CN106406094B - A kind of sewage treatment dissolved oxygen concentration tracking and controlling method based on two type fuzzy neural network of section - Google Patents
A kind of sewage treatment dissolved oxygen concentration tracking and controlling method based on two type fuzzy neural network of section Download PDFInfo
- Publication number
- CN106406094B CN106406094B CN201610900248.2A CN201610900248A CN106406094B CN 106406094 B CN106406094 B CN 106406094B CN 201610900248 A CN201610900248 A CN 201610900248A CN 106406094 B CN106406094 B CN 106406094B
- Authority
- CN
- China
- Prior art keywords
- moment
- dissolved oxygen
- section
- neural network
- fuzzy neural
- 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
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Abstract
The invention proposes a kind of dissolved oxygen DO concentration tracing control method based on two type fuzzy neural network of section, dissolved oxygen DO concentration tracing control in sewage disposal process is realized.It is difficult to set up for the accurate mathematical model of sewage disposal process, there is excessive uncertain and interference in the environment of system operation, sewage disposal process has apparent non-linear and hysteresis quality, the uncontrollable feature of dissolved oxygen concentration, the control method is by establishing two type fuzzy neural network controller of section, build the circuit of two type fuzzy neural network controller and Controlling model of section, dissolved oxygen DO concentration is controlled using two type fuzzy Neural Network Control Method of section, it can be quick, accurately control dissolved oxygen DO concentration, compared with traditional PID control method, improve the efficiency of sewage treatment, reduce energy consumption, there is advantage in control precision simultaneously, obtain satisfactory control performance.
Description
Technical field
The present invention realizes dissolved oxygen in sewage disposal process using the control method based on two type fuzzy neural network of section
The tracing control of DO concentration, dissolved oxygen DO concentration is one of key control parameter during sewage biochemical reaction, to sewage treatment
Process effluent quality has a major impact；Dissolved oxygen DO concentration tracing control method based on two type fuzzy neural network of section is answered
In sewage disposal process, the control of dissolved oxygen DO concentration tracing is realized；The invention had not only belonged to wate research field, but also belonged to intelligence
Control field.
Background technique
It is one of risk most crucial in coming 10 years social risk that water resource, which supplies crisis, once occurring will be to the whole world
Economy and society cause essence to destroy.The situation very severe of current China Proposals of Water Resources, shortage of water resources, water pollution are tight
The problems such as weight, water ecological environment deteriorate becomes increasingly conspicuous, it has also become restricts the main bottleneck of the sustainable development of socio-economy.With me
The quickening of state industrialized development and Development of China's Urbanization, urban population are increasingly concentrated, the demand of freshwater resources are also got over
Come bigger；Water quality is severe, and the frequent generation of water body eutrophication phenomenon makes urban water pollution problem increasingly sharpen；At the same time, state
The growth of people's economy and the enhancing of Public environmental attitude make sewage treatment automatic technology welcome unprecedented development machine
It meets；Water pollution how is prevented and treated, how sewage is timely and effectively handled and utilizes again, becomes the extremely urgent problem in China；
In recent years, China actively builds sewage treatment facility, and by the end of the year 2015, National urban sewage treatment plant processing capacity 1.4
Billion cubic meter/day, whole year, the accumulative sewage quantity that handles was up to 410.3 billion cubic meters；However, under the pressure of the need for reducing cost of sewage disposal
It wants, the directions such as the enlargement of municipal sewage treatment forward direction scale, technologically advancedization and operation optimization are developed.Therefore, sewage is studied
Treatment process optimization operation control technology, realizes that low cost operation is the inexorable trend of future city sewage treatment plant development,
It is the inevitable choice of municipal sewage plant's upgrading, technological innovation.
