CN115231668A - Multi-dimensional fusion automatic medicine feeding method, device and equipment - Google Patents
Multi-dimensional fusion automatic medicine feeding method, device and equipment Download PDFInfo
- Publication number
- CN115231668A CN115231668A CN202210835340.0A CN202210835340A CN115231668A CN 115231668 A CN115231668 A CN 115231668A CN 202210835340 A CN202210835340 A CN 202210835340A CN 115231668 A CN115231668 A CN 115231668A
- Authority
- CN
- China
- Prior art keywords
- flocculation
- value
- data
- turbidity
- effluent
- 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
- 239000003814 drug Substances 0.000 title claims abstract description 120
- 238000000034 method Methods 0.000 title claims abstract description 56
- 230000004927 fusion Effects 0.000 title claims abstract description 37
- 238000012544 monitoring process Methods 0.000 claims abstract description 146
- 239000002245 particle Substances 0.000 claims abstract description 125
- 238000005189 flocculation Methods 0.000 claims abstract description 112
- 230000016615 flocculation Effects 0.000 claims abstract description 109
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 73
- 238000012549 training Methods 0.000 claims abstract description 59
- 230000015654 memory Effects 0.000 claims abstract description 55
- 229940079593 drug Drugs 0.000 claims abstract description 37
- 238000001556 precipitation Methods 0.000 claims abstract description 18
- 230000000694 effects Effects 0.000 claims abstract description 17
- 230000007613 environmental effect Effects 0.000 claims description 29
- 238000001647 drug administration Methods 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 239000003792 electrolyte Substances 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 230000010355 oscillation Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 16
- 238000004062 sedimentation Methods 0.000 description 14
- 230000003311 flocculating effect Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 230000007787 long-term memory Effects 0.000 description 4
- 230000006403 short-term memory Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000036039 immunity Effects 0.000 description 3
- 230000035484 reaction time Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 239000008213 purified water Substances 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000084 colloidal system Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000008394 flocculating agent Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000000491 multivariate analysis Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000013049 sediment Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Images
Classifications
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D21/00—Separation of suspended solid particles from liquids by sedimentation
- B01D21/01—Separation of suspended solid particles from liquids by sedimentation using flocculating agents
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D21/00—Separation of suspended solid particles from liquids by sedimentation
- B01D21/30—Control equipment
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D21/00—Separation of suspended solid particles from liquids by sedimentation
- B01D21/30—Control equipment
- B01D21/32—Density control of clear liquid or sediment, e.g. optical control ; Control of physical properties
-
- 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
-
- 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
-
- 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
- C02F2209/11—Turbidity
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2303/00—Specific treatment goals
- C02F2303/22—Eliminating or preventing deposits, scale removal, scale prevention
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Hydrology & Water Resources (AREA)
- Environmental & Geological Engineering (AREA)
- Water Supply & Treatment (AREA)
- Organic Chemistry (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- General Chemical & Material Sciences (AREA)
- Separation Of Suspended Particles By Flocculating Agents (AREA)
Abstract
The invention discloses a multidimensional fusion automatic medicine feeding method, a multidimensional fusion automatic medicine feeding device and multidimensional fusion automatic medicine feeding equipment. The method comprises the following steps: acquiring at least one environment monitoring data and an underwater monitoring image; wherein the environment monitoring data is used for reflecting the water quality state; determining at least one index data of the flocculation particles according to the underwater monitoring image; wherein the index data of the flocculation particles is used for reflecting the flocculation precipitation effect; inputting environment monitoring data and flocculation particle index data into a long-short term memory model obtained through pre-training to obtain a effluent turbidity predicted value output by the long-short term memory model; and adding the medicine according to the effluent turbidity predicted value and the effluent turbidity preset value. By using the technical scheme of the invention, the time lag effect of drug adding control can be relieved, the effectiveness and the anti-interference performance of automatic drug adding are improved, and the total drug consumption is reduced while the turbidity oscillation of the effluent is stabilized.
Description
Technical Field
The invention relates to the technical field of purified water production, in particular to a multidimensional fusion automatic medicine feeding method, a multidimensional fusion automatic medicine feeding device and equipment.
Background
The water treatment plant is the first station for ensuring the water safety, and flocculation and precipitation are the core process in the water treatment process flow. The flocculating agent is added into raw water entering a plant, so that raw water impurities such as colloid, suspended particles and the like can form large flocculating particles with a certain volume and easy precipitation and filtration, and the quality of the water discharged from the water treatment plant can be directly determined by the effect of flocculating precipitation.
In the flocculation precipitation process, the state observation and the dosing control mainly depend on experience. Or the staff observes the sedimentation tank, or after taking a water sample to test parameters such as pH value, electrolyte concentration and the like, the medicine is added according to experience. Or the dosage proportional to the inflow is determined by depending on the operation experience of the water treatment plant. The dosing mode of the flocculation precipitation process in the prior art has great subjectivity and hysteresis quality, is low in accuracy, and is difficult to deal with sudden changes such as weather changes, sediment accumulation and upstream pollution discharge.
Disclosure of Invention
The invention provides a multidimensional fusion automatic medicine feeding method, a multidimensional fusion automatic medicine feeding device and multidimensional fusion automatic medicine feeding equipment, which are used for relieving the time lag effect of medicine feeding control, improving the effectiveness and anti-interference of automatic medicine feeding, stabilizing turbidity oscillation of effluent and reducing the total medicine consumption.
