CN115259318A - Self-adaptive PAC dosing basic automation method - Google Patents
Self-adaptive PAC dosing basic automation method Download PDFInfo
- Publication number
- CN115259318A CN115259318A CN202210952977.8A CN202210952977A CN115259318A CN 115259318 A CN115259318 A CN 115259318A CN 202210952977 A CN202210952977 A CN 202210952977A CN 115259318 A CN115259318 A CN 115259318A
- Authority
- CN
- China
- Prior art keywords
- iteration
- model
- pac
- parameter
- dosing
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000008569 process Effects 0.000 claims abstract description 21
- 239000000126 substance Substances 0.000 claims abstract description 20
- 238000004519 manufacturing process Methods 0.000 claims abstract description 12
- 230000007246 mechanism Effects 0.000 claims abstract description 12
- 239000003814 drug Substances 0.000 claims abstract description 8
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 7
- 238000012795 verification Methods 0.000 claims abstract description 6
- 238000013461 design Methods 0.000 claims abstract description 5
- 238000012417 linear regression Methods 0.000 claims abstract description 5
- 238000009795 derivation Methods 0.000 claims abstract description 4
- 230000006698 induction Effects 0.000 claims abstract description 4
- 238000004458 analytical method Methods 0.000 claims abstract description 3
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 39
- 229910052698 phosphorus Inorganic materials 0.000 claims description 39
- 239000011574 phosphorus Substances 0.000 claims description 39
- 230000000694 effects Effects 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 229910052731 fluorine Inorganic materials 0.000 claims description 2
- 125000001153 fluoro group Chemical group F* 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 238000006243 chemical reaction Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 229910019142 PO4 Inorganic materials 0.000 description 5
- 239000010865 sewage Substances 0.000 description 5
- 229910052782 aluminium Inorganic materials 0.000 description 4
- 238000006116 polymerization reaction Methods 0.000 description 4
- 238000001179 sorption measurement Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 229940079593 drug Drugs 0.000 description 3
- 229920000642 polymer Polymers 0.000 description 3
- 239000002244 precipitate Substances 0.000 description 3
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 2
- 229910000147 aluminium phosphate Inorganic materials 0.000 description 2
- -1 aluminum ions Chemical class 0.000 description 2
- 150000002500 ions Chemical group 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012067 mathematical method Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 239000010452 phosphate Substances 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 229910018626 Al(OH) Inorganic materials 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- AZDRQVAHHNSJOQ-UHFFFAOYSA-N alumane Chemical class [AlH3] AZDRQVAHHNSJOQ-UHFFFAOYSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 239000000084 colloidal system Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- NBIIXXVUZAFLBC-UHFFFAOYSA-K phosphate Chemical compound [O-]P([O-])([O-])=O NBIIXXVUZAFLBC-UHFFFAOYSA-K 0.000 description 1
- 239000010802 sludge Substances 0.000 description 1
- 238000012360 testing method 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
- C02F1/5209—Regulation methods for flocculation or precipitation
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F1/00—Treatment of water, waste water, or sewage
- C02F1/52—Treatment of water, waste water, or sewage by flocculation or precipitation of suspended impurities
- C02F1/5236—Treatment of water, waste water, or sewage by flocculation or precipitation of suspended impurities using inorganic agents
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2101/00—Nature of the contaminant
- C02F2101/10—Inorganic compounds
- C02F2101/105—Phosphorus compounds
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- Environmental & Geological Engineering (AREA)
- Water Supply & Treatment (AREA)
- Hydrology & Water Resources (AREA)
- Organic Chemistry (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Inorganic Chemistry (AREA)
- Feedback Control In General (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a self-adaptive PAC dosing basic automation method, which comprises the following two steps: one part is a modeling process, and the other part is parameter determination and debugging verification. The modeling process includes: PAC mechanism medicine feeding mechanism analysis, principle model design, model induction and linear regression equation derivation. The parameter debugging verification comprises the following steps: determining an original value of an iteration coefficient, setting and debugging the dosing parameter according with the actual working condition, and applying the parameter amplitude limiting logic of the model/the working condition. The invention conforms to the chemical and physical mechanisms: the basic application level is added with mathematical modeling. The designed PAC dosing model can realize self-iteration and self-adaptation according to working conditions. The hardware universality and the cost are low: the PLC codes are universal and can be realized only by performing code iteration on the original PLC. Stability and robustness: the method combines the algorithm of data processing and the logic function of the basic controller, and accords with the habit of a production user.