In sewage disposal process, dissolved oxygen DO concentration is most important control parameter during sewage biochemical reaction；It is aerobic
When area's oxygen deficiency, der Pilz mass propagation leads to sludge bulking；When oxygen excess, suspended solid settleability variation leads to energy consumption
It is excessively high；Dissolved oxygen DO concentration can also cause certain to effluent quality, energy consumption, the operating cost of sewage disposal process simultaneously
It influences；Therefore, being controlled for quickly, efficiently and accurately is premise that can sewage disposal process operate normally in the reasonable scope；
According to different water quality, corresponding change can occur for dissolved oxygen DO concentration, while sewage disposal process non-linear, time variation, move
The features such as state is not known increases the control difficulty of dissolved oxygen DO；Tradition using the method for control is realized by PID controller
The control of dissolved oxygen concentration, however PID controller needs a large amount of empirical data, control parameter design is relatively complicated；Therefore, such as
What rapidly and efficiently, reliably accurately becomes urgent problem to be solved to the control of dissolved oxygen DO concentration tracing；Two pattern of section paste mind
Priori knowledge is expressed by fuzzy rule through network, there is stronger study, adaptation and fuzzy message processing capacity；Base
It can be realized in the dissolved oxygen DO concentration tracing control method of two type fuzzy neural network of section and dissolved oxygen DO concentration controlled in real time
System has good practical application value；
The present invention devises a kind of dissolved oxygen DO concentration tracing control method based on two type fuzzy neural network of section, main
Tracing control is carried out to control target by two type fuzzy neural network controller of section, realize dissolved oxygen DO On-line Control.
Summary of the invention
Present invention obtains a kind of dissolved oxygen DO concentration tracing control methods based on two type fuzzy neural network of section, should
Controller is that the dissolved oxygen DO concentration tracing control method solution sewage disposal process based on two type fuzzy neural network of section is molten
Oxygen control problem is solved, achievees the purpose that control dissolved oxygen DO concentration by the aeration quantity after control optimization；Realize sewage treatment
The control of journey dissolved oxygen DO concentration tracing reduces energy consumption and processing cost under the premise of guaranteeing that effluent quality is up to standard；
Present invention employs the following technical solution and realize step:
1. a kind of dissolved oxygen DO concentration tracing control method based on two type fuzzy neural network of section,
It is controlled for dissolved oxygen DO in batch-type interval activated Sludge System, wherein aeration quantity is control amount, dissolution
Oxygen DO concentration is controlled volume；
Characterized by comprising the following steps:
(1) the two type fuzzy neural network of section designed for the control of dissolved oxygen DO concentration tracing, two pattern of section paste mind
It is divided into four layers through network: input layer, membership function layer, active coating, output layer；Specifically:
1. input layer: the layer is made of 2 neurons:
X (t)=[x1(t),x2(t)]T (1)
Wherein, X (t) indicates the input of two type fuzzy neural network of section, x1(t) it is set for t moment dissolved oxygen DO concentration
The error of value and actual value, x2It (t) is the change rate of t moment dissolved oxygen DO concentration set point and actual value error, T is matrix
Transposition；
2. membership function layer: the layer has R neuron, and each neuron represents two π membership function of section, indicates
It is as follows:
Wherein,The lower bound of j-th of membership function layer neuron output value when being inputted for i-th of t moment,For t
The upper bound of j-th of membership function layer neuron output value when i-th of moment input, c ijIt (t) is t moment
The lower bound of j-th of membership function layer neuronal center value when i-th of input,It is subordinate to for j-th when for i-th of input of t moment
The upper bound of function layer neuronal center value,σij(t) be i-th of input of t moment when j-th of membership function layer
The width value of neuron；The input number of i expression two type fuzzy neural network of section, i=1,2；J=1,2 ..., R；
3. active coating: the layer has R neuron, the intensity of activation of each neuron are as follows:
Wherein, FjIt (t) is the intensity of activation of j-th of neuron of t moment active coating,f jIt (t) is j-th of mind of t moment active coating
