CN116774632A - Sewage monitoring control method and storage medium for digital twin water plant - Google Patents
Sewage monitoring control method and storage medium for digital twin water plant Download PDFInfo
- Publication number
- CN116774632A CN116774632A CN202310775114.2A CN202310775114A CN116774632A CN 116774632 A CN116774632 A CN 116774632A CN 202310775114 A CN202310775114 A CN 202310775114A CN 116774632 A CN116774632 A CN 116774632A
- Authority
- CN
- China
- Prior art keywords
- model
- data
- water
- monitoring
- sewage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 110
- 239000010865 sewage Substances 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012544 monitoring process Methods 0.000 title claims abstract description 35
- 238000003860 storage Methods 0.000 title claims abstract description 11
- 238000005457 optimization Methods 0.000 claims abstract description 35
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims abstract description 33
- 229910052799 carbon Inorganic materials 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 27
- 238000004519 manufacturing process Methods 0.000 claims abstract description 26
- 230000001276 controlling effect Effects 0.000 claims abstract description 18
- 238000005265 energy consumption Methods 0.000 claims abstract description 15
- 230000001105 regulatory effect Effects 0.000 claims abstract description 13
- 238000004088 simulation Methods 0.000 claims abstract description 13
- 239000003814 drug Substances 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000010924 continuous production Methods 0.000 claims abstract description 8
- 229940079593 drug Drugs 0.000 claims abstract description 5
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 21
- 229910052760 oxygen Inorganic materials 0.000 claims description 21
- 239000001301 oxygen Substances 0.000 claims description 21
- 229910002651 NO3 Inorganic materials 0.000 claims description 16
- NHNBFGGVMKEFGY-UHFFFAOYSA-N Nitrate Chemical compound [O-][N+]([O-])=O NHNBFGGVMKEFGY-UHFFFAOYSA-N 0.000 claims description 16
- IOVCWXUNBOPUCH-UHFFFAOYSA-M Nitrite anion Chemical compound [O-]N=O IOVCWXUNBOPUCH-UHFFFAOYSA-M 0.000 claims description 16
- 238000013507 mapping Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 11
- 239000000178 monomer Substances 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 7
- 230000001360 synchronised effect Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000013499 data model Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 4
- 238000007599 discharging Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000009877 rendering Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 10
- OKKJLVBELUTLKV-UHFFFAOYSA-N Methanol Chemical compound OC OKKJLVBELUTLKV-UHFFFAOYSA-N 0.000 description 9
- 239000013598 vector Substances 0.000 description 6
- MMDJDBSEMBIJBB-UHFFFAOYSA-N [O-][N+]([O-])=O.[O-][N+]([O-])=O.[O-][N+]([O-])=O.[NH6+3] Chemical compound [O-][N+]([O-])=O.[O-][N+]([O-])=O.[O-][N+]([O-])=O.[NH6+3] MMDJDBSEMBIJBB-UHFFFAOYSA-N 0.000 description 4
- 238000005094 computer simulation Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000007788 liquid Substances 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010992 reflux Methods 0.000 description 2
- 238000004062 sedimentation Methods 0.000 description 2
- JVMRPSJZNHXORP-UHFFFAOYSA-N ON=O.ON=O.ON=O.N Chemical compound ON=O.ON=O.ON=O.N JVMRPSJZNHXORP-UHFFFAOYSA-N 0.000 description 1
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000005469 granulation Methods 0.000 description 1
- 230000003179 granulation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
Landscapes
- Activated Sludge Processes (AREA)
Abstract
The application discloses a sewage monitoring control method and a storage medium of a digital twin water plant, wherein the monitoring control method comprises the following steps: s1: establishing a three-dimensional digital model of the outer facade of the water plant; s2: establishing a three-dimensional digital model of internal equipment and a pipe network of the water plant; s3: collecting and processing monitoring data in real time; s4: regulating and controlling the carbon source adding amount of the sewage; s5: generating a simulated dosing control model; s6: a multivariable simulation optimization simulation dosing control model; s7: continuous production control and tuning. According to the application, simulation optimization of each parameter of the simulated dosing control model is realized from a multivariable angle by combining an SS-MOEA/D algorithm until the simulation optimization is consistent with actual production conditions, an optimal model which meets the minimum energy consumption, the minimum drug consumption and the most stable standard reaching rate of the water quality of the effluent is generated, the optimal model is applied to actual sewage treatment, and a large number of water inlet input parameters and water outlet output parameters are repeatedly compared and trained in actual operation, so that continuous production control and optimization are realized.
Description
Technical Field
The application relates to the technical field of digital twin water plants, in particular to a sewage monitoring control method and a storage medium of a digital twin water plant.
Background
The digital twin water works application is based on a digital twin technology, a live-action three-dimensional river basin is constructed, the panoramic and full-element situation of the river basin is reproduced in a refined mode, the data resources of the existing information systems of various departments of water conservancy are supported, the front-edge technology application such as 5G, big data, cloud computing, AI and fusion communication is combined, the information, technology and equipment are organically combined with water conservancy management requirements, a plurality of service fields such as river basin overview, river basin flood monitoring, reservoir monitoring, water conservancy scheduling, intelligent water affairs and river and lake inspection are covered, rich functions such as data analysis, object management, object subdivision, equipment control, real-time alarm management and virtual roaming are provided, the user service application is comprehensively enabled, and the water conservancy cross-department decision and resource coordination efficiency are effectively improved.
At present, how to combine digital twin technology to realize optimal control in the sewage treatment process is a problem to be solved by the current sewage treatment plant in order to ensure that the effluent quality in the sewage treatment process reaches the standard and is discharged, and reduce the cost in the sewage treatment process.
Disclosure of Invention
The application provides an intelligent and efficient sewage monitoring control method and a storage medium for a digital twin water plant, which can at least solve one of the technical problems.
In order to solve the technical problems, the application adopts the following technical scheme: a sewage monitoring control method of a digital twin water plant comprises the following steps:
s1: establishing a three-dimensional digital model of the outer facade of the water plant;
s2: establishing a three-dimensional digital model of internal equipment and a pipe network of the water plant;
s3: collecting and processing monitoring data in real time;
s4: regulating and controlling the carbon source adding amount of the sewage;
s5: generating a simulated dosing control model;
s6: the multi-variable simulation optimization simulation dosing control model correspondingly generates a plurality of multi-objective optimization model parameters meeting the standard rate of the water quality of the effluent, and selects an optimal model meeting the lowest energy consumption, the lowest drug consumption and the most stable standard rate;
s7: continuous production control and tuning.
Further, the step S1 further includes:
s11: modeling oblique photography data;
s111: acquiring image data and POS data through aerial photography;
s112: preprocessing image data and POS data, synchronously resolving GPS observation data and airborne POS data of a synchronous base station, and checking various parameters of the image data according to the resolved POS data and matching with the existing DEM and DOM data in a region;
s12: modeling the images in an automatic matching way;
s121: manufacturing a monomer three-dimensional model, and performing automatic texture mapping treatment and artificial texture inspection on the monomer three-dimensional model;
s122: UV mapping is carried out on the monomer three-dimensional model, and a illusion engine is introduced.
Further, the step S3 further includes:
s31: the method comprises the steps of monitoring and collecting a plurality of index data in real time and transmitting the index data into a database;
s32: rendering, recording, storing and displaying the data obtained through monitoring.
Further, the step S4 further includes:
s41: the sensor is arranged separately: a first nitrate analyzer, a first nitrite tester, a first dissolved oxygen meter and a first flowmeter are arranged at the water outlet of the anoxic tank, and a second nitrate analyzer, a second nitrite tester, a second dissolved oxygen meter and a second flowmeter are arranged at the water outlet of the aerobic tank;
s42: uploading measured data: each nitrate analyzer, each nitrite analyzer, each dissolved oxygen meter and each flowmeter are respectively and wirelessly connected to a computer, and the computer receives real-time measurement data of each sensor;
s43: analyzing and adjusting the carbon source addition amount: and calculating the real-time required carbon source adding amount by using the data model embedded in the computer, synchronously feeding back the calculation result to the PID controller, regulating and controlling the flow of the pump by the PID controller, further controlling the carbon source adding amount, and regulating the carbon source adding amount in real time according to the effluent quality.
Further, the step S5 further includes:
s51: establishing a functional relation M=lambda between the carbon source addition amount and the effluent quality 1 X 1 +λ 2 X 2 +···+λ n X n The effluent quality is formed by superposing a plurality of variables X with uncertain tracking set values lambda;
s52: and (3) adjusting tracking set values lambda of different variables X to generate a simulated dosing control model.
Further, the step S6 further includes:
s61: the SS-MOEA/D algorithm is adopted, the input of the algorithm is a multi-objective optimization problem and an algorithm termination condition, and the output of the algorithm is a pareto optimal solution { lambda } 1 ，···，λ n Function value { F (lambda) 1 )，···，F(λ n )}；
S62: sequentially selecting any one group of solutions in the pareto optimal solution set obtained by calculation of an SS-MOEA/D algorithm as tracking set values of different variables in the simulated dosing control model, and generating various multi-objective optimization parameters of the effluent quality meeting emission standards;
s63: and comparing the energy consumption, the medicine consumption and the effluent quality standard reaching degree of the system at the current moment corresponding to each solution, and selecting the solution with the lowest energy consumption, the lowest medicine consumption and the most stable standard reaching rate as the optimal setting value which is satisfied at present to generate the optimal model.
Further, the step S7 further includes:
s71: continuously recording each group of inflow water input values, the carbon source adding amount of the dosing control model and the water quality value of the outflow water in the sewage treatment process;
s72: continuously training a tracking set value of a dosing control model by using an SS-MOEA/D algorithm, forming a plurality of multi-objective optimization model parameters after the simulated dosing control model is stable, and recording the optimization set value of the optimal model and the current corresponding water quality value of the effluent;
s73: selecting an optimization set value for production, recording the difference between a real water outlet value and a model water outlet value, entering the step S5, and continuously optimizing an analog dosing control model to enable the model production value to be consistent with the actual production value;
s74: repeating the step S72 to optimize the existing condition of the dosing control model;
s75: and (3) continuously feeding and discharging water, and repeatedly training a dosing control model until a stable optimized set value and a stable water quality value of discharged water are obtained.
A computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the above-described monitoring control method.
The beneficial effects of the application are as follows:
according to the application, an integral three-dimensional digital model of the water outlet plant is built by means of pre-modeling inside and outside to form a digital twin water plant, the interaction aim of combining the digital twin scene with the dynamic simulation deduction capability is achieved, on one hand, the regulation and control of the carbon source addition amount of sewage can be carried out according to the measured data to generate an analog dosing control model, the traditional mode of manual field measurement data is abandoned, the carbon source addition amount is not required to be checked manually, the working efficiency is higher, on the other hand, the simulation optimization of all parameters of the analog dosing control model is achieved from the multivariable angle by combining an SS-MOEA/D algorithm until the model is consistent with the production condition in reality, the optimal model which meets the minimum energy consumption and the minimum water quality rate of the effluent is generated, and further, the optimal model is applied to the actual sewage treatment, a large number of input parameters and output parameters of the water reach the standard in the training are repeatedly compared in the actual operation, and continuous production control and regulation are achieved.
Drawings
FIG. 1 is a schematic flow chart of the overall method according to the embodiment of the application.
FIG. 2 is an algorithmic optimization control block diagram of an embodiment of the present application.
Fig. 3 is a schematic view of monitoring a dosing control module of a sewage plant according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the application. It should be noted that, if there is a description of "first", "second", etc. in the embodiments of the present application, the description of "first", "second", etc. is only for descriptive purposes, and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, "a plurality of" means two or more. In addition, various technologies related in the application, such as an aerial photography technology, a modeling technology, a data processing technology, an algorithm regulation technology and the like, are all existing and mature application technologies.
Referring to fig. 1, an embodiment of the present application provides a sewage monitoring control method for a digital twin water plant, including the following steps:
s1: establishing a three-dimensional digital model of the outer facade of the water plant;
s2: establishing a three-dimensional digital model of internal equipment and a pipe network of the water plant;
s3: collecting and processing monitoring data in real time;
s4: regulating and controlling the carbon source adding amount of the sewage;
s5: generating a simulated dosing control model;
s6: the multi-variable simulation optimization simulation dosing control model correspondingly generates a plurality of multi-objective optimization model parameters meeting the standard rate of the water quality of the effluent, and selects an optimal model meeting the lowest energy consumption, the lowest drug consumption and the most stable standard rate;
s7: continuous production control and tuning.
According to the application, an integral three-dimensional digital model of the water outlet plant is built by means of pre-modeling inside and outside to form a digital twin water plant, the interaction aim of combining the digital twin scene with the dynamic simulation deduction capability is achieved, on one hand, the regulation and control of the carbon source addition amount of sewage can be carried out according to the measured data to generate an analog dosing control model, the traditional mode of manual field measurement data is abandoned, the carbon source addition amount is not required to be checked manually, the working efficiency is higher, on the other hand, the simulation optimization of all parameters of the analog dosing control model is achieved from the multivariable angle by combining an SS-MOEA/D algorithm until the model is consistent with the production condition in reality, the optimal model which meets the minimum energy consumption and the minimum water quality rate of the effluent is generated, and further, the optimal model is applied to the actual sewage treatment, a large number of input parameters and output parameters of the water reach the standard in the training are repeatedly compared in the actual operation, and continuous production control and regulation are achieved.
In this embodiment, the step S1 further includes:
s11: modeling oblique photography data;
s111: acquiring image data and POS data through aerial photography;
s112: preprocessing image data and POS data, synchronously resolving GPS observation data and airborne POS data of a synchronous base station, and checking various parameters of the image data according to the resolved POS data and matching with the existing DEM and DOM data in a region;
s12: modeling the images in an automatic matching way;
s121: manufacturing a monomer three-dimensional model, and performing automatic texture mapping treatment and artificial texture inspection on the monomer three-dimensional model;
s122: UV mapping is carried out on the monomer three-dimensional model, and a illusion engine is introduced.
The digital twin water plant three-dimensional digital model is mainly divided into an outer vertical surface model, internal equipment of the water plant and a pipe network model, wherein the outer vertical surface three-dimensional model is mainly converted through oblique photography data, and the internal equipment and the pipe network three-dimensional model are converted through BIM model data;
the construction of the three-dimensional digital model of the outer facade of the water plant is mainly carried out in the following way:
firstly, regarding the modeling of the oblique photography data in the step 11, the oblique photography data is acquired through unmanned aerial vehicle aerial photography, a oblique photography measurement means is adopted to acquire three-dimensional model data, then the oblique photography model data is imported and is constructed in an OSGB standard data format, finally, the oblique photography model data is converted into data files in OBJ and 3d Tiles formats, and the data files are imported into 3DMax modeling software to perform model optimization, and the specific steps are as follows:
shooting by using a large aerial photo plane with the diameter of more than 1.5 meters, carrying a high-definition 2k lens, completing high-precision model data acquisition of a water plant area, designing aerial photo images to have average resolution of not less than 0.03 meter/pixel, and according to requirements of CH/Z3005-2010 low-altitude digital aerial photogrammetry Specification, the course overlapping degree is 80%, the minimum is not less than 53%, the side overlapping degree is 65% and the minimum is not less than 50%;
after each frame of flying is finished, downloading the frame of image data and POS data at the first time, synchronously resolving the GPS observation data of the synchronous base station and the airborne POS data by using matched software of an unmanned aerial vehicle system, finally obtaining the space position of a camera center corresponding to each image shooting moment, wherein the photo number is formed by adopting a mode of shooting date, frame number, camera number and sheet number, ensuring that all image file names cannot be repeated, and checking the course overlapping degree, side overlapping degree, flying height, route bending degree, coverage range and the like of the image by utilizing the resolved POS data and matching with the existing DEM (digital model) and DOM (digital model) data in a region;
the method comprises the steps that three-dimensional model reconstruction processing can be started after image three-dimensional completion and meets the requirements by using oblique photography software, an OSGB (open-view type) format triangular surface model is automatically generated, DP-Modeler and other monomerized modeling software is used, model manufacturing is carried out on the basis of the automatically generated triangular surface live-view three-dimensional model, in ContextCaputre, an aerial image subjected to distortion correction and an XML (extensive makeup language) format empty three-dimensional fruit file are derived, in the DP-Modeler software, images of a plurality of view angles are used as plane and elevation references, a monomerized three-dimensional model with the shape, fineness and number of patches meeting the requirements is manufactured, automatic texture mapping processing is carried out on the monomerized model, texture of the model is checked manually, if more shielding, distortion and color inconsistency exist on the texture, adjustment processing is needed, finally, the processed and checked model is output as an OSGB file, and the OSGB file is converted into an OBJ and 3d Tiles data file by using a data conversion tool;
then, regarding the step 12 of automatic matching modeling of the images, using the factory OBJ model, importing 3D Max for model optimization and mapping, firstly, needing to unify model units, needing to be consistent with model default units (cm) in UE5, then, performing mapping and UV splitting, and then, manufacturing two sets of UV for the models, wherein the first set of UV is mainly used for manufacturing texture mapping, the second set of UV is used for generating illumination mapping, also called illumination mapping UV, in UE5, finally, splitting UV of a three-dimensional model into planar convenient mapping to be better attached to the 3D model, and the mapping content position corresponds to the model position accurately, and importing the optimized water factory model into the UE5 engine;
the construction of the three-dimensional digital model of the internal equipment and the pipe network of the water plant is mainly carried out according to the following modes:
the plug-in for Revit is installed in the illusion engine 5, BIM model data (Revit model) provided in the implementation process of the water plant are exported to the file, the Datesmith importer in the illusion editor toolbar is used for importing the file, the BIM data are only selected to be needed when exported because of thinner data granulation, and parts such as ground, equipment, pipe network, switch valve and the like in the water plant are exported in the application.
In this embodiment, the step S3 further includes:
s31: the method comprises the steps of monitoring and collecting a plurality of index data in real time and transmitting the index data into a database;
s32: rendering, recording, storing and displaying the data obtained through monitoring.
By design, a plurality of index data that real-time supervision gathered in the water plant mainly includes: instantaneous flow of water inlet and outlet, accumulated flow, water level of primary sedimentation tank, water level of secondary sedimentation tank, water level of contact tank, COD of water inlet and outlet, ammonia nitrogen, PH, turbidity, running state of equipment, fault state, voltage, current and the like, and the specific implementation steps are as follows:
firstly, PIC data is transmitted to a routing gateway;
the gateway reads the data and then sends the data to the MQTT server;
thirdly, the kafka server subscribes to the MQTT message;
fourth, MQTT message is sent to kafka;
fifthly, the kafka server-side queue analyzes data;
sixth, the data is stored in hbase (time sequence database) through opensdb api;
the monitoring data processing of the water plant mainly comprises three aspects: firstly, recording water inlet numerical indexes and water outlet quality, and providing a data base for production control optimization; secondly, the dosing and the running state of each device in the treatment process are recorded, and the dosing control and the water outlet stability reach the standard are ensured; thirdly, the digital factory monitoring data index display is convenient for operators to master the running state of the sewage factory.
In this embodiment, the step S4 further includes:
s41: the sensor is arranged separately: a first nitrate analyzer, a first nitrite tester, a first dissolved oxygen meter and a first flowmeter are arranged at the water outlet of the anoxic tank, and a second nitrate analyzer, a second nitrite tester, a second dissolved oxygen meter and a second flowmeter are arranged at the water outlet of the aerobic tank;
s42: uploading measured data: each nitrate analyzer, each nitrite analyzer, each dissolved oxygen meter and each flowmeter are respectively and wirelessly connected to a computer, and the computer receives real-time measurement data of each sensor;
s43: analyzing and adjusting the carbon source addition amount: and calculating the real-time required carbon source adding amount by using the data model embedded in the computer, synchronously feeding back the calculation result to the PID controller, regulating and controlling the flow of the pump by the PID controller, further controlling the carbon source adding amount, and regulating the carbon source adding amount in real time according to the effluent quality.
The dosing control module of the sewage plant mainly comprises a sewage treatment unit, a data acquisition unit, a dosing unit and a control unit, wherein the sewage treatment unit consists of an anaerobic tank, an anoxic tank and an aerobic tank, an internal reflux pipeline is communicated between the anoxic tank and the aerobic tank, the data acquisition unit comprises a plurality of nitrate analyzers, nitrite testers, an oxygen dissolving instrument and a flowmeter, the dosing unit comprises a liquid storage tank and an automatic regulating pump, and the control unit comprises a computer, model calculation software and an MCP control cabinet;
specifically, a first nitrate analyzer, a first nitrite tester, a first dissolved oxygen meter and a first flowmeter are arranged at a water outlet of the anoxic tank, a second nitrate analyzer, a second nitrite tester, a second dissolved oxygen meter and a second flowmeter are arranged at a water outlet of the aerobic tank, the nitrate analyzers, the nitrite testers, the dissolved oxygen meters and the flowmeters are respectively and wirelessly connected with a computer, the computer receives data measured by the acquisition instruments, calculates the real-time required carbon source adding amount by a data model embedded in the computer, feeds back the calculation result to a PID controller, and the PID controller adjusts the flow of the automatic regulating pump, so as to control the carbon source adding amount, and realize the purpose of real-time regulation of the carbon source adding amount according to the water quality condition of water.
In this embodiment, the step S5 further includes:
s51: establishing a functional relation M=lambda between the carbon source addition amount and the effluent quality 1 X 1 +λ 2 X 2 +···+λ n X n The effluent quality is formed by superposing a plurality of variables X with uncertain tracking set values lambda;
s52: and (3) adjusting tracking set values lambda of different variables X to generate a simulated dosing control model.
In such a design, for example, methanol is used as a carbon source and is stored in the liquid storage tank, the liquid storage tank is connected with the inlet of the anoxic tank through a pipeline, the methanol is controlled by the automatic regulating pump to enter the anoxic tank, the adding amount of the methanol is influenced by nitrate nitrogen (NO 3-N), nitrite nitrogen (NO 2-N) and dissolved oxygen content DO, and the adding amount M of the required carbon source can be calculated by the following formula:
M＝2.47*(NO3--N)+1.53*(NO2--N)+0.87*DO
the nitrate content, the nitrite content and the dissolved oxygen content are monitored and measured by the first nitrate analyzer, the first nitrite analyzer, the first dissolved oxygen meter and the first flowmeter which are arranged at the anoxic tank, and data measured by the second nitrate analyzer, the second nitrite analyzer, the second dissolved oxygen meter and the second flowmeter which are arranged at the aerobic tank are used for checking and correcting.
In this embodiment, the step S6 further includes:
s61: the SS-MOEA/D algorithm is adopted, the input of the algorithm is a multi-objective optimization problem and an algorithm termination condition, and the output of the algorithm is a pareto optimal solution { lambda } 1 ，···，λ n Function value { F (lambda) 1 ，···，F(λ n )}；
S62: sequentially selecting any one group of solutions in the pareto optimal solution set obtained by calculation of an SS-MOEA/D algorithm as tracking set values of different variables in the simulated dosing control model, and generating various multi-objective optimization parameters of the effluent quality meeting emission standards;
s63: and comparing the energy consumption, the medicine consumption and the effluent quality standard reaching degree of the system at the current moment corresponding to each solution, and selecting the solution with the lowest energy consumption, the lowest medicine consumption and the most stable standard reaching rate as the optimal setting value which is satisfied at present to generate the optimal model.
The whole SS-MOEA/D algorithm flow is designed as follows:
the first step is initialized: the following operations are performed in the feasibility space:
1) Generation of initial population X 1 ，···，X n Generating N weight vectors that are uniformly distributed: lambda (lambda) 1 ，λ n The method comprises the steps of carrying out a first treatment on the surface of the Initializing reference point zx, let zx=min f i (X 1 )，···，f i (X n ) The method comprises the steps of carrying out a first treatment on the surface of the Initializing an individual set B (i) in the neighborhood, and setting EP to be null; n is the population scale defined by the algorithm and is also the sub-problem scale;
2) Calculating Euclidean distance between any two weight vectors, finding out T nearest weight vectors of each weight vector, wherein T is the neighborhood scale;
and step two, updating: for each i=1, ·, N operates as follows:
1) Gene recombination: randomly selecting two sequence numbers k and l from B (i), and using genetic operator to obtain the sequence number from X k And X l Generating a new solution y;
2) Improvement: repairing and improving y to produce y';
3) Update z: from j=1 to the point where, the terms, m, if z < fj (y '), let z=fj (y');
4) Updating the neighborhood solution: calculating to obtain the most suitable sub-problem i of the newly generated solution, i=arg min (X) -gte (Xnew); for each solution Xj in neighborhood B (i) and neighborhood B (i), let xj=y 'if gte (y' |λj, z) > gte (xj|λj, z);
4) Update EP: removing all vectors dominated by F (y ') from the EP, adding F (y ') to the EP if none of the vectors in the EP dominate F (y ');
and thirdly, judging termination conditions: stopping and outputting the EP, and if the condition is not met, turning to a second step;
in the sewage treatment process, when any solution in the pareto optimal solution set calculated by the SS-MOEA/D algorithm is selected as a tracking set value of the dissolved oxygen and nitrate nitrogen controller, the water quality finally obtained by sewage treatment accords with the emission standard, so that the current most satisfactory set value is found from the pareto solution set in consideration of that all solution sets meet constraint conditions, the energy consumption of the system at the current moment is compared by adopting each solution, the solution with the lowest energy consumption is selected as the current most satisfactory optimal set value, and the found optimal set value according to the method not only meets the requirement of the water quality of effluent, but also ensures that the medicine consumption of the system is the lowest;
it should be noted that after the SS-MOEA/D optimization algorithm is added into the established simulated dosing control model of the sewage, the obtained parameter solution set is a group of pareto optimal solutions aiming at the EC and EQ optimization problems in the sewage treatment process, and the parameters solution set needs to be found out whenA group of satisfactory optimized solutions in the previous state are used as controller method tracking set values, the multivariable controller performs tracking control on the real values of dissolved oxygen and nitrate nitrogen in the sewage treatment process by the difference value between the real values and the optimized set values, namely, each group of value parameters and output value parameters are recorded into a database, the controller adopted in the application is a PID controller, other automatic controllers can also be selected, the application is not limited in particular, the controller is used for tracking the set values by adjusting the dissolved oxygen conversion coefficient (K La5 ) Controlling the concentration of dissolved oxygen in the sewage, and adjusting the internal reflux quantity (Q) a ) The concentration of nitrate nitrogen is controlled.
In this embodiment, the step S7 further includes:
s71: continuously recording each group of inflow water input values, the carbon source adding amount of the dosing control model and the water quality value of the outflow water in the sewage treatment process;
s72: continuously training a tracking set value of a dosing control model by using an SS-MOEA/D algorithm, forming a plurality of multi-objective optimization model parameters after the simulated dosing control model is stable, and recording the optimization set value of the optimal model and the current corresponding water quality value of the effluent;
s73: selecting an optimization set value for production, recording the difference between a real water outlet value and a model water outlet value, entering the step S5, and continuously optimizing an analog dosing control model to enable the model production value to be consistent with the actual production value;
s74: repeating the step S72 to optimize the existing condition of the dosing control model;
s75: and (3) continuously feeding and discharging water, and repeatedly training a dosing control model until a stable optimized set value and a stable water quality value of discharged water are obtained.
In the actual sewage treatment production process, each group of water inflow input value, production process dosing value (model dosing value) and production water quality value (model water quality value) are recorded, after the simulated dosing control model is optimized and stabilized, the current multi-objective optimization model control optimal value (synchronous recording of simulated dosing value) and production water quality value (model water quality value) of the production process are adopted, and comparison training is repeated, so that the production control is optimal.
The embodiment of the application also provides a computer readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the processor is caused to execute the steps of the monitoring control method. The steps of the monitoring control method herein may be the steps of the monitoring control method of the above-described respective embodiments.
In summary, the application builds a three-dimensional digital model of the whole water outlet plant by means of internal and external modeling in advance, forms a digital twin water plant, realizes the automatic and intelligent real-time monitoring of the target data to be tested, completes the interactive aim of combining the digital twin scene with the dynamic simulation deduction capability, on one hand, can regulate and control the carbon source dosage of sewage according to the measured data to generate an analog dosing control model, abandons the traditional mode of manual field measurement data, does not need to manually check the carbon source dosage, has higher working efficiency, and on the other hand, realizes the simulation optimization of all parameters of the analog dosing control model from the multivariable angle by combining an SS-MOEA/D algorithm until the model is consistent with the production condition in reality, generates the optimal model which meets the minimum energy consumption and the minimum drug consumption and has the highest standard reaching rate of the water quality of the effluent, and further, applies the optimal model to the actual sewage treatment, repeatedly compares and trains a large number of water inlet input parameters and water outlet output parameters in the actual operation, and realizes the continuous production control and regulation.
It should be understood that the examples and embodiments described herein are for illustrative purposes only and are not intended to limit the present application, and that various modifications or changes in light thereof will be suggested to persons skilled in the art and are to be included within the spirit and purview of this application.
Claims (8)
1. The sewage monitoring and controlling method for the digital twin water plant is characterized by comprising the following steps:
s1: establishing a three-dimensional digital model of the outer facade of the water plant;
s2: establishing a three-dimensional digital model of internal equipment and a pipe network of the water plant;
s3: collecting and processing monitoring data in real time;
s4: regulating and controlling the carbon source adding amount of the sewage;
s5: generating a simulated dosing control model;
s6: the multi-variable simulation optimization simulation dosing control model correspondingly generates a plurality of multi-objective optimization model parameters meeting the standard rate of the water quality of the effluent, and selects an optimal model meeting the lowest energy consumption, the lowest drug consumption and the most stable standard rate;
s7: continuous production control and tuning.
2. The method for monitoring and controlling sewage in a digital twin water plant according to claim 1, wherein the step S1 further comprises:
s11: modeling oblique photography data;
s111: acquiring image data and POS data through aerial photography;
s112: preprocessing image data and POS data, synchronously resolving GPS observation data and airborne POS data of a synchronous base station, and checking various parameters of the image data according to the resolved POS data and matching with the existing DEM and DOM data in a region;
s12: modeling the images in an automatic matching way;
s121: manufacturing a monomer three-dimensional model, and performing automatic texture mapping treatment and artificial texture inspection on the monomer three-dimensional model;
s122: UV mapping is carried out on the monomer three-dimensional model, and a illusion engine is introduced.
3. The method for monitoring and controlling sewage in a digital twin water plant according to claim 1, wherein the step S3 further comprises:
s31: the method comprises the steps of monitoring and collecting a plurality of index data in real time and transmitting the index data into a database;
s32: rendering, recording, storing and displaying the data obtained through monitoring.
4. The method for monitoring and controlling sewage in a digital twin water plant according to claim 1, wherein the step S4 further comprises:
s41: the sensor is arranged separately: a first nitrate analyzer, a first nitrite tester, a first dissolved oxygen meter and a first flowmeter are arranged at the water outlet of the anoxic tank, and a second nitrate analyzer, a second nitrite tester, a second dissolved oxygen meter and a second flowmeter are arranged at the water outlet of the aerobic tank;
s42: uploading measured data: each nitrate analyzer, each nitrite analyzer, each dissolved oxygen meter and each flowmeter are respectively and wirelessly connected to a computer, and the computer receives real-time measurement data of each sensor;
s43: analyzing and adjusting the carbon source addition amount: and calculating the real-time required carbon source adding amount by using the data model embedded in the computer, synchronously feeding back the calculation result to the PID controller, regulating and controlling the flow of the pump by the PID controller, further controlling the carbon source adding amount, and regulating the carbon source adding amount in real time according to the effluent quality.
5. The method for monitoring and controlling sewage in a digital twin water plant according to claim 1, wherein the step S5 further comprises:
s51: establishing a functional relation M=lambda between the carbon source addition amount and the effluent quality 1 X 1 +λ 2 X 2 +···+λ n X n The effluent quality is formed by superposing a plurality of variables X with uncertain tracking set values lambda;
s52: and (3) adjusting tracking set values lambda of different variables X to generate a simulated dosing control model.
6. The method for monitoring and controlling sewage in a digital twin water plant according to claim 1, wherein the step S6 further comprises:
s61: the SS-MOEA/D algorithm is adopted, the input of the algorithm is a multi-objective optimization problem and an algorithm termination condition, and the output of the algorithm is a pareto optimal solution { lambda } 1 ，···，λ n Function value { F (lambda) 1 )，···，F(λ n )}；
S62: sequentially selecting any one group of solutions in the pareto optimal solution set obtained by calculation of an SS-MOEA/D algorithm as tracking set values of different variables in the simulated dosing control model, and generating various multi-objective optimization parameters of the effluent quality meeting emission standards;
s63: and comparing the energy consumption, the medicine consumption and the effluent quality standard reaching degree of the system at the current moment corresponding to each solution, and selecting the solution with the lowest energy consumption, the lowest medicine consumption and the most stable standard reaching rate as the optimal setting value which is satisfied at present to generate the optimal model.
7. The method for monitoring and controlling sewage in a digital twin water plant according to claim 1, wherein the step S7 further comprises:
s71: continuously recording each group of inflow water input values, the carbon source adding amount of the dosing control model and the water quality value of the outflow water in the sewage treatment process;
s72: continuously training a tracking set value of a dosing control model by using an SS-MOEA/D algorithm, forming a plurality of multi-objective optimization model parameters after the simulated dosing control model is stable, and recording the optimization set value of the optimal model and the current corresponding water quality value of the effluent;
s73: selecting an optimization set value for production, recording the difference between a real water outlet value and a model water outlet value, entering the step S5, and continuously optimizing an analog dosing control model to enable the model production value to be consistent with the actual production value;
s74: repeating the step S72 to optimize the existing condition of the dosing control model;
s75: and (3) continuously feeding and discharging water, and repeatedly training a dosing control model until a stable optimized set value and a stable water quality value of discharged water are obtained.
8. A computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310775114.2A CN116774632A (en) | 2023-06-27 | 2023-06-27 | Sewage monitoring control method and storage medium for digital twin water plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310775114.2A CN116774632A (en) | 2023-06-27 | 2023-06-27 | Sewage monitoring control method and storage medium for digital twin water plant |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116774632A true CN116774632A (en) | 2023-09-19 |
Family
ID=87985667
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310775114.2A Pending CN116774632A (en) | 2023-06-27 | 2023-06-27 | Sewage monitoring control method and storage medium for digital twin water plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116774632A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117602767A (en) * | 2023-12-20 | 2024-02-27 | 石家庄正中科技有限公司 | Efficient intensive denitrification and dephosphorization sewage treatment process |
-
2023
- 2023-06-27 CN CN202310775114.2A patent/CN116774632A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117602767A (en) * | 2023-12-20 | 2024-02-27 | 石家庄正中科技有限公司 | Efficient intensive denitrification and dephosphorization sewage treatment process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110214506A (en) | Liquid manure management-control method and system | |
| CN109558973B (en) | Water quality and water ecology integrated early warning system, control equipment and storage medium | |
| CN116774632A (en) | Sewage monitoring control method and storage medium for digital twin water plant | |
| CN112464746A (en) | Water quality monitoring method and system based on satellite images and machine learning | |
| CN108007438A (en) | The estimating and measuring method of unmanned plane aeroplane photography remote sensing wetland plant biomass | |
| CN110517311A (en) | Pest and disease monitoring method based on leaf spot lesion area | |
| CN106444378A (en) | Plant culture method and system based on IoT (Internet of things) big data analysis | |
| CN108694444A (en) | A kind of plant cultivating method based on intelligent data acquisition Yu cloud service technology | |
| CN112581083B (en) | Forest growth monitoring system based on satellite technology | |
| CN108520165A (en) | Rainfall Runoff Forecasting | |
| CN106650212A (en) | Intelligent plant breeding method and system based on data analysis | |
| CN111008733A (en) | Crop growth control method and system | |
| CN114757807A (en) | Multi-mode fused online accounting method for actual emission of atmospheric pollutants | |
| CN114442705B (en) | Intelligent agricultural system based on Internet of things and control method | |
| CN117291444B (en) | Digital rural business management method and system | |
| CN110648020A (en) | Greenhouse crop water demand prediction method and device | |
| EP3333802B1 (en) | Method and system for quantifying greenhouse gases emissions produced in a wastewater treatment plant and method of multivariable control for optimizing the operation of such plants | |
| CN117434235A (en) | Water bloom early warning method, device, equipment and medium based on water quality monitoring | |
| CN117314469A (en) | Tap water plant carbon emission calculation method, medium and equipment | |
| CN116993030A (en) | Reservoir pressure salty taste adjustment method and system under variable conditions | |
| CN208937029U (en) | A kind of silt arrester fouling status investigation apparatus | |
| CN115034159A (en) | Power prediction method, device, storage medium and system for offshore wind farm | |
| CN114219673A (en) | Agricultural cloud service system based on Internet of things | |
| CN112699287A (en) | Configurable automatic model data preprocessing and distributing method and system | |
| CN115861827B (en) | Decision method and device for crop water and fertilizer stress and mobile phone terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |