CN110054274B - Water purification flocculation precipitation dosing control method - Google Patents
Water purification flocculation precipitation dosing control method Download PDFInfo
- Publication number
- CN110054274B CN110054274B CN201910393945.7A CN201910393945A CN110054274B CN 110054274 B CN110054274 B CN 110054274B CN 201910393945 A CN201910393945 A CN 201910393945A CN 110054274 B CN110054274 B CN 110054274B
- Authority
- CN
- China
- Prior art keywords
- water
- coagulant
- turbidity
- neural network
- pac
- 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.)
- Active
Links
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
Abstract
The invention discloses a control method for chemical dosing of flocculation and precipitation of purified water, which comprises the following steps of firstly preprocessing equipment terminal data in the water treatment process; then constructing a water purification effect index, analyzing the correlation between the water purification effect and the coagulant adding amount, and determining the reaction time of the coagulant; on the basis, a mathematical model among a PH value, raw water turbidity, effluent turbidity, water intake and coagulant input is established based on a BP neural network model of finite residual error fitting; finally, through numerical experiments, a proper dosing scheme is provided for a decision maker of a water plant. The invention fully considers the time lag and nonlinear characteristics of the dosing control system, compared with the existing dosing control technology, the invention can carry out self-adaptive control on the water quality, has stronger anti-interference capability and can better adapt to the change of the control condition.
Description
Technical Field
The invention relates to a water treatment technology, in particular to an intelligent dosing control method for a water supply plant.
Background
Water resources are the foundation for human survival and development and play an irreplaceable role in social progress. With the continuous development of economy, the demand of people for water resources is continuously increased, and the requirement on water quality is higher and higher; however, with the modernization of the industry, the shortage of water resources is more and more serious, and the water quality is more and more poor, so the requirement of the social development on the water purification of the water supply plant is higher and higher. However, sewage treatment plants in China generally have the defects of high energy consumption and low efficiency, so that the water purification process of water supply plants needs to be improved urgently. The coagulation dosing technology is an important technology for improving the water purification efficiency of a water plant, so that how to accurately dose the medicine has a vital practical significance in controlling the cost on the premise of ensuring the water quality.
China controls the coagulation dosage by manual work for a long time, which has high requirements on the experience of operators. In recent thirty years, China enters an automatic dosing control stage, and dosing is performed by combining computer judgment and manual adjustment. In recent years, a chemical dosing control system is in the beginning stage of intelligent control, domestic intelligent water affair related researches are few, and intelligent chemical dosing control is a vigorous development research field. In the existing research of the dosing control system, only the dosage and real-time water content data are mainly concerned, but actually, the coagulation dosing process is a complex physical and chemical reaction process which has time lag and nonlinearity. In addition, the current coagulation dosage control method has some disadvantages: firstly, the beaker experiment method requires frequent experiments every day or every week, which greatly affects the output water quality and consumes much time; secondly, in the flowing current method, the precision of the detector is gradually reduced in the use process and cannot be used in water with high turbidity and serious pollution; thirdly, the mathematical model method is difficult to satisfy the requirements of high precision and high reliability because the coagulation process is very complicated, so that the model fails when the conditions change. In general, the current administration control method has poor robustness, and no self-adaptive water quality control method exists.
Therefore, the existing dosing control system has time lag and poor interference resistance, cannot adapt to the change of the control condition, and needs to be improved.
Disclosure of Invention
In order to solve the problem of controlling the dosage in the process of water treatment flocculation and precipitation in the background technology, the invention provides a coagulant dosage control method, which realizes the real-time control of sewage treatment automation.
The technical scheme adopted by the invention for solving the technical problems is as follows: a coagulant dosage control method in a water treatment flocculation precipitation process comprises the following steps:
step (1), data acquisition and pretreatment are carried out on a water treatment plant equipment terminal;
step (2), calculating the optimal lag time from the reaction of adding a coagulant into raw water to the water outlet after the precipitation is finished according to the acquired data;
step (3), generating training samples by taking the optimal lag time as a time interval, and establishing a BP neural network model based on finite residual error fitting;
and (4) obtaining a coagulant feeding curve through BP neural network model simulation, and determining a coagulant feeding scheme according to the actual effluent turbidity requirement.
Specifically, in the step (1), raw data collected by equipment terminals such as sensors in the water treatment process needs to be preprocessed. The original data comprises a sampling time window, a PH value detected by a sensor, raw water turbidity, sedimentation tank water outlet turbidity, water intake, water supply amount, coagulant input amount and the like. The processing method includes processing of missing values and abnormal values, conversion of time windows, and the like.
(1.1) missing value and abnormal value processing: the missing value is usually generated due to equipment reasons such as sensor failure, and in order to ensure time consistency, a linear interpolation method can be adopted for processing. Abnormal values usually appear on two characteristics of water intake and water supply, and the reason of the abnormal values is usually irregular adjustment of the operation mode of the water plant, the task amount of a plurality of time periods is accumulated to one time period, and at the moment, the water intake of a peak time period needs to be distributed to the time period of data loss.
(1.2) time window transformation: and (2) when the coagulant reaction time is calculated, the original data samples are required to be separated by minutes. If the sampled data is in other dimensions, such as in hours, linear interpolation is required to convert the time window.
Further, in the step (2), the reaction time of the coagulant is determined by analyzing the correlation between the water purification effect and the coagulant addition amount.
(2.1) constructing water purification effect indexes:
by QtIndicates the index of water purification effect, DtAnd WtRespectively the turbidity of the raw water and the water intake at time t, Dt+nAnd Wt+nThe concentration and the water supply amount of the sedimentation tank after n minutes are expressed, and the turbidity after purification needs to be converted to a certain extent by considering the water loss in the water purification process, and the formula is as follows:
(2.2) calculating Water purification Effect QtCorrelation coefficient with coagulant dosage:
taking a correlation coefficient rhonThe maximum n value is used as the best lag time with the strongest correlation between the coagulant adding amount and the water purifying effect.
Wherein D istAnd WtRespectively the turbidity of the raw water and the water intake at time t, Dt+nAnd Wt+nConcentration and water supply to the sedimentation tank after n minutes, QnAs an index sequence of water purification effect, pacnAs a sequence of coagulant dosage amounts, cov (Q)n，pacn) Represents QnAnd pacnCovariance of (a)nAnd σpacRespectively represent QnAnd pacnStandard deviation of (2).
Further, in the step (3), a mathematical model among the PH value, the raw water turbidity, the effluent turbidity, the water intake amount and the coagulant adding amount is established based on a BP neural network model of finite residual error fitting.
And (3.1) generating a training sample according to the coagulant reaction time n calculated in the step (2). Assuming that N records are in total, taking the first N-N records for 4 characteristics of pH value, raw water turbidity, water intake and coagulant input amount, and taking the (N + 1) th to the Nth records for the effluent turbidity characteristics.
(3.2) the classical BP neural network model is easy to fall into a local minimum value because the initial threshold is randomly selected. In order to improve the training precision, the traditional BP neural network model is improved, and considering that the fitting residual still contains predictable information when the training falls into a local minimum value, the method for learning the residual by repeatedly constructing the neural network is adopted, so that the prediction precision is improved, and the model is constructed as follows:
1) by X ═ X1,X2,...,Xn) As input variable, where X1Is the pH value, X2Is the turbidity of raw water, X3For turbidity in the sedimentation tank, X4Taking water quantity;
PAC dosage Y ═ Y1,Y2,...,Ym) A BP neural network is established as a predictor variable,
the predicted PAC dosage output in the first round is recorded as O ═ O (O)1,O2,...,Om) The prediction residual is
2) Constructing a 2 nd BP neural network by taking (X, O) as an input variable and e1 as a prediction variable, predicting the residual error of the 1 st neural network, and outputting the prediction
Having a residual error of
3) Then use
As input object, with e2Constructing a 3 rd neural network as a prediction variable, predicting the residual error of the 2 nd neural network, and repeating the steps;
4) assuming that the residual is fitted M times, the node Y is outputkThe final predicted result of (c) is:
(3.3) in addition to the improvement of residual fitting on the classical BP neural network, in order to solve the defects that the traditional gradient descent method is low in convergence speed and easy to fall into a local minimum value, the Levenberg-Marguardt algorithm (also called damping least square method) is adopted to train the neural network. The method is a nonlinear least square optimization algorithm, is between a Newton method and a gradient descent method, can effectively solve the problem of redundant parameters, and reduces the possibility that the cost function falls into a local minimum value.
