CN105739325A - Aeration intelligent control system in sewage treatment process - Google Patents
Aeration intelligent control system in sewage treatment process Download PDFInfo
- Publication number
- CN105739325A CN105739325A CN201610226233.2A CN201610226233A CN105739325A CN 105739325 A CN105739325 A CN 105739325A CN 201610226233 A CN201610226233 A CN 201610226233A CN 105739325 A CN105739325 A CN 105739325A
- Authority
- CN
- China
- Prior art keywords
- aeration
- control unit
- module
- data
- model
- 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
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
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Activated Sludge Processes (AREA)
Abstract
An aeration intelligent control system in a sewage treatment process relates to a sewage treatment system. The aeration intelligent control system in the sewage treatment process includes a monitoring computer, a central control unit, n on-site control units, n detection instrument groups and n execution units. A model storage module (including n theoretical calculation models of the aeration control amount and n artificial neural network models for calculating the aeration control correction amount) and a data storage module (for storing on-site detection data of n aeration tanks) are stored in the monitoring computer. The fully automatic control of an aeration process can be realized, and the problem that the aeration process in the prior art is in a semi-automatic operation state is solved. The aeration amount can be timely adjusted according to the water quality condition, and the stability of effluent quality is ensured. The ''aeration as required'' is performed according to a load change condition, so that the energy consumption in the sewage treatment process is reduced.
Description
Technical field
The invention belongs to a kind of intelligent control method and equipment, especially one sewage disposal station-service intelligent control method and intelligence control system.
Background technology
Sewage disposal floating filler technique is activated sludge process method and biomembrane process method to be combined together, and uses a kind of process of flotation bed.This technique is mainly in Aeration tank, a certain proportion of bio-carrier is added according to volume, microorganism grows certain thickness biomembrane at carrier surface, carrier fluctuates with current and air-flow, frequently contact with Organic substance and dissolved oxygen, drastically increase the absorption degradation ability of microorganism, also improve the utilization rate of oxygen.The feature of this technique is that flow process is short, sludge reflux facility scale is little, plant area's floor space is few, treatment effeciency is high, stable effluent quality, construction and cost low.In floating filler technique, the aeration control to biochemical filter tank is the core that whole sewage disposal runs control process.At present, the domestic control to the aeration in sewage treatment process based on floating filler technique there is also following deficiency: (1) is not carried out full automation control, and aeration process is in semi-automatic running status；(2) system can not according to entering water, effluent quality situation adjusts aeration parameter in time, it is ensured that stablizing of effluent quality；(3) aeration process carries out " on-demand aeration " not according to the situation of change of load, and aeration process energy consumption is bigger.
Summary of the invention
It is an object of the invention to for deficiency existing in prior art, a kind of online sewage disposal process aeration intelligent control method is provided, it can solve the problem that following problem: achieves the fully automated control of aeration process, solves the problem that aeration process in prior art is in semi-automatic running status；Aeration rate can be adjusted in time according to water quality situation, it is ensured that stablizing of effluent quality, and can carry out " on-demand aeration " according to the situation of change of load, make sewage disposal process energy consumption reduce.
The present invention is realized by following steps:
Sewage disposal process aeration intelligence control system is made up of monitoring calculation machine, central control unit, n field control unit, n instrumentation group and n performance element.A model memory module (theoretical calculation model and the n that include n aeration control amount are individual for calculating the artificial nerve network model of aeration control correction) and a data memory module (for storing the Site Detection data of n Aeration tank) is had inside described monitoring calculation machine；Described central control unit is made up of ethernet communication module CP343 and central processor CPU 315-2DP；Described field control unit is by PROFIBUS-DP(ProcessFieldBus-DecentralizedPeriphery) bus communication module EM277,244,2 analog input and output expansion module EM235 of central processor CPU form；Described instrumentation group includes: flow of inlet water measures instrument, influent COD measures instrument, influent ammonia nitrogen measures instrument, sludge concentration measures instrument, Aeration tank temperature measuring instrument and dissolved oxygen sensing instrument；Described performance element is made up of converter and aerator.Monitoring calculation machine is connected with EPA ETHERNET by communication cable；Central control unit is connected with EPA ETHERNET through communication cable by CP343 ethernet communication module；Central control unit is connected with PROFIBUS-DP bus through communication cable；N field control unit, respectively through bus extender module EM277, is connected with PROFIBUS-DP bus through communication cable；N field control unit performs module respectively through EM235 module with corresponding, instrumentation group is connected.