In a first aspect, an embodiment of the present invention provides a multidimensional fusion automated drug administration method, where the method includes:
acquiring at least one environment monitoring data and an underwater monitoring image; wherein the environmental monitoring data is used for reflecting the water quality state;
determining at least one index data of the flocculation particles according to the underwater monitoring image; wherein the index data of the flocculated particles is used for reflecting the effect of flocculation and precipitation;
inputting environment monitoring data and flocculation particle index data into a long-short term memory model obtained through pre-training to obtain a effluent turbidity predicted value output by the long-short term memory model;
and adding the medicament according to the effluent turbidity predicted value and the effluent turbidity preset value.
In a second aspect, an embodiment of the present invention further provides a multidimensional fusion automated drug adding apparatus, including:
the data acquisition module is used for acquiring at least one environment monitoring data and an underwater monitoring image; wherein the environmental monitoring data is used for reflecting the water quality state;
the flocculation particle index data determining module is used for determining at least one flocculation particle index data according to the underwater monitoring image; wherein the index data of the flocculated particles is used for reflecting the effect of flocculation and precipitation;
The effluent turbidity predicted value determining module is used for inputting the environmental monitoring data and the index data of the flocculation particles into a long-short term memory model obtained by pre-training to obtain an effluent turbidity predicted value output by the long-short term memory model;
and the drug adding module is used for adding drugs according to the effluent turbidity predicted value and the effluent turbidity preset value.
In a third aspect, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the multidimensional fusion automated drug administration method according to any one of the embodiments of the present invention.
In a fourth aspect, embodiments of the present invention also provide a storage medium storing computer-executable instructions for performing the multidimensional fusion automated drug administration method as described in any one of the embodiments of the present invention when executed by a computer processor.
According to the technical scheme of the embodiment of the invention, the environmental monitoring data are obtained, the index data of the flocculating particles are determined according to the obtained underwater monitoring image, the environmental monitoring data and the index data of the flocculating particles are input into the long-short term memory model to obtain the effluent turbidity predicted value output by the long-short term memory model, and the medicine is added according to the effluent turbidity predicted value and the effluent turbidity preset value. The problem of the mode of adding medicine of flocculating settling process among the prior art, have very big subjectivity and hysteresis quality, the accuracy is lower, also difficult to deal with the sudden change is solved, the time lag effect of medicine throwing control has been alleviated, the validity and the interference immunity that the medicine was thrown automatically are improved, stabilize the play water turbidity and vibrate and reduced the total medicine consumption simultaneously.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a multidimensional fusion automated drug administration method according to an embodiment of the present invention;
FIG. 2a is a flowchart of a multidimensional fusion automated drug administration method according to a second embodiment of the present invention;
FIG. 2b is a schematic diagram of a modeling process of a long-term and short-term memory model according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a multidimensional fusion automated drug adding device provided in the third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, 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 terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
Fig. 1 is a flowchart of a multidimensional fusion automatic drug adding method provided in an embodiment of the present invention, where this embodiment is applicable to a situation where intelligent drug adding is performed in a flocculation precipitation process, the method may be performed by a multidimensional fusion automatic drug adding device, the multidimensional fusion automatic drug adding device may be implemented in a hardware and/or software manner, and the multidimensional fusion automatic drug adding device may be configured in a computer device and used in cooperation with an environment monitoring device, a shooting device, and a drug adding device.
As shown in fig. 1, the method includes:
and S110, acquiring at least one environment monitoring data and an underwater monitoring image.
Wherein the environmental monitoring data is used for reflecting the water quality state. Optionally, the environmental monitoring data may include at least one of: the system comprises an inlet water flow, a raw water turbidity monitoring value, an outlet water turbidity monitoring value, a drug adding amount, a water sample pH value, a water sample electrolyte concentration and a water sample temperature.
In the flocculation and precipitation process, raw water is filled into a flocculation and precipitation tank at unfixed flow and turbidity, and after flocculation and precipitation, upper-layer purified water meeting the turbidity preset value flows out of the precipitation tank and enters a subsequent treatment flow. The inflow water flow is water flow passing through the section of the water inlet of the sedimentation tank at a unit moment and can be measured by a flowmeter arranged at the water inlet. Turbidity is the turbid degree of water, and raw water turbidity monitoring value and play water turbidity monitoring value can be obtained through the turbidimeter measurement of setting at water inlet and delivery port respectively. The medicine adding amount refers to the amount of medicine added into the sedimentation tank and can be obtained by a medicine adding device. The temperature of the water sample can be measured by a thermometer arranged in the sedimentation tank, and the pH value and the electrolyte concentration of the water sample can be obtained by sampling the water sample in the sedimentation tank and then testing the pH value and the electrolyte concentration of the water sample.
In the embodiment of the invention, the inflow water flow, the raw water turbidity monitoring value, the effluent turbidity monitoring value and the water sample temperature can be obtained in real time or at preset time intervals. The medicine adding amount can be obtained at preset time intervals, and the medicine adding amount can also be fed back to the multidimensional fusion automatic medicine adding device after the medicine adding device performs medicine adding each time. The pH value and the electrolyte concentration of the water sample can be acquired after the water sample is sampled at preset time intervals. The present embodiment does not limit the type of the environmental monitoring data, and the frequency and the manner of acquiring the environmental monitoring data.
