CN111966053A - Intelligent flocculant decision making system - Google Patents
Intelligent flocculant decision making system Download PDFInfo
- Publication number
- CN111966053A CN111966053A CN202010658358.9A CN202010658358A CN111966053A CN 111966053 A CN111966053 A CN 111966053A CN 202010658358 A CN202010658358 A CN 202010658358A CN 111966053 A CN111966053 A CN 111966053A
- Authority
- CN
- China
- Prior art keywords
- flocculant
- intelligent
- water
- flocculation
- image
- 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 claims abstract description 111
- 238000005189 flocculation Methods 0.000 claims abstract description 54
- 230000016615 flocculation Effects 0.000 claims abstract description 54
- 239000008394 flocculating agent Substances 0.000 claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 19
- 230000008569 process Effects 0.000 claims abstract description 15
- 238000000746 purification Methods 0.000 claims abstract description 9
- 238000012937 correction Methods 0.000 claims description 31
- 238000012545 processing Methods 0.000 claims description 28
- 238000004062 sedimentation Methods 0.000 claims description 22
- 229940037003 alum Drugs 0.000 claims description 21
- 238000007781 pre-processing Methods 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000003706 image smoothing Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000011403 purification operation Methods 0.000 claims description 2
- 230000003311 flocculating effect Effects 0.000 claims 1
- 239000003814 drug Substances 0.000 abstract description 5
- 230000008859 change Effects 0.000 abstract description 4
- 238000001556 precipitation Methods 0.000 abstract description 3
- 239000013049 sediment Substances 0.000 abstract description 2
- 230000009467 reduction Effects 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 238000005314 correlation function Methods 0.000 description 4
- 230000000877 morphologic effect Effects 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000002699 waste material Substances 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]
- G05B19/41885—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 modeling, simulation of the manufacturing system
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G05B2219/32339—Object oriented modeling, design, analysis, implementation, simulation language
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Manufacturing & Machinery (AREA)
- Environmental & Geological Engineering (AREA)
- Water Supply & Treatment (AREA)
- Chemical & Material Sciences (AREA)
- Organic Chemistry (AREA)
- Hydrology & Water Resources (AREA)
- Quality & Reliability (AREA)
- Automation & Control Theory (AREA)
- Separation Of Suspended Particles By Flocculating Agents (AREA)
Abstract
The invention discloses an intelligent flocculant decision making system, which is applied to a water purification subsystem of a water supply system of a water plant and specifically comprises a water quality acquisition module, a feedforward control module, an image acquisition module and a feedback control module. Through this technical scheme, can be respectively at the beginning of flocculating agent input and the water body sediment change according to raw water quality and flocculation and precipitation pond midway nimble adjustment of carrying out the flocculating agent input volume, realized intelligent independently guide the reasonable interpolation of control flocculating agent, and then reach help water works and save the medicine consumption, the automatic process of water works with higher speed promotes the purpose of fine-tuning management.
Description
Technical Field
The invention relates to the technical field of intelligent management of water treatment, in particular to an intelligent flocculant decision-making system.
Background
For a standard modern water supply system, the intelligent control link of the water supply system is very important. In the water purification treatment process of a water plant, the flocculation dosing link is a core process in the purification process, and the flocculation precipitation effect directly influences the quality of the factory water, so that the automatic control of the dosing amount of the flocculating agent becomes a key link in a modern water supply system. Although various flocculating agent adding control schemes are proposed in the prior art, no related mature products exist temporarily, and alum addition is still carried out in a fixed adding rate mode in daily operation of many water plants.
At present, a flocculating agent is generally added at a fixed adding rate in the actual operation process of a water plant, the adding rate is often higher, and a waste phenomenon exists; in addition, a flocculating agent is added at a fixed adding rate, only the factor of raw water flow is considered, and the quality of the water of the factory water can not be guaranteed to meet the standard even when the parameters of the raw water quality are suddenly changed, so that an intelligent flocculating agent adding management system is urgently needed.
