A high-density sedimentation tank intelligent control system and control method

Abstract

The present invention discloses an intelligent control system for a high-density sedimentation tank, comprising: a signal detection module for obtaining detection indicators of the high-density sedimentation tank, wherein the detection indicators include water inlet indicators and water outlet indicators; an image acquisition module for obtaining underwater images; an analysis module for generating control parameters according to the underwater images and the detection indicators; and a control module for controlling an execution module according to the second control parameters. The present invention applies image recognition technology to coagulation process analysis, constructs an intelligent control model using an adaptive intelligent algorithm, and realizes intelligent control of a high-density sedimentation tank.

Description

Technical Field

[0001] The invention relates to the field of sewage treatment, and in particular to an intelligent control system and a control method for a high-density sedimentation tank. Background Art

[0002] Coagulation and sedimentation process is a very important link in the water treatment process. The effect of the reaction is directly related to the effluent water quality and treatment cost. Whether it is tap water, domestic sewage or various industrial wastewater treatment, coagulation and sedimentation process must be applied. Coagulation and sedimentation process refers to the process of adding an appropriate amount of coagulant to the water to destroy the stability of colloidal particles and fine suspended matter in the water to make them agglomerate, and under the capture effect of the flocculant and certain hydraulic conditions, flocs (generally called alum flowers in water treatment) are formed and separated from the water. High-density sedimentation tank is a technology of Degrémont, France, which was introduced into China in the mid-1990s. Because the high-density sedimentation tank process integrates good mechanical mixing, flocculation and clarification, and has the advantages of high separation efficiency, low sludge discharge, small footprint, and low effluent turbidity, it is widely used in municipal water supply, sewage treatment, and industrial wastewater treatment in China. It is currently a widely used coagulation process tank configuration.

[0003] However, in order to achieve good treatment effects in high-density sedimentation tanks, the amount of coagulant and flocculant added, the speed of the mixer, the amount of sludge return and other parameters need to be adjusted in real time according to the water quality. At present, the manual control mode is usually adopted, that is, the shape of alum flowers in the water (including size, density, uniformity, etc.) is identified by human eyes during operation, and experienced workers judge whether the amount of coagulant or flocculant added is appropriate and whether it needs to be adjusted. Although this method can ensure that the effluent water quality meets the standard to a certain extent, there are the following problems: 1) The raw water quality usually fluctuates greatly and frequently, and regular manual inspections cannot adapt to water quality fluctuations in real time; 2) A large amount of manpower is required; 3) The amount of reagents used and the operating cost are high. Summary of the invention

[0004] In view of the above-mentioned shortcomings of the prior art, an object of the present invention is to provide a high-density sedimentation tank intelligent control system and control method to solve the defects of the prior art.

[0005] To achieve the above objectives and other related objectives, the present invention provides an intelligent control system for a high-density sedimentation tank, comprising:

[0006] A signal detection module, used to obtain a detection index and a first control parameter of the high-density sedimentation tank, wherein the detection index includes an inlet water index and an outlet water index;

[0007] An image acquisition module, used for acquiring underwater images;

[0008] An analysis module, configured to generate a water discharge index according to the underwater image, the water inflow index and the first control parameter, and generate a second control parameter according to the water discharge index;

[0009] A control module is used to control the execution module according to the second control parameter.

[0010] Optionally, the analysis module includes:

[0011] An image recognition submodule, used to recognize the underwater image to obtain image feature parameters of the underwater image;

[0012] An intelligent algorithm submodule is used to generate the water outlet index according to the image feature parameter, the water inlet index and the first control parameter; and generate the second control parameter according to the water outlet index.

[0013] Optionally, the image characteristic parameters include at least one of the following: average equivalent diameter of alum flowers and fractal dimension.

[0014] Optionally, generating a water discharge index according to the underwater image, the water inflow index and the first control parameter includes:

[0015] The underwater image, the water inflow index and the first control parameter are input into a pre-trained prediction model, and a water outflow index is output.

[0016] Optionally, a method for obtaining a pre-trained prediction model includes:

[0017] Acquire training data and construct a training data set, wherein the training data includes the detection index, the image feature parameter of the underwater image, and the first control parameter;

[0018] A prediction model is obtained by training with a regression model algorithm based on the training data set.

[0019] Optionally, the inlet water index and / or outlet water index include at least one of the following: turbidity, pH, temperature, flow rate, conductivity, dissolved oxygen content, COD, total phosphorus, and total hardness.