Description
Technical Field
The invention relates to a PAC dosing base automation method, belongs to the technical field of PAC automation dosing control, and particularly relates to a self-adaptive PAC dosing base automation method.
Background
The existing PAC automatic dosing method mainly comprises two types, one type is simpler empirical modeling, generally, a unary linear equation y = kx + b in each partition interval is adopted, the basic automation is easy to realize, and the application is wide; but is quite lack of precision and self-adaptation; the other is an intelligent dosing model based on chemical reaction, CFD state, and polymer growth adsorption process, although in theory there is a perfect discussion; the application of an accurate prediction and self-learning self-adaptive mathematical method; but the modeling is complex, the computation is large, and the hardware configuration and the engineering implementation are expensive. The actual investment on site is only a few cases of successful operation, and the maturity and practicability of the technology are further developed.
PAC dosing technology belongs to one of advanced sewage treatment technologies. By adding PAC agent, one part of aluminum ions and phosphate radical in sewage chemically react to form precipitate, and the other part of charged ions form polymer to remove phosphorus by adsorbing phosphate radical by negative charges. Therefore, the phosphorus index in the effluent index is effectively controlled. The PAC dosing dephosphorization is adopted in the three-stage treatment process of most domestic sewage plants, so that the general requirements of the industry on reducing unit consumption, accurately controlling the drug and improving economic benefits are met.
At present, the mainstream PAC automatic medicine adding methods in China mainly comprise two types. One type is a simpler empirical formula, generally is a one-dimensional linear equation y = kx + b in a partitioned interval, is easy to realize in basic automation, is a current mainstream method and is widely applied; but the method also has the defects of low accuracy and incapability of self-adaption; the other is an intelligent dosing model established according to chemical reaction, CFD state and polymer growth and adsorption process, although the theory has more perfect discussion; also includes mathematical methods such as accurate prediction, self-learning self-adaptation, etc.; but the modeling is complex, the calculation amount is large, and the implementation price of matched hardware and engineering is high; few cases of actual investment into successful operation; the maturity and practicability of the technology are further developed.
Simple operation, self-adaptive method, consumption reduction and efficiency improvement, and is the general demand of each water treatment user. The old method has gradually lagged behind the current industry level, and the new model theory is not satisfactory in cost and application effect. Aiming at the current development requirements, a self-adaptive basic automatic PAC control medicine adding method is developed, the automation degree is improved, and the consumption reduction requirement is the new trend of the development of the prior art.
Disclosure of Invention
Based on the respective problems of the two prior arts, the invention designs a relatively accurate and self-adaptive PAC dosing base automation method which not only accords with the PAC model mechanism, but also is easy to realize on PLC modification. Therefore, based on the respective problems of the two prior art, the invention designs a relatively accurate and self-adaptive PAC dosing base automation method which not only accords with the PAC model mechanism, but also is easy to realize on PLC modification.
The core of the invention is mathematical modeling, and the implemented process can be divided into two parts in general: one part is a modeling process, and the other part is parameter determination and debugging verification. The modeling process comprises the following steps: PAC mechanism medicine feeding mechanism analysis, principle model design, model induction and linear regression equation derivation. The parameter debugging verification comprises the following steps: determining an original value of an iteration coefficient, setting and debugging the dosing parameter according with the actual working condition, and applying the parameter amplitude limiting logic of the model/the working condition. Through the implementation steps, the PAC dosing basic automation method which is simple in operation, matched with a model mechanism, adaptive, stable and reliable as well and accords with the habit of a production user can be realized on the basic automation layer.
S1, chemical phosphorus removal of Al +3 /PO4 -3 Is completely linear and can directly express y by a linear equation 1 ＝wx 1 +b 1 。
The physical phosphorus removal model is simplified into a convex parabola y with extreme point (XH, YH) 2 ＝u(x 2 -XH) 2 + YH. The physical/chemical dosage is replaced by the total dosage x and the ratio coefficient k.