Disclosure of Invention
Aiming at the problems in the prior art, an intelligent flocculant decision-making system is provided, and the specific technical scheme is as follows:
an intelligent flocculating agent decision-making system is applied to a water purification subsystem of a water supply system of a water plant, the water purification subsystem mainly comprises a raw water tank, a flocculation sedimentation tank and a flocculating agent dosing pump, and the flocculation sedimentation tank is connected with the raw water tank and is used for carrying out flocculation sedimentation operation on raw water;
the intelligent flocculant decision system specifically comprises:
the water quality acquisition module is used for continuously monitoring the raw water quality of the raw water pool at a first preset frequency and outputting a water quality parameter set;
the feed-forward control module is connected with the water quality acquisition module, processes the water quality parameter set and a preset dosing model and outputs a feed-forward dosing amount;
a flocculating agent dosing pump puts flocculating agent into the flocculation sedimentation tank according to the feed-forward dosing amount;
the image acquisition module is used for continuously acquiring and preprocessing a flocculation image of the flocculation sedimentation tank at a second preset frequency and outputting a flocculation characteristic set;
the feedback control module is connected with the image acquisition module, processes according to the flocculation characteristic set and a preset correction model and outputs a feedback dosing correction quantity;
and the flocculant dosing pump corrects the amount of the flocculant fed into the flocculation sedimentation tank according to the feedback dosing correction.
Preferably, the intelligent flocculant decision system, wherein the water quality parameter set comprises raw water flow data, raw water turbidity data, raw water PH data and raw water temperature data.
Preferably, the intelligent flocculant decision system is obtained by training a dosing model based on an Elman neural network algorithm according to historical water quality parameter sample data.
Preferably, the intelligent flocculant decision system, wherein the image acquisition module specifically comprises:
the image acquisition module is arranged in the flocculation sedimentation tank and used for continuously acquiring images of the flowing water sample;
and the processing module is connected with the image acquisition module and used for processing the flowing water sample image and outputting a flocculation characteristic set.
Preferably, the intelligent flocculant decision system is provided with a self-cleaning function through an image acquisition module.
Preferably, this kind of intelligent flocculating agent decision-making system, wherein the processing module further includes:
the preprocessing unit is used for sequentially carrying out graying processing, image smoothing processing and gray level correction processing on the flowing water sample image and outputting a preprocessed image;
the segmentation processing unit is connected with the preprocessing unit and used for carrying out alum blossom image segmentation on the preprocessed image and counting the alum blossom number and distribution density;
and the characteristic extraction unit is connected with the segmentation processing unit and is used for extracting and standardizing the alum blossom characteristics according to the alum blossom number and the distribution density and outputting a flocculation characteristic set.
Preferably, the intelligent flocculant decision system, wherein the feedback dosing correction quantity output by the correction model comprises five correction states of more addition, less addition, proper, more reduction and less reduction.
Preferably, the intelligent flocculant decision system is characterized in that the correction model comprises a first-stage classifier and a second-stage classifier, and the second-stage classifier is connected with the first-stage classifier;
the primary classifier classifies according to the flocculation characteristic set and maps the flocculation characteristic set to a corresponding feedback dosing correction amount area;
and the secondary classifier performs secondary re-classification on the flocculation feature set which is difficult to be classified by the primary classifier.
Preferably, the intelligent flocculant decision system, wherein the first predetermined frequency is in the order of minutes.
This technical scheme has following advantage or beneficial effect:
through this technical scheme, can be respectively at the beginning of flocculating agent input and the water body sediment change according to raw water quality and flocculation and precipitation pond midway nimble adjustment of carrying out the flocculating agent input volume, realized intelligent independently guide the reasonable interpolation of control flocculating agent, and then reach help water works and save the medicine consumption, the automatic process of water works with higher speed promotes the purpose of fine-tuning management.
Drawings
FIG. 1 is a schematic structural diagram of an intelligent flocculant decision system according to the present invention.
Fig. 2 is a schematic structural diagram of an Elman neural network model for training a dosing model in an intelligent flocculant decision making system according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The invention is further described with reference to the following drawings and specific examples, which are not intended to be limiting.