[0020] Optionally, the first control parameter and / or the second control parameter include at least one of the following: coagulant dosage, flocculant dosage, de-hardening agent dosage, dosing pump speed frequency, sludge return pump speed frequency, sludge discharge pump speed frequency, sludge return volume, sludge discharge volume, mixing zone agitator speed, flocculation reaction zone agitator speed, sedimentation zone sludge agitator speed, dosing pump speed frequency.

[0021] To achieve the above-mentioned purpose and other related purposes, the present invention provides a high-density sedimentation tank intelligent control method, characterized in that it includes:

[0022] Obtaining a detection index and a first control parameter of the high-density sedimentation tank, wherein the detection index includes an inlet water index and an outlet water index;

[0023] Acquire underwater images;

[0024] generating a water discharge index according to the underwater image, the water inflow index and a first control parameter;

[0025] generating a second control parameter according to the water output index;

[0026] The execution module is controlled according to the second control parameter.

[0027] Optionally, generating a water discharge index according to the underwater image, the water inflow index and the first control parameter includes:

[0028] Recognizing the underwater image to obtain image feature parameters of the underwater image;

[0029] The water outflow index is generated according to the image feature parameter, the water inflow index and the first control parameter.

[0030] Optionally, the image characteristic parameters include at least one of the following: average equivalent diameter of alum flowers and fractal dimension.

[0031] Optionally, generating a water discharge index according to the underwater image, the water inflow index and the first control parameter includes:

[0032] The underwater image, the water inflow index and the first control parameter are input into a pre-trained prediction model, and a water outflow index is output.

[0033] Optionally, a method for obtaining a pre-trained prediction model includes:

[0034] Acquire training data and construct a training data set, wherein the training data includes the detection index, the image feature parameter of the underwater image, and the first control parameter;

[0035] A prediction model is obtained by training with a regression model algorithm based on the training data set.

[0036] Optionally, the inlet water index and / or outlet water index include at least one of the following: turbidity, pH, temperature, flow rate, conductivity, dissolved oxygen content, COD, total phosphorus, and total hardness.

[0037] Optionally, the first control parameter and / or the second control parameter include at least one of the following: coagulant dosage, flocculant dosage, de-hardening agent dosage, dosing pump speed frequency, sludge return pump speed frequency, sludge discharge pump speed frequency, sludge return volume, sludge discharge volume, mixing zone agitator speed, flocculation reaction zone agitator speed, sedimentation zone sludge agitator speed, dosing pump speed frequency.

[0038] As described above, the intelligent control system and control method of a high-density sedimentation tank of the present invention have the following beneficial effects:

[0039] The present invention applies image recognition technology to coagulation process analysis, constructs an intelligent control model using an adaptive intelligent algorithm, and realizes intelligent control of a high-density sedimentation tank. According to different water quality conditions, the model can realize self-updating, and the calculation result is the optimal control parameter value, avoiding the reaction delay caused by constantly correcting the existing parameters, and can realize the coordinated control of the control parameters of each link of the high-density sedimentation tank, realizing intelligent optimal control. The application of the intelligent control system and method of the high-density sedimentation tank, under the premise of ensuring that the effluent water quality is stable and up to standard, continuously and uninterruptedly collects the state of alum flowers in the water, adapts to the water quality fluctuation in real time, reduces manual input, reduces labor intensity and cost, and significantly reduces the dosage of reagents in the high-density sedimentation tank, reducing the system operation cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 Shown is a principle block diagram of an intelligent control system for a high-density sedimentation tank in one embodiment of the present invention;

[0041] Figure 2 Shown is a principle block diagram of an intelligent control system for a high-density sedimentation tank in one embodiment of the present invention;

[0042] Figure 3 Shown is a schematic top view of the installation position of an underwater image acquisition device in one embodiment of the present invention;

[0043] Figure 4 Shown is a schematic front view of the installation position of an underwater image acquisition device in one embodiment of the present invention;

[0044] Figure 5 Shown is a schematic structural diagram of an underwater image acquisition device in one embodiment of the present invention;