The underwater monitoring image can visually reflect the flocculation state in the sedimentation tank, and can be shot by shooting equipment arranged in the sedimentation tank. Preferably, a plurality of shooting devices can be installed at different positions in the sedimentation tank in a distributed manner, so that the water quality states of the sedimentation tank at different positions can be reflected more comprehensively. Preferably, the shooting equipment can be camera equipment, correspondingly, the underwater monitoring image is a frame image in an underwater monitoring video, namely a video frame image for monitoring the sedimentation tank in real time, and the real-time monitoring of the flocculation state in the sedimentation tank can be ensured by the arrangement.
In the embodiment of the invention, the environmental monitoring data can reflect the water quality state, the underwater monitoring image can reflect the flocculation state, and the environmental monitoring data is combined with the underwater monitoring image, so that the effluent turbidity can be more accurately predicted.
And S120, determining at least one index data of the flocculation particles according to the underwater monitoring image.
Wherein the index data of the flocculated particles is used for reflecting the effect of flocculation and sedimentation. Optionally, the flocculated particles indicator data includes at least one of: the area ratio of the flocculated particles, the average equivalent diameter of the flocculated particles and the roundness of the flocculated particles.
The flocculation particle area proportion refers to the proportion of the area detected as flocculation particles in the underwater monitoring image to the area of the underwater monitoring image. Specifically, the flocculation particle detection can be carried out on the underwater monitoring image, a flocculation particle area is obtained, and the proportion of the flocculation particle area can be determined. The underwater monitoring image can also be subjected to binarization processing, and the underwater monitoring image is divided into a flocculation particle area and a background area, so that the ratio of the flocculation particle area is determined. The present example does not limit the manner of determining the flocculated particle zone.
The average equivalent diameter of the flocculation particles may be an average of equivalent diameters of the respective flocculation particles in the underwater monitoring image, the equivalent diameter being a diameter of a circle equal to a contour area of the flocculation particles, and since the flocculation particles are almost unlikely to be a perfect circle, the size of the flocculation particles can be reflected by the equivalent diameter. Or after determining the contour boundary of each flocculating particle, fitting according to the boundary to obtain an optimal ellipse, and taking the average value of the diameters of the optimal ellipses obtained by fitting as the average equivalent diameter of the flocculating particles. The present example does not limit the specific calculation manner of the average equivalent diameter of the flocculated particles.
The flocculation particle roundness refers to the degree of approximate perfect roundness of each flocculation particle in the underwater monitoring image. Specifically, the contour boundary of each flocculation particle may be determined, an optimal ellipse may be obtained by fitting according to the boundary, the absolute value of the difference between the area enclosed by the contour boundary and the elliptical area, and the ratio between the elliptical areas are taken as the circularity of each flocculation particle, and the average value of the circularity of each flocculation particle is calculated. However, the present embodiment is not limited to the calculation of the roundness of the flocculated particles.
In the embodiment of the invention, a flocculation particle index data curve can be generated after the flocculation particle index data of the underwater monitoring image acquired in real time is determined, and the underwater monitoring video and the flocculation particle index data curve are displayed in a view mode, so that a manager can conveniently monitor the flocculation state of the sedimentation tank in real time, and when sudden change occurs, problems can be timely checked, and safety production accidents are avoided.
S130, inputting the environmental monitoring data and the index data of the flocculation particles into a long-short term memory model obtained through pre-training to obtain a water outlet turbidity predicted value output by the long-short term memory model.
Long-short term memory models can be used to predict long-term, high-latency, multivariate sequence data. The effluent turbidity reflects the effluent quality, and in order to ensure the stable and standard effluent quality, the effluent turbidity monitoring value is required to meet the effluent turbidity preset value and keep stable, and meanwhile, certain flocculation reaction time is required after the medicine is added. Therefore, in the embodiment, the effluent turbidity is predicted based on the multi-factor effect of the environmental monitoring data and the index data of the flocculation particles through the long-term and short-term memory model, and the drug addition is performed based on the effluent turbidity prediction value. The technical scheme of this embodiment can reduce the influence that the hysteresis quality of flocculation process caused the control of throwing with the medicine to can realize high-efficient, accurate water quality monitoring and flocculation state monitoring.
And S140, adding the medicine according to the effluent turbidity predicted value and the effluent turbidity preset value.
And determining whether the medicine needs to be added or not and the dosage when the medicine needs to be added according to the difference value between the effluent turbidity predicted value and the effluent turbidity preset value.
Optionally, the adding of the medicine is performed according to the effluent turbidity predicted value and the effluent turbidity preset value, and may include: calculating the dosage of the medicine according to the difference between the predicted value of the turbidity of the effluent and the preset value of the turbidity of the effluent by a proportional-integral-derivative control algorithm; and sending the medicine adding amount to a medicine adding device so as to enable the medicine adding device to add the medicine.
Specifically, the drug dosage can be calculated by a PID (Proportional Integral, differential, proportional Integral derivative) controller according to the difference between the predicted value of the effluent turbidity and the preset value of the effluent turbidity. The PID controller can calculate the drug dosage by the following formula:
wherein u (t) is the dosage of the medicine, e (t) is the difference between the predicted value and the preset value of the turbidity of the effluent, and K p To proportional gain, K i To integrate the gain, K d For differential gain, t is the current time, τ is the integral variable, and the value is from 0 to t.
After the PID Controller calculates the drug adding amount, the drug adding amount can be sent to a PLC (Programmable Logic Controller), and the PLC controls the size of a valve of the drug adding device, so as to add the drug.
