CN108375534A - MBR fouling membrane intelligent early-warning methods - Google Patents
MBR fouling membrane intelligent early-warning methods Download PDFInfo
- Publication number
- CN108375534A CN108375534A CN201810117548.2A CN201810117548A CN108375534A CN 108375534 A CN108375534 A CN 108375534A CN 201810117548 A CN201810117548 A CN 201810117548A CN 108375534 A CN108375534 A CN 108375534A
- Authority
- CN
- China
- Prior art keywords
- output
- layer
- mbr
- neuron
- moment
- 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
- 239000012528 membrane Substances 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000035699 permeability Effects 0.000 claims abstract description 40
- 238000013528 artificial neural network Methods 0.000 claims abstract description 28
- 230000000306 recurrent effect Effects 0.000 claims abstract description 26
- 239000010865 sewage Substances 0.000 claims abstract description 16
- 230000008569 process Effects 0.000 claims abstract description 12
- 238000013461 design Methods 0.000 claims abstract description 3
- 230000006870 function Effects 0.000 claims description 34
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 29
- 210000002569 neuron Anatomy 0.000 claims description 27
- 238000004519 manufacturing process Methods 0.000 claims description 8
- 210000004205 output neuron Anatomy 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 6
- 229910002651 NO3 Inorganic materials 0.000 claims description 4
- NHNBFGGVMKEFGY-UHFFFAOYSA-N Nitrate Chemical compound [O-][N+]([O-])=O NHNBFGGVMKEFGY-UHFFFAOYSA-N 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 210000005036 nerve Anatomy 0.000 claims description 3
- 230000001537 neural effect Effects 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 claims description 2
- 238000012937 correction Methods 0.000 claims description 2
- 238000004836 empirical method Methods 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims description 2
- 238000000691 measurement method Methods 0.000 claims description 2
- 238000011160 research Methods 0.000 claims description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims 1
- 230000002596 correlated effect Effects 0.000 claims 1
- 230000000875 corresponding effect Effects 0.000 claims 1
- 229910052760 oxygen Inorganic materials 0.000 claims 1
- 239000001301 oxygen Substances 0.000 claims 1
- 230000007774 longterm Effects 0.000 abstract description 2
- 230000000116 mitigating effect Effects 0.000 abstract description 2
- 230000004927 fusion Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 239000010802 sludge Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- JEGUKCSWCFPDGT-UHFFFAOYSA-N h2o hydrate Chemical compound O.O JEGUKCSWCFPDGT-UHFFFAOYSA-N 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000004065 wastewater treatment Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/08—Investigating permeability, pore-volume, or surface area of porous materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/08—Investigating permeability, pore-volume, or surface area of porous materials
- G01N2015/086—Investigating permeability, pore-volume, or surface area of porous materials of films, membranes or pellicules
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Dispersion Chemistry (AREA)
- Separation Using Semi-Permeable Membranes (AREA)
Abstract
It takes place frequently for fouling membrane event in MBR sewage disposal process, endanger the problems such as huge, the present invention proposes MBR fouling membrane intelligent early-warning methods, specially a kind of MBR fouling membrane intelligent early-warning methods based on Recurrent Fuzzy Neural Network realize the online accurate early warning to fouling membrane；The method for early warning realizes the prediction steady in a long-term to permeability rate by building Recurrent Fuzzy Neural Network soft-sensing model, based on recurrence multi-step prediction strategy, realizes the Accurate Prediction to fouling membrane；The on-line early warning to fouling membrane is realized based on operation data design early warning rule using the fusion of permeability rate predicted value and relevant parameter variable；Solve the problems, such as that it is difficult to predict improve the pretreatment potentiality to fouling membrane, endangered caused by mitigating fouling membrane, ensure MBR sewage disposal process safe operations, promote the efficient stable operation of MBR sewage treatment plants fouling membrane in MBR sewage disposal process.
Description
Technical field
The present invention relates to the fouling membrane intelligent early-warning methods of MBR sewage disposal process；Using Recurrent Fuzzy Neural Network and
Multi-step prediction strategy realizes the multi-step prediction of film permeability rate, the class of pollution is judged using early warning rule, by intelligent early-warning side
Method is applied to MBR treated sewage processes, realizes the early warning to fouling membrane, ensures the operation of sewage treatment plant's stability and high efficiency.Film
Pollution prewarning system not only belongs to water treatment field, but also belongs to field of intelligent control.
Background technology
MBR sewage treatment process with membrane module replace traditional biological treatment technology end secondary settling tank, be one kind by activity
The Novel sewage treatment technology that sludge is combined with membrane separation technique.In recent years, with the continuous maturation of membrane technology, film skill
Art is applied more and more extensive in municipal sewage treatment.Compared with traditional waste water treatment process, membrane technology is at municipal sewage
Reason field advantage is fairly obvious, including effluent quality it is good and stablize, sludge concentration is high, floor space is small, flexible operation, automatic
Change degree is high.However, film, during filter sewage, the pollutant for separation of shutting off must generate film pollution to cause out
The decline of water water quality；To mitigate fouling membrane, film needs are regularly cleaned replacement operation, this will necessarily increase energy consumption and fortune
Row cost, therefore the harm for how mitigating fouling membrane is a topic for needing persistently to pay close attention to.
The present invention relates to a kind of MBR fouling membranes intelligent early-warning method, this method is using Recurrent Fuzzy Neural Network and passs
Multi-step prediction strategy is returned to realize that permeability rate is long-term, accurately predicts；On the basis of Accurate Prediction, in conjunction with early warning rule, realize
Online accurate early warning to fouling membrane.It may be implemented before water quality deteriorates, can propose prediction police ahead of time, and
Take corresponding measure in time.Fouling membrane processing cost greatly reduces in the method for early warning, and one kind is provided for sewage treatment plant
Effective reply means, substantially increase the benefit of water factory.
Invention content
1. a kind of MBR fouling membrane intelligent early-warning methods based on Recurrent Fuzzy Neural Network, it is characterised in that：
MBR fouling membrane intelligent early-warnings method mainly realizes pollution prewarning by being discharged permeability rate prediction to MBR films, wherein
MBR films, which are discharged permeability rate and are based on Recurrent Fuzzy Neural Network, carries out multi-step prediction, MBR fouling membranes knowledge based and rule base into
Row early warning；Specifically include following steps：
(1) MBR films are discharged permeability rate multi-step prediction：
1) input variable and output variable of water outlet permeability rate soft-sensing model are determined；With membrane bioreactor-MBR sewage
Processing system is research object, carries out signature analysis to water quality data, extraction production water flow, production water pressure, single pond film clean gas
Amount, anaerobic zone ORP and aerobic zone nitrate are as input variable, to be discharged permeability rate as output variable；
2) water outlet permeability rate soft-sensing model is established；During Recurrent Fuzzy Neural Network design MBR treated sewages
The soft-sensing model of prediction water outlet permeability rate, the topological structure of water outlet permeability rate soft-sensing model are divided into four layers：Input layer, person in servitude
Membership fuction layer, rules layer, output layer；Topological structure is the connection type (2 of 5-R-R-1<R<30), input layer and membership function
Connection weight between layer is 1, and the desired output of Recurrent Fuzzy Neural Network is expressed as yd(t), reality output is expressed as y
(t)；The multi-step prediction flexible measurement method calculating of water outlet permeability rate based on Recurrent Fuzzy Neural Network is followed successively by：
1. input layer：The layer is made of 5 neurons, output be,
X (t)=[x1(t),x2(t),…,x5(t)]T (1)
Wherein, x (t) indicates the output of t moment input layer, x1(t) value, the x of t moment production water flow are indicated2(t) when indicating t
Carve value, the x of production water pressure3(t) indicate that t moment list pond film cleans the value of tolerance, x4(t) indicate t moment anaerobic zone ORP value,
x5(t) value of t moment aerobic zone nitrate is indicated；
2. membership function layer：The layer is made of R neuron, and the output of each neuron is,
Wherein φj(t) be t moment membership function j-th of neuron of layer output, cj(t) it is that t moment is subordinate to letter j-th
The center vector of several layers of neuron, cj(t)=[c1j(t),c2j(t),…,cij(t)], i=1,2 ... 5, cij(t) it indicates to be subordinate to
I-th of element of j-th of neuronal center value of function layer t moment,For the width of j-th of membership function layer neuron of t moment
Degree vector,dij(t) j-th of nerve of membership function layer t moment is indicated
I-th of element of first width value；
3. rules layer：Recurrent Fuzzy Neural Network rules layer add self feed back connection, the neuron number of this layer and
Membership function layer is identical, is R, and the output of each neuron is,
Wherein vj(t) be j-th of neuron of t moment rules layer output, vj(t-1) it is j-th of god of t-1 moment rules layer
Output through member, φj(t) be t moment membership function j-th of neuron of layer output,It is exported for membership function
With；
4. output layer：Output layer output is the reality output of water outlet permeability rate soft-sensing model,
Y (t) is the output of t moment output neuron, wj(t) j-th of neuron of t moment rules layer and output nerve are indicated
Weights between member define Recurrent Fuzzy Neural Network soft-sensing model output y (t) and desired output yd(t) error function
E (t) is：
E (t)=yd(t)-y(t) (5)
3) MBR is discharged permeability rate hard measurement recurrence multi-step prediction strategy：Multi-step prediction can not only forecasting system current letter
Breath, moreover it is possible to predict that the information of hereafter multistep, recurrence multi-step prediction strategy consider the correlation between prediction data, be walked according to prediction
Several differences, process are as follows：
Wherein h ∈ (1 ..., H) are the prediction step numbers of multi-step prediction, and d is the dimension of input variable, is also the step number of time delay,
Y (t+h) is the output of output neuron after the following h steps；
4) MBR is discharged the correction of permeability rate soft-sensing model, and process is as follows：
1. given neural network membership function layer and rules layer neuron number R, R are natural number, R is true by empirical method
Fixed, the training input for being discharged the soft-sensing model of permeability rate is x (1), x (2) ..., x (t) ..., x (N), and corresponding expectation is defeated
Go out yd(1), yd(2) ..., yd(t) ..., yd(N), the training sample of soft-sensing model is N groups, and anticipation error is set as Ed, iteration
Step number is set as s, calculates cost function value E (t), stopping criterion is defined, as E (t)<Ed, enable t=0；
The cost function E (t) of network is defined,
2. setting study step number s=s+1；Calculating membrane water outlet permeability rate intelligent characteristic model output y (t), error e (t),
Calculate vector J (t), wherein
Intending sea plucked instrument matrix Q (t) calculation formula is,
Q (t)=JT(t)J(t) (9)
Gradient vector g (t) calculation formula are,
G (t)=JT(t)e(t) (10)
Wherein, error calculates as follows about the partial derivative of parameters；
Calculate partial derivative of the error about center
Calculate partial derivative of the error about width
Calculate partial derivative of the error about weights
3. using the parameter of Adaptive Second-Order algorithm update Recurrent Fuzzy Neural Network,
Δ (t+1)=Δ (t)+(Q (t)+λ (t) I)-1g(t) (14)
Wherein, I is unit matrix, Δ=[w1(t) ... wR(t), c11(t) ... c51(t) ..., c1j(t) ... c5j
(t) ... c1R(t) ... c5R(t), d11(t) ... d51(t) ..., d1j(t) ... d5j(t) ... d1R(t) ... d5R(t)], wj(t) table
Show the weights between j-th of neuron of t moment rules layer and output neuron, cij(t) be membership function layer center, dij
(t) be membership function layer width；
Wherein, autoadapted learning rate λ (t) is,
λ (t)=θ | | e (t) | |+(1- θ) | | g (t) | | (15)
0<θ<1 is real parameter, and e (t) is error vector；
4. cost function E (t) is calculated, when meeting precision E (t)<Ed, otherwise 2. iteration stopping jumps to step；
Using test sample data as training after Recurrent Fuzzy Neural Network input, Recurrent Fuzzy Neural Network it is defeated
Go out to be discharged the predicted value of permeability rate as film,
(2) warning function of MBR fouling membranes early warning system：After the description that the priori of specific field is formalized, shape
At system convention.For rule base for storing relevant rule knowledge, each rule in rule base signifies certain in the field
The answer of some similar problems, the ability that ordinary user can be made to possess difficult problem in the solution field same with expert.Film
Pollute the adjustment that intelligent early-warning system supports early warning rule base and threshold value of warning, it can be artificial with artificial experience according to actual needs
Dependency rule in increase or alteration ruler library.
(--- indicate that the size without consideration value, the recovery rate of permeability rate are the ratio of the front and back permeability rate of on-line/off-line cleaning
Value)
Description of the drawings
Fig. 1 is MBR fouling membrane method for early warning framework maps；
Fig. 2 Recurrent Fuzzy Neural Network structure charts；
Fig. 3 is discharged permeability rate soft-sensing model multistep (5 steps, 10 steps, 15 steps) prediction result figure, and wherein black line zone circle is
Permeability rate actual value, black line band point are the predicted value of Recurrent Fuzzy Neural Network soft-sensing model.
Specific implementation mode
(1) MBR fouling membranes intelligent early-warning system is embodied
1. the on-line checking instrument by being placed in technique scene acquires input variable, the variable that need to be acquired includes 5 kinds,
Parameter information and acquisition position are as shown in table 1.
The process variable type that table 1 acquires
2. building the soft-sensing model of the vertical water outlet permeability rate in pond using Recurrent Fuzzy Neural Network and multi-step prediction strategy, use
The data acquired in real time are trained and test to Recurrent Fuzzy Neural Network.80 groups of data are selected to be tested.The number of acquisition
According to as shown in table 2.
3. the water outlet permeability rate soft-sensing model to foundation is corrected, obtained prediction result figure is respectively shown in Fig. 3.
2 soft-sensing model test data of table
Claims (1)
1.MBR fouling membrane intelligent early-warning methods, it is characterised in that：
Realize that pollution prewarning, wherein MBR films water outlet permeability rate are based on recurrence fuzzy neural by being discharged permeability rate prediction to MBR films
Network carries out multi-step prediction, and MBR fouling membranes knowledge based and rule base carry out early warning；Specifically include following steps：
(1) MBR films are discharged permeability rate multi-step prediction：
1) input variable and output variable of water outlet permeability rate soft-sensing model are determined；With membrane bioreactor-MBR sewage disposals
System is research object, carries out signature analysis to water quality data, extraction production water flow, production water pressure, single pond film are cleaned tolerance, detested
Oxygen area ORP and aerobic zone nitrate are discharged permeability rate as output variable as input variable using MBR films；
2) water outlet permeability rate soft-sensing model is established；Utilize prediction during Recurrent Fuzzy Neural Network design MBR treated sewages
It is discharged the soft-sensing model of permeability rate, the topological structure of water outlet permeability rate soft-sensing model is divided into four layers：Input layer, membership function
Layer, rules layer, output layer；Topological structure is the connection type of 5-R-R-1, wherein 2<R<30, input layer and membership function layer it
Between connection weight be 1, the desired output of Recurrent Fuzzy Neural Network is expressed as yd(t), reality output is expressed as y (t)；It is based on
The multi-step prediction flexible measurement method calculating of the MBR films water outlet permeability rate of Recurrent Fuzzy Neural Network is followed successively by：
1. input layer：The layer is made of 5 neurons, output be,
X (t)=[x1(t),x2(t),…,x5(t)]T (1)
Wherein, x (t) indicates the output of t moment input layer, x1(t) value, the x of t moment production water flow are indicated2(t) t moment production is indicated
The value of water pressure, x3(t) indicate that t moment list pond film cleans the value of tolerance, x4(t) value, the x of t moment anaerobic zone ORP are indicated5(t)
Indicate the value of t moment aerobic zone nitrate；
2. membership function layer：The layer is made of R neuron, and the output of each neuron is,
WhereinIt is the output of t moment membership function j-th of neuron of layer, cj(t) it is j-th of membership function layer nerve of t moment
The center vector of member, cj(t)=[c1j(t),c2j(t),…,cij(t)], i=1,2 ... 5, cij(t) when indicating membership function layer t
I-th of element of j-th of neuronal center value is carved,It is vectorial for the width of j-th of membership function layer neuron of t moment,dij(t) i-th yuan of membership function layer j-th of neuron width value of t moment is indicated
Element；
3. rules layer：Recurrent Fuzzy Neural Network adds self feed back connection in rules layer, the neuron number of this layer and is subordinate to
Function layer is identical, is R, and the output of each neuron is,
Wherein vj(t) be j-th of neuron of t moment rules layer output, vj(t-1) it is t-1 moment j-th of neuron of rules layer
Output,It is the output of t moment membership function j-th of neuron of layer,For the sum of membership function output；
4. output layer：Output layer output is the reality output that MBR films are discharged permeability rate soft-sensing model,
Y (t) is the output of t moment output neuron, wj(t) indicate j-th of neuron of t moment rules layer and output neuron it
Between weights, define Recurrent Fuzzy Neural Network soft-sensing model output y (t) with desired output yd(t) error function e (t)
For：
E (t)=yd(t)-y(t) (5)
3) MBR films are discharged permeability rate hard measurement recurrence multi-step prediction strategy：Multi-step prediction can not only forecasting system current information,
It can also predict that the information of hereafter multistep, recurrence multi-step prediction strategy consider the correlation between prediction data, according to prediction step number
Difference, process are as follows：
Wherein h ∈ (1 ..., H) are the prediction step numbers of multi-step prediction, and d is the dimension of input variable, is also the step number of time delay, y (t+
H) be output neuron after following h step output；
4) correction of MBR films water outlet permeability rate soft-sensing model, process are as follows：
1. given neural network membership function layer and rules layer neuron number R, R are natural number, R is determined by empirical method, MBR
The training input that film is discharged the soft-sensing model of permeability rate is x (1), x (2) ..., x (t) ..., x (N), corresponding desired output
yd(1), yd(2) ..., yd(t) ..., yd(N), the training sample of soft-sensing model is N groups, and anticipation error is set as Ed, iterative steps
It is set as s, calculates cost function value E (t), stopping criterion is defined, as E (t)<Ed, enable t=0；
The cost function E (t) of network is defined,
2. setting study step number s=s+1；Calculate MBR films water outlet permeability rate intelligent characteristic model output y (t), error e (t),
Calculate vector J (t), wherein
Intending sea plucked instrument matrix Q (t) calculation formula is,
Q (t)=JT(t)J(t) (9)
Gradient vector g (t) calculation formula are,
G (t)=JT(t)e(t) (10)
Wherein, error calculates as follows about the partial derivative of parameters；
Calculate partial derivative of the error about center
Calculate partial derivative of the error about width
Calculate partial derivative of the error about weights
3. using the parameter of Adaptive Second-Order algorithm update Recurrent Fuzzy Neural Network,
Δ (t+1)=Δ (t)+(Q (t)+λ (t) I)-1g(t) (14)
Wherein, I is unit matrix, Δ=[w1(t) ... wR(t), c11(t) ... c51(t) ..., c1j(t) ... c5j(t) ... c1R
(t) ... c5R(t), d11(t) ... d51(t) ..., d1j(t) ... d5j(t) ... d1R(t) ... d5R(t)], wj(t) t moment rule are indicated
The then weights between j-th of neuron of layer and output neuron, cij(t) be membership function layer center, dij(t) it is to be subordinate to letter
Several layers of width；
Wherein, autoadapted learning rate λ (t) is,
λ (t)=θ | | e (t) | |+(1- θ) | | g (t) | | (15)
0<θ<1 is real parameter, and e (t) is error vector；
4. cost function E (t) is calculated, when meeting precision E (t)<Ed, otherwise 2. iteration stopping jumps to step；
Using test sample data as the input of the Recurrent Fuzzy Neural Network after training, the output of Recurrent Fuzzy Neural Network is
The predicted value of permeability rate is discharged for film；
(2) MBR fouling membranes early warning
The correlated condition of membrane bioreactor-MBR sewage disposal systems field alarm early warning is described as early warning rule, to MBR
Fouling membrane carries out early warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810117548.2A CN108375534A (en) | 2018-02-06 | 2018-02-06 | MBR fouling membrane intelligent early-warning methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810117548.2A CN108375534A (en) | 2018-02-06 | 2018-02-06 | MBR fouling membrane intelligent early-warning methods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108375534A true CN108375534A (en) | 2018-08-07 |
Family
ID=63017374
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810117548.2A Pending CN108375534A (en) | 2018-02-06 | 2018-02-06 | MBR fouling membrane intelligent early-warning methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108375534A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109133351A (en) * | 2018-08-29 | 2019-01-04 | 北京工业大学 | Membrane bioreactor-MBR fouling membrane intelligent early-warning method |
| CN109473182A (en) * | 2018-11-12 | 2019-03-15 | 北京北排科技有限公司 | A kind of MBR film permeability rate intelligent detecting method based on deepness belief network |
| CN111204842A (en) * | 2019-12-23 | 2020-05-29 | 光大环境科技（中国）有限公司 | Method, device and system for realizing ultrafiltration membrane pollution evaluation through neural network |
| CN112101402A (en) * | 2020-07-22 | 2020-12-18 | 北京工业大学 | Membrane pollution early warning method based on knowledge fuzzy learning |
| CN112488286A (en) * | 2019-11-22 | 2021-03-12 | 大唐环境产业集团股份有限公司 | MBR membrane pollution online monitoring method and system |
| CN113274885A (en) * | 2021-03-24 | 2021-08-20 | 重庆工商大学 | Membrane pollution intelligent early warning method applied to membrane sewage treatment |
| CN113283481A (en) * | 2021-05-14 | 2021-08-20 | 群智未来人工智能科技研究院(无锡)有限公司 | Intelligent membrane pollution decision-making method based on knowledge type-two fuzzy |
| CN113313230A (en) * | 2021-04-19 | 2021-08-27 | 北京工业大学 | Intelligent membrane pollution decision-making method based on knowledge fuzzy width learning |
| CN114477429A (en) * | 2022-01-17 | 2022-05-13 | 中信环境技术（广州）有限公司 | Method and storage medium for controlling membrane pollution of MBR (membrane bioreactor) sewage treatment system |
| CN114660248A (en) * | 2020-12-22 | 2022-06-24 | 中国石油化工股份有限公司 | COD early warning method and device based on multi-step prediction strategy |
| US11727279B2 (en) | 2019-06-11 | 2023-08-15 | Samsung Electronics Co., Ltd. | Method and apparatus for performing anomaly detection using neural network |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096730A (en) * | 2016-06-09 | 2016-11-09 | 北京工业大学 | A kind of intelligent detecting method of MBR film permeability rate based on Recurrent RBF Neural Networks |
| CN106706491A (en) * | 2016-11-21 | 2017-05-24 | 北京工业大学 | Intelligent detection method for water permeation rate of membrane bioreactor MBR |
-
2018
- 2018-02-06 CN CN201810117548.2A patent/CN108375534A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096730A (en) * | 2016-06-09 | 2016-11-09 | 北京工业大学 | A kind of intelligent detecting method of MBR film permeability rate based on Recurrent RBF Neural Networks |
| CN106706491A (en) * | 2016-11-21 | 2017-05-24 | 北京工业大学 | Intelligent detection method for water permeation rate of membrane bioreactor MBR |
Non-Patent Citations (1)
| Title |
|---|
| HONG-GUI HAN 等: ""An early warning system for MBR based on multi-step prediction and deep belief network classifier"", 《2017 CHINESE AUTOMATION CONGRESS (CAC)》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109133351A (en) * | 2018-08-29 | 2019-01-04 | 北京工业大学 | Membrane bioreactor-MBR fouling membrane intelligent early-warning method |
| CN109473182B (en) * | 2018-11-12 | 2021-10-19 | 北京北排科技有限公司 | MBR (Membrane biological reactor) membrane water permeability intelligent detection method based on deep belief network |
| CN109473182A (en) * | 2018-11-12 | 2019-03-15 | 北京北排科技有限公司 | A kind of MBR film permeability rate intelligent detecting method based on deepness belief network |
| US11727279B2 (en) | 2019-06-11 | 2023-08-15 | Samsung Electronics Co., Ltd. | Method and apparatus for performing anomaly detection using neural network |
| CN112488286A (en) * | 2019-11-22 | 2021-03-12 | 大唐环境产业集团股份有限公司 | MBR membrane pollution online monitoring method and system |
| CN112488286B (en) * | 2019-11-22 | 2024-05-28 | 大唐环境产业集团股份有限公司 | On-line monitoring method and system for MBR membrane pollution |
| CN111204842A (en) * | 2019-12-23 | 2020-05-29 | 光大环境科技（中国）有限公司 | Method, device and system for realizing ultrafiltration membrane pollution evaluation through neural network |
| CN112101402A (en) * | 2020-07-22 | 2020-12-18 | 北京工业大学 | Membrane pollution early warning method based on knowledge fuzzy learning |
| CN112101402B (en) * | 2020-07-22 | 2024-04-09 | 北京工业大学 | Membrane pollution early warning method based on knowledge fuzzy learning |
| CN114660248A (en) * | 2020-12-22 | 2022-06-24 | 中国石油化工股份有限公司 | COD early warning method and device based on multi-step prediction strategy |
| CN113274885A (en) * | 2021-03-24 | 2021-08-20 | 重庆工商大学 | Membrane pollution intelligent early warning method applied to membrane sewage treatment |
| CN113274885B (en) * | 2021-03-24 | 2023-02-07 | 重庆工商大学 | Membrane pollution intelligent early warning method applied to membrane sewage treatment |
| CN113313230A (en) * | 2021-04-19 | 2021-08-27 | 北京工业大学 | Intelligent membrane pollution decision-making method based on knowledge fuzzy width learning |
| CN113313230B (en) * | 2021-04-19 | 2024-04-16 | 北京工业大学 | Film pollution intelligent decision-making method based on knowledge fuzzy width learning |
| CN113283481A (en) * | 2021-05-14 | 2021-08-20 | 群智未来人工智能科技研究院(无锡)有限公司 | Intelligent membrane pollution decision-making method based on knowledge type-two fuzzy |
| CN114477429A (en) * | 2022-01-17 | 2022-05-13 | 中信环境技术（广州）有限公司 | Method and storage medium for controlling membrane pollution of MBR (membrane bioreactor) sewage treatment system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108375534A (en) | MBR fouling membrane intelligent early-warning methods | |
| Elkiran et al. | Artificial intelligence-based approaches for multi-station modelling of dissolve oxygen in river | |
| Bagheri et al. | Modeling and optimization of activated sludge bulking for a real wastewater treatment plant using hybrid artificial neural networks-genetic algorithm approach | |
| CN103744293B (en) | Wastewater treatment monitoring method and system based on fuzzy neural network | |
| Vyas et al. | Performance forecasting of common effluent treatment plant parameters by artificial neural network | |
| CN109473182A (en) | A kind of MBR film permeability rate intelligent detecting method based on deepness belief network | |
| Pisa et al. | LSTM-based wastewater treatment plants operation strategies for effluent quality improvement | |
| CN102262147A (en) | Soft measurement method and system for effluent chemical oxygen demand (COD) of waste water treatment system | |
| CN107402586A (en) | Dissolved Oxygen concentration Control method and system based on deep neural network | |
| CN109828089A (en) | A kind of on-line prediction method of the water quality parameter cultured water based on DBN-BP | |
| CN112417765B (en) | Sewage treatment process fault detection method based on improved teacher-student network model | |
| CN109657790A (en) | A kind of Recurrent RBF Neural Networks water outlet BOD prediction technique based on PSO | |
| Yao et al. | Predicting membrane fouling in a high solid AnMBR treating OFMSW leachate through a genetic algorithm and the optimization of a BP neural network model | |
| Abba et al. | Neuro-fuzzy ensemble techniques for the prediction of turbidity in water treatment plant | |
| CN106706491B (en) | Intelligent detection method for membrane bioreactor-MBR water permeability | |
| CN113156074B (en) | Effluent total nitrogen prediction method based on fuzzy migration | |
| Türkmenler et al. | Performance assessment of advanced biological wastewater treatment plants using artificial neural networks | |
| CN113627506A (en) | Intelligent detection method for total phosphorus in effluent based on information fusion-interval two-type fuzzy neural network | |
| CN106769748B (en) | Intelligent detection system for water permeability of membrane bioreactor-MBR (Membrane bioreactor) | |
| CN111204867B (en) | Membrane bioreactor-MBR membrane pollution intelligent decision-making method | |
| Vyas et al. | Artificial neural network based model in effluent treatment process | |
| Shammi et al. | Desalination technologies and potential mathematical modeling for sustainable water–energy nexus | |
| CN115206444A (en) | Optimal drug dosage prediction method based on FCM-ANFIS model | |
| Huang et al. | Modeling and optimization of the activated sludge process | |
| Mellal et al. | Prediction of purified water quality in industrial hydrocarbon wastewater treatment using an artificial neural network and response surface methodology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180807 |