Lower bound through first intensity of activation,For the upper bound of j-th of neuronal activation intensity of t moment active coating,
4. output layer: the layer has 1 neuron, output are as follows:
Wherein, u (t) is the aeration quantity of t moment controller, and Δ u (t) is the defeated of two type fuzzy neural network of t moment section
Out, the aeration increment of controller, Δ are indicateduIt (t) is the lower bound of two type fuzzy neural network of t moment section output,For t
Moment section two type fuzzy neural network output the upper bound,Q (t) is two pattern of t moment section paste mind
Ratio value through network output lower bound, q (t) ∈ (0,1]；zj(t) power between j-th of neuron of t moment and output neuron
Value, aijIt (t) is t moment weight coefficient, bjIt (t) is t moment weight bias；
(2) training two type fuzzy neural network of section, specific as follows:
1. utilizing training sample and gradient descent algorithm training two type fuzzy neural network of section；Objective function are as follows:
Wherein, e (t) is the error of t moment dissolved oxygen DO concentration set point and actual value, and y (t) is dissolved oxygen DO concentration
Actual value, ydIt (t) is the setting value of dissolved oxygen DO concentration；
2. being updated to the parameter of two type fuzzy neural network of section:
Wherein,c ij(t+1) lower bound of the central value of j-th of membership function layer neuron when being inputted for i-th of the t+1 moment,The upper bound of the central value of j-th of membership function layer neuron when being inputted for i-th of the t+1 moment；σij(t+1) be t+1 when
The width value of j-th of membership function layer neuron when carving i-th of input, q (t+1) are two type fuzznet of t+1 moment section
Network exports the ratio value of lower bound, aijIt (t+1) is the weight coefficient at t+1 moment, bjIt (t+1) is the weight bias at t+1 moment；η is
The learning rate of parameter, η ∈ (0,1]；
(3) it is designed for dissolved oxygen DO concentration tracing control method in sewage disposal process, specifically:
1. according to the output of two type fuzzy neural network of formula (4) computation interval；
2. judging that the size of the objective function of current time dissolved oxygen DO concentration tracing control is gone to if e (t) > 0.01
Step is 3.；If e (t)≤0.01, step is gone to 5.；
3. solving the updated value of parameters according to formula (6)；
4. calculating the control amount u (t) at current time
U (t)=Δ um(t)+u(t-1) (7)
Wherein, u (t) is the aeration quantity of t moment controller, Δ um(t) new aeration increment, u after being updated for t moment parameter
It (t-1) is the aeration quantity of t-1 moment controller；Go to step 6.；
5. calculating the control amount u (t) at current time
U (t)=Δ u (t)+u (t-1) (8)
6. u (t) is the amount of actually entering of current time sewage disposal system dissolved oxygen DO concentration tracing control system；
(4) dissolved oxygen DO is controlled using the u (t) solved, u (t) the i.e. aeration quantity of t moment, control system
Output is the concentration value of practical dissolved oxygen DO.
Innovative point of the invention is mainly reflected in:
(1) present invention is anti-for complicated, dynamic, the unstable biology of current active sludge sewage disposal process
The characteristics of answering process and non-linear, time variation, hysteresis quality；Meanwhile the mathematical models of sewage disposal process are difficult to build
It is vertical, the characteristics of according to the preferable learning ability of neural network and approximation capability, using based on two type fuzzy neural network of section
Control method controls dissolved oxygen DO concentration, has the characteristics that control precision is high, stability is good；
(2) present invention employs the dissolved oxygen DO concentration tracing control methods based on two type fuzzy neural network of section to dirt
The dissolved oxygen DO concentration of water treatment procedure carries out tracing control, which takes full advantage of two type fuzzy neural network of section
Systematicness and accuracy, so that controller is better met the variation of current environment, realize preferable control；The controlling party simultaneously
The features such as method realizes the Closed loop track control of dissolved oxygen DO concentration, has strong real-time, and structure is simple；
It is important to note that: the present invention is intended merely to description conveniently, controls using to dissolved oxygen DO concentration tracing, equally
The control etc. of the invention also applicable sewage disposal process nitrate nitrogen all should as long as using the principle of the present invention and being controlled
Belong to the scope of the present invention.