Aiming at the problems in the prior art, an intelligent flocculant decision-making system is provided, and the specific technical scheme is as follows:
an intelligent flocculant decision-making system is applied to a water purification subsystem of a water supply system of a water plant, as shown in fig. 1, the water purification subsystem mainly comprises a raw water tank 01, a flocculation sedimentation tank 02 and a flocculant dosing pump 03, and the flocculation sedimentation tank 02 is connected with the raw water tank 01 and is used for performing flocculation water purification operation on raw water;
the intelligent flocculant decision system specifically comprises:
the water quality acquisition module 1 is used for continuously monitoring the raw water quality of the raw water pool at a first preset frequency and outputting a water quality parameter set;
the feed-forward control module 2 is connected with the water quality acquisition module 1, processes according to the water quality parameter set and a preset dosing model and outputs a feed-forward dosing amount;
a flocculating agent feeding pump 03 feeds a flocculating agent into the flocculation sedimentation tank according to the feed-forward dosage;
the image acquisition module 3 is used for continuously acquiring and preprocessing a flocculation image of the flocculation sedimentation tank at a second preset frequency and outputting a flocculation characteristic set;
the feedback control module 4 is connected with the image acquisition module 3, processes according to the flocculation feature set and a preset correction model, and outputs a feedback dosing correction quantity;
and the flocculant dosing pump 03 corrects the amount of the flocculant added to the flocculation sedimentation tank according to the feedback dosing correction.
In a preferred embodiment of the present invention,
in a preferred embodiment, the intelligent flocculant decision system comprises a raw water flow data, a raw water turbidity data, a raw water PH data and a raw water temperature data.
In another preferred embodiment of the present invention, the detection of the data of the flow rate, turbidity, PH value, temperature, etc. reflecting the water quality change of the raw water can adjust the flocculation strategy in time when the water quality parameter of the raw water changes suddenly, so as to ensure that the quality of the factory water meets the standard
In a preferred embodiment, the intelligent flocculant decision system is obtained by training a dosing model based on an Elman neural network algorithm according to historical water quality parameter sample data.
In another preferred embodiment of the invention, the dosing model is obtained based on the training of the Elman neural network algorithm, and the neural network model between the raw water quality parameter and the flocculant dosing amount is established by taking a certain amount of historical data of the water plant as sample data. The Elman neural network is a typical dynamic recurrent neural network, which, in addition to the input layer, hidden layer and output layer in the conventional neural network, also provides a specific receiving layer for memorizing the output value of the hidden layer unit at the previous moment and feeding back the output value to the input of the network
As shown in FIG. 2, the neural network input is u, and the outputs of the hidden layer and the accepting layer are x and x, respectivelycThe output is y, and the mathematical expression is as follows:
x(t)＝f(W1u(t-1)+W3xc(t))
xc(t)＝x(t-1)+αxc(t-1)
y(t)＝g(W2x(t))
in the above formula: u (t-1) is the input of the node of the input layer; x (t) is the output of the hidden layer node; y (t) is the output of the output node; x is the number ofc(t) is a feedback state vector; w1，W3，W2Respectively connecting weights from a receiving layer to a hidden layer, from an input layer to the hidden layer and from the hidden layer to an output layer; g () is the transfer function of the output layer neurons; f () is the transfer function of hidden layer neuron, f () takes sigmoid function more, f (x) is 1/(1+ e)-x) (ii) a Alpha is a feedback weight; t is the neuron number.
In the above preferred embodiment, the input of the neural network comprises 10000 groups of raw water flow data, raw water turbidity data, raw water temperature data, raw water PH data and historical dosing flow data to form a sample library for predicting the control amount; the output quantity is the dosage (Flow), and the network training is stopped when the relative error and the mean square value E reach the preset error, and the network model is the required flocculation dosage prediction model.
As a preferred embodiment, the intelligent flocculant decision system, wherein the image acquisition module 3 specifically includes:
the image acquisition module 31 is arranged in the flocculation sedimentation tank and used for continuously acquiring the flowing water sample image;
and the processing module 32 is connected with the image acquisition module 31 and used for processing the flowing water sample image and outputting a flocculation characteristic set.
In a preferred embodiment, the intelligent flocculant decision system is provided with the image acquisition module 31 having a self-cleaning function.