The effluent turbidity prediction value under the influence of multiple factors is obtained through time series prediction based on the LSTM, and dynamic control over the drug adding amount is realized through a PID controller, so that the effluent turbidity is stabilized. The technical scheme of the embodiment can effectively eliminate time lag caused by flocculation reaction time, and realize automatic, scientific and accurate addition of the medicine.
According to the technical scheme of the embodiment of the invention, the environmental monitoring data are obtained, the index data of the flocculating particles are determined according to the obtained underwater monitoring image, the environmental monitoring data and the index data of the flocculating particles are input into the long-short term memory model to obtain the effluent turbidity predicted value output by the long-short term memory model, and the medicine is added according to the effluent turbidity predicted value and the effluent turbidity preset value. The problem of the mode of adding medicine of flocculating settling process among the prior art, have very big subjectivity and hysteresis quality, the accuracy is lower, also difficult to deal with the sudden change is solved, the time lag effect of medicine throwing control has been alleviated, the validity and the interference immunity that the medicine was thrown automatically are improved, stabilize the play water turbidity and vibrate and reduced the total medicine consumption simultaneously.
Example two
Fig. 2a is a flowchart of a multidimensional fusion automatic drug adding method provided by the second embodiment of the present invention, and the second embodiment of the present invention further embodies the process of determining index data of the flocculation particles according to the underwater monitoring image, and the process of adding the drug according to the predicted value and the preset value of the turbidity of the effluent, and adds a process of performing long-short term memory model training in advance.
As shown in fig. 2a, the method comprises:
s210, acquiring historical environment monitoring data and historical flocculation particle index data as sample data.
In the embodiment of the invention, historical environment monitoring data and historical flocculation particle index data are collected as sample data.
S220, dividing the sample data into a training set and a testing set, wherein the training set comprises a first training set and a second training set.
Wherein the time of the first training set is prior to the time of the second training set.
The time span of the first training set and the second training set can be determined according to the size of the flocculation reaction time. For example, the sample data may be continuous 75 minutes of data, the first training set is the first 60 minutes of data, and the second training set is the last 15 minutes of data, but the time of the first training set and the second training set is not limited in this embodiment.
And S230, training a preset long-short term memory model according to the effluent turbidity monitoring values in the first training set and the second training set, and calculating the model precision of the long-short term memory model according to the testing set.
In the embodiment of the invention, the effluent turbidity matched with the second training set can be predicted according to the historical environment monitoring data and the historical flocculation particle index data of the first training set, and the model can be trained by performing loss calculation according to the effluent turbidity monitoring value in the second training set. Meanwhile, sample data is divided into a training set and a testing set, model training is carried out through the training set, and model precision is detected through the testing set.
And S240, judging whether the model precision is larger than or equal to a preset model precision threshold, if so, executing S250, otherwise, returning to execute S230.
And S250, determining that the training of the long-term and short-term memory model is finished.
And when the model precision is greater than or equal to a preset model precision threshold value, stopping model training, and using the obtained long-term and short-term memory model for predicting the effluent turbidity.
Fig. 2b provides a schematic diagram of a modeling process of a long-short term memory model, as shown in fig. 2b, the long-short term memory model comprises an input layer, a hidden layer and an output layer, the input layer normalizes data after acquiring historical environmental monitoring data and historical flocculation particle index data, the training of the hidden layer is performed according to the normalized data, and the output layer performs inverse normalization on an effluent turbidity predicted value after obtaining the effluent turbidity predicted value, so that the data dimension of the effluent turbidity predicted value is the same as the dimension of an input turbidity monitoring value. And after inverse normalization, outputting an outlet water turbidity predicted value, performing loss calculation according to the outlet water turbidity predicted value and the outlet water turbidity monitoring value, and performing model training again according to a loss calculation result by adopting an Adam optimization algorithm.
And S260, acquiring at least one environment monitoring data and an underwater monitoring image.
Optionally, in this embodiment, after the underwater monitoring image is acquired, the underwater monitoring image may be preprocessed.
Specifically, the image preprocessing may include image clipping, gradation conversion, and noise filtering processing. Allowing for underwater monitoringThe image edge may be blurred due to the effect of the underwater light source, and includes white text interference information such as distribution position, time, and the like, and the underwater monitoring image may be intercepted, for example, by intercepting 75% of the central area, but the embodiment does not limit the interception position and the interception proportion. Considering that the underwater monitoring image is colored and the color is affected by the underwater illumination and the color of the raw water in the sedimentation tank, the colored image can be converted into a gray image for better analyzing the flocculated particles. Specifically, the following formula can be used for the gradation conversion:
g (x, y) represents the gray value of a pixel point with the coordinate (x, y) after the underwater monitoring image is converted, and P (x, y) represents the gray value of a pixel point with the coordinate (x, y) before the underwater monitoring image is converted. Alpha and beta respectively represent the minimum value and the maximum value of the image gray before the underwater monitoring image is converted. In consideration of noise influence, nonlinear median filtering can be used for filtering out noise components in the underwater monitoring image.
And S270, determining a target gray threshold matched with the underwater monitoring image.
In the embodiment of the invention, when the underwater monitoring images are subjected to binarization processing and the flocculation particle area and the background area are distinguished, a uniform predetermined gray level threshold value can be adopted for each underwater monitoring image, and a dynamic threshold value method can also be adopted for each underwater monitoring image to respectively determine the gray level threshold value, which is not limited in the embodiment. The following is a specific description of determining the gray level threshold using the dynamic threshold method:
accordingly, S270 may further include:
s271, taking the average value of the maximum image gray level value and the minimum image gray level value of the underwater monitoring image as a current gray level threshold value.
And calculating the average value of the maximum image gray value and the minimum image gray value of the underwater monitoring image as the initial value of the gray threshold value.
And S272, dividing the underwater monitoring image into a middle flocculation particle area and a middle background area according to the current gray threshold.
And S273, calculating the gray level average value of the average gray level of the middle flocculation particle area and the average gray level of the middle background area.
And according to the current gray threshold, dividing the underwater monitoring image into a middle flocculation particle area and a middle background area. The average gray level of the middle flocculated particle region and the average gray level of the middle background region are obtained separately, but the embodiment does not limit the way of calculating the average gray level of each region.
And S274, judging whether the difference value of the current gray threshold value and the gray average value is smaller than or equal to a preset value, if so, executing S275, otherwise, executing S276.
If the difference between the current gray threshold and the average gray value is less than or equal to the preset value, the current gray threshold is used as the target gray threshold, otherwise, the average gray value is used as the new current gray threshold, and S272-S274 are repeatedly executed until the difference between the current gray threshold and the average gray value is less than or equal to the preset value.
And S275, taking the current gray threshold value as a target gray threshold value.
And S276, taking the gray average value as a new current gray threshold value. Execution returns to S272.
S280, carrying out binarization processing on the underwater monitoring image according to a target gray threshold value to obtain a flocculation particle area and a background area.
After a target gray threshold matched with the underwater monitoring image is determined, binarization processing is carried out on the underwater monitoring image according to the target gray threshold, and the underwater monitoring image is divided into a flocculation particle area and a background area.
And S290, determining index data of the flocculated particles according to the flocculated particle area and the background area.
The index data of the flocculated particles can be the area ratio of the flocculated particles, the average equivalent diameter of the flocculated particles and the roundness of the flocculated particles. The above embodiments have described specific ways of calculating the ratio of the flocculated particle area, the average equivalent diameter of the flocculated particles and the circularity of the flocculated particles according to the flocculated particle area and the background area, and the details of the embodiments are not repeated herein.
S2100, inputting the environmental monitoring data and the flocculation particle index data into a long-short term memory model obtained through pre-training to obtain a water outlet turbidity predicted value output by the long-short term memory model.
In the embodiment of the invention, the environmental monitoring data such as the water inlet flow, the raw water turbidity monitoring value, the effluent turbidity monitoring value, the medicine adding amount, the pH value of a water sample, the electrolyte concentration of the water sample, the temperature of the water sample and the like, and the flocculation particle index data such as the area proportion of the flocculation particles, the average equivalent diameter of the flocculation particles, the roundness of the flocculation particles and the like are input into the LSTM model. The LSTM model output is based on the effluent turbidity prediction under multivariate influence.
And S2110, calculating the dosage of the medicine according to the difference between the predicted value of the effluent turbidity and the preset value of the effluent turbidity through a proportional-integral-derivative control algorithm.
S2120, sending the medicine adding amount to a medicine adding device so that the medicine adding device can add the medicine.
Through the PID controller, the medicine adding amount can be calculated according to the difference value between the effluent turbidity predicted value and the effluent turbidity preset value, so that automatic and accurate medicine adding is realized.
Through the technical scheme of this embodiment, can be through underwater monitoring video and flocculation particle index data on the one hand, realize the real-time supervision to the flocculation state. On the other hand, the effluent turbidity predicted value after a period of time can be predicted based on multivariate analysis by combining environmental monitoring data and flocculation particle index data, automatic and accurate medicament addition is realized by utilizing a PID controller, the influence of the hysteresis of the flocculation process on the control performance is reduced, various sudden changes of the flocculation process can be coped with, the effluent quality is ensured, the medicament addition amount is reduced, and cost reduction and efficiency improvement are realized.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a multidimensional fusion automated drug adding device provided in the third embodiment of the present invention. The device can be realized in a hardware and/or software mode, and the multidimensional fusion automatic medicine adding device can be configured in computer equipment and is matched with an environment monitoring device, a shooting device and a medicine adding device for use.
As shown in fig. 3, the apparatus includes: the system comprises a data acquisition module 310, a flocculation particle index data determination module 320, a effluent turbidity prediction value determination module 330 and a drug adding module 340. Wherein:
a data acquisition module 310, configured to acquire at least one environmental monitoring data and an underwater monitoring image; wherein the environment monitoring data is used for reflecting the water quality state;
a flocculation particle index data determination module 320, configured to determine at least one flocculation particle index data according to the underwater monitoring image; wherein the index data of the flocculated particles is used for reflecting the effect of flocculation and precipitation;
the effluent turbidity predicted value determining module 330 is configured to input the environment monitoring data and the flocculation particle index data into a long-short term memory model obtained through pre-training, so as to obtain an effluent turbidity predicted value output by the long-short term memory model;
And the medicine adding module 340 is used for adding medicines according to the effluent turbidity predicted value and the effluent turbidity preset value.
According to the technical scheme of the embodiment of the invention, the environmental monitoring data are obtained, the index data of the flocculating particles are determined according to the obtained underwater monitoring image, the environmental monitoring data and the index data of the flocculating particles are input into the long-short term memory model to obtain the effluent turbidity predicted value output by the long-short term memory model, and the medicine is added according to the effluent turbidity predicted value and the effluent turbidity preset value. The problem of the mode of adding medicine of flocculating settling process among the prior art, have very big subjectivity and hysteresis quality, the accuracy is lower, also difficult to deal with the sudden change is solved, the time lag effect of medicine throwing control has been alleviated, the validity and the interference immunity that the medicine was thrown automatically are improved, stabilize the play water turbidity and vibrate and reduced the total medicine consumption simultaneously.
On the basis of the above embodiment, the environmental monitoring data comprises at least one of: the system comprises an inlet water flow, a raw water turbidity monitoring value, an outlet water turbidity monitoring value, a drug adding amount, a water sample pH value, a water sample electrolyte concentration and a water sample temperature.
On the basis of the above example, the flocculated particle indicator data comprises at least one of: the flocculation particle area ratio, the average equivalent diameter of the flocculation particles and the roundness of the flocculation particles.
On the basis of the above embodiment, the flocculation particle index data determination module 320 includes:
the target gray threshold value determining unit is used for determining a target gray threshold value matched with the underwater monitoring image;
the image binarization processing unit is used for carrying out binarization processing on the underwater monitoring image according to a target gray threshold value to obtain a flocculation particle area and a background area;
and the flocculation particle index data determining unit is used for determining the flocculation particle index data according to the flocculation particle area and the background area.
On the basis of the above embodiment, the target gray threshold determining unit is specifically configured to:
taking the average value of the maximum image gray value and the minimum image gray value of the underwater monitoring image as a current gray threshold value;
dividing the underwater monitoring image into a middle flocculation particle area and a middle background area according to the current gray threshold;
calculating the average gray level of the middle flocculation particle area and the average gray level of the middle background area;
if the difference value between the current gray threshold value and the average gray value is smaller than or equal to a preset value, taking the current gray threshold value as a target gray threshold value;
and if not, taking the gray average value as a new current gray threshold value, and returning to execute the operation of dividing the underwater monitoring image into an intermediate flocculation particle area and an intermediate background area according to the current gray threshold value.
On the basis of the above embodiment, the apparatus further includes:
the sample data acquisition module is used for acquiring historical environment monitoring data and historical flocculation particle index data as sample data;
the sample data dividing module is used for dividing the sample data into a training set and a test set, wherein the training set comprises a first training set and a second training set, and the time of the first training set is before the time of the second training set;
the model training module is used for training a preset long-short term memory model according to the effluent turbidity monitoring values in the first training set and the second training set and calculating the model precision of the long-short term memory model according to the testing set;
and the model precision judging module is used for determining that the training of the long-short term memory model is finished if the model precision is determined to be greater than or equal to a preset model precision threshold value, and otherwise, returning to execute the operation of training the preset long-short term memory model.
On the basis of the above embodiment, the drug adding module 340 includes:
the medicine adding amount calculating unit is used for calculating the medicine adding amount according to the difference value between the effluent turbidity predicted value and the effluent turbidity preset value through a proportional-integral-derivative control algorithm;
And the medicine adding amount sending unit is used for sending the medicine adding amount to the medicine adding device so as to enable the medicine adding device to add the medicine.
The multidimensional fusion automatic medicine adding device provided by the embodiment of the invention can execute the multidimensional fusion automatic medicine adding method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 4 is a schematic structural diagram of a computer apparatus according to a fourth embodiment of the present invention, as shown in fig. 4, the computer apparatus includes a processor 70, a memory 71, an input device 72, and an output device 73; the number of processors 70 in the computer device may be one or more, and one processor 70 is taken as an example in fig. 4; the processor 70, the memory 71, the input device 72 and the output device 73 in the computer apparatus may be connected by a bus or other means, and the connection by the bus is exemplified in fig. 4.
The memory 71 is used as a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as modules corresponding to the multidimensional fusion automatic drug adding method in the embodiment of the present invention (for example, the data obtaining module 310, the flocculated particle index data determining module 320, the effluent turbidity predicting value determining module 330, and the drug adding module 340 in the multidimensional fusion automatic drug adding device). The processor 70 executes various functional applications and data processing of the computer device by executing software programs, instructions and modules stored in the memory 71, so as to implement the multidimensional fusion automated drug administration method described above. The method comprises the following steps:
Acquiring at least one environment monitoring data and an underwater monitoring image; wherein the environmental monitoring data is used for reflecting the water quality state;
determining at least one index data of the flocculation particles according to the underwater monitoring image; wherein the index data of the flocculated particles is used for reflecting the effect of flocculation and precipitation;
inputting environment monitoring data and flocculation particle index data into a long-short term memory model obtained through pre-training to obtain a effluent turbidity predicted value output by the long-short term memory model;
and adding the medicament according to the effluent turbidity predicted value and the effluent turbidity preset value.
The memory 71 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 71 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 71 may further include memory located remotely from the processor 70, which may be connected to a computer device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 72 may be used to receive input numeric or character information and generate key signal inputs relating to user settings and function controls of the computer device. The output device 73 may include a display device such as a display screen.
EXAMPLE five
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method for multidimensional fusion automated drug administration, the method comprising:
acquiring at least one environment monitoring data and an underwater monitoring image; wherein the environment monitoring data is used for reflecting the water quality state;
determining at least one index data of the flocculation particles according to the underwater monitoring image; wherein the index data of the flocculation particles is used for reflecting the flocculation precipitation effect;
inputting the environmental monitoring data and the index data of the flocculation particles into a long-short term memory model obtained by pre-training to obtain a effluent turbidity predicted value output by the long-short term memory model;
and adding the medicine according to the effluent turbidity predicted value and the effluent turbidity preset value.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the operations of the method described above, and may also perform related operations in the multidimensional fusion automated drug administration method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention or portions thereof contributing to the prior art may be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the multi-dimensional fusion automatic drug adding device, the included units and modules are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A multidimensional fusion automated drug administration method, comprising:
acquiring at least one environment monitoring data and an underwater monitoring image; wherein the environmental monitoring data is used for reflecting the water quality state;
determining at least one index data of the flocculation particles according to the underwater monitoring image; wherein the index data of the flocculated particles is used for reflecting the effect of flocculation and precipitation;
inputting environment monitoring data and flocculation particle index data into a long-short term memory model obtained through pre-training to obtain a effluent turbidity predicted value output by the long-short term memory model;
And adding the medicine according to the effluent turbidity predicted value and the effluent turbidity preset value.
2. The method of claim 1, wherein the environmental monitoring data comprises at least one of:
the system comprises an inlet water flow, a raw water turbidity monitoring value, an outlet water turbidity monitoring value, a drug adding amount, a water sample pH value, a water sample electrolyte concentration and a water sample temperature.
3. The method of claim 1, wherein the flocculated particle indicator data includes at least one of:
the flocculation particle area ratio, the average equivalent diameter of the flocculation particles and the roundness of the flocculation particles.
4. The method of claim 3, wherein determining at least one flocculation particle index data from the underwater monitoring image comprises:
determining a target gray threshold value matched with the underwater monitoring image;
carrying out binarization processing on the underwater monitoring image according to a target gray threshold value to obtain a flocculation particle area and a background area;
and determining index data of the flocculated particles according to the flocculated particle area and the background area.
5. The method of claim 4, wherein determining a target gray threshold value that matches the underwater monitoring image comprises:
Taking the average value of the maximum image gray value and the minimum image gray value of the underwater monitoring image as a current gray threshold value;
dividing the underwater monitoring image into a middle flocculation particle area and a middle background area according to the current gray threshold;
calculating the average gray level of the middle flocculation particle area and the average gray level of the middle background area;
if the difference value between the current gray threshold and the gray average value is smaller than or equal to a preset value, taking the current gray threshold as a target gray threshold;
and if not, taking the gray average value as a new current gray threshold value, and returning to execute the operation of dividing the underwater monitoring image into an intermediate flocculation particle area and an intermediate background area according to the current gray threshold value.
6. The method of claim 1, further comprising, prior to acquiring at least one of environmental monitoring data and underwater monitoring images:
acquiring historical environment monitoring data and historical flocculation particle index data as sample data;
dividing sample data into a training set and a testing set, wherein the training set comprises a first training set and a second training set, and the time of the first training set is before the time of the second training set;
Training a preset long-short term memory model according to the effluent turbidity monitoring values in the first training set and the second training set, and calculating the model precision of the long-short term memory model according to the test set;
and if the model precision is determined to be greater than or equal to the preset model precision threshold, determining that the training of the long-short term memory model is finished, otherwise, returning to execute the operation of training the preset long-short term memory model.
7. The method of claim 1, wherein the step of adding the medicine according to the effluent turbidity predicted value and the effluent turbidity preset value comprises the following steps:
calculating the dosage of the medicine according to the difference between the predicted value of the turbidity of the effluent and the preset value of the turbidity of the effluent by a proportional-integral-derivative control algorithm;
and sending the medicine adding amount to a medicine adding device so as to enable the medicine adding device to add the medicine.
8. A multidimensional fusion automated drug adding device, comprising:
the data acquisition module is used for acquiring at least one environment monitoring data and an underwater monitoring image; wherein the environment monitoring data is used for reflecting the water quality state;
the flocculation particle index data determining module is used for determining at least one flocculation particle index data according to the underwater monitoring image; wherein the index data of the flocculation particles is used for reflecting the flocculation precipitation effect;
The effluent turbidity predicted value determining module is used for inputting the environmental monitoring data and the index data of the flocculated particles into a long-short term memory model obtained by pre-training to obtain an effluent turbidity predicted value output by the long-short term memory model;
and the drug adding module is used for adding drugs according to the effluent turbidity predicted value and the effluent turbidity preset value.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the multi-dimensional fusion automated drug administration method according to any one of claims 1-7.
10. A storage medium storing computer-executable instructions for performing the method for multidimensional fusion automated drug administration of any one of claims 1-7 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210835340.0A CN115231668A (en) | 2022-07-15 | 2022-07-15 | Multi-dimensional fusion automatic medicine feeding method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210835340.0A CN115231668A (en) | 2022-07-15 | 2022-07-15 | Multi-dimensional fusion automatic medicine feeding method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115231668A true CN115231668A (en) | 2022-10-25 |
Family
ID=83673517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210835340.0A Pending CN115231668A (en) | 2022-07-15 | 2022-07-15 | Multi-dimensional fusion automatic medicine feeding method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115231668A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117133381A (en) * | 2023-08-01 | 2023-11-28 | 观星智能科技(西安)有限责任公司 | Flocculant addition amount real-time optimization method and system based on multi-cup tank flocculation experiment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1885006A (en) * | 2006-06-23 | 2006-12-27 | 哈尔滨工业大学 | Granularity fractal dimension determination method for deciding optimal charging amount of flocculant for water treatment |
| CN101805050A (en) * | 2010-03-17 | 2010-08-18 | 上海大学 | Method and system for controlling coagulant dosing through on-line prediction of turbidity after flocculation water sedimentation |
| CN103011356A (en) * | 2012-08-15 | 2013-04-03 | 重庆水务集团股份有限公司 | Method for controlling automatic chemical dosing of high-turbidity water system |
| CN108486522A (en) * | 2018-06-26 | 2018-09-04 | 中国科学院金属研究所 | A kind of catalytic cracking unit valve wear-and corrosion-resistant coating and preparation method thereof |
| US20190270655A1 (en) * | 2017-05-02 | 2019-09-05 | ClearCorp | Methods and systems for optimizing water treatment coagulant dosing |
| US20200223719A1 (en) * | 2016-04-01 | 2020-07-16 | Kemira Oyj | A method and system for optimization of coagulation and/or flocculation in a water treatment process |
| CN111966053A (en) * | 2020-07-09 | 2020-11-20 | 上海威派格智慧水务股份有限公司 | Intelligent flocculant decision making system |
-
2022
- 2022-07-15 CN CN202210835340.0A patent/CN115231668A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1885006A (en) * | 2006-06-23 | 2006-12-27 | 哈尔滨工业大学 | Granularity fractal dimension determination method for deciding optimal charging amount of flocculant for water treatment |
| CN101805050A (en) * | 2010-03-17 | 2010-08-18 | 上海大学 | Method and system for controlling coagulant dosing through on-line prediction of turbidity after flocculation water sedimentation |
| CN103011356A (en) * | 2012-08-15 | 2013-04-03 | 重庆水务集团股份有限公司 | Method for controlling automatic chemical dosing of high-turbidity water system |
| US20200223719A1 (en) * | 2016-04-01 | 2020-07-16 | Kemira Oyj | A method and system for optimization of coagulation and/or flocculation in a water treatment process |
| US20190270655A1 (en) * | 2017-05-02 | 2019-09-05 | ClearCorp | Methods and systems for optimizing water treatment coagulant dosing |
| CN108486522A (en) * | 2018-06-26 | 2018-09-04 | 中国科学院金属研究所 | A kind of catalytic cracking unit valve wear-and corrosion-resistant coating and preparation method thereof |
| CN111966053A (en) * | 2020-07-09 | 2020-11-20 | 上海威派格智慧水务股份有限公司 | Intelligent flocculant decision making system |
Non-Patent Citations (1)
| Title |
|---|
| 蒋绍阶;仇洪建;段果;冯海翔;: "基于短程反馈BP神经网络的混凝投药控制中试", 中国给水排水, no. 11 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117133381A (en) * | 2023-08-01 | 2023-11-28 | 观星智能科技(西安)有限责任公司 | Flocculant addition amount real-time optimization method and system based on multi-cup tank flocculation experiment |
| CN117133381B (en) * | 2023-08-01 | 2024-03-19 | 观星智能科技(西安)有限责任公司 | Flocculant addition amount real-time optimization method and system based on multi-cup tank flocculation experiment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112417788A (en) | Water environment pollution analysis system and method based on big data | |
| CN113429013B (en) | Method for determining coagulant addition amount and method for determining compound addition amount | |
| KR101889510B1 (en) | Method of estimating coagulant injection rate in water treatment using deep neural network | |
| CN115231668A (en) | Multi-dimensional fusion automatic medicine feeding method, device and equipment | |
| CN102531121A (en) | Optimum input forecast system of water treatment coagulant and forecast method | |
| CN109426225A (en) | A kind of method of quality control of tobacco cutting production | |
| Ritch et al. | AxoNet: A deep learning-based tool to count retinal ganglion cell axons | |
| CN113695366B (en) | Intelligent screening method and system for fly ash chelating agent based on environmental monitoring | |
| CN111695730B (en) | Vertical mill vibration prediction method and device based on ARIMA and RNN | |
| CN114061705A (en) | Intelligent water level monitoring, analyzing and early warning method and system | |
| CN114037673A (en) | Hardware connection interface monitoring method and system based on machine vision | |
| CN107247649A (en) | Method, device and the gateway of detecting system health status | |
| CN111268780B (en) | Sewage treatment method | |
| CN112598443A (en) | Online channel business data processing method and system based on deep learning | |
| JP2023033927A (en) | Water treatment state monitoring system and water treatment state monitoring method | |
| CN114331114A (en) | Intelligent supervision method and system for pipeline safety risks | |
| CN117591978A (en) | Environment pollution detection method, system, equipment and storage medium | |
| CN117434235A (en) | Water bloom early warning method, device, equipment and medium based on water quality monitoring | |
| CN116699093A (en) | Underground water quality detection method, system and readable storage medium | |
| CN115375009B (en) | Method for establishing intelligent monitoring linkage system for coagulation | |
| Sivchenko et al. | Floc sensor prototype tested in the municipal wastewater treatment plant | |
| CN115010232A (en) | Drinking water plant coagulation dosing prediction method based on weak time-lag neural network model | |
| CN115423383A (en) | Distributed village and town drinking water monitoring and regulation system and method based on artificial intelligence | |
| CN105630017B (en) | A kind of method and its equipment for automatically controlling dense seitan liquid butt protein content | |
| CN110991841B (en) | Analysis method for nonstandard behaviors in bidding process based on AI technology |
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 |