The field data that each instrumentation group records sends affiliated field control unit to through analog input and output module EM235 respectively, described field data is sent to central control unit by field control unit, it is sent to monitoring calculation machine by central control unit again, is stored in data memory module.The field data of the storage each Aeration tank detected by n instrumentation group in monitoring calculation machine memory module.The monitoring calculation machine field data according to each Aeration tank, in calling model memory module, the aeration mathematical model of corresponding Aeration tank calculates the theoretical aeration control amount of each Aeration tank respectively, field data further according to each Aeration tank, corresponding human artificial neural networks model in calling model memory module calculates the aeration control correction of each Aeration tank respectively, calculates the actual aeration control amount (actual aeration control amount=theory aeration control amount+aeration control correction) of each Aeration tank.The actual aeration control amount of calculated each Aeration tank is sent to central control unit by monitoring calculation machine, by central control unit, the actual aeration control amount of each Aeration tank is sent to corresponding field control unit, the converter in affiliated on-the-spot performance element is controlled through analog input and output module EM235 again by field control unit, again by Frequency Converter Control blower motor, it is achieved aeration control.
There are model memory module and data memory module in monitoring calculation machine of the present invention, described model memory module stores theoretical calculation model and the individual artificial nerve network model for calculating aeration control correction of n of n aeration control amount.The corresponding Aeration tank of each aeration mathematical model, calculates the theoretical aeration control amount of each Aeration tank respectively；The corresponding Aeration tank of everyone artificial neural networks model, in order to calculate the aeration control correction of this Aeration tank.Artificial nerve network model described in this programme is according to system operation history data timing training network, updates network model's parameter.
The invention has the beneficial effects as follows: owing to the model memory module in this programme monitoring calculation machine storing n for calculating the theoretical calculation model of aeration control amount and n for calculating the artificial nerve network model of aeration control correction, monitoring calculation machine calls the ARTOICAL NEURAL NETWORK MODEL corresponding to each Aeration tank and calculates the aeration control correction of each Aeration tank respectively, therefore, it is possible to the actual aeration control amount of change each Aeration tank of correction in time according to water quality and load, what energy was in good time carries out Based Intelligent Control, makes sewage disposal water quality more stable.Monitoring calculation machine calls the detection data of each Aeration tank in data memory module, corresponding human artificial neural networks model in timing training pattern memory module, timing updates artificial nerve network model parameter, makes aeration correction reflect the impact of system parameter variations in time.
Accompanying drawing explanation
Fig. 1 is the system structure block diagram of the specific embodiment of the invention；
Fig. 2 is the DRNN artificial neural network topology diagram of the specific embodiment of the invention.
Detailed description of the invention
Come below in conjunction with specific embodiments present invention is further described.
Seeing Fig. 1, the sewage disposal process aeration intelligence control system of this programme is to be become with n instrumentation fabric by monitoring calculation machine, central control unit, n field control unit, n performance element.Described monitoring calculation machine adopts industrial computer, is connected by EPA ETHERNET with central control unit；Central control unit through PROFIBUS-DP bus respectively with field control unit 1, field control unit 2 until field control unit n is connected；Field control unit 1 is connected by analog input and output module EM235 with affiliated performance element 1 and instrumentation group 1, field control unit 2 is connected by analog input and output module EM235 with affiliated performance element 2 and instrumentation group 2, until field control unit n is connected by analog input and output module EM235 with affiliated performance element n and instrumentation group n.Model memory module and data memory module is had in described monitoring calculation machine.Described model memory module stores n the individual aeration mathematical model for calculating theoretical aeration control amount of artificial nerve network model and n for calculating each Aeration tank aeration Correction and Control amount；Described data memory module is every the data (i.e. sampled data) detected by 2 minutes storage once each instrumentation groups.Monitoring calculation machine called 100 sampled datas that each Aeration tank in a data memory module is up-to-date every 10 minutes, including: flow of inlet water data, influent COD data, influent ammonia nitrogen data, sludge concentration data, Aeration tank average temperature data and dissolved oxygen data, train the artificial nerve network model of each Aeration tank, it is achieved timing updates each network model's parameter.
The described system process model for calculating theoretical aeration control amount is:
IfFor theoretical aeration rate, Q be Aeration tank flow of inlet water ()；Influent COD value is S(mg/L)；Influent ammonia nitrogen value is N(mg/L)；Activated sludge concentration is M(mg/L), calculate theoretical aeration control amount when temperature is 20 ° by following equation:
Wherein, k1For COD oxygen consumption constant, value is 0.01～0.03；k2For ammonia nitrogen oxygen consumption constant, value is 0.1～0.35；k3For activated sludge oxygen consumption constant, value is 0.01～0.028；k4For aeration oxygen transfer efficiency, value is 9.5～12.E is aeration correction term, and value is 9.5～12.
When Aeration tank mean temperature is 20 °, actual aeration control amount is theoretical aeration control amount, when temperature is higher or lower than 20 °, actual aeration control amount is by theoretical aeration control amount and the synthesis of aeration control correction, i.e. actual aeration control amount=theory aeration control amount+aeration control correction.
The described artificial nerve network model for calculating aeration control correction as shown in Figure 2, adopts the three layers DRNN neural network structure of 5-11-1, and namely input layer is 5 neurons, and input quantity corresponding respectively is: Aeration tank flow of inlet water, influent COD value；Influent ammonia nitrogen value；Sludge concentration and Aeration tank mean temperature.Hidden layer is 11 neurons, and each hidden layer neuron, except be connected with self (self feed back), is also connected with each neuron of input layer；The third layer (output layer) of model has 1 neuron, and this neuron is connected with each neuron of hidden layer, third layer neuronic output y(k) for aeration Correction and Control amount.The mathematical model of DRNN neutral net is:
Wherein:
Connection weight matrix for input layer Yu hidden layer neuron；For hidden layer neuron and the neuronic connection weight matrix of output layer；For hidden layer neuron self feed back weight matrix；Output vector for hidden layer neuron；K is sampling instant；Transfer function for hidden layer neuron；In present embodiment, this hidden layer transfer function is:
Network input vector
。
Wherein, X1(k) be Aeration tank flow of inlet water；X2K () is influent COD value；X3K () is influent ammonia nitrogen value；X4K () is sludge concentration；X5K () is Aeration tank mean temperature.
The artificial nerve network model of each Aeration tank of described training, it is achieved timing updates the process of network model's parameter and is:
In monitoring calculation machine called data memory element same sampling instant Aeration tank flow of inlet water data X1(k), influent COD data X2(k), influent ammonia nitrogen data X3(k), sludge concentration data X4(k), Aeration tank average temperature data X5(k) and dissolved oxygen data y1K (), by flow of inlet water data X1(k), influent COD data X2(k), influent ammonia nitrogen data X3(k), sludge concentration data X4(k) and Aeration tank average temperature data X5K () inputs sample as one, by the expected value of dissolved oxygenWith dissolved oxygen sampled data y1The difference of (k) and coefficient k5Long-pending export sample as one, namely.In present embodiment, monitoring calculation machine was every 10 minutes, transfers current 100 groups of input samples and output sample data, trains described DRNN artificial neural network.
Training error E(k) adopt error sum of squares:
WhereinFor output sample data, k5For aeration oxygen departure transfer ratio, value is 9.2～11.
The learning algorithm updating DRNN network model parameter is:
In formula,The respectively learning rate of input layer, hidden layer and output layer.The respectively inertia coeffeicent of input layer, hidden layer and output layer.
Claims (6)
1. a sewage disposal process aeration intelligence control system, it is characterised in that described system sewage disposal process aeration intelligence control system is made up of monitoring calculation machine, central control unit, n field control unit, n instrumentation group and n performance element；A model memory module (theoretical calculation model and the n that include n aeration control amount are individual for calculating the artificial nerve network model of aeration control correction) and a data memory module (for storing the Site Detection data of n Aeration tank) is had inside monitoring calculation machine；Central control unit is made up of ethernet communication module CP343 and central processor CPU 315-2DP；Field control unit is by PROFIBUS-DP(ProcessFieldBus-DecentralizedPeriphery) bus communication module EM277,244,2 analog input and output expansion module EM235 of central processor CPU form；Instrumentation group includes: flow of inlet water measures instrument, influent COD measures instrument, influent ammonia nitrogen measures instrument, sludge concentration measures instrument, Aeration tank temperature measuring instrument and dissolved oxygen sensing instrument；Performance element is made up of converter and aerator；Monitoring calculation machine is connected with EPA ETHERNET by communication cable；Central control unit is connected with EPA ETHERNET through communication cable by CP343 ethernet communication module；Central control unit is connected with PROFIBUS-DP bus through communication cable；N field control unit, respectively through bus extender module EM277, is connected with PROFIBUS-DP bus through communication cable；N field control unit performs module respectively through EM235 module with corresponding, instrumentation group is connected.
2. a kind of sewage disposal process aeration intelligence control system according to claim 1, it is characterized in that, the field data that described instrumentation group records connects affiliated field control unit through analog input and output module EM235 respectively, the field data of field control unit connects central control unit, central control unit connects monitoring calculation machine, is connected to data memory module.
3. a kind of sewage disposal process aeration intelligence control system according to claim 1, it is characterised in that the field data of the storage each Aeration tank detected by n instrumentation group in described control Computer Storage module.
4. a kind of sewage disposal process aeration intelligence control system according to claim 1, it is characterised in that store theoretical calculation model and the individual artificial nerve network model for calculating aeration control correction of n of n aeration control amount in described model memory module.
5. a kind of sewage disposal process aeration intelligence control system according to claim 1, it is characterised in that the corresponding Aeration tank of described each aeration mathematical model, calculates the theoretical aeration control amount of each Aeration tank respectively；The corresponding Aeration tank of everyone artificial neural networks model, in order to calculate the aeration control correction of this Aeration tank.
6. a kind of sewage disposal process aeration intelligence control system according to claim 1, it is characterised in that described artificial nerve network model is according to system operation history data timing training network, updates network model's parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610226233.2A CN105739325A (en) | 2016-04-13 | 2016-04-13 | Aeration intelligent control system in sewage treatment process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610226233.2A CN105739325A (en) | 2016-04-13 | 2016-04-13 | Aeration intelligent control system in sewage treatment process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105739325A true CN105739325A (en) | 2016-07-06 |
Family
ID=56254232
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610226233.2A Pending CN105739325A (en) | 2016-04-13 | 2016-04-13 | Aeration intelligent control system in sewage treatment process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105739325A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106354019A (en) * | 2016-11-21 | 2017-01-25 | 北京工业大学 | Accurate control method for dissolved oxygen based on RBF neural network |
| CN109857056A (en) * | 2019-03-08 | 2019-06-07 | 中冶华天南京电气工程技术有限公司 | A kind of Intelligent sewage processing control system |
Citations (8)
| 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 |
| CN101625353A (en) * | 2009-03-06 | 2010-01-13 | 北京工商大学 | Soft measurement method of outflow water quality of sewage treatment and on-line intelligent detecting instrument |
| 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 |
| CN202075272U (en) * | 2011-03-30 | 2011-12-14 | 北京中拓百川投资有限公司 | Soft measurement system applied to sewage treatment |
| CN102662040A (en) * | 2012-04-20 | 2012-09-12 | 辽宁工程技术大学 | Ammonian online soft measuring method for dynamic modularized nerve network |
| CN102778884A (en) * | 2012-08-09 | 2012-11-14 | 张涤非 | Intelligent control method and intelligent control system for sewage treatment plant |
| CN102902257A (en) * | 2012-10-30 | 2013-01-30 | 威水星空（北京）环境技术有限公司 | Sewage treatment process optimization and energy-saving control system and method |
| CN204116928U (en) * | 2014-09-24 | 2015-01-21 | 天津创业环保集团股份有限公司 | The accuracy-control system of sewage treatment plant's aeration total amount |
-
2016
- 2016-04-13 CN CN201610226233.2A patent/CN105739325A/en active Pending
Patent Citations (8)
| 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 |
| CN101625353A (en) * | 2009-03-06 | 2010-01-13 | 北京工商大学 | Soft measurement method of outflow water quality of sewage treatment and on-line intelligent detecting instrument |
| 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 |
| CN202075272U (en) * | 2011-03-30 | 2011-12-14 | 北京中拓百川投资有限公司 | Soft measurement system applied to sewage treatment |
| CN102662040A (en) * | 2012-04-20 | 2012-09-12 | 辽宁工程技术大学 | Ammonian online soft measuring method for dynamic modularized nerve network |
| CN102778884A (en) * | 2012-08-09 | 2012-11-14 | 张涤非 | Intelligent control method and intelligent control system for sewage treatment plant |
| CN102902257A (en) * | 2012-10-30 | 2013-01-30 | 威水星空（北京）环境技术有限公司 | Sewage treatment process optimization and energy-saving control system and method |
| CN204116928U (en) * | 2014-09-24 | 2015-01-21 | 天津创业环保集团股份有限公司 | The accuracy-control system of sewage treatment plant's aeration total amount |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106354019A (en) * | 2016-11-21 | 2017-01-25 | 北京工业大学 | Accurate control method for dissolved oxygen based on RBF neural network |
| CN106354019B (en) * | 2016-11-21 | 2019-01-22 | 北京工业大学 | A kind of dissolved oxygen accuracy control method based on RBF neural |
| CN109857056A (en) * | 2019-03-08 | 2019-06-07 | 中冶华天南京电气工程技术有限公司 | A kind of Intelligent sewage processing control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2021101438A4 (en) | Adaptive control method and system for aeration process | |
| US9747544B2 (en) | Method and system for wastewater treatment based on dissolved oxygen control by fuzzy neural network | |
| CN106873379B (en) | Sewage treatment optimal control method based on iterative ADP algorithm | |
| CN105404151B (en) | Sewage disposal process dynamic multi-objective optimization control method | |
| CN103744293B (en) | Wastewater treatment monitoring method and system based on fuzzy neural network | |
| CN103197544B (en) | Sewage disposal process multi-purpose control method based on nonlinear model prediction | |
| CN106802563B (en) | A kind of sewage procedure optimization control method based on drosophila optimization and LSSVM | |
| Langergraber | Numerical modelling: a tool for better constructed wetland design? | |
| CN108549234A (en) | A kind of multiobjective optimization control method based on dynamic variate | |
| CN102854296A (en) | Sewage-disposal soft measurement method on basis of integrated neural network | |
| CN108762082A (en) | A kind of sewage disposal process collaboration Optimal Control System | |
| US20190359510A1 (en) | Cooperative optimal control method and system for wastewater treatment process | |
| CN102262147A (en) | Soft measurement method and system for effluent chemical oxygen demand (COD) of waste water treatment system | |
| CN103197539A (en) | Wastewater disposal intelligent optimization control aeration quantity method | |
| CN108445757A (en) | A kind of sewage disposal process optimal control method based on dynamic multi-objective particle cluster algorithm | |
| CN108569756A (en) | A kind of Intellectualized sewage water treatment process control new method（EBIS） | |
| CN110606620A (en) | Sewage treatment process and method for controlling biochemical links in sewage treatment process based on neural network | |
| CN111762958A (en) | Deep well aeration process optimization method and device for sewage treatment plant based on ASM2D model | |
| CN102778884B (en) | Intelligent control method and intelligent control system for sewage treatment plant | |
| CN105739325A (en) | Aeration intelligent control system in sewage treatment process | |
| CN103792844A (en) | Sewage treatment control method based on sequential clusters | |
| Han et al. | Robust optimal control for anaerobic-anoxic-oxic reactors | |
| JP4188200B2 (en) | Plant-wide optimum process controller | |
| CN114314823A (en) | Dissolved oxygen control system and method in aeration link | |
| CN106769748B (en) | Intelligent detection system for water permeability of membrane bioreactor-MBR (Membrane bioreactor) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160706 |
|
| WD01 | Invention patent application deemed withdrawn after publication |