In another preferred embodiment of the present invention, the image collecting module 31 may be an underwater image collecting device (an industrial camera with 500 ten thousand pixels and a fixed focus lens) with a light source, which is disposed at a certain depth in the water in the flocculation sedimentation tank, and controls the camera shooting and image information transmission through a computer serial port, and continuously collects the flowing water sample image at a certain frame rate, and matches and compares the data recorded by the turbidity meter of the waterworks; the image capture module 31 also has a mechanism to periodically self-clean the camera lens.
In a preferred embodiment, the intelligent flocculant decision system, wherein the processing module 32 further comprises:
the preprocessing unit 321 is configured to perform graying processing, image smoothing processing and grayscale correction processing on the flowing water sample image in sequence, and output a preprocessed image;
the segmentation processing unit 322 is connected with the preprocessing unit 321, and is used for performing alum blossom image segmentation on the preprocessed image and counting the alum blossom number and distribution density;
and the feature extraction unit 323 is connected with the segmentation processing unit 322 and used for extracting and standardizing alum blossom features according to the alum blossom number and distribution density and outputting a flocculation feature set.
In a preferred embodiment of the present invention, the main processes and functions of the processing module 32 include:
image preprocessing, namely converting the acquired color image into a gray image with 256 gray levels of 0 to 255 for processing, namely, expressing image data in an RGB (red, green and blue) form, removing interference colors in the image, filtering noise by adopting a nonlinear median filtering algorithm for smoothing the image, and uniformly converting the gray level of the original image mainly focusing on 80 to 255 into a range between 0 and 255 by adopting a gray level conversion method so as to improve the contrast of the image.
In the above preferred embodiment, the Kaolinitum image is divided by Otsu method, after obtaining the preliminary binary image, the binary image is finely divided by using region growing technique, and the number of Kaolinitum therein is counted to calculate the distribution density.
Further processing the morphological image and analyzing the texture, further simplifying the image through the processing of the morphological image, separating fine alum flocs adhered to the image, and eliminating noise interference in the image, in the process of analyzing the texture, firstly calculating a cross-correlation function, and defining the measure of the cross-correlation function as follows:
wherein: x is 0,1,2, …, N-1; s (x, y) is an original image, T (x, y) is a template image, the sizes of the S (x, y) and the T (x, y) are all M multiplied by N, and the S (x, y) and the T (x, y) both represent pixel values of the image at coordinates (x, y); then, feature extraction is carried out through a gray co-occurrence matrix, and core feature quantities are respectively extracted according to the gray feature, the image texture feature and the image morphological feature of the image, and the method mainly comprises the following steps: variance, gradient, kurtosis and entropy of the alum blossom gray level image; and (3) carrying out standardization treatment to the average area, the average perimeter, the average equivalent diameter, the distribution density and the like of alum flocs in the binary image after eliminating the weak correlation characteristics in the binary image to obtain a flocculation characteristic set.
In a preferred embodiment, the intelligent flocculant decision system is provided, wherein the feedback dosing correction output by the correction model comprises five correction states of more addition, less addition, proper, more reduction and less reduction.
In another preferred embodiment of the present invention, since the purpose of the correction model is to correct the result of the medication model, according to the template image corresponding to the five states of adding more, adding less, appropriateness, decreasing less and decreasing more, a certain correction needs to be performed on the basis of the result of the flocculation medication prediction model. In this embodiment, the correction scaling factors corresponding to the five states are set to 5%, 2.5%, 0, -2.5%, and-5%, respectively, and are mapped to the corresponding correction scaling factors and output, for example, when the dosage result output by the dosage model is x, and the correction scaling factor result of the current alum blossom image is 5%, the final dosage is (1+ 5%) x, and the frequency of the frequency converter of the dosage pump is calculated according to the final dosage to control the dosage of the flocculant.
In a preferred embodiment, the intelligent flocculant decision system is characterized in that the correction model comprises a first-stage classifier and a second-stage classifier, and the second-stage classifier is connected with the first-stage classifier;
the primary classifier classifies according to the flocculation characteristic set and maps the flocculation characteristic set to a corresponding feedback dosing correction amount area;
and the secondary classifier performs secondary re-classification on the flocculation feature set which is difficult to be classified by the primary classifier.
In another preferred embodiment of the present invention, according to the simulated alum addition amount corresponding to five states of more addition, less addition, proper, more reduction and less reduction, 500 images of the underwater alum blossom image in different states are respectively collected, 300 images are respectively selected corresponding to the five states to be used for training the classifier, and the remaining images are used for testing the classification recognition rate. In the preferred embodiment, a two-stage classifier is constructed for identifying and classifying the collected alum blossom images, wherein:
the first-stage classifier adopts the cross-correlation function characteristics after image preprocessing, calculates the cross-correlation functions of the input image and the five template images to obtain a maximum value, calculates the absolute value of the difference value between the maximum value and 1, and identifies the image state if the absolute value is lower than a certain preset threshold value R; if the threshold value is larger than the threshold value, the second-stage classifier is refused to be entered.
The second-stage classifier is a multi-classifier combination, extracts three characteristics (including alumen ustum distribution density, image moment characteristics and co-occurrence moment characteristics) of the image, constructs three characteristic classifiers and forms a comprehensive decision for the identification of the image; when a multi-classifier combination is constructed, distance measurement information of each classifier is adopted, and a calculation formula is as follows:
where M is the number of classifiers, which is set to 3 in the present embodiment. dIF [ i ] is the central feature value of the ith classifier of the input image, and dSF [ i ] is the central statistical feature value of the ith classifier corresponding to the template image. The classification mapping can be effectively and accurately carried out through the arrangement of the two stages of classifiers.
In a preferred embodiment, the intelligent flocculant decision system is one in which the first preset frequency is in the order of minutes.
In another preferred embodiment of the present invention, the frequency of acquisition is set to 1 to 5 minutes/time. Because the water quality fluctuation of raw water is usually stabilized in a certain interval, and the condition of large mutation is very few, the data acquisition frequency does not need to be very high in the practical application process and is limited to the minute level.
In conclusion, according to the technical scheme, the feeding amount of the flocculating agent can be flexibly adjusted at the beginning and in the midway of the feeding of the flocculating agent according to the quality of raw water and the water body sedimentation change of the flocculation sedimentation tank, so that the reasonable feeding of the flocculating agent is intelligently and independently guided and controlled, the purposes of helping a water plant to save medicine consumption, accelerating the automation process of the water plant and promoting fine management are achieved.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention.
Claims (9)
1. An intelligent flocculating agent decision-making system is characterized in that the intelligent alum adding decision-making system is applied to a water purification subsystem of a water supply system of a water plant, the water purification subsystem comprises a raw water tank, a flocculation sedimentation tank and a flocculating agent dosing pump, and the flocculation sedimentation tank is connected with the raw water tank and is used for flocculating and settling raw water so as to finish water purification operation;
the intelligent flocculant decision system specifically comprises:
the water quality acquisition module is used for continuously monitoring the raw water quality of the raw water pool at a first preset frequency and outputting a water quality parameter set;
the feed-forward control module is connected with the water quality acquisition module, processes according to the water quality parameter set and a preset dosing model and outputs a feed-forward dosing amount;
the flocculant dosing pump puts a flocculant into the flocculation sedimentation tank according to the feed-forward dosing amount;
the image acquisition module is used for continuously acquiring and preprocessing a flocculation image of the flocculation sedimentation tank at a second preset frequency and outputting a flocculation characteristic set;
the feedback control module is connected with the image acquisition module, processes according to the flocculation feature set and a preset correction model and outputs a feedback dosing correction amount;
and the flocculant dosing pump corrects the amount of the flocculant added to the flocculation sedimentation tank according to the feedback dosing correction.
2. The intelligent flocculant decision system of claim 1, wherein the set of water quality parameters comprises raw water flow data, raw water turbidity data, raw water PH data, and raw water temperature data.
3. The intelligent flocculant decision system of claim 1, wherein the dosing model is trained based on an Elman neural network algorithm based on historical water quality parameter sample data.
4. The intelligent flocculant decision system of claim 1, wherein the image acquisition module specifically comprises:
the image acquisition module is arranged in the flocculation sedimentation tank and is used for continuously acquiring images of the flowing water sample;
and the processing module is connected with the image acquisition module and used for processing the flowing water sample image and outputting the flocculation characteristic set.
5. The intelligent flocculant decision system of claim 4, wherein the image acquisition module is self-cleaning.
6. The intelligent flocculant decision system of claim 4, wherein the processing module further comprises:
the preprocessing unit is used for sequentially carrying out graying processing, image smoothing processing and gray level correction processing on the flowing water sample image and outputting a preprocessed image;
the segmentation processing unit is connected with the preprocessing unit and is used for carrying out alum blossom image segmentation on the preprocessed image and counting the alum blossom number and distribution density;
and the characteristic extraction unit is connected with the segmentation processing unit and is used for extracting and standardizing alum blossom characteristics according to the alum blossom number and the distribution density and outputting the flocculation characteristic set.
7. The intelligent flocculant decision system of claim 1 wherein the feedback dosing corrections output by the correction model comprise five correction states of plus, minus, proper, plus, minus.
8. The intelligent flocculant decision system of claim 1, wherein the modified model comprises a primary classifier and a secondary classifier, the secondary classifier being connected to the primary classifier;
the primary classifier classifies according to the flocculation feature set and maps the flocculation feature set to a corresponding feedback dosing correction amount area;
and the secondary classifier performs secondary re-classification on the flocculation feature set which is difficult to be classified by the primary classifier.
9. The intelligent flocculant decision system of claim 1, wherein the first predetermined frequency is on the order of minutes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010658358.9A CN111966053A (en) | 2020-07-09 | 2020-07-09 | Intelligent flocculant decision making system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010658358.9A CN111966053A (en) | 2020-07-09 | 2020-07-09 | Intelligent flocculant decision making system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111966053A true CN111966053A (en) | 2020-11-20 |
Family
ID=73360336
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010658358.9A Pending CN111966053A (en) | 2020-07-09 | 2020-07-09 | Intelligent flocculant decision making system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111966053A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111912752A (en) * | 2020-09-07 | 2020-11-10 | 上海易清智觉自动化科技有限公司 | Flocculation detection device and method and sewage treatment system |
| CN112456621A (en) * | 2020-11-24 | 2021-03-09 | 四川齐力绿源水处理科技有限公司 | Intelligent flocculation dosing control system and control method |
| CN112723505A (en) * | 2020-12-04 | 2021-04-30 | 上海上实龙创智能科技股份有限公司 | Sewage treatment wisdom charge system |
| CN112919605A (en) * | 2021-03-24 | 2021-06-08 | 四川康信科创农业有限公司 | Sewage treatment system and method based on image acquisition |
| CN113307341A (en) * | 2021-06-03 | 2021-08-27 | 大连亚泰科技新材料股份有限公司 | Preparation process of magnesium-based composite water treatment flocculant |
| CN113429013A (en) * | 2021-06-03 | 2021-09-24 | 阿里巴巴新加坡控股有限公司 | Method for determining coagulant addition amount and method for determining compound addition amount |
| CN113480054A (en) * | 2021-08-23 | 2021-10-08 | 陈晓娟 | Environment-friendly wastewater circulating treatment system and method |
| CN113517036A (en) * | 2020-12-22 | 2021-10-19 | 阿里巴巴集团控股有限公司 | Data processing method, device and storage medium |
| CN113687040A (en) * | 2021-07-28 | 2021-11-23 | 广州杰赛科技股份有限公司 | Decision tree algorithm-based water plant real-time dosing quantity prediction method, device and medium |
| CN114047720A (en) * | 2021-11-04 | 2022-02-15 | 海宸大智(南京)信息科技有限责任公司 | Control method, device and equipment for medium processing |
| CN114545985A (en) * | 2022-04-21 | 2022-05-27 | 神美科技有限公司 | Floc characteristic monitoring and process feedback-based dosing system and method |
| CN115147617A (en) * | 2022-09-06 | 2022-10-04 | 聊城集众环保科技有限公司 | Intelligent sewage treatment monitoring method based on computer vision |
| CN115231668A (en) * | 2022-07-15 | 2022-10-25 | 北京航空航天大学 | Multi-dimensional fusion automatic medicine feeding method, device and equipment |
| CN116216807A (en) * | 2023-02-24 | 2023-06-06 | 青岛张村河水务有限公司 | Intelligent dosing system based on sewage treatment |
| WO2024021150A1 (en) * | 2022-07-28 | 2024-02-01 | 上海城市水资源开发利用国家工程中心有限公司 | Method for establishing coagulation intelligent monitoring linkage system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN200950228Y (en) * | 2006-01-27 | 2007-09-19 | 深圳市开天源自动化工程有限公司 | Equipment for controlling coagulant dosage |
| CN201749385U (en) * | 2009-04-10 | 2011-02-16 | 华南理工大学 | Water plant dosage control system for feedforward-feedback composite control |
| CN102385315A (en) * | 2011-09-01 | 2012-03-21 | 深圳市开天源自动化工程有限公司 | Intelligent coagulation chemical dosing control system for water plant and control method thereof |
| CN106168759A (en) * | 2016-07-12 | 2016-11-30 | 武汉长江仪器自动化研究所有限公司 | A kind of coagulant dosage control method and system based on artificial neural network algorithm |
| CN206440945U (en) * | 2016-07-12 | 2017-08-25 | 武汉长江仪器自动化研究所有限公司 | A kind of coagulant dosage control system based on artificial neural network algorithm |
-
2020
- 2020-07-09 CN CN202010658358.9A patent/CN111966053A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN200950228Y (en) * | 2006-01-27 | 2007-09-19 | 深圳市开天源自动化工程有限公司 | Equipment for controlling coagulant dosage |
| CN201749385U (en) * | 2009-04-10 | 2011-02-16 | 华南理工大学 | Water plant dosage control system for feedforward-feedback composite control |
| CN102385315A (en) * | 2011-09-01 | 2012-03-21 | 深圳市开天源自动化工程有限公司 | Intelligent coagulation chemical dosing control system for water plant and control method thereof |
| CN106168759A (en) * | 2016-07-12 | 2016-11-30 | 武汉长江仪器自动化研究所有限公司 | A kind of coagulant dosage control method and system based on artificial neural network algorithm |
| CN206440945U (en) * | 2016-07-12 | 2017-08-25 | 武汉长江仪器自动化研究所有限公司 | A kind of coagulant dosage control system based on artificial neural network algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 王新增、黄 山: "矾花图像的处理及应用研究", 《成都信息工程学院学报》 * |
| 黄念禹、武彦林: "自来水厂矾花状态自动监测应用研究", 《给水排水》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111912752A (en) * | 2020-09-07 | 2020-11-10 | 上海易清智觉自动化科技有限公司 | Flocculation detection device and method and sewage treatment system |
| CN112456621A (en) * | 2020-11-24 | 2021-03-09 | 四川齐力绿源水处理科技有限公司 | Intelligent flocculation dosing control system and control method |
| CN112723505A (en) * | 2020-12-04 | 2021-04-30 | 上海上实龙创智能科技股份有限公司 | Sewage treatment wisdom charge system |
| CN113517036A (en) * | 2020-12-22 | 2021-10-19 | 阿里巴巴集团控股有限公司 | Data processing method, device and storage medium |
| CN112919605A (en) * | 2021-03-24 | 2021-06-08 | 四川康信科创农业有限公司 | Sewage treatment system and method based on image acquisition |
| CN113307341A (en) * | 2021-06-03 | 2021-08-27 | 大连亚泰科技新材料股份有限公司 | Preparation process of magnesium-based composite water treatment flocculant |
| CN113429013A (en) * | 2021-06-03 | 2021-09-24 | 阿里巴巴新加坡控股有限公司 | Method for determining coagulant addition amount and method for determining compound addition amount |
| CN113429013B (en) * | 2021-06-03 | 2022-12-27 | 阿里巴巴新加坡控股有限公司 | Method for determining coagulant addition amount and method for determining compound addition amount |
| CN113687040A (en) * | 2021-07-28 | 2021-11-23 | 广州杰赛科技股份有限公司 | Decision tree algorithm-based water plant real-time dosing quantity prediction method, device and medium |
| CN113480054A (en) * | 2021-08-23 | 2021-10-08 | 陈晓娟 | Environment-friendly wastewater circulating treatment system and method |
| CN114047720A (en) * | 2021-11-04 | 2022-02-15 | 海宸大智(南京)信息科技有限责任公司 | Control method, device and equipment for medium processing |
| CN114545985A (en) * | 2022-04-21 | 2022-05-27 | 神美科技有限公司 | Floc characteristic monitoring and process feedback-based dosing system and method |
| CN115231668A (en) * | 2022-07-15 | 2022-10-25 | 北京航空航天大学 | Multi-dimensional fusion automatic medicine feeding method, device and equipment |
| CN115231668B (en) * | 2022-07-15 | 2024-07-16 | 北京航空航天大学 | Multi-dimensional fusion automatic drug adding method, device and equipment |
| WO2024021150A1 (en) * | 2022-07-28 | 2024-02-01 | 上海城市水资源开发利用国家工程中心有限公司 | Method for establishing coagulation intelligent monitoring linkage system |
| CN115147617A (en) * | 2022-09-06 | 2022-10-04 | 聊城集众环保科技有限公司 | Intelligent sewage treatment monitoring method based on computer vision |
| CN115147617B (en) * | 2022-09-06 | 2022-11-22 | 聊城集众环保科技有限公司 | Intelligent monitoring method for sewage treatment based on computer vision |
| CN116216807A (en) * | 2023-02-24 | 2023-06-06 | 青岛张村河水务有限公司 | Intelligent dosing system based on sewage treatment |
| CN116216807B (en) * | 2023-02-24 | 2023-09-01 | 青岛张村河水务有限公司 | Intelligent Dosing System Based on Sewage Treatment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111966053A (en) | Intelligent flocculant decision making system | |
| Latha et al. | Automatic detection of tea leaf diseases using deep convolution neural network | |
| CN109635744A (en) | A kind of method for detecting lane lines based on depth segmentation network | |
| CN112819802B (en) | Method for supervising and predicting blast furnace condition abnormality based on tuyere information deep learning | |
| CN108205891B (en) | A kind of vehicle monitoring method of monitoring area | |
| CN116310845B (en) | Intelligent monitoring system for sewage treatment | |
| WO2023029117A1 (en) | Method and apparatus for analyzing alum floc feature by using image recognition technology | |
| JP7147933B2 (en) | Water quality analysis method | |
| CN109919012A (en) | A kind of indicative microorganism image-recognizing method of sewage treatment based on convolutional neural networks | |
| CN115108617B (en) | Method and system for adding medicine by coagulation | |
| CN114663684A (en) | Method, system and operation equipment for real-time intelligent analysis of flocculation reaction | |
| CN117787511B (en) | Industrial high-density aquaculture monitoring and early warning method and system thereof | |
| CN108460481A (en) | Unmanned plane spot development law prediction technique based on Recognition with Recurrent Neural Network | |
| CN117237244B (en) | Animal husbandry veterinary animal body temperature intelligent monitoring system based on data enhancement | |
| Saidane et al. | Robust binarization for video text recognition | |
| CN115546720A (en) | Image type analytic regulation and control method and device for flocculation working condition | |
| CN117253024A (en) | Industrial salt quality inspection control method and system based on machine vision | |
| CN114781249A (en) | High-density clarification tank dosage prediction and control method based on multidimensional scoring model | |
| CN1538177A (en) | Coagulating process flocculate detection method based on image processing technology and optimization control system | |
| CN117237773B (en) | Sewage purification analysis method and system based on multiple modes | |
| CN114819376A (en) | Sedimentation tank mud amount prediction system and method | |
| CN113781224A (en) | Stock trading data prediction method and system | |
| CN117197005A (en) | Image enhancement system of steelmaking engineering area image and safety monitoring system thereof | |
| CN116935293B (en) | Automatic processing method and system for remote video exploration and damage assessment | |
| CN116664431B (en) | Image processing system and method based on artificial intelligence |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201120 |