In the error training process of the neural network, an error function is defined as:
wherein, tkIs the target value of the kth neuron of the output layer, a2kFor its output value, s2The number of neurons in the output layer. Compared with the traditional gradient descent method which usually adopts the first derivative (namely the gradient) when optimizing the error function and has simple calculation and slow convergence rate, the Newton method considers the information of the second derivative (namely the Hessian matrix) and has complex calculation and fast convergence rate.
The Hessian matrix, denoted H as E (W, B), whose i, j-th element can be represented as:
wherein e ispIndicating the deviation of the prediction of the p-th sample from the target. If the second term in the above equation is omitted, the Hessian matrix can be approximately expressed as H ═ JTJ, the gradient may be expressed as g ═ JTe, wherein, JTThe first derivative of the error function to the weight and the deviation is expressed as a Jacobian matrix; e is the error vector. The iterative formula of the LM algorithm is:
ωn+1＝ωn-[JTJ+μI]-1JTe。
where μ denotes a damping factor. It can be seen that the LM algorithm obtains a high-order training speed without calculating a Hessian matrix by using the concept of approximate calculation of a Jacobian matrix. In the iteration process, the LM algorithm achieves convergence by adaptively adjusting the damping factor, and if the training is successful and the error is reduced, mu is reduced; if training fails, the error increases, increasing μ.
It can be seen that when μ is large, the LM algorithm degenerates to the gradient descent method:
when μ ═ 0, the LM algorithm degenerates to the quasi-newton method:
ωn+1＝ωn-[JTJ]-1JTe。
further, in the step (4), the PH value, the raw water turbidity and the water supply amount measured by the current equipment terminal are substituted into the trained model, numerical experiments are performed on the effluent turbidity of the sedimentation tank and the coagulant dosage, and a decision maker in a water plant can select the most appropriate dosage scheme according to the actual effluent turbidity requirement.
The invention has the beneficial effects that: the invention fully considers the influence of coagulant reaction time on model prediction, combines the actual flow of water treatment flocculation and precipitation, and provides a plurality of coagulant dosing schemes aiming at different water supply requirements.
Drawings
FIG. 1 is a flow chart of flocculation in an embodiment of the present invention.
FIG. 2 is a general flow diagram of an embodiment of the present invention.
FIG. 3 is a graph of correlation coefficients according to an embodiment of the present invention.
FIG. 4 is a graph of mean absolute error in accordance with an embodiment of the present invention.
FIG. 5 is a prediction error frequency histogram according to an embodiment of the present invention.
Fig. 6 is a graph of coagulant dosing concentration and effluent turbidity according to an embodiment of the present invention.
FIG. 7 is a graph of coagulant dosing concentration and turbidity removal rate in accordance with an embodiment of the present invention.
FIG. 8 is a table of sample formats according to an embodiment of the present invention.
Detailed Description
The embodiments of the invention will be further described with reference to the accompanying drawings in which:
the invention takes a certain water purification plant in Guangzhou as an example research object, the flocculation precipitation process is shown in figure 1, and the flocculation precipitation is an initial link of water treatment and is a necessary process for treating impurities such as suspended particles, colloid and the like. Factors influencing the flocculation effect are many, including raw water flow, raw water turbidity, raw water pH value, raw water temperature, coagulant dosage, algae in raw water and the like. The dosing control is to comprehensively consider the factors to dose the coagulant, thereby achieving the satisfactory flocculation effect. The administration control protocol study is shown in fig. 2, and the steps are described in detail below.
Step (1), preprocessing of sampling data
The real-time data of a water treatment plant dosing control system is taken as an example raw sample, the data are instantaneous measured values, the water intake is the flow rate of raw water, the water supply is the flow rate of factory water (water loss caused by partial process after a sedimentation tank), the unit of the water intake and the water supply is m3/h (cubic meter per hour), the PAC consumption is the consumption of a coagulant PAC, and the unit is mg/L (1L of raw water consumes the PAC). The sample format is shown in fig. 8.
2013.08.08-2014.09.05 is covered by an original data time window, a total of 9397 data are obtained, 288 PAC sample records with missing dosage are deleted according to the data preprocessing method in the step 1, the data account for 3.06% of the total data, 4 days of 2014.03.28, 2014.05.27, 2014.06.20 and 2014.09.04 are found, the water intake and water supply data are abnormal, linear interpolation processing is adopted, and the increased data amount accounts for 0.51% of the total data amount. The time interval of the original samples is 1 hour, in order to conveniently calculate the drug administration reaction time, a linear interpolation method is adopted, the time interval is converted into minutes, and 547381 sample data are processed.