Detailed description of the invention
Fig. 1 is control structure figure of the invention
Fig. 2 is two type structure of fuzzy neural network figure of section of the invention
Fig. 3 is control system dissolved oxygen DO concentration results figure of the present invention of the invention
Fig. 4 is control system dissolved oxygen DO concentration error figure of the invention
Specific embodiment
Present invention obtains a kind of dissolved oxygen DO concentration tracing control methods based on two type fuzzy neural network of section, should
Controller is that the dissolved oxygen DO concentration tracing control method solution sewage disposal process based on two type fuzzy neural network of section is molten
Oxygen control problem is solved, achievees the purpose that control dissolved oxygen DO by the aeration quantity after control optimization；Realize that sewage disposal process is molten
The control of oxygen DO concentration tracing is solved, under the premise of guaranteeing that effluent quality is up to standard, reduces energy consumption and processing cost；
1. a kind of dissolved oxygen DO concentration tracing control method based on two type fuzzy neural network of section,
It is controlled for dissolved oxygen DO in batch-type interval activated Sludge System, wherein aeration quantity is control amount, dissolution
Oxygen DO concentration is controlled volume, control structure such as Fig. 1；
Characterized by comprising the following steps:
(1) the two type fuzzy neural network of section designed for the control of dissolved oxygen DO concentration tracing, two pattern of section paste mind
It is divided into four layers through network: input layer, membership function layer, active coating, output layer, two type structure of fuzzy neural network such as Fig. 2 of section,
Specifically:
1. input layer: the layer is made of 2 neurons:
X (t)=[x1(t),x2(t)]T
(9)
Wherein, X (t) indicates the input of two type fuzzy neural network of section, x1(t) it is set for t moment dissolved oxygen DO concentration
The error of value and actual value, x2It (t) is the change rate of t moment dissolved oxygen DO concentration set point and actual value error, T is matrix
Transposition；
2. membership function layer: the layer has 6 neurons, and each neuron represents two π membership function of section, indicates
It is as follows:
Wherein,The lower bound of j-th of membership function layer neuron output value when being inputted for i-th of t moment,For t
The upper bound of j-th of membership function layer neuron output value when i-th of moment input, c ijIt (t) is t moment
The lower bound of j-th of membership function layer neuronal center value when i-th of input,It is subordinate to for j-th when for i-th of input of t moment
The upper bound of function layer neuronal center value,σij(t) j-th of membership function layer is refreshing when being i-th of input of t moment
Width value through member；The input number of i expression two type fuzzy neural network of section, i=1,2；J=1,2 ..., 6；
3. active coating: the layer has 6 neurons, the intensity of activation of each neuron are as follows:
Wherein, FjIt (t) is the intensity of activation of j-th of neuron of t moment active coating,f jIt (t) is j-th of mind of t moment active coating
Lower bound through first intensity of activation,For the upper bound of j-th of neuronal activation intensity of t moment active coating,
4. output layer: the layer has 1 neuron, output are as follows:
Wherein, u (t) is the aeration quantity of t moment controller, and Δ u (t) is the defeated of two type fuzzy neural network of t moment section
Out, the aeration increment of controller, Δ are indicateduIt (t) is the lower bound of two type fuzzy neural network of t moment section output,For t
Moment section two type fuzzy neural network output the upper bound,Q (t) is two pattern of t moment section paste mind
Ratio value through network output lower bound, q (t) ∈ (0,1]；zj(t) power between j-th of neuron of t moment and output neuron
Value, aijIt (t) is t moment weight coefficient, bjIt (t) is t moment weight bias；
(2) training two type fuzzy neural network of section, specific as follows:
1. utilizing training sample and gradient descent algorithm training two type fuzzy neural network of section；Objective function are as follows:
Wherein, e (t) is the error of t moment dissolved oxygen DO concentration set point and actual value, and y (t) is dissolved oxygen DO concentration
Actual value, ydIt (t) is the setting value of dissolved oxygen DO concentration；
2. being updated to the parameter of two type fuzzy neural network of section:
Wherein,c ij(t+1) lower bound of the central value of j-th of membership function layer neuron when being inputted for i-th of the t+1 moment,The upper bound of the central value of j-th of membership function layer neuron when being inputted for i-th of the t+1 moment；σij(t+1) be t+1 when
The width value of j-th of membership function layer neuron when carving i-th of input, q (t+1) are two type fuzznet of t+1 moment section
Network exports the ratio value of lower bound, aijIt (t+1) is the weight coefficient at t+1 moment, bjIt (t+1) is the weight bias at t+1 moment；η is
The learning rate of parameter, η 0.05；
(3) it is designed for dissolved oxygen DO concentration tracing control method in sewage disposal process, specifically:
1. according to the output of two type fuzzy neural network of formula (4) computation interval；
2. judging that the size of the objective function of current time dissolved oxygen DO concentration tracing control is gone to if e (t) > 0.01
Step is 3.；If e (t)≤0.01, step is gone to 5.；
3. solving the updated value of parameters according to formula (6)；
4. calculating the control amount u (t) at current time
U (t)=Δ um(t)+u(t-1) (15)
Wherein, u (t) is the aeration quantity of t moment controller, Δ um(t) new aeration increment, u after being updated for t moment parameter
It (t-1) is the aeration quantity of t-1 moment controller；Go to step 6.；
5. calculating the control amount u (t) at current time
U (t)=Δ u (t)+u (t-1) (16)
6. u (t) is the amount of actually entering of current time sewage disposal system dissolved oxygen DO concentration tracing control system；
(4) dissolved oxygen DO is controlled using the u (t) solved, u (t) the i.e. aeration quantity of t moment, control system
Output is the concentration value of practical dissolved oxygen DO.The dissolved oxygen DO concentration value of Fig. 3 display system, X-axis: the time, unit is 15 minutes/
Sample, Y-axis: dissolved oxygen DO concentration, unit are mg/litres, and solid line is dissolved oxygen DO concentration set point, and black dotted lines are dissolved oxygens
DO concentration actual value；Error such as Fig. 4 of dissolved oxygen DO concentration set point and dissolved oxygen DO concentration actual value, X-axis: time, unit
It is 15 minutes/sample, Y-axis: dissolved oxygen DO concentration error value, unit is mg/litre；The results show this method it is effective
Property.
Claims (1)
1. a kind of dissolved oxygen DO setting value tracking and controlling method based on two type fuzzy neural network of section, for batch-type interval
Dissolved oxygen DO is controlled in activated Sludge System, wherein aeration quantity is control amount, and dissolved oxygen DO concentration is controlled volume；
Characterized by comprising the following steps:
(1) the two type fuzzy neural network of section of dissolved oxygen DO setting value tracing control, two type fuzzy neural of section are designed for
Network is divided into four layers: input layer, membership function layer, active coating, output layer；Specifically:
1. input layer: the layer is made of 2 neurons:
X (t)=[x1(t),x2(t)]T (1)
Wherein, X (t) indicates the input of two type fuzzy neural network of section, x1It (t) is t moment dissolved oxygen DO concentration set point and reality
The error of actual value, x2It (t) is the change rate of t moment dissolved oxygen DO concentration set point and actual value error, T is the transposition of matrix；
2. membership function layer: the layer has R neuron, and each neuron represents two π membership function of section, is expressed as follows:
Wherein,The lower bound of j-th of membership function layer neuron output value when being inputted for i-th of t moment,For t moment
The upper bound of j-th of membership function layer neuron output value when i-th of input, c ijIt (t) is t moment i-th
The lower bound of j-th of membership function layer neuronal center value when a input,It is subordinate to letter j-th when for i-th of input of t moment
The upper bound of several layers of neuronal center value,σij(t) j-th of membership function layer is refreshing when being i-th of input of t moment
Width value through member；The input number of i expression two type fuzzy neural network of section, i=1,2；J=1,2 ..., R；
3. active coating: the layer has R neuron, the intensity of activation of each neuron are as follows:
Wherein, FjIt (t) is the intensity of activation of j-th of neuron of t moment active coating,f jIt (t) is j-th of neuron of t moment active coating
The lower bound of intensity of activation,For the upper bound of j-th of neuronal activation intensity of t moment active coating,
4. output layer: the layer has 1 neuron, output are as follows:
Wherein, u (t) is the aeration quantity of t moment controller, and Δ u (t) is the output of two type fuzzy neural network of t moment section, table
Show the aeration increment of controller, ΔuIt (t) is the lower bound of two type fuzzy neural network of t moment section output,For t moment
The upper bound of two type fuzzy neural network of section output,Q (t) is two type fuzznet of t moment section
The ratio value of network output lower bound, q (t) ∈ (0,1]；zj(t) weight between j-th of neuron of t moment and output neuron, aij
It (t) is t moment weight coefficient, bjIt (t) is t moment weight bias；
(2) training two type fuzzy neural network of section, specific as follows:
1. utilizing training sample and gradient descent algorithm training two type fuzzy neural network of section；Objective function are as follows:
Wherein, e (t) is the error of t moment dissolved oxygen DO concentration set point and actual value, and y (t) is the reality of dissolved oxygen DO concentration
Value, ydIt (t) is the setting value of dissolved oxygen DO concentration；
2. being updated to the parameter of two type fuzzy neural network of section:
Wherein,c ij(t+1) lower bound of the central value of j-th of membership function layer neuron when being inputted for i-th of the t+1 moment,The upper bound of the central value of j-th of membership function layer neuron when being inputted for i-th of the t+1 moment；σijIt (t+1) is t+1
The width value of j-th of membership function layer neuron when i-th of moment input, q (t+1) are two type fuzzy neural of t+1 moment section
Network exports the ratio value of lower bound, aijIt (t+1) is the weight coefficient at t+1 moment, bjIt (t+1) is the weight bias at t+1 moment；η
For the learning rate of parameter, η ∈ (0,1]；
(3) it is designed for dissolved oxygen DO setting value tracking and controlling method in sewage disposal process, specifically:
1. according to the output of two type fuzzy neural network of formula (4) computation interval；
2. judging the size of the objective function of current time dissolved oxygen DO setting value tracing control, if e (t) > 0.01, step is gone to
Suddenly 3.；If e (t)≤0.01, step is gone to 5.；
3. solving the updated value of parameters according to formula (6)；
4. calculating the control amount u (t) at current time
U (t)=Δ um(t)+u(t-1) (7)
Wherein, u (t) is the aeration quantity of t moment controller, Δ um(t) new aeration increment, u (t-1) after being updated for t moment parameter
For the aeration quantity of t-1 moment controller；Go to step 6.；
5. calculating the aeration u (t) of t moment controller
U (t)=Δ u (t)+u (t-1) (8)
6. u (t) is the aeration of t moment controller；
(4) dissolved oxygen DO is controlled using the u (t) solved, u (t) is the aeration of t moment controller, control system
Output is the concentration value of practical dissolved oxygen DO.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610900248.2A CN106406094B (en) | 2016-10-16 | 2016-10-16 | A kind of sewage treatment dissolved oxygen concentration tracking and controlling method based on two type fuzzy neural network of section |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610900248.2A CN106406094B (en) | 2016-10-16 | 2016-10-16 | A kind of sewage treatment dissolved oxygen concentration tracking and controlling method based on two type fuzzy neural network of section |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106406094A CN106406094A (en) | 2017-02-15 |
| CN106406094B true CN106406094B (en) | 2019-06-14 |
Family
ID=58011683
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610900248.2A Active CN106406094B (en) | 2016-10-16 | 2016-10-16 | A kind of sewage treatment dissolved oxygen concentration tracking and controlling method based on two type fuzzy neural network of section |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106406094B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109213174B (en) * | 2018-10-24 | 2021-10-01 | 北京工业大学 | Sewage treatment plant intelligent patrol obstacle avoidance method based on fuzzy neural network |
| CN110647037B (en) * | 2019-09-23 | 2022-03-15 | 北京工业大学 | Cooperative control method for sewage treatment process based on two-type fuzzy neural network |
| CN111125907B (en) * | 2019-12-23 | 2023-09-01 | 河南理工大学 | Sewage treatment ammonia nitrogen soft measurement method based on hybrid intelligent model |
| CN111026146B (en) * | 2019-12-24 | 2021-04-06 | 西北工业大学 | Attitude control method for composite wing vertical take-off and landing unmanned aerial vehicle |
| CN113191483A (en) * | 2021-04-19 | 2021-07-30 | 北京工业大学 | Two-type fuzzy width learning-based intelligent decision-making method for sludge bulking |
| 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 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1998003434A1 (en) * | 1996-07-19 | 1998-01-29 | Mitsubishi Chemical Corporation | Device for controlling dissolved oxygen concentration of aeration tank, device for controlling temperature of aeration tank, device for controlling flow rate of raw water for homogeneous-flow liquid surface, and wastewater treatment equipment used in activated sludge process |
| CN102122134A (en) * | 2011-02-14 | 2011-07-13 | 华南理工大学 | Method and system for wastewater treatment of dissolved oxygen control based on fuzzy neural network |
| CN102411308A (en) * | 2011-12-24 | 2012-04-11 | 北京工业大学 | Adaptive control method of dissolved oxygen (DO) based on recurrent neural network (RNN) model |
| CN103064290A (en) * | 2013-01-01 | 2013-04-24 | 北京工业大学 | Dissolved oxygen model prediction control method based on self-organization radial basis function neural network |
| CN103197544A (en) * | 2013-02-25 | 2013-07-10 | 北京工业大学 | Sewage disposal process multi-purpose control method based on nonlinear model prediction |
| CN104965971A (en) * | 2015-05-24 | 2015-10-07 | 北京工业大学 | Ammonia nitrogen concentration soft-measuring method based on fuzzy neural network |
-
2016
- 2016-10-16 CN CN201610900248.2A patent/CN106406094B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1998003434A1 (en) * | 1996-07-19 | 1998-01-29 | Mitsubishi Chemical Corporation | Device for controlling dissolved oxygen concentration of aeration tank, device for controlling temperature of aeration tank, device for controlling flow rate of raw water for homogeneous-flow liquid surface, and wastewater treatment equipment used in activated sludge process |
| CN102122134A (en) * | 2011-02-14 | 2011-07-13 | 华南理工大学 | Method and system for wastewater treatment of dissolved oxygen control based on fuzzy neural network |
| CN102411308A (en) * | 2011-12-24 | 2012-04-11 | 北京工业大学 | Adaptive control method of dissolved oxygen (DO) based on recurrent neural network (RNN) model |
| CN103064290A (en) * | 2013-01-01 | 2013-04-24 | 北京工业大学 | Dissolved oxygen model prediction control method based on self-organization radial basis function neural network |
| CN103197544A (en) * | 2013-02-25 | 2013-07-10 | 北京工业大学 | Sewage disposal process multi-purpose control method based on nonlinear model prediction |
| CN104965971A (en) * | 2015-05-24 | 2015-10-07 | 北京工业大学 | Ammonia nitrogen concentration soft-measuring method based on fuzzy neural network |
Non-Patent Citations (1)
| Title |
|---|
| 自组织区间二型模糊神经网络及其自适应学习算法;姚兰 等;《控制理论与应用》;20130630;第30卷(第6期);第785-791页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106406094A (en) | 2017-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106406094B (en) | A kind of sewage treatment dissolved oxygen concentration tracking and controlling method based on two type fuzzy neural network of section | |
| CN103197544B (en) | Sewage disposal process multi-purpose control method based on nonlinear model prediction | |
| AU2021101438A4 (en) | Adaptive control method and system for aeration process | |
| CN102854296B (en) | Sewage-disposal soft measurement method on basis of integrated neural network | |
| CN106354014B (en) | A kind of sewage treatment optimal control method based on multiple target differential evolution algorithm | |
| CN103064290B (en) | Dissolved oxygen model prediction control method based on self-organization radial basis function neural network | |
| US20200385286A1 (en) | Dynamic multi-objective particle swarm optimization-based optimal control method for wastewater treatment process | |
| CN109711070A (en) | A kind of dissolved oxygen concentration optimization method based on activated sludge water process | |
| CN105573115B (en) | Sewage disposal process energy-conserving and optimizing control method based on quantum genetic algorithm | |
| CN105404151A (en) | Sewage processing process dynamic multi-target optimization control method | |
| CN108445757B (en) | Sewage treatment process optimization control method based on dynamic multi-target particle swarm algorithm | |
| CN109669352A (en) | Oily waste water treatment procedure optimization control method based on adaptive multi-objective particle swarm | |
| CN105676649A (en) | Control method for sewage treatment process based on self-organizing neural network | |
| CN103499982B (en) | A kind of sewage disposal process self-organization control method | |
| Chen et al. | Three-dimensional short-term prediction model of dissolved oxygen content based on pso-bpann algorithm coupled with kriging interpolation | |
| CN110716432B (en) | Multi-objective optimization control method for urban sewage treatment process based on self-adaptive selection strategy | |
| CN110647037B (en) | Cooperative control method for sewage treatment process based on two-type fuzzy neural network | |
| Zhang et al. | Calculation of permissible load capacity and establishment of total amount control in the Wujin River Catchment—a tributary of Taihu Lake, China | |
| Wang et al. | Energy and materials-saving management via deep learning for wastewater treatment plants | |
| CN108536106A (en) | A kind of aerating system dissolved oxygen based on Kalman filtering-extreme learning machine regulates and controls method online | |
| Xu et al. | Integrated data-driven strategy to optimize the processes configuration for full-scale wastewater treatment plant predesign | |
| CN106354019B (en) | A kind of dissolved oxygen accuracy control method based on RBF neural | |
| CN106094517A (en) | A kind of Multi model Predictive Controllers of variable working condition sewage disposal process | |
| CN113568311A (en) | Intelligent sewage treatment optimization control method based on knowledge information | |
| CN108563118A (en) | A kind of dissolved oxygen model predictive control method based on Adaptive Fuzzy Neural-network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |