CN113433910A - Water purification plant intelligent dosing control system and method based on digital twin - Google Patents
Water purification plant intelligent dosing control system and method based on digital twin Download PDFInfo
- Publication number
- CN113433910A CN113433910A CN202110732899.6A CN202110732899A CN113433910A CN 113433910 A CN113433910 A CN 113433910A CN 202110732899 A CN202110732899 A CN 202110732899A CN 113433910 A CN113433910 A CN 113433910A
- Authority
- CN
- China
- Prior art keywords
- dosing
- digital twin
- physical
- room
- real
- 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 104
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000000746 purification Methods 0.000 title claims description 9
- 238000012544 monitoring process Methods 0.000 claims abstract description 45
- 239000003814 drug Substances 0.000 claims abstract description 42
- 238000013528 artificial neural network Methods 0.000 claims abstract description 23
- 230000000007 visual effect Effects 0.000 claims abstract description 23
- 230000008569 process Effects 0.000 claims abstract description 22
- 230000005540 biological transmission Effects 0.000 claims abstract description 20
- 238000004519 manufacturing process Methods 0.000 claims abstract description 15
- 239000007788 liquid Substances 0.000 claims description 16
- 230000002452 interceptive effect Effects 0.000 claims description 10
- 238000004062 sedimentation Methods 0.000 claims description 10
- 238000012800 visualization Methods 0.000 claims description 10
- 230000002457 bidirectional effect Effects 0.000 claims description 5
- 230000009471 action Effects 0.000 claims description 3
- 238000010790 dilution Methods 0.000 claims description 2
- 239000012895 dilution Substances 0.000 claims description 2
- 238000005189 flocculation Methods 0.000 abstract description 11
- 230000016615 flocculation Effects 0.000 abstract description 11
- 229940079593 drug Drugs 0.000 abstract description 4
- 238000013507 mapping Methods 0.000 abstract description 4
- 239000002699 waste material Substances 0.000 abstract description 3
- 238000013480 data collection Methods 0.000 abstract description 2
- 238000007726 management method Methods 0.000 description 24
- 239000010410 layer Substances 0.000 description 19
- 238000004088 simulation Methods 0.000 description 15
- 241000196324 Embryophyta Species 0.000 description 13
- 238000012549 training Methods 0.000 description 9
- 238000003062 neural network model Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 6
- 239000000243 solution Substances 0.000 description 5
- 230000000875 corresponding effect Effects 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 229940037003 alum Drugs 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 208000025174 PANDAS Diseases 0.000 description 1
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 1
- 240000000220 Panda oleosa Species 0.000 description 1
- 235000016496 Panda oleosa Nutrition 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001311 chemical methods and process Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000008394 flocculating agent Substances 0.000 description 1
- 239000002346 layers by function Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000008399 tap water Substances 0.000 description 1
- 235000020679 tap water Nutrition 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F1/00—Treatment of water, waste water, or sewage
- C02F1/008—Control or steering systems not provided for elsewhere in subclass C02F
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F1/00—Treatment of water, waste water, or sewage
- C02F1/52—Treatment of water, waste water, or sewage by flocculation or precipitation of suspended impurities
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F1/00—Treatment of water, waste water, or sewage
- C02F1/52—Treatment of water, waste water, or sewage by flocculation or precipitation of suspended impurities
- C02F1/5209—Regulation methods for flocculation or precipitation
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F1/00—Treatment of water, waste water, or sewage
- C02F1/52—Treatment of water, waste water, or sewage by flocculation or precipitation of suspended impurities
- C02F1/5281—Installations for water purification using chemical agents
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F1/00—Treatment of water, waste water, or sewage
- C02F2001/007—Processes including a sedimentation step
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/06—Controlling or monitoring parameters in water treatment pH
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/11—Turbidity
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/40—Liquid flow rate
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Hydrology & Water Resources (AREA)
- Environmental & Geological Engineering (AREA)
- Water Supply & Treatment (AREA)
- Organic Chemistry (AREA)
- Manufacturing & Machinery (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Chemical Kinetics & Catalysis (AREA)
- General Chemical & Material Sciences (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention belongs to the technical field of water treatment, and discloses a water treatment plant intelligent dosing control system and method based on a digital twin. Establishing a medicated digital twin body; real-time monitoring data in the operation process of the physical dosing room are collected through data collection equipment and transmitted to a management platform through a network transmission system; the management platform transmits real-time monitoring data to the dosing room digital twin body through a network transmission system; dynamically mapping the production condition of the physical dosing room by the digital twin organism of the dosing room; carrying out three-dimensional visual monitoring and displaying on the digital twin body between the medicines through a three-dimensional visual system; the management platform predicts the dosing quantity by using an LSTM neural network based on real-time monitoring data to obtain dosing quantity prediction information, and obtains adjustment control information according to the dosing quantity prediction information and the real-time monitoring data; and the physical dosing room adjusts the dosing amount according to the adjustment control information. The invention can solve the problem of serious waste of flocculation dosing mode in water plants.
Description
Technical Field
The invention belongs to the technical field of water treatment, and particularly relates to a water treatment plant intelligent dosing control system and method based on digital twin.
Background
Tap water is an indispensable part of production and life, and has huge consumption every year. In the water purification treatment process of a water plant, a flocculation chemical dosing link is a core process in the purification process, and the flocculation precipitation effect directly influences the quality of the water leaving the plant. However, in the actual operation of the existing water plant, a flocculating agent is usually added at a fixed adding rate, which is often higher, so that the existing flocculation adding mode of the water plant has a serious waste phenomenon.
In addition, the establishment of an appropriate mathematical model can greatly help to accurately control the dosage of the medicament and improve the operation level of the water purification treatment. However, since the flocculation chemical administration process is a complicated physical chemical process, it is difficult to accurately establish a mathematical model based on the chemical reaction mechanism by studying the chemical reaction mechanism. The existing flocculation dosing method of the water plant which is generally and practically adopted can not track the change of water containing quality in time, the reaction is delayed, and the robustness is poor.
How to reduce the waste under the prerequisite of guaranteeing quality of water, improve the intelligent of dosing among the water purification treatment process, realize accurate dosing, have crucial realistic meaning.
Disclosure of Invention
The invention provides a water treatment plant intelligent dosing control system and method based on a digital twin, and solves the problem that the flocculation dosing mode of a water plant is seriously wasted in the prior art.
The invention provides a water treatment plant intelligent dosing control method based on digital twin, which comprises the following steps:
establishing a dosing room digital twin body based on an entity structure, an operation flow and historical operation data of a physical dosing room; the medicated digital twin body is a virtual medicated model which is mapped with the physical medicated chamber in a bidirectional manner;
acquiring real-time monitoring data in the operation process of the physical dosing room through data acquisition equipment, and transmitting the real-time monitoring data to a management platform through a network transmission system;
the management platform transmits the real-time monitoring data to the medicated digital twin body through the network transmission system;
the dosing room digital twin body synchronously operates under the driving of the real-time monitoring data, and the production condition of the physical dosing room is dynamically mapped;
carrying out three-dimensional visual monitoring and displaying on the dosing chamber digital twin body through the three-dimensional visual system;
the management platform predicts the dosing quantity by using an LSTM neural network based on the real-time monitoring data to obtain dosing quantity prediction information;
the management platform obtains adjustment control information according to the dosing quantity prediction information and the real-time monitoring data, and transmits the adjustment control information to the physical dosing room through the network transmission system;
and the physical dosing room adjusts the dosing amount according to the adjustment control information.
Preferably, the intelligent dosing control method for the water purification plant based on the digital twin further comprises the following steps: and displaying the related data information of the management platform in real time through the three-dimensional visualization system.
Preferably, the three-dimensional visual system is used for carrying out three-dimensional visual monitoring on the equipment running state, the medicine adding state and the water flow circulation state of the physical medicine adding room.
Preferably, the data acquisition equipment comprises a flow meter, a temperature sensor, a pH sensor and a turbidity sensor; the real-time monitoring data comprises water flow, temperature, raw water PH value and raw water turbidity in a main water pipe in the physical dosing room.
In another aspect, the present invention provides a water treatment plant intelligent dosing control system based on digital twin, comprising: a physical dosing room, a dosing room digital twin body, data acquisition equipment, a network transmission system, a three-dimensional visualization system and a management platform;
the intelligent dosing control system based on the digital twin for the water treatment plant is used for realizing the steps in the intelligent dosing control method based on the digital twin for the water treatment plant.
Preferably, the physical medicine adding room comprises: a water pump, a tee joint, a main pipeline, a branch pipe, a stirrer, a dosing room, a variable-frequency dosing pump, a dosing hose and a sedimentation tank;
water flow enters the main water pipe through the water pump in a pressurized mode, the data acquisition equipment is arranged on the main water pipe, and the data acquisition equipment transmits real-time monitoring data in the operation process of the physical dosing room to the management platform through the network transmission system;
before entering the dosing room, after water flows through the tee joint, water flow with a first proportion directly flows into the sedimentation tank through the main water pipe, water flow with a second proportion enters the dosing room through the branch pipe, and the water flow entering the dosing room is mixed with the liquid medicine under the action of the stirrer to obtain the liquid medicine after primary dilution; meanwhile, the variable-frequency dosing pump adjusts the dosing amount in real time according to the feedback of the management platform, and adjusts the preliminarily diluted liquid medicine to obtain the adjusted liquid medicine; and the adjusted liquid medicine enters the sedimentation tank through a medicine conveying hose.
Preferably, the physical medicine adding room further comprises: an interactive interface; the interactive interface is used for displaying the real-time medicine adding amount and carrying out the regulation and control operation between the physical medicine adding.
One or more technical schemes provided by the invention at least have the following technical effects or advantages:
in the invention, a dosing room digital twin body is established based on the entity structure, the operation flow and the historical operation data of a physical dosing room, and the dosing room digital twin body is a virtual dosing room model which is mapped with the physical dosing room in a bidirectional way; the method comprises the following steps of collecting real-time monitoring data in the operation process of a physical dosing room through data collection equipment, and transmitting the real-time monitoring data to a management platform through a network transmission system; the management platform transmits real-time monitoring data to the dosing room digital twin body through a network transmission system; the dosing room digital twin body synchronously operates under the driving of real-time monitoring data, and the production condition of the physical dosing room is dynamically mapped; carrying out three-dimensional visual monitoring and displaying on the digital twin body between the medicines through a three-dimensional visual system; the management platform predicts the dosing quantity by using an LSTM neural network based on real-time monitoring data to obtain dosing quantity prediction information; the management platform obtains adjustment control information according to the dosing amount prediction information and the real-time monitoring data, and transmits the adjustment control information to the physical dosing room through the network transmission system; and the physical dosing room adjusts the dosing amount according to the adjustment control information. According to the invention, the LSTM neural network is used for predicting the dosing amount, so that the dosing amount is regulated, the control on the flocculation dosing amount can be greatly improved, and the method has higher energy-saving and emission-reducing benefits. Meanwhile, the whole production process of the physical dosing room is monitored and displayed in real time by using a digital twin technology and a three-dimensional visualization technology, the information utilization rate in operation is improved, real-time monitoring data is compared with a theoretical model by using a management platform, the actual work of the physical dosing room can be adjusted and corrected, the function of artificial intelligence auxiliary safety prediction is realized, and quality guarantee is provided for the work of the dosing room.
Drawings
FIG. 1 is a schematic layer diagram of a digital twin-based intelligent dosing control system for a water treatment plant according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a simulation prediction framework of an inter-dosing digital twin;
FIG. 3 is a schematic structural diagram of a physical dosing room in a water treatment plant intelligent dosing control system based on digital twin according to an embodiment of the present invention;
FIG. 4 is a flow chart of the physical dosing chamber.
Wherein, the device comprises a water pump 1, a flowmeter 2, a tee joint 3, a ball valve 4, a joint 5, an interactive interface 6, a stirrer 7, a dosing room 8, a variable-frequency dosing pump 9, a dosing hose 10 and a sedimentation tank 11.
Detailed Description
In order to improve the utilization rate of alum liquid and intelligently modify a water plant, the invention applies an LSTM neural network to process accurate large alum addition data, applies a digital twin technology to construct a physical model, accurately measures turbidity, flow, temperature, pH and the like of raw water in real time through a sensor, feeds back the data in real time, and displays and monitors the data in real time through a three-dimensional visualization system to realize the fine control of flocculation chemical dosing.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Example 1:
establishing a dosing room digital twin body based on an entity structure, an operation flow and historical operation data of a physical dosing room; the medicated digital twin body is a virtual medicated model which is mapped with the physical medicated chamber in a bidirectional manner;
acquiring real-time monitoring data in the operation process of the physical dosing room through data acquisition equipment, and transmitting the real-time monitoring data to a management platform through a network transmission system;
the management platform transmits the real-time monitoring data to the medicated digital twin body through the network transmission system;
the dosing room digital twin body synchronously operates under the driving of the real-time monitoring data, and the production condition of the physical dosing room is dynamically mapped;
carrying out three-dimensional visual monitoring and displaying on the dosing chamber digital twin body through the three-dimensional visual system;
the management platform predicts the dosing quantity by using an LSTM neural network based on the real-time monitoring data to obtain dosing quantity prediction information;
the management platform obtains adjustment control information according to the dosing quantity prediction information and the real-time monitoring data, and transmits the adjustment control information to the physical dosing room through the network transmission system;
and the physical dosing room adjusts the dosing amount according to the adjustment control information.
In addition, the related data information of the management platform can be displayed in real time through the three-dimensional visualization system. For example, dosing amount, device information, regulation information may be displayed.
The three-dimensional visual system can be used for carrying out three-dimensional visual monitoring on the equipment running state, the medicine adding state and the water flow circulation state of the physical medicine adding room.
The data acquisition equipment comprises a flowmeter, a temperature sensor, a PH sensor, a turbidity sensor and the like; the real-time monitoring data comprises water flow, temperature, raw water PH value, raw water turbidity and the like in a main water pipe in the physical dosing room.
Example 2:
Wherein, referring to fig. 3 and 4, the physical medicine adding room mainly comprises: the device comprises a water pump 1, a tee joint 3, a main pipeline, branch pipes, a stirrer 7, a dosing room 8, a variable-frequency dosing pump 9, a medicine conveying hose 10 and a sedimentation tank 11. The water flow enters the main water pipe through the water pump 1 in a pressurized mode, the data acquisition equipment (comprising a flowmeter 2, a temperature sensor, a pH sensor and a turbidity sensor) is arranged on the main water pipe, and the data acquisition equipment transmits real-time monitoring data (comprising information such as water flow, temperature, pH value and turbidity in the main water pipe) in the operation process of the physical dosing room to the management platform through the network transmission system; before entering the dosing room, after water flows through the tee joint 3, water flow (most of water flow) with a first proportion directly flows into the sedimentation tank 11 through the main water pipe, water flow with a second proportion enters the dosing room 8 through the branch pipe (the branch pipe is rotated out through the ball valve 4 and the adapter 5), and the water flow entering the dosing room 8 is mixed with the liquid medicine under the action of the stirrer 7 to obtain the liquid medicine after being primarily diluted; meanwhile, the variable-frequency dosing pump 9 adjusts the dosing amount in real time according to the feedback of the management platform, and adjusts the preliminarily diluted liquid medicine to obtain the adjusted liquid medicine; the adjusted liquid medicine enters the sedimentation tank 11 through the medicine conveying hose 10.
In addition, the physical medicine adding room can also comprise an interactive interface 6; the interactive interface 6 is used for displaying the real-time medicine adding amount and carrying out the regulation and control operation between the physical medicine adding. The interactive interface 6 can facilitate daily overhaul and operation of workers.
Through the reasonable arrangement and the optimized combination of the devices in the system, the maximum utilization of the medicines can be realized, and the turbidity of water can be ensured to reach the standard while the medicine adding amount is accurate.
The present invention is further described below.
The intelligent dosing control system for the water treatment plant based on the digital twin can be summarized into the following 4 levels (as shown in figure 1):
(1) the physical layer is formed by a set of all objectively existing entities such as equipment, products, personnel and the like in the physical dosing room.
(2) And the data layer comprises static data of a physical dosing room and dosing process real-time data acquired based on the Internet of things. The collected data is processed and cleaned in the layer, and finally transmitted to the model layer through a data communication mechanism.
(3) And the model layer refers to an inter-dosing digital twin body constructed in a virtual space.
(4) And the functional layer refers to that the dosing room digital twin body synchronously operates under the drive of real-time data, so that the real production condition of the physical dosing room is dynamically mapped, and finally, the functions of real description of the production state of the physical dosing room, real-time display of production data, simulation prediction of the operation state and the like are realized, and the decision of dosing room management is assisted.
The inter-dosing digital twin body is a complex production system which comprises integration and fusion of all elements, all processes and all data of a physical dosing room, and the interactive fusion of the physical dosing room and a virtual dosing room is realized through sensor communication, simulation evaluation and iterative optimization, so that optimal dosing production and control are achieved. The digital twin body is a simulation process which fully utilizes data integration of a physical model, sensor updating, operation history and the like, mapping between physical dosing and dosing process is completed in a virtual space, external conditions can be reflected on the virtual body, a function similar to predictive maintenance is achieved by using powerful computer computing power of a management platform, and a worker can see dosing results under the condition that the dosing process is not completed, and can timely adjust the dosing results if large deviation is found. Meanwhile, the working life cycle of the equipment can be reflected, the damage condition of the equipment is predicted and maintained in advance, and the damage caused by the equipment is reduced.
As shown in fig. 2, the simulation prediction framework based on the medicated digital twin mainly includes: a dosing room digital twin body, a physical dosing room, an LSTM neural network dosing quantity prediction model based on real-time data and a visual interface. The device comprises a dosing room digital twin body, a physical dosing room digital twin body, a visual interface, an LSTM neural network dosing quantity prediction model based on real-time data, a simulation result, a physical dosing room and a visual interface, wherein the dosing room digital twin body and the physical dosing room are subjected to bidirectional mapping, the physical dosing room is subjected to data acquisition, the dosing room digital twin body is driven by the data to run synchronously, the dosing room digital twin body is subjected to visual monitoring through the visual interface, the dosing quantity is simulated through the LSTM neural network dosing quantity prediction model based on the real-time data, the simulation result is fed back to the physical dosing room, and the simulation result is visually displayed through the visual interface.
The present invention is explained below from another point of view. The invention provides a water treatment plant intelligent dosing control method based on digital twin, which comprises the following implementation processes:
(1) and establishing a digital twin dosing room data management framework by taking data as a driving source, and realizing interactive management of acquisition, driving, input, update, display and the like of production data.
(2) And constructing a three-dimensional static model of the physical dosing room equipment, constructing a virtual dosing room model which is completely mapped with the physical dosing room on the basis of the actual dosing room production layout, and establishing a dosing room digital twin body under a virtual platform.
(3) And establishing a data communication mechanism between the physical dosing room and the digital twin body between the physical dosing rooms to drive the three-dimensional model of the virtual dosing room to dynamically operate by real-time data, so as to realize three-dimensional visual monitoring on the operation state of the equipment, the dosing state and the water flow state in a virtual space. On the basis, multi-level information such as equipment state information, dosage prediction information, production environment information and the like is displayed in a visual interface mode, and dynamic mapping of information between the physical workshop and the virtual workshop is achieved.
(4) Establishing system simulation input parameters, generating simulation water flow variables, scanning the current simulation water flow state on the basis of an LSTM neural network as the initial state of simulation, executing a neural network program for predicting the dosing amount, continuously changing the water flow state in the simulation reality to realize continuous transient simulation, and simultaneously outputting the dosing amount simulation operation result to a visual interface to further realize the online prediction of the operation state between physical dosing rooms.
The structure determination of the LSTM neural network mainly comprises the following steps: collecting water treatment plant data, preprocessing the water treatment plant data to obtain standardized data, establishing a data set based on the standardized data, and dividing the data set into a training set and a testing set; constructing a neural network model comprising an input layer, a hidden layer and an output layer based on a Keras framework, and setting the number of neurons of each layer, an optimizer, a loss function, random seeds, the size of each batch of neural networks and the training times of the neural network model; and training the neural network model based on the training set, and verifying and optimizing the neural network model based on the testing set to obtain the trained neural network.
The water treatment plant data comprises two columns, the first column is dosing time, and the second column is dosing amount data corresponding to the dosing time. The preprocessing of the water treatment plant data comprises: performing root mean square deviation and matrix calculation on the original data; the input format of the neural network model is a matrix, the matrix is represented as [ samples, time steps, features ], wherein samples represents observed quantity, namely dosing quantity corresponding to certain dosing time; time steps represent a time window, the step size of which is 1; features are values corresponding to the factors that affect the amount of drug added observed at the time when the observed value is obtained.
The following description is from a programming perspective. The LSTM neural network is based on Keras to establish a neural network model and mainly comprises the following steps:
the data in the code data folder contains the sine wave.csv file we created, which contains the training data set provided by the water plant. The data in the CSV file is first loaded into the pandas data frame and then used for output, which will provide the numpy array of data for the LSTM neural network.
Firstly, importing an array module and a drawing module, importing a CSV (common mode vector) file into a dataframe structure, importing a mathematic module, calculating a root-mean-square difference, and introducing a sequence model of a Kears module, wherein the sequence model is formed by linearly overlapping all layers, using a full-connection layer as an output layer and introducing an LSTM layer; data normalization, root mean square deviation, matrix calculation were then performed.
Then set random seed, size of each batch of neural network and round of neural network training.
And importing a data file, wherein the data file comprises two columns, one column is dosing time, the subsequent training of the neural network is conveniently prepared by arranging dosing quantity data, and the other column is daily dosing quantity data.
Setting a time window with the step size of 1, wherein the time window represents 1 day, namely, the tomorrow is predicted by today.
The hidden layer is 3 layers, input _ shape is an input data format, the input format of the LSTM layer is a matrix, and the content of the matrix is as follows: [ samples, time steps, features ]. samples, namely observed values, namely the dosing amount corresponding to certain dosing time; time steps is a time window; features are that the observed influence factors of the medicine adding amount correspond to the observed values when the observed values are obtained.
The output layer adopts a full connection layer.
The loss function is the mean square error and the optimizer is to use adam.
A random seed is then set in order to ensure that the results of the neural network training can be reproduced.
The data is then imported along with the normalized data, and then trained, tested, and dataset created, with the data being correlated.
After the above work is completed, the model is trained, the prediction data of the model is optimized, and denormalization data (performing a normal denormalization operation or denormalization on the data) is also required to ensure the accuracy of the MSE.
And finally, evaluating the model, constructing chart data predicted by the training set and constructing chart data predicted by the testing set, and displaying the chart data.
Specifically, the parameters of the LSTM neural network employed in the present invention are shown in table 1.
TABLE 1 LSTM neural network parameters
In conclusion, the optimal neural network model is obtained after the flocculation dosing data obtained from the water plant is analyzed and trained, the LSTM neural network is used for predicting the dosing amount, so that the dosing amount is regulated, the control on the flocculation dosing amount is greatly improved, and the energy-saving and emission-reducing benefits are higher. The invention integrates the internet of things, deep learning and finite element models to build an intelligent construction method frame based on digital twins, and the frame also comprises an intelligent decision platform, and real-time monitoring data is compared with a theoretical model to further adjust and correct the actual working process of a physical space. The digital twin model gives real-time feedback and regulation to the whole dosing room process, improves the information utilization rate in construction operation, and accelerates the digitization process of a water plant; meanwhile, the intelligent decision realizes the function of artificial intelligence for assisting safety prediction, and provides quality guarantee for the work of dosing rooms.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to examples, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (7)
1. A water treatment plant intelligent dosing control method based on digital twin is characterized by comprising the following steps:
establishing a dosing room digital twin body based on an entity structure, an operation flow and historical operation data of a physical dosing room; the medicated digital twin body is a virtual medicated model which is mapped with the physical medicated chamber in a bidirectional manner;
acquiring real-time monitoring data in the operation process of the physical dosing room through data acquisition equipment, and transmitting the real-time monitoring data to a management platform through a network transmission system;
the management platform transmits the real-time monitoring data to the medicated digital twin body through the network transmission system;
the dosing room digital twin body synchronously operates under the driving of the real-time monitoring data, and the production condition of the physical dosing room is dynamically mapped;
carrying out three-dimensional visual monitoring and displaying on the dosing chamber digital twin body through the three-dimensional visual system;
the management platform predicts the dosing quantity by using an LSTM neural network based on the real-time monitoring data to obtain dosing quantity prediction information;
the management platform obtains adjustment control information according to the dosing quantity prediction information and the real-time monitoring data, and transmits the adjustment control information to the physical dosing room through the network transmission system;
and the physical dosing room adjusts the dosing amount according to the adjustment control information.
2. The intelligent dosing control method for the water treatment plant based on the digital twin as claimed in claim 1, further comprising: and displaying the related data information of the management platform in real time through the three-dimensional visualization system.
3. The intelligent dosing control method for the water treatment plant based on the digital twin as claimed in claim 1, characterized in that the equipment operation state, the dosing amount adding state and the water flow circulation state of the physical dosing room are monitored in a three-dimensional visualization manner through the three-dimensional visualization system.
4. The intelligent dosing control method for water treatment plant based on digital twin as claimed in claim 1, characterized in that the data acquisition equipment comprises a flow meter, a temperature sensor, a PH sensor and a turbidity sensor; the real-time monitoring data comprises water flow, temperature, raw water PH value and raw water turbidity in a main water pipe in the physical dosing room.
5. The utility model provides a water purification plant intelligence medicine control system based on digit twin which characterized in that includes: a physical dosing room, a dosing room digital twin body, data acquisition equipment, a network transmission system, a three-dimensional visualization system and a management platform;
the digital twin-based water treatment plant intelligent dosing control system is used for realizing the steps in the digital twin-based water treatment plant intelligent dosing control method according to any one of claims 1 to 4.
6. The digitally twin based water treatment plant intelligent dosing control system of claim 5, wherein the physical dosing booth comprises: a water pump, a tee joint, a main pipeline, a branch pipe, a stirrer, a dosing room, a variable-frequency dosing pump, a dosing hose and a sedimentation tank;
water flow enters the main water pipe through the water pump in a pressurized mode, the data acquisition equipment is arranged on the main water pipe, and the data acquisition equipment transmits real-time monitoring data in the operation process of the physical dosing room to the management platform through the network transmission system;
before entering the dosing room, after water flows through the tee joint, water flow with a first proportion directly flows into the sedimentation tank through the main water pipe, water flow with a second proportion enters the dosing room through the branch pipe, and the water flow entering the dosing room is mixed with the liquid medicine under the action of the stirrer to obtain the liquid medicine after primary dilution; meanwhile, the variable-frequency dosing pump adjusts the dosing amount in real time according to the feedback of the management platform, and adjusts the preliminarily diluted liquid medicine to obtain the adjusted liquid medicine; and the adjusted liquid medicine enters the sedimentation tank through a medicine conveying hose.
7. The digitally twin based water treatment plant intelligent dosing control system of claim 6, wherein the physical dosing booth further comprises: an interactive interface; the interactive interface is used for displaying the real-time medicine adding amount and carrying out the regulation and control operation between the physical medicine adding.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110732899.6A CN113433910A (en) | 2021-06-30 | 2021-06-30 | Water purification plant intelligent dosing control system and method based on digital twin |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110732899.6A CN113433910A (en) | 2021-06-30 | 2021-06-30 | Water purification plant intelligent dosing control system and method based on digital twin |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113433910A true CN113433910A (en) | 2021-09-24 |
Family
ID=77757959
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110732899.6A Pending CN113433910A (en) | 2021-06-30 | 2021-06-30 | Water purification plant intelligent dosing control system and method based on digital twin |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113433910A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114031147A (en) * | 2021-11-02 | 2022-02-11 | 航天环保(北京)有限公司 | Method and system for improving water quality by utilizing wave cracking nano material |
| CN114380379A (en) * | 2022-02-22 | 2022-04-22 | 太原理工大学 | Chemical adding control method and system for slime water |
| CN114563988A (en) * | 2022-01-26 | 2022-05-31 | 浙江中控信息产业股份有限公司 | Water plant intelligent PAC adding method and system based on random forest algorithm |
| CN114573120A (en) * | 2022-05-06 | 2022-06-03 | 齐鲁工业大学 | Multivariable control method, device and system for coal chemical industry grey water granulation and hardness removal |
| CN115083535A (en) * | 2022-08-23 | 2022-09-20 | 佰墨思(成都)数字技术有限公司 | Configuration digital twin construction method and system for biological pharmaceutical workshop |
| CN116307565A (en) * | 2023-03-06 | 2023-06-23 | 物产中大公用环境投资有限公司 | Three-dimensional digital twin operation management system for real-time analog simulation deduction of sewage treatment |
| CN116375119A (en) * | 2023-06-06 | 2023-07-04 | 深圳垚鑫淼环境科技有限公司 | Data visualization method and device for realizing sewage treatment based on big data |
| CN116415776A (en) * | 2023-02-27 | 2023-07-11 | 物产中大公用环境投资有限公司 | Sewage treatment monitoring operation management system and method based on digital twin technology |
| CN116703352A (en) * | 2023-04-17 | 2023-09-05 | 艾尔科工程技术有限公司 | Clean room intelligent operation and maintenance system and method based on digital twin |
| CN116909238A (en) * | 2023-08-29 | 2023-10-20 | 广东青藤环境科技有限公司 | Intelligent water plant integrated management system based on digital twinning |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340948A (en) * | 2020-04-16 | 2020-06-26 | 中冶京诚工程技术有限公司 | BIM-based water treatment plant operation and maintenance system |
| CN112765718A (en) * | 2021-02-02 | 2021-05-07 | 中冶京诚工程技术有限公司 | Water treatment plant operation and maintenance system and method based on BIM and Internet of things technology |
-
2021
- 2021-06-30 CN CN202110732899.6A patent/CN113433910A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340948A (en) * | 2020-04-16 | 2020-06-26 | 中冶京诚工程技术有限公司 | BIM-based water treatment plant operation and maintenance system |
| CN112765718A (en) * | 2021-02-02 | 2021-05-07 | 中冶京诚工程技术有限公司 | Water treatment plant operation and maintenance system and method based on BIM and Internet of things technology |
Non-Patent Citations (1)
| Title |
|---|
| 周圣文 等: "数字孪生净水厂运维管控一体化平台关键技术及应用", 《计算机集成制造系统》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114031147A (en) * | 2021-11-02 | 2022-02-11 | 航天环保(北京)有限公司 | Method and system for improving water quality by utilizing wave cracking nano material |
| CN114563988A (en) * | 2022-01-26 | 2022-05-31 | 浙江中控信息产业股份有限公司 | Water plant intelligent PAC adding method and system based on random forest algorithm |
| CN114380379A (en) * | 2022-02-22 | 2022-04-22 | 太原理工大学 | Chemical adding control method and system for slime water |
| CN114573120A (en) * | 2022-05-06 | 2022-06-03 | 齐鲁工业大学 | Multivariable control method, device and system for coal chemical industry grey water granulation and hardness removal |
| CN115083535A (en) * | 2022-08-23 | 2022-09-20 | 佰墨思(成都)数字技术有限公司 | Configuration digital twin construction method and system for biological pharmaceutical workshop |
| CN115083535B (en) * | 2022-08-23 | 2022-11-08 | 佰墨思(成都)数字技术有限公司 | Configuration digital twin construction method and system for biological pharmaceutical workshop |
| CN116415776A (en) * | 2023-02-27 | 2023-07-11 | 物产中大公用环境投资有限公司 | Sewage treatment monitoring operation management system and method based on digital twin technology |
| CN116415776B (en) * | 2023-02-27 | 2023-12-01 | 物产中大公用环境投资有限公司 | Sewage treatment monitoring operation management system and method based on digital twin technology |
| CN116307565A (en) * | 2023-03-06 | 2023-06-23 | 物产中大公用环境投资有限公司 | Three-dimensional digital twin operation management system for real-time analog simulation deduction of sewage treatment |
| CN116307565B (en) * | 2023-03-06 | 2023-12-01 | 物产中大公用环境投资有限公司 | Three-dimensional digital twin operation management system for real-time analog simulation deduction of sewage treatment |
| CN116703352A (en) * | 2023-04-17 | 2023-09-05 | 艾尔科工程技术有限公司 | Clean room intelligent operation and maintenance system and method based on digital twin |
| CN116703352B (en) * | 2023-04-17 | 2023-12-08 | 艾尔科工程技术有限公司 | Clean room intelligent operation and maintenance system and method based on digital twin |
| CN116375119A (en) * | 2023-06-06 | 2023-07-04 | 深圳垚鑫淼环境科技有限公司 | Data visualization method and device for realizing sewage treatment based on big data |
| CN116375119B (en) * | 2023-06-06 | 2023-08-29 | 深圳垚鑫淼环境科技有限公司 | Data visualization method and device for realizing sewage treatment based on big data |
| CN116909238A (en) * | 2023-08-29 | 2023-10-20 | 广东青藤环境科技有限公司 | Intelligent water plant integrated management system based on digital twinning |
| CN116909238B (en) * | 2023-08-29 | 2024-01-19 | 广东青藤环境科技有限公司 | Intelligent water plant integrated management system based on digital twinning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113433910A (en) | Water purification plant intelligent dosing control system and method based on digital twin | |
| CN114297954A (en) | Big data intelligent analysis digital management and control platform based on sewage treatment plant | |
| CN111553468B (en) | Method for accurately predicting water quality of effluent of sewage treatment plant | |
| CN101763084B (en) | System and method for minimizing chemical oxygen demand (COD) discharge of pesticide production waste liquid incinerator | |
| CN110824923A (en) | Sewage treatment control method and system based on deep learning and cloud computing | |
| CN101607151B (en) | Embedded intelligent dosing controller and control method thereof | |
| CN106503967A (en) | Wisdom laboratory big data platform based on BIM and VR | |
| CN109032061A (en) | A kind of dosing intelligence control system for water process | |
| CN101706648A (en) | Design method of motion controller based on RCP and DSP | |
| CN106769748B (en) | Intelligent detection system for water permeability of membrane bioreactor-MBR (Membrane bioreactor) | |
| CN202671285U (en) | Automatic medicine feeding device for industrial sewage of coal-fired power plant | |
| CN117113719A (en) | Sewage treatment simulation modeling system construction method | |
| CN217034779U (en) | Three-dimensional visual intelligent factory | |
| CN216014298U (en) | Building supervisory systems based on BIM | |
| CN116029612A (en) | Precise control method for additional carbon source of town sewage plant based on deep learning | |
| CN113885463B (en) | System and method for regulating and controlling technological parameters of livestock biological bacterial fertilizer aerobic fermentation tank | |
| CN217025677U (en) | Intelligent dosing system of water purification plant based on BIM | |
| Duarte et al. | Multi-platform controller interface for SCADA application | |
| CN106651184A (en) | Vineyard chemical fertilizer utilization efficiency measurement and calculation method and device | |
| CN103488089A (en) | System and method for controlling emission of noxious substances of pesticide waste liquid incinerator to reach standards in self-adaptation mode | |
| Meng et al. | Design and implementation of intelligent integrated measuring and controlling system for sugar cane crystallization process | |
| CN111694286A (en) | High-frequency adjustment type water treatment control system based on artificial intelligence | |
| CN114397861A (en) | Reaction rectification intelligent factory simulation test system and development method | |
| CN103472729B (en) | The pesticide waste liquid incinerator hazardous emission controls up to par system and method for gunz | |
| CN103488090B (en) | Incinerator hazardous emission control system up to standard and the method for gunz machine learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210924 |
|
| RJ01 | Rejection of invention patent application after publication |