after obtaining the predicted floating sludge probability value output by the floating sludge probability prediction model and the sludge bulking index output by the sludge distribution model, different control strategies are performed on the secondary sedimentation tank according to the first preset threshold and the second preset threshold set in advance.

[0068] If the floating sludge probability value exceeds the first preset threshold, the hydraulic flushing system in the secondary sedimentation tank is started;

[0069] If the sludge bulking index exceeds the second preset threshold, the water inflow load of the secondary sedimentation tank is reduced and the mud scraping speed of the mud scraper in the secondary sedimentation tank is increased;

[0070] If both the predicted floating sludge probability value and the sludge bulking index exceed the preset threshold, the defoaming agent is automatically added to the secondary sedimentation tank and the reflux ratio is adjusted (to 150%).

[0071] S3, according to the predicted floating sludge probability value output by the floating sludge probability prediction model, different control strategies are performed on the secondary sedimentation tank.

[0072] Figure 3A frame diagram of the floating sludge treatment process provided by the embodiments of the present application is shown in FIG. 1. Figure 3 As shown in FIG. 1, in the process of floating sludge, first, the pressure change rate data is collected by the pressure transmitter, the nitrate concentration data is collected by the nitrate analyzer, and the sludge concentration gradient data is collected by the sludge concentration meter; then these parameter data are input into the pre-trained floating sludge probability prediction model to output the predicted floating sludge probability value; finally, the aeration + sludge scraping speed-up, the increase of sludge discharge frequency or data recording and other control strategies are performed according to the predicted floating sludge probability.

[0073] Further, according to the size of the predicted floating sludge probability value, a low-risk preset range, a medium-risk preset range and a high-risk preset range are divided.

[0074] When the predicted floating sludge probability value output by the model is in the low-risk preset range, data recording is performed.

[0075] When the predicted floating sludge probability value output by the model is in the medium-risk preset range, the sludge discharge frequency is increased.

[0076] When the predicted floating sludge probability value output by the model is in the high-risk preset range, aeration is performed at the bottom of the secondary sedimentation tank and the sludge scraping speed is increased.

[0077] In the high-risk preset range, by increasing the sludge scraping speed to twice the original sludge scraping speed, the sludge block structure can be destroyed. In the medium-risk preset range, by increasing the sludge discharge frequency to twice the original sludge discharge frequency, the sludge discharge time can be increased and the sludge layer height can be reduced.

[0078] Further, in the process of increasing the sludge scraping speed, the sludge scraping frequency and the scraping plate inclination angle are adjusted according to the activated sludge concentration of the bottom layer of the secondary sedimentation tank.

[0079] For example, when the activated sludge concentration of the bottom layer of the secondary sedimentation tank is less than 6 g / L, the sludge scraping frequency is adjusted to 0.5 times / hour and the scraping plate inclination angle is adjusted to 30 degrees; when the activated sludge concentration of the bottom layer of the secondary sedimentation tank is between 6 g / L and 10 g / L, the sludge scraping frequency is adjusted to 1 time / hour and the scraping plate inclination angle is adjusted to 45 degrees; when the activated sludge concentration of the bottom layer of the secondary sedimentation tank is more than 10 g / L, the sludge scraping frequency is adjusted to 2 times / hour and the scraping plate inclination angle is adjusted to 60 degrees.

[0080] Optionally, for different risk ranges, various ways such as triggering hydraulic flushing and adding carbon source can also be set.

[0081] In some embodiments, after the floating sludge probability prediction model outputs the predicted floating sludge probability value, the following steps are further included: selecting different types of carbon sources according to the predicted floating sludge probability value; and determining the required dosage of the carbon source according to the nitrate nitrogen deficiency and the influent flow.

[0082] The carbon source types include: NMP wastewater, biogas, and sodium acetate.

[0083] The NMP wastewater adding process: the nitrate concentration at the bottom layer of the secondary sedimentation tank is greater than 3 mg / L; the liquid level of the NMP wastewater storage tank in the plant is inquired (if greater than 10%, it is enabled); the adding amount is calculated according to the formula: Q_NMP = 0.0005*Q_in*DeltaTN, wherein Q_NMP represents the wastewater adding amount, Q_in represents the inflow, and DeltaTN represents the nitrate nitrogen deficiency; the NMP wastewater is pumped into the backflow sludge pipeline (after mixing, it enters the anaerobic tank).

[0084] The biogas adding process: the dissolved oxygen content at the bottom layer of the secondary sedimentation tank is less than 0.3 mg / L, and the nitrate concentration is greater than 3 mg / L; the biogas dilution device is started (the CH4 concentration is reduced to ≤2%); the formula is: Q_biogas = 0.1*Q_in*DeltaTN, wherein Q_biogas represents the biogas adding amount; and the micro-porous aeration disc is injected into the bottom of the tank.

[0085] The traditional carbon source adding: it is only enabled when there is no NMP wastewater and no biogas; the adding amount is: Q_sodium acetate = 0.002*Q_in*DeltaTN, wherein Q_sodium acetate represents the carbon source adding amount.

[0086] The technical scheme in the embodiment of the present application can accurately predict the probability of the floating sludge risk in the current secondary sedimentation tank, and automatically execute the corresponding control decision when the floating sludge risk is detected, the process from detection to execution is extremely short, and no additional large equipment is needed, only a plurality of sensors are needed to be deployed in the secondary sedimentation tank, and a controller is needed to control the secondary sedimentation tank system to automatically add carbon source, start hydraulic flushing, increase sludge discharge efficiency and the like to reduce the floating sludge risk when the floating sludge risk is predicted.

[0087] Figure 4 A schematic diagram of a secondary sedimentation tank control device provided by the embodiment of the present application is shown in Figure 4 The device specifically includes:

[0088] The data acquisition module 100 is used for periodically acquiring various parameter data in the secondary sedimentation tank area;

[0089] The model construction module 200 is used for constructing a floating sludge probability prediction model and model training; various parameter data are used as the input of the floating sludge probability prediction model, and a predicted floating sludge probability value is output; the predicted floating sludge probability value and the upper layer floating sludge concentration value of the secondary sedimentation tank are established in a corresponding relationship;

[0090] The decision execution module 300 is used for executing different control strategies for the secondary sedimentation tank according to the predicted floating sludge probability value output by the floating sludge probability prediction model.

[0091] The technical solution in this embodiment of the invention, by establishing various system modules and coordinating the monitoring of floating sludge risk and the control operation of the secondary sedimentation tank, can predict the probability of floating sludge being generated in the secondary sedimentation tank and execute corresponding control decisions.

[0092] Figure 5 This is a schematic diagram of an electronic device implementing the secondary sedimentation tank control method of this invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0093] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0094] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0095] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, and the like. The processor 11 performs various methods and processes described above, such as the secondary clarifier control method.

[0096] In some embodiments, the secondary clarifier control method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of the secondary clarifier control method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the secondary clarifier control method by any other suitable means, such as by means of firmware.

[0097] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0098] Computer programs used to implement the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed by the processor of the machine, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0099] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0100] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0101] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0102] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business expansion in traditional physical host and VPS service.

[0103] It should be understood that the various forms of flow shown above can be used to reorder, add or delete steps. For example, each step described in the present application can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which is not limited herein.

[0104] The above only is the preferred embodiment of the present application, and does not limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for controlling a secondary sedimentation tank, characterized in that, include: Periodically collect various parameter data within the secondary sedimentation tank area; A floating sludge probability prediction model is constructed and trained; the various parameter data are used as inputs to the floating sludge probability prediction model, and the predicted floating sludge probability value is output; a correspondence is established between the predicted floating sludge probability value and the floating sludge concentration value in the upper layer of the secondary sedimentation tank. Based on the predicted floating mud probability value output by the floating mud probability prediction model, different control strategies are implemented for the secondary sedimentation tank.

2. The method according to claim 1, characterized in that, The various parameter data include: pressure change rate data, nitrate concentration data, and sludge concentration gradient data; After collecting the various parameter data, the data is preprocessed, specifically: the various parameter data with different collection frequencies are time-series aligned; for parameter data with consecutive missing durations less than a preset duration, linear interpolation is performed to fill the missing durations; for parameter data with consecutive missing durations greater than or equal to a preset duration, historical averages are used to fill the missing durations; for parameter data of the same type, all values ​​are scaled to a unit interval through linear normalization.

3. The method according to claim 1, characterized in that, In the process of constructing the floating mud probability prediction model, historical data of various parameters and corresponding floating mud concentration values ​​are collected, and training set and test set are divided proportionally. The test set is used to adjust the parameters in the floating mud probability prediction model, and the test set is used to verify the accuracy of the floating mud probability prediction model. Historical data of various parameters in the test set are input into the floating mud probability prediction model. The parameters in the floating mud probability prediction model are adjusted so that the error between the predicted floating mud probability value output by the floating mud probability prediction model and the floating mud probability value converted from the floating mud concentration value is within a preset range.

4. The method according to claim 1, characterized in that, After the floating mud probability prediction model outputs the predicted floating mud probability value, it also includes: Based on the predicted probability of floating sludge, different types of carbon sources are selected; based on the nitrate nitrogen deficit and influent flow rate, the required dosage of carbon source is determined. The types of carbon sources include: NMP wastewater, biogas, and sodium acetate.

5. The method according to claim 1, characterized in that, Also includes: A sludge distribution model is constructed based on the aforementioned parameter data; The sludge distribution model takes pressure change rate data, nitrate concentration data, sludge concentration gradient data, sludge settling rate and activated sludge concentration as inputs and outputs sludge bulking index.

6. The method according to claim 5, characterized in that, After obtaining the predicted floating mud probability value output by the floating mud probability prediction model and the sludge bulking index output by the sludge distribution model, different control strategies are implemented on the secondary sedimentation tank according to the first preset threshold and the second preset threshold. If the probability value of floating mud exceeds the first preset threshold, hydraulic flushing will be initiated. If the sludge bulking index exceeds the second preset threshold, reduce the influent load and increase the sludge scraping speed; If the probability value of floating sludge exceeds the first preset threshold and the sludge bulking index exceeds the second preset threshold, then add defoamer and adjust the reflux ratio.

7. The method according to claim 1, characterized in that, Based on the magnitude of the predicted floating mud probability value, a low-risk preset range, a medium-risk preset range, and a high-risk preset range are divided. Data is recorded when the predicted probability value of floating mud output by the model is within the low-risk preset range; When the predicted probability value of floating mud output by the model is within the preset range of medium risk, increase the mud discharge frequency; When the predicted probability value of floating sludge output by the model is within the high-risk preset range, aeration is carried out at the bottom of the secondary sedimentation tank and the sludge scraping speed is increased.

8. A secondary sedimentation tank control device, characterized in that, The apparatus is configured to implement the method according to any one of claims 1-7, the apparatus comprising: The data acquisition module is used to periodically collect various parameter data within the secondary sedimentation tank area; The model building module is used to build a floating sludge probability prediction model and train the model; it takes the various parameter data as input to the floating sludge probability prediction model and outputs the predicted floating sludge probability value; the predicted floating sludge probability value is correlated with the floating sludge concentration value in the upper layer of the secondary sedimentation tank. The decision execution module is used to implement different control strategies on the secondary sedimentation tank based on the predicted floating mud probability value output by the floating mud probability prediction model.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the steps of the secondary sedimentation tank control method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the steps of the secondary sedimentation tank control method according to any one of claims 1-7.

Images