[0045] Figure 6 Shown is a flow chart of an intelligent control method for a high-density sedimentation tank in one embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0047] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0048] like Figure 1 As shown, a high-density sedimentation tank intelligent control system is used to control the parameters of the high-density sedimentation tank, wherein, Figures 2 to 4 As shown, the high-density sedimentation tank includes a high-density sedimentation tank mixing zone 2, a high-density sedimentation tank flocculation reaction zone 3 connected to the high-density sedimentation tank mixing zone, and a high-density sedimentation tank sedimentation zone 4 connected to the high-density sedimentation tank flocculation reaction zone, which are arranged in sequence; one or more image acquisition modules 20 are arranged in the high-density sedimentation tank flocculation reaction zone 3 or the high-density sedimentation tank sedimentation zone 4; the underwater image of the high-density sedimentation tank flocculation reaction zone 3 or the high-density sedimentation tank sedimentation zone 4 is acquired by the one or more image acquisition modules, that is, the image acquisition module is located below the liquid surface of the high-density sedimentation tank flocculation reaction zone 3 or the high-density sedimentation tank sedimentation zone 4 when installed.

[0049] The high-density sedimentation tank mixing zone 2 is provided with a water inlet 1, the high-density sedimentation tank sedimentation zone 4 is provided with a water outlet 5, a drug inlet is provided on the connecting channel connected to the high-density sedimentation tank mixing zone, and the drug inlet is communicated with the dosing pump, and drug inlets are provided on the connecting channels respectively connected to the high-density sedimentation tank mixing zone and the high-density sedimentation tank flocculation reaction zone, and the drug inlet is communicated with the dosing pump.

[0050] In one embodiment, the bottom of the mixing zone of the high-density sedimentation tank is connected to the bottom of the flocculation reaction zone of the high-density sedimentation tank through a pipeline.

[0051] like Figure 5 As shown, the image acquisition module includes a protection chamber 101, a fill light 104 and a high-speed camera 102. The protection chamber is provided with a transparent window 105. The high-speed camera is installed in the sealed protection chamber, collects external images through the transparent window, and provides a light source for illuminating the external image through the fill light.

[0052] The image acquisition module can be installed vertically 0.5m to 1.5m below the water surface outside the central tube of the flocculation reaction zone of the high-density sedimentation tank. Several units can be installed at the same time, and it is recommended to install 1 to 3 units; or it can be installed horizontally at the top of the retaining wall of the sedimentation zone of the high-density sedimentation tank. Several units can be installed at the same time, and it is recommended to install 1 to 3 units, and they are installed symmetrically with the center of the retaining wall. When multiple image acquisition modules are configured, they shall not be installed at the same time in the flocculation reaction zone and the sedimentation zone, and the installation depth of all the underwater image acquisition devices shall be consistent.

[0053] An inclined tube sedimentation area 17 is arranged near the water outlet in the sedimentation area 4 of the high-density sedimentation tank, and a water outlet weir 16 is arranged above the inclined tube sedimentation area 17 .

[0054] A retaining wall 14 is provided in the sedimentation area of ​​the high-density sedimentation tank, and the image acquisition device is provided on the retaining wall.

[0055] A high-density sedimentation tank mixing zone agitator 11 is arranged in the high-density sedimentation tank mixing zone 2.

[0056] A high-density sedimentation tank flocculation reaction zone agitator 12 is arranged in the high-density sedimentation tank flocculation reaction zone 3 .

[0057] A high-density sedimentation tank sedimentation zone sludge thickening mixer 15 is arranged in the high-density sedimentation tank sedimentation zone 4.

[0058] The high-density sedimentation tank flocculation reaction zone 3 is provided with a high-density sedimentation tank flocculation reaction zone central cylinder 13 opening downward, and the stirring part of the high-density sedimentation tank flocculation reaction zone stirrer 12 extends into the high-density sedimentation tank flocculation reaction zone central cylinder 13.

[0059] like Figure 1 As shown, a high-density sedimentation tank intelligent control system includes:

[0060] A signal detection module 11 is used to obtain a detection index and a first control parameter of the high-density sedimentation tank, wherein the detection index includes an inlet index and an outlet index;

[0061] An image acquisition module 12, used to acquire underwater images;

[0062] An analysis module 13, configured to generate a water discharge index according to the underwater image, the water inflow index and the first control parameter, and generate a second control parameter according to the water discharge index;

[0063] The control module 14 is used to control the execution module according to the second control parameter.

[0064] The execution module includes a dosing pump, a high-density sedimentation tank mixing zone mixer 11, a high-density sedimentation tank flocculation reaction zone mixer 12, and a high-density sedimentation tank sedimentation zone sludge thickening mixer 15.

[0065] The present invention applies image recognition technology to coagulation process analysis, constructs an intelligent control model using an adaptive intelligent algorithm, and realizes intelligent control of a high-density sedimentation tank.

[0066] In one embodiment, the control module is a PLC control module, and exchanges data with the analysis module via a socket protocol or an OPC protocol.

[0067] In one embodiment, the analysis module includes:

[0068] An image recognition submodule, used to recognize the underwater image to obtain image feature parameters of the underwater image;

[0069] An intelligent algorithm submodule is used to generate the water outlet index according to the image feature parameter, the water inlet index and the first control parameter; and generate the second control parameter according to the water outlet index.

[0070] The image characteristic parameters include at least one of the following: average equivalent diameter of alum flowers and fractal dimension. The water inlet index includes at least one of the following: turbidity, pH, temperature, flow, conductivity, dissolved oxygen content, COD, total phosphorus, and total hardness. The water outlet index includes at least one of the following: turbidity, pH, temperature, flow, conductivity, dissolved oxygen content, COD, total phosphorus, and total hardness. The first control parameter includes at least one of the following: coagulant dosage, flocculant dosage, de-hardening agent dosage, dosing pump speed frequency, sludge return pump speed frequency, sludge discharge pump speed frequency, sludge return volume, sludge discharge volume, mixing zone agitator speed, flocculation reaction zone agitator speed, sedimentation zone sludge agitator speed, and dosing pump speed frequency. The second control parameter includes at least one of the following: coagulant dosage, flocculant dosage, de-hardening agent dosage, dosing pump speed frequency, sludge return pump speed frequency, sludge discharge pump speed frequency, sludge return volume, sludge discharge volume, mixing zone agitator speed, flocculation reaction zone agitator speed, sedimentation zone sludge agitator speed, dosing pump speed frequency. The dosing pump is a variable frequency metering pump, a variable frequency centrifugal pump or a variable frequency screw pump, and the dosing pump speed frequency signal is transmitted to the PLC control module.

[0071] The image captured by the image acquisition module is transmitted to the image recognition submodule as the first input signal, the image recognition submodule outputs a signal that is transmitted to the intelligent algorithm submodule as the second input signal, the detection index of the signal detection module received by the PLC control module is transmitted to the intelligent algorithm submodule as the third input signal, the intelligent algorithm submodule outputs a control parameter that is transmitted to the PLC control module, and the PLC control module controls the execution module according to the control parameter.

[0072] Among them, the signal detection module is a detection instrument, which can be an online real-time detection instrument. The detection signal is transmitted to the PLC control module and then transmitted to the intelligent algorithm submodule.

[0073] In one embodiment, the analysis module may also be a server, in which an intelligent control algorithm is embedded, wherein the server may be deployed locally around the high-density sedimentation tank or remotely deployed in a central control room.

[0074] In one embodiment, generating a water discharge index according to the underwater image, the water inflow index and the first control parameter includes:

[0075] The underwater image (specifically, the image feature parameters of the underwater image), the water inflow index and the first control parameter are input into a pre-trained prediction model, and the water outflow index is output.

[0076] In one embodiment, a method for obtaining a pre-trained prediction model includes:

[0077] Acquire training data and construct a training data set, wherein the training data includes the detection index, the image feature parameters of the underwater image, and the first control parameter; wherein the training data is data within a historical time period.

[0078] A prediction model is obtained by training with a regression model algorithm based on the training data set.

[0079] The water discharge index can be obtained through the prediction model. After the water discharge index is obtained, it is judged whether the water quality meets the standard according to the water discharge index. If the water quality meets the standard, no subsequent treatment is performed. If the water quality does not meet the standard, the next step of treatment is entered, that is, the corresponding second control parameter is adjusted according to the water discharge index until the water quality meets the standard. It can be understood that the second control parameter corresponding to the water quality meeting the standard can include many groups, that is, each corresponding indicator in the second control parameter can include multiple groups, and the second control parameter combination with the lowest cost is selected as the final second control parameter.

[0080] At the same time, during the operation of the algorithm, the final model will be continuously updated and optimized according to real-time image parameters, water inlet indicators, control parameters and water outlet indicators to ensure the accuracy of the final model.

[0081] The present invention avoids the influence of the coagulation reaction process on the control, and the algorithm can predict the possible water discharge situation in the future in advance and respond in advance. At the same time, the self-learning ability can ensure that the accuracy of the model is getting higher and higher, and the applicability is also stronger.

[0082] The present invention applies image recognition technology to coagulation process analysis, constructs an intelligent control model using an adaptive intelligent algorithm, and realizes intelligent control of a high-density sedimentation tank. According to different water quality conditions, the model can realize self-updating, and the calculation result is the optimal control parameter value, avoiding the reaction delay caused by constantly correcting the existing parameters, and can realize the coordinated control of the control parameters of each link of the high-density sedimentation tank, realizing intelligent optimal control. The application of the intelligent control system and method of the high-density sedimentation tank, under the premise of ensuring that the effluent water quality is stable and up to standard, continuously and uninterruptedly collects the state of alum flowers in the water, adapts to the water quality fluctuation in real time, reduces manual input, reduces labor intensity and cost, and significantly reduces the dosage of reagents in the high-density sedimentation tank, reducing the system operation cost.

[0083] like Figure 6 , an intelligent control method for a high-density sedimentation tank, comprising:

[0084] S61 obtains a detection index and a first control parameter of the high-density sedimentation tank, wherein the detection index includes an inlet index and an outlet index;

[0085] S62 acquires underwater images;

[0086] S63 generates a water discharge index according to the underwater image, the water inflow index and the first control parameter;

[0087] S64 generates a second control parameter according to the water output index;

[0088] S65: Control the execution module according to the second control parameter.

[0089] The present invention applies image recognition technology to coagulation process analysis, constructs an intelligent control model using an adaptive intelligent algorithm, and realizes intelligent control of a high-density sedimentation tank.

[0090] In one embodiment, generating a water discharge index according to the underwater image, the water inflow index and the first control parameter includes:

[0091] Recognizing the underwater image to obtain image feature parameters of the underwater image;

[0092] The water outflow index is generated according to the image feature parameter, the water inflow index and the first control parameter.

[0093] In one embodiment, the image characteristic parameters include at least one of the following: average equivalent diameter of alum flowers and fractal dimension.

[0094] The inlet water index includes at least one of the following: turbidity, pH, temperature, flow rate, conductivity, dissolved oxygen content, COD, total phosphorus, and total hardness. The outlet water index includes at least one of the following: turbidity, pH, temperature, flow rate, conductivity, dissolved oxygen content, COD, total phosphorus, and total hardness.

[0095] In one embodiment, generating a water discharge index according to the underwater image, the water inflow index and the first control parameter includes:

[0096] The underwater image (specifically, the image feature parameters of the underwater image), the water inflow index and the first control parameter are input into a pre-trained prediction model, and the water outflow index is output.

[0097] In one embodiment, a method for obtaining a pre-trained prediction model includes:

[0098] Acquire training data and construct a training data set, wherein the training data includes the detection index, the image feature parameter of the underwater image, and the first control parameter;

[0099] A prediction model is obtained by training with a regression model algorithm based on the training data set.

[0100] In one embodiment, the control parameters include at least one of the following: coagulant dosage, flocculant dosage, de-hardening agent dosage, dosing pump speed frequency, sludge return pump speed frequency, sludge discharge pump speed frequency, sludge return volume, sludge discharge volume, mixing zone agitator speed, flocculation reaction zone agitator speed, sedimentation zone sludge agitator speed, dosing pump speed frequency. The image feature parameters include at least one of the following: average equivalent diameter of alum flowers, fractal dimension.

[0101] The inlet water index includes at least one of the following: turbidity, pH, temperature, flow rate, conductivity, dissolved oxygen content, COD, total phosphorus, and total hardness. The outlet water index includes at least one of the following: turbidity, pH, temperature, flow rate, conductivity, dissolved oxygen content, COD, total phosphorus, and total hardness. Optionally, the sludge index includes at least one of the following: sludge return flow rate and sludge discharge flow rate.

[0102] The dosing pump is a variable frequency metering pump, a variable frequency centrifugal pump or a variable frequency screw pump, and the speed frequency signal of the dosing pump is transmitted to the PLC control module.

[0103] In this embodiment, the embodiment of the method part corresponds to the embodiment of the aforementioned device part. The method part embodiment and the device part embodiment can refer to each other, and the method embodiment will not be described in detail here.

[0104] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0105] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0106] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0107] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0108] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0109] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0110] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory ((RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0111] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A high-density sedimentation tank intelligent control system, characterized in that: include: A signal detection module, used to obtain a detection index and a first control parameter of the high-density sedimentation tank, wherein the detection index includes an inlet water index and an outlet water index; An image acquisition module, used for acquiring underwater images; An analysis module, configured to generate a water discharge index according to the underwater image, the water inflow index and the first control parameter, and generate a second control parameter according to the water discharge index; A control module, used for controlling the execution module according to the second control parameter; The analysis module comprises: An image recognition submodule, used to recognize the underwater image to obtain image feature parameters of the underwater image; An intelligent algorithm submodule, configured to generate the water outlet index according to the image feature parameter, the water inlet index and the first control parameter through an intelligent control model constructed based on an adaptive intelligent algorithm; and generate the second control parameter according to the water outlet index; The image characteristic parameters include at least one of the following: average equivalent diameter of alum flowers and fractal dimension; The inlet water index and / or outlet water index include at least one of the following: turbidity, pH, temperature, flow rate, conductivity, dissolved oxygen content, COD, total phosphorus, and total hardness; The first control parameter and / or the second control parameter include at least one of the following: coagulant dosage, flocculant dosage, de-hardening agent dosage, dosing pump speed frequency, sludge return pump speed frequency, sludge discharge pump speed frequency, sludge return volume, sludge discharge volume, mixing zone agitator speed, flocculation reaction zone agitator speed, sedimentation zone sludge agitator speed, dosing pump speed frequency; The second control parameter is a parameter combination corresponding to the lowest cost.

2. The high-density sedimentation tank intelligent control system according to claim 1 is characterized in that: The step of generating a water discharge index according to the underwater image, the water inflow index and the first control parameter comprises: The underwater image, the water inflow index and the first control parameter are input into a pre-trained prediction model, and a water outflow index is output.

3. The high-density sedimentation tank intelligent control system according to claim 2 is characterized in that: Methods for obtaining pre-trained prediction models include: Acquire training data and construct a training data set, wherein the training data includes the detection index, the image feature parameter of the underwater image, and the first control parameter; A prediction model is obtained by training with a regression model algorithm based on the training data set.

4. A high-density sedimentation tank intelligent control method, characterized in that: include: Obtaining a detection index and a first control parameter of the high-density sedimentation tank, wherein the detection index includes an inlet water index and an outlet water index; Acquire underwater images; generating a water discharge index according to the underwater image, the water inflow index and a first control parameter; generating a second control parameter according to the water output index; Controlling the execution module according to the second control parameter; The step of generating a water discharge index according to the underwater image, the water inflow index and the first control parameter comprises: Recognizing the underwater image to obtain image feature parameters of the underwater image; Generate the water discharge index according to the image feature parameter, the water inlet index and the first control parameter through an intelligent control model constructed based on an adaptive intelligent algorithm; The image characteristic parameters include at least one of the following: average equivalent diameter of alum flowers and fractal dimension; The inlet water index and / or outlet water index include at least one of the following: turbidity, pH, temperature, flow rate, conductivity, dissolved oxygen content, COD, total phosphorus, and total hardness; The first control parameter and / or the second control parameter include at least one of the following: coagulant dosage, flocculant dosage, de-hardening agent dosage, dosing pump speed frequency, sludge return pump speed frequency, sludge discharge pump speed frequency, sludge return volume, sludge discharge volume, mixing zone agitator speed, flocculation reaction zone agitator speed, sedimentation zone sludge agitator speed, dosing pump speed frequency; The second control parameter is a parameter combination corresponding to the lowest cost.

5. The high-density sedimentation tank intelligent control method according to claim 4 is characterized in that: The step of generating a water discharge index according to the underwater image, the water inflow index and the first control parameter comprises: The underwater image, the water inflow index and the first control parameter are input into a pre-trained prediction model, and a water outflow index is output.

6. The intelligent control method for a high-density sedimentation tank according to claim 5, characterized in that: Methods for obtaining pre-trained prediction models include: Acquire training data and construct a training data set, wherein the training data includes the detection index, the image feature parameter of the underwater image, and the first control parameter; A prediction model is obtained by training with a regression model algorithm based on the training data set.

7. The intelligent control method for a high-density sedimentation tank according to claim 4, characterized in that: The first control parameter and / or the second control parameter include at least one of the following: coagulant dosage, flocculant dosage, hardness remover dosage, dosing pump speed frequency, sludge return pump speed frequency, sludge discharge pump speed frequency, sludge return volume, sludge discharge volume, mixing zone agitator speed, flocculation reaction zone agitator speed, sedimentation zone sludge agitator speed, dosing pump speed frequency.

Images