The chemical phosphorus removal model is transformed into: y is 1 = w (1-k) x + b1; the material model can be simplified as follows: y is 2 ＝u(kx-SH) 2 + YH model addition, chemical phosphorus removal model induction to y = u (kx-XH) 2 +w(1-k)x+b。
Wherein x is more than 0, y is >0,0 is less than k is less than 1.w is less than 0, u is less than 0, b is greater than YH.XH is the maximum limit value of the drug quantity, and YH is the maximum value set by the phosphorus index.
S2, the adaptive PAC dosing basic automation model obtains an iterative formula through a gradient descent method and a loss function partial derivative (equation solution unary equation linear regression problem):
wherein k is set by the artificial ratio coefficient, eta is set by the learning step length, and n is set by the learning iteration times. x is the number of i For a given dose, y i Is the current feedback value of the TP phosphorus meter, and XH is set for the maximum value of the dosage. And (4) performing simultaneous loop iteration and gradient iterative approximation on the formulas (1), (2) and (3) to obtain predicted coefficients w, u and b.
And S3, determining iteration initial values w0, u0 and b 0. K =0.5, namely, the initial state when the effect of the chemical/physical phosphorus removal treatment is comparable. The b0 value is YH, i.e. the maximum amount of phosphorus to be treated. YH, YL, XH and XL were subjected to iteration, and w0 and u0 were calculated as initial values.
S4, the whole self-adaptive PAC dosing basic automatic modeling and method steps are as follows: firstly, establishing a self-adaptive PAC dosing basic automatic model, and secondly, carrying out iterative algorithm program design according to an equation. The method comprises the following steps of calculating the amplitude limit of a parameter, and judging jump logic after the parameter amplitude limit is strictly substituted in the program design process, so that the program is prevented from being clamped into a dead cycle or interrupted. Then, the initial coefficients w0, u0, b0, the empirical coefficient k, and the amplitudes YH, YL, XH, XL of equations (1), (2), (3) are determined. And then combining the actual production values (the dosage x and the phosphorus removal instrument value y) to input an algorithm for iteration, and solving the equation coefficients w, u and b. And finally, properly adjusting the parameters k, the step length eta and the iteration times n according to production experience, and gradually determining the existing working condition to adapt to an adding rule.
The intelligent PAC dosing model is the direction of future technology development. However, no mature commercial application model exists at present in China, and the modeling is complex, the price is high, and the effect is not ideal. Therefore, the technology matured in China is also a piecewise linear function. The invention is based on the principle of meeting the two points of process principle and engineering practicality and reliability, and is oriented to basic automation layer users with wide audience range. The invention has the advantages that 1, the invention accords with the chemical and physical mechanisms: the basic application level is added with mathematical modeling. 2. Self-adaptation: the designed PAC dosing model can realize self-iteration and self-adaptation according to working conditions. 3. The hardware universality and the cost are low: the PLC codes are universal and can be realized only by performing code iteration on the original PLC. 4. Stability and robustness: the method combines the algorithm of data processing and the logic function of the basic controller, and accords with the habit of a production user.
Drawings
FIG. 1 is a graph of the effect of a technical analytical model of PAC administration according to the method of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and examples.
As shown in figure 1, the technical scheme adopted by the invention is a self-adaptive PAC dosing basic automation method, and (1) sewage PAC dosing is a phosphorus removal method mainly based on chemistry and secondarily based on physical adsorption. Principle of PAC chemical phosphorus removal: when PAC aluminum salt is dissolved in sewage to form ions, the following chemical reactions occur: al (aluminum) +3 +PO4 -3 = AlPO4 ↓. AlPO4 is a precipitate, and the effect of chemical phosphorus removal is achieved by discharging sludge and water. The reaction molar ratio of the aluminum ions to the phosphate ions is 1: 1. On the other hand, the principle of physical phosphorus removal by PAC: al (Al) +3 Can be prepared by hydrolysisFormation of the mononuclear complex Al (OH) 2 + 、Al(OH) +2 And AlO -2 Etc. these mononuclear complexes are further polymerized to form polynuclear complexes Al n (OH) m (3n-m)+ (n>1，m<=3 n), the polynuclear complex of aluminum has higher positive charge and specific surface area, can rapidly adsorb impurities with negative charges in a water body, neutralize colloid charge, agglomerate and precipitate, and realize physical phosphorus removal.
(2) The principle of adding drugs and removing phosphorus by PAC is known as follows: in chemical phosphorus removal process, al +3 /PO4 -3 Is completely linear and can directly express y by a linear equation 1 ＝wx 1 +b 1 . In the physical phosphorus removal method, the adsorption phosphorus removal effect is not obvious in the initial polymerization stage; in the middle stage of polymerization, the effect is obvious; in the later period of the transitional administration, the polynuclear complex with positive charges is mutually exclusive, and the phosphorus removal effect is influenced, so that the marginal effect is obvious. The process of "growth-maturation use-arrest" can be modeled by a growth function, but is too complex at the basic control tool level due to the nonlinear regression problem of the growth function, and the actual dosing is always in dynamic continuity. In combination with the high and low dosage limiting method, the actual process basically does not need to consider the polymerization condition in the initial polymerization stage. Here the model is simplified to a convex parabola y with extreme points (XH, YH) 2 ＝u(x 2 -XH) 2 +YH。
(3) x1 and x2 are respectively the amount used for chemical reaction and physical reaction in the dosage, and y represents the corresponding phosphorus removal amount. The respective dosage can be replaced by the total dosage x and the ratio coefficient k. The chemical model can be transformed into: y1= w (1-k) x + b1; the material model can be simplified as follows: y is 2 ＝u(kx-SH) 2 Model addition, the overall model can be summarized as y = u (kx-XH) 2 + w (1-k) x + b. Wherein x is>0，y>0，0<k<1.w>0，u<0，b>Yh.xh is the dose clipping maximum, YH is the phosphorus index set maximum.
The meaning of the coefficient k: when k → 0, it means that chemical phosphorus removal is dominant in the treatment process. When k =0.5, chemical-physical phosphorus removal is at an equivalent level. When k → 1, it means that physical phosphorus removal is dominant in the treatment process.
By a gradient descent method, partial derivatives are solved by loss functions (equation solution is used for solving a linear regression problem of a unary equation), and an iterative formula is obtained:
wherein k is set by the artificial ratio coefficient, eta is set by the learning step length, and n is set by the learning iteration number. x is a radical of a fluorine atom i For a given dose, y i Is the current feedback value of the TP phosphorus meter, and XH is set for the maximum value of the dosage. And (1), (2) and (3) performing simultaneous loop iteration and performing gradient method iterative approximation to obtain predicted coefficients w, u and b.
(4) And determining iteration initial values w0, u0 and b 0. The model takes k =0.5, namely the initial state when the effect of the chemical/physical dephosphorization treatment is relatively good. The b0 value is YH, i.e. the maximum amount of phosphorus to be treated. YH, YL, XH and XL were subjected to iteration, and w0 and u0 were calculated as initial values.
(5) Parameter debugging: in the actual production process, the parameter setting and the iterative process are analyzed by combining the dosing principle. The k value represents the ratio (0-1) of the chemical/physical phosphorus removal process, and a relatively stable empirical coefficient can be found out through an enumeration method test on site; the iteration step length eta and the iteration number n of the iteration equations of the coefficients w, u and b are generally set to be uniform. But can be adjusted according to practical experience conditions, and when chemical phosphorus removal has obvious advantages, the iteration step size and the coefficient in the w coefficient equation (1) can be properly adjusted to be large. When physical phosphorus removal is dominant, the iteration step size and the coefficient in the u coefficient equation (2) can be adjusted to be larger appropriately. When the phosphorus removal rule is not obviously influenced by interference to a large extent, the iteration step size and the coefficient in the b coefficient equation (3) can be adjusted to be large appropriately.
(6) Parameter limiting: in actual production, the input and set parameters which accord with the actual process in the working condition are limited. Compared with the smart water service pursuit mechanism perfection and model accuracy, the foundation automation layer is closer to the production practice, and the stability and the engineering practicability in the algorithm iteration process are more considered. Therefore, in the iterative logic process, when the parameter limitation of the algorithm occurs, other executable logics are required to be jumped to in time. Besides considering model calculation, the judgment of the amplitude limit of the conforming parameters is also important logic for program perfection.
(7) Summarizing the steps: firstly establishing a model, and secondly carrying out iterative algorithm program design according to an equation. In the program design process, the judgment jump logic after the parameter amplitude limiting is strictly substituted, so that the program is prevented from being clamped into a dead loop or being interrupted. Then, the initial coefficients w0, u0, b0, the empirical coefficient k, and the amplitude values YH, YL, XH, XL of equations (1) (2) (3) are determined. And then combining the actual production values (the dosage x and the phosphorus removal instrument value y) to input an algorithm for iteration, and solving the equation coefficients w, u and b. And finally, properly adjusting the parameter k, the step length eta and the iteration number n according to production experience, and gradually determining the existing working condition to adapt to the adding rule. And continuously iterating the regression equation along with continuous accumulation of the x and y linear data to finally reproduce the accurate working condition.
Claims (1)
1. An adaptive PAC dosing base automation method is characterized in that the implementation process is divided into two parts: one part is a modeling process, and the other part is parameter determination and debugging verification; the modeling process includes: PAC mechanism chemical feeding mechanism analysis, principle model design, model induction and linear regression equation derivation; the parameter debugging verification comprises the following steps: determining an original value of an iteration coefficient, setting and debugging dosing parameters which accord with the actual working conditions, and performing parameter amplitude limiting logic application of a model/working conditions; the method comprises the following steps of,
s1, chemical phosphorus removal of Al +3 /PO4 -3 Is completely linear and is directly expressed by a linear equation;
simplifying the physical phosphorus removal model into a convex parabola with an extreme point of (XH, YH); the physical/chemical dosage is replaced by the total dosage x and the ratio coefficient k;
the chemical phosphorus removal model is summarized as y = u (kx-XH) 2 +w(1-k)x+b；
Wherein x >0, y > -0, 0 sj k < -1, w > -0, u < -0; XH is the maximum amplitude limiting value of the medicine amount, YH is the maximum setting value of the phosphorus index;
s2, the adaptive PAC dosing basic automation model obtains an iterative formula by loss function partial derivation through a gradient descent method:
wherein k is set by an artificial ratio coefficient, eta is set by a learning step length, and n is set by the learning iteration times; x is a radical of a fluorine atom i For a given dose, y i Is the current feedback value of the TP phosphorus instrument, and XH is set for the maximum value of the dosage; simultaneous loop iteration of formulas (1), (2) and (3) and iterative approximation by a gradient method are carried out to obtain predicted coefficients w, u and b;
s3, determining iteration initial values w0, u0 and b 0; k =0.5, namely the initial state is obtained when the chemical/physical dephosphorization treatment effect is relatively good; b0 value YH, the maximum phosphorus amount to be treated; putting YH, YL, XH and XL into iteration, and calculating w0 and u0 as initial values;
s4, firstly, establishing a self-adaptive PAC dosing basic automation model, and secondly, carrying out iterative algorithm program design according to an equation; the method comprises the steps that a decision jump logic after parameter amplitude limiting is strictly substituted in the iterative algorithm program design process; then determining initial coefficients w0, u0 and b0, empirical coefficient k and amplitude values YH, YL, XH and XL of formulas (1), (2) and (3); then inputting an iteration algorithm for iteration by combining with the actual production value, and solving coefficients w, u and b; and finally, properly adjusting the parameters k, the step length eta and the iteration times n according to production experience, and gradually determining the existing working condition to adapt to an adding rule.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210952977.8A CN115259318B (en) | 2022-08-09 | 2022-08-09 | Self-adaptive PAC dosing basic automation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210952977.8A CN115259318B (en) | 2022-08-09 | 2022-08-09 | Self-adaptive PAC dosing basic automation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115259318A true CN115259318A (en) | 2022-11-01 |