Step (2) calculating the time from the reaction of adding the coagulant into the raw water to the water yielding after the precipitation is finished
According to the method, a water purification effect index is constructed, and a correlation coefficient between the index and the PAC coagulant adding amount is calculated, as shown in FIG. 3. It can be found that when the lag phase is 125 minutes, the correlation between the PAC coagulant dosage and the water purification effect is strongest, so the lag reaction time is 125 minutes in the embodiment.
Step (3) establishing a mathematical model about the quality of raw water, the water intake, the turbidity of outlet water and the coagulant adding amount
And (4) generating a training sample according to the coagulant reaction time calculated in the step (2). 547381 sample data are obtained after pretreatment in the step 1, 547256 records are obtained before 4 characteristics of pH value, raw water turbidity, water intake and coagulant input amount, 126 th to 547381 th records are obtained for effluent turbidity characteristics, and 547256 records are obtained in total for the treated data set. The data set is divided according to the proportion of 80 percent of the training set and 20 percent of the testing set to obtain 437805 data of the training set and 109451 data of the testing set. Substituting the data set into the residual fitting BP neural network for training and testing, wherein the PH value, raw water turbidity, sedimentation tank turbidity and water intake are used as independent variables in the 1 st training, the PAC dosage is used as a dependent variable, and the later 4 times of training are used as residual fitting training. The number of hidden neurons of the neural network takes an empirical value of 2I +1, wherein I represents the number of input neurons. The input neurons for 5 times of training are respectively 4,5,6,7 and 8; the number of hidden neurons is 9,11,13,15, and 17, respectively, the average absolute error of the model on the test set is shown in fig. 4, and the distribution of the prediction error is shown in fig. 5.
Step (4) solving the current optimal coagulant adding amount
Given the current water treatment parameters: the pH is 6.8, the original turbidity is 100NTU, the water intake is 9000m3/h, namely 150m3/min, the turbidity of the effluent of the sedimentation tank is required to be less than 1.1NTU, and the simulation experiment is carried out as follows:
the interval of effluent turbidity is taken as [0.6,1.1], an experimental sample is taken every 0.5 and is substituted into the trained model, and the relation between the effluent turbidity and the PAC coagulant throwing concentration is obtained and is shown in FIG. 7. Fig. 7 shows the relationship between turbidity removal rate and PAC coagulant feed concentration, where turbidity removal rate is defined as (raw water turbidity-effluent turbidity)/raw water turbidity. It can be seen that the turbidity removing effect of PAC coagulant feeding has the marginal decreasing effect, and the most economic PAC feeding concentration can be selected by a water purification plant according to the actual effluent turbidity requirement.
The skilled person should understand that: although the invention has been described in terms of the above specific embodiments, the inventive concept is not limited thereto and any modification applying the inventive concept is intended to be included within the scope of the patent claims.
Claims (3)
1. A water purification flocculation precipitation dosing control method is characterized by comprising the following steps:
step (1), carry out data acquisition and carry out the preliminary treatment to water treatment plant equipment terminal, the preliminary treatment includes: processing missing values and abnormal values in the acquired data by adopting a linear interpolation method, and unifying the sampling time interval unit and the calculated time unit;
step (2), calculating the optimal lag time from the reaction of raw water adding a coagulant to the water yielding after the precipitation is finished according to the collected data, and specifically comprising the following steps: constructing a water purification effect index sequence according to the collected data:
calculating a correlation coefficient between the water purification effect index sequence and the coagulant adding quantity sequence:
taking a correlation coefficient rhonThe maximum n value is used as the best lag time with the strongest correlation between the coagulant adding amount and the water purification effect;
wherein D istAnd WtRespectively the turbidity of the raw water and the water intake at time t, Dt+nAnd Wt+nConcentration and water supply to the sedimentation tank after n minutes, QnAs an index sequence of water purification effect, pacnAs a sequence of coagulant dosage amounts, cov (Q)n，pacn) Represents QnAnd pacnCovariance of (a)nAnd σpacRespectively represent QnAnd pacnStandard deviation of (d);
step (3), generating training samples by taking the optimal lag time as a time interval, and establishing a BP neural network model based on finite residual error fitting;
and (4) obtaining a coagulant feeding curve through BP neural network model simulation, and determining a coagulant feeding scheme according to the actual effluent turbidity requirement.
2. The water purification flocculation precipitation dosing control method as claimed in claim 1, wherein: the data comprises PH value, raw water turbidity, raw water flow, coagulant adding amount, concentration of a sedimentation tank, effluent turbidity and water taking amount.
3. The water purification flocculation precipitation dosing control method as claimed in claim 1, wherein: in the step (3), a BP neural network model based on finite residual error fitting is needed to establish a mathematical model among a PH value, raw water turbidity, effluent turbidity, water intake and coagulant adding amount, and the method specifically comprises the following steps:
1) by X ═ X1,X2,...,Xn) As input variable, where X1Is the pH value, X2Is the turbidity of raw water, X3For turbidity in the sedimentation tank, X4Taking water quantity;
PAC dosage Y ═ Y1,Y2,...,Ym) A BP neural network is established as a predictor variable,
the predicted PAC dosage output in the first round is recorded as O ═ O (O)1,O2,...,Om) The prediction residual is
2) Constructing a 2 nd BP neural network by taking (X, O) as an input variable and e1 as a prediction variable, predicting the residual error of the 1 st neural network, and outputting the prediction
Having a residual error of
3) Then use
As input object, with e2Constructing a 3 rd neural network as a prediction variable, predicting the residual error of the 2 nd neural network, and repeating the steps;
4) assuming that the residual is fitted M times, the node Y is outputkThe final predicted result of (c) is:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910393945.7A CN110054274B (en) | 2019-05-13 | 2019-05-13 | Water purification flocculation precipitation dosing control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910393945.7A CN110054274B (en) | 2019-05-13 | 2019-05-13 | Water purification flocculation precipitation dosing control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110054274A CN110054274A (en) | 2019-07-26 |
| CN110054274B true CN110054274B (en) | 2022-03-15 |
Family
ID=67322870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910393945.7A Active CN110054274B (en) | 2019-05-13 | 2019-05-13 | Water purification flocculation precipitation dosing control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110054274B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110426957B (en) * | 2019-07-31 | 2020-03-13 | 深圳信息职业技术学院 | Water plant dosing system self-adaptive sliding mode control method based on time delay observer |
| CN110980898A (en) * | 2019-10-11 | 2020-04-10 | 浙江华晨环保有限公司 | Medicament adding system of water purifying equipment |
| CN111783289B (en) * | 2020-06-19 | 2024-01-30 | 浙江大学 | Seawater coagulation dosing method based on model prediction |
| CN112766384A (en) * | 2021-01-24 | 2021-05-07 | 湖南大学 | Deep learning-based algae floc removal rate evaluation method |
| CN113582309A (en) * | 2021-07-28 | 2021-11-02 | 长三角(义乌)生态环境研究中心 | Method and device for determining coagulant adding amount |
| CN113778028B (en) * | 2021-08-12 | 2023-09-26 | 西安交通大学 | Bian Yun cooperation and double increment based intelligent coagulation algorithm |
| CN114275867A (en) * | 2021-12-25 | 2022-04-05 | 盐城工学院 | Intelligent coagulating sedimentation integrated device |
| CN115072849B (en) * | 2022-07-21 | 2022-11-11 | 江苏中安建设集团有限公司 | Water resource treatment process control method for water supply and drainage engineering |
| CN116976854B (en) * | 2023-07-31 | 2024-03-19 | 深圳市科荣软件股份有限公司 | Intelligent inspection system for water works based on Internet of things |
| CN117275615B (en) * | 2023-10-31 | 2024-04-09 | 源康(东阿)健康科技有限公司 | Intelligent treatment method and system for gelatin production wastewater |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080035577A1 (en) * | 2004-02-12 | 2008-02-14 | Uniqkleen-Wastewater Treatment Ltd. | System and Method for Treatment of Industrial Wastewater |
| CN101825870A (en) * | 2010-05-18 | 2010-09-08 | 浙江浙大中控信息技术有限公司 | Method and system for controlling supply quantity of water-treatment flocculating agent |
| CN106168759A (en) * | 2016-07-12 | 2016-11-30 | 武汉长江仪器自动化研究所有限公司 | A kind of coagulant dosage control method and system based on artificial neural network algorithm |
| CN108975553A (en) * | 2018-08-03 | 2018-12-11 | 华电电力科学研究院有限公司 | A kind of thermal power plant's coal-contained wastewater processing coagulant charging quantity accuracy control method |
-
2019
- 2019-05-13 CN CN201910393945.7A patent/CN110054274B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080035577A1 (en) * | 2004-02-12 | 2008-02-14 | Uniqkleen-Wastewater Treatment Ltd. | System and Method for Treatment of Industrial Wastewater |
| CN101825870A (en) * | 2010-05-18 | 2010-09-08 | 浙江浙大中控信息技术有限公司 | Method and system for controlling supply quantity of water-treatment flocculating agent |
| CN106168759A (en) * | 2016-07-12 | 2016-11-30 | 武汉长江仪器自动化研究所有限公司 | A kind of coagulant dosage control method and system based on artificial neural network algorithm |
| CN108975553A (en) * | 2018-08-03 | 2018-12-11 | 华电电力科学研究院有限公司 | A kind of thermal power plant's coal-contained wastewater processing coagulant charging quantity accuracy control method |
Non-Patent Citations (1)
| Title |
|---|
| 基于有限次残差拟合的BP 神经网络组合模型;杨程炜;《广东水利电力职业技术学院学报》;20150630;第13卷(第2期);第32页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110054274A (en) | 2019-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110054274B (en) | Water purification flocculation precipitation dosing control method | |
| CN108898215B (en) | Intelligent sludge bulking identification method based on two-type fuzzy neural network | |
| JP6609808B2 (en) | Prediction program using decision tree learning algorithm, apparatus and method | |
| CN109583663B (en) | Night water dissolved oxygen amount prediction method suitable for aquaculture pond | |
| CN110824923A (en) | Sewage treatment control method and system based on deep learning and cloud computing | |
| CN105301960B (en) | A kind of control method of tap water flocculant dosage | |
| CN112817299A (en) | Industrial wastewater treatment data management cloud platform and control method thereof | |
| CN111994970A (en) | LSTM-based dosing prediction method and dosing system for efficient sewage sedimentation tank | |
| CN114849316A (en) | Automatic control system for intelligent backwashing filtration | |
| CN115527628A (en) | Online control method and system for municipal sewage chemical phosphorus removal process | |
| CN114380379B (en) | Chemical adding control method and system for slime water | |
| CN115611393A (en) | Multi-end cooperative coagulant feeding method and system for multiple water plants | |
| CN105372995B (en) | Sewage disposal system investigating method | |
| CN115793471B (en) | Adjustable control method and system based on sewage treatment monitoring | |
| CN116956156A (en) | Sewage treatment intelligent aeration method and system based on artificial intelligence | |
| CN116640886A (en) | Fermentation control method, device, equipment and readable storage medium | |
| CN102053568B (en) | Accident modeling and data drive water quality control system and induced intervention control method | |
| CN114693493B (en) | IoT-based polluted river water ecological restoration system | |
| CN103942600B (en) | Sludge bulking Forecasting Methodology based on spike self-organizing radial base neural net | |
| CN114149076B (en) | Intelligent debugging system of anaerobic ammonia oxidation sewage treatment system | |
| Sengul et al. | Prediction of optimal coagulant dosage in drinking water treatment by artificial neural network | |
| CN113487062A (en) | Power load prediction method based on periodic automatic encoder | |
| CN114349188A (en) | Self-adaptive intelligent oxygen control method in sewage treatment biochemical process | |
| CN109165247B (en) | Intelligent pretreatment method for sewage measurement data | |
| CN113156074A (en) | Effluent total nitrogen prediction method based on fuzzy migration |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221207 Address after: 518000 1405, Building 1, Longguang Century Building, No.23 Haixiu Road, Binhai Community, Xin'an Street, Bao'an District, Shenzhen, Guangdong Patentee after: Shenzhen Jiangxing Smart Energy Technology Co.,Ltd. Address before: 518110 707, floor 7, No. 3, Minglang Road, Xinshi community, Dalang street, Longhua District, Shenzhen, Guangdong Patentee before: Shenzhen Jianghang Lianjia Intelligent Technology Co.,Ltd. |