| CN115259318B CN115259318B (en) | 2024-01-09 |
Family
ID=83751928
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210952977.8A Active CN115259318B (en) | 2022-08-09 | 2022-08-09 | Self-adaptive PAC dosing basic automation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115259318B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015157239A (en) * | 2014-02-21 | 2015-09-03 | メタウォーター株式会社 | Method and device for controlling water treatment process |
| CN107601632A (en) * | 2017-10-30 | 2018-01-19 | 清华大学深圳研究生院 | A kind of coagulation Automatic Dosing control method and system |
| CN109188998A (en) * | 2018-10-25 | 2019-01-11 | 成都市自来水有限责任公司 | Water treatment plant PAC Intelligent adding control system based on data fitting method |
| CN113683169A (en) * | 2021-09-18 | 2021-11-23 | 深圳市科荣软件股份有限公司 | Intelligent coagulation chemical dosing method and device for water treatment plant |
-
2022
- 2022-08-09 CN CN202210952977.8A patent/CN115259318B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015157239A (en) * | 2014-02-21 | 2015-09-03 | メタウォーター株式会社 | Method and device for controlling water treatment process |
| CN107601632A (en) * | 2017-10-30 | 2018-01-19 | 清华大学深圳研究生院 | A kind of coagulation Automatic Dosing control method and system |
| CN109188998A (en) * | 2018-10-25 | 2019-01-11 | 成都市自来水有限责任公司 | Water treatment plant PAC Intelligent adding control system based on data fitting method |
| CN113683169A (en) * | 2021-09-18 | 2021-11-23 | 深圳市科荣软件股份有限公司 | Intelligent coagulation chemical dosing method and device for water treatment plant |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115259318B (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106873379B (en) | Sewage treatment optimal control method based on iterative ADP algorithm | |
| CN103011356B (en) | Method for controlling automatic chemical dosing of high-turbidity water system | |
| CN110054274B (en) | Water purification flocculation precipitation dosing control method | |
| CN101825870B (en) | Method and system for controlling supply quantity of water-treatment flocculating agent | |
| CN105676814A (en) | SFLA-SVM-based digital water island online agent adding control method | |
| EP3938854A1 (en) | Method of performing a process and optimizing control signals used in the process | |
| CN110981021B (en) | Intelligent dosing system and method for advanced wastewater oxidation treatment based on fuzzy BP neural network | |
| KR101889510B1 (en) | Method of estimating coagulant injection rate in water treatment using deep neural network | |
| CN102616927A (en) | Adjusting method of technological parameters of sewage treatment and device | |
| CN113687040A (en) | Decision tree algorithm-based water plant real-time dosing quantity prediction method, device and medium | |
| CN114380378B (en) | Intelligent phosphorus control drug feeding method and device and storage medium | |
| CN110357236B (en) | Sewage plant intelligent control method based on mutation inversion effluent prediction model | |
| CN111709585A (en) | Air conditioner load prediction method and device and storage medium | |
| CN115259318A (en) | Self-adaptive PAC dosing basic automation method | |
| CN109437456B (en) | Heavy metal wastewater purification control method based on dynamic matching of operation modes | |
| Chaimberg et al. | Kinetic modeling of free-radical polymerization: a conservational polymerization and molecular weight distribution model | |
| CN115481720A (en) | Coagulant dosing amount prediction method based on BR-NARX neural network | |
| CN109271753A (en) | The process parameter optimizing method of vanadium wastewater ammonia nitrogen recycling based on response surface analysis | |
| CN115108595A (en) | Intelligent water purifying agent adding method based on machine learning | |
| CN110671340B (en) | Flow self-adaptive adjustment method of single-stage full-adjustment pump station | |
| JP2004121953A (en) | Sewage treatment process simulation method and sewage treatment process simulator | |
| CN1257110C (en) | Flocculating dispensing compound control method | |
| CN113036769A (en) | Static voltage stability analysis method and system for power system | |
| CN112403259B (en) | SCR desulfurization method based on intelligent regulation of flue gas concentration | |
| CN108875927B (en) | Convergence method and device of high-dimensional deep learning model |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |