CN108319150B - Full-running state information sensing and optimal control system and method for biogas system - Google Patents
Full-running state information sensing and optimal control system and method for biogas system Download PDFInfo
- Publication number
- CN108319150B CN108319150B CN201810378406.1A CN201810378406A CN108319150B CN 108319150 B CN108319150 B CN 108319150B CN 201810378406 A CN201810378406 A CN 201810378406A CN 108319150 B CN108319150 B CN 108319150B
- Authority
- CN
- China
- Prior art keywords
- biogas
- value
- methane
- anaerobic fermentation
- fermentation unit
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims abstract description 140
- 238000000855 fermentation Methods 0.000 claims abstract description 86
- 239000010865 sewage Substances 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000009826 distribution Methods 0.000 claims abstract description 12
- 230000005540 biological transmission Effects 0.000 claims abstract description 10
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 26
- 239000001301 oxygen Substances 0.000 claims description 26
- 229910052760 oxygen Inorganic materials 0.000 claims description 26
- 239000007787 solid Substances 0.000 claims description 17
- 239000000463 material Substances 0.000 claims description 16
- 238000003756 stirring Methods 0.000 claims description 16
- 230000004151 fermentation Effects 0.000 claims description 13
- 150000007524 organic acids Chemical class 0.000 claims description 13
- 239000000126 substance Substances 0.000 claims description 13
- 238000007599 discharging Methods 0.000 claims description 12
- 238000004519 manufacturing process Methods 0.000 claims description 12
- 239000007788 liquid Substances 0.000 claims description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 9
- 239000000779 smoke Substances 0.000 claims description 9
- 238000010977 unit operation Methods 0.000 claims description 9
- 230000008447 perception Effects 0.000 claims description 4
- 238000010438 heat treatment Methods 0.000 claims description 3
- 238000002898 library design Methods 0.000 claims description 3
- 230000033116 oxidation-reduction process Effects 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 244000144972 livestock Species 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 238000010792 warming Methods 0.000 description 2
- 102000004190 Enzymes Human genes 0.000 description 1
- 108090000790 Enzymes Proteins 0.000 description 1
- CKUAXEQHGKSLHN-UHFFFAOYSA-N [C].[N] Chemical compound [C].[N] CKUAXEQHGKSLHN-UHFFFAOYSA-N 0.000 description 1
- 238000003915 air pollution Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003851 biochemical process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000003608 fece Anatomy 0.000 description 1
- 230000000813 microbial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000003900 soil pollution Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
Images
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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E50/00—Technologies for the production of fuel of non-fossil origin
- Y02E50/30—Fuel from waste, e.g. synthetic alcohol or diesel
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Processing Of Solid Wastes (AREA)
Abstract
The invention discloses a system and a method for sensing and optimally controlling full running state information of a methane system, wherein the system comprises a full running state cloud real-time database of the methane system, and the full running state cloud real-time database of the methane system is communicated with a running state sensing system of a pretreatment unit of the methane system, an anaerobic fermentation unit information acquisition system of the methane system, a methane transmission and distribution running state sensing system, a sewage treatment unit running state sensing system and a methane system environment information sensing system. Selecting the running state characteristics of the biogas system; constructing a deep belief network DBN; performing layer-by-layer greedy training, namely adjusting parameters by using a back propagation BP algorithm, and performing the training; inputting real-time data of the biogas system into the trained DBN to generate an optimal control variable; and completing control according to the optimal control variable. The problems that the operation process of the biogas system is difficult to optimally control in real time and the gas yield is low due to the characteristics of complex operation process, numerous influence factors and the like can be effectively solved.
Description
Technical Field
The invention relates to the technical field of operation optimization control of a methane system, in particular to a system and a method for sensing and optimally controlling full operation state information of the methane system.
Background
The shortage of energy, environmental pollution and climate change are important factors for restricting the sustainable development of the economy and society in the world today, and the energy and environmental problems have become important strategic problems with high attention at home and abroad.
The feces discharged by the livestock in the large farm not only causes serious water pollution, air pollution and soil pollution, but also easily causes the disease of the livestock, and directly affects the epidemic prevention and the sanitation of the cultivation and the quality of livestock products. The development of the large and medium-sized biogas system is an important way for realizing the ecological cultivation to promote the regional circular economy development, reducing the cultivation pollution to improve the environmental quality, developing nuisanceless agricultural products to ensure the food safety and developing and utilizing the new biogas energy, and has important significance.
However, the biogas system is an intricate and complex microbial biochemical process, anaerobic environment, carbon-nitrogen ratio of raw materials, fermentation temperature, pH value, enzyme concentration, substrate concentration and the like are important key factors influencing the efficient gas production of the biogas system, and the operation mechanism of the biogas system and the optimal control of the production process are extremely difficult to be observed. Whether the biogas system can operate efficiently or not depends on the device structure of the biogas system, and further depends on a full-state information sensing and real-time optimal control method for the operation process of the biogas system, the operation mechanism of the biogas system is excavated based on historical operation data, and real-time optimal regulation and control of the intelligent expert system on the operation process of the biogas system are established, so that the biogas system operates efficiently and the gas yield is improved.
Disclosure of Invention
The invention aims to solve the problems, and provides a system and a method for sensing and optimally controlling the full operation state information of a methane system, which can effectively solve the problems of difficult real-time optimal control and low methane yield in the operation process of the methane system with the characteristics of complex operation process, numerous influencing factors and the like.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the full-running state information sensing system of the biogas system comprises a full-running state cloud real-time database of the biogas system, wherein the full-running state cloud real-time database of the biogas system is communicated with a running state sensing system of a pretreatment unit of the biogas system, an anaerobic fermentation unit information acquisition system of the biogas system, a biogas transmission and distribution running state sensing system, a sewage treatment unit running state sensing system and a biogas system environment information sensing system.
The operation state sensing system of the pretreatment unit of the biogas system comprises a first CPU module, wherein the first CPU module is connected with a first AI analog input module, the first AI analog input module is connected with a first ultrasonic water level meter, a first temperature transmitter and a first total solid concentration detector, and the first CPU module is used for sensing and collecting information of the water level, the temperature and the total solid concentration of the pretreatment unit.
The anaerobic fermentation unit running state sensing system of the biogas system comprises a second CPU module, and the second CPU module is connected with a second AI analog quantity input module and a first DI digital quantity input module;
the second AI analog input module is connected with a second ultrasonic water level meter, a second temperature transmitter, a PH value detector, a second total solid concentration detector, a first chemical oxygen demand value detector, a first biochemical oxygen demand value detector, a first volatile organic acid detector and an oxidation reduction potentiometer;
the first DI digital quantity input module is connected with the overload limit switch;
the information sensing and acquisition of the liquid level of the anaerobic fermentation unit, the temperature and the PH value of the middle and lower parts of the upper part and the total solid concentration and overload alarm are realized.
The biogas transmission and distribution unit operation state sensing system comprises a third CPU module, wherein the third CPU module is connected with a third AI analog quantity input module and a second DI digital quantity input module;
the third AI analog input module and CH 4 Concentration detector, CO 2 Concentration detector, O 2 Concentration detector, H 2 The S concentration detector, the biogas flowmeter, the biogas moisture detector and the biogas pressure gauge are connected;
the second DI digital quantity input module is connected with the biogas leakage alarm;
CH for realizing biogas transmission and distribution unit 4 、CO 2 、O 2 And H 2 S concentration, methane flow, water content, pressure and methane leakage alarm information sensing and acquisition.
The sewage treatment unit running state sensing system comprises a fourth CPU module, wherein the fourth CPU module is connected with a fourth AI analog quantity input module and a third DI digital quantity input module;
the fourth AI analog input module is connected with a sewage thermometer, a sewage flowmeter, a sewage level meter, a second chemical oxygen demand value detector, a second biochemical oxygen demand value detector, a second volatile organic acid detector and a suspended matter value detector;
the third DI digital quantity input module is connected with the smoke detection alarm;
realizing the information sensing and collection of sewage flow, temperature, liquid level, chemical oxygen demand, biochemical oxygen demand, volatile organic acid and suspended matters.
The methane system environment information acquisition system comprises a fifth CPU module, wherein the fifth CPU module is connected with a fifth AI analog quantity input module and a fourth DI digital quantity input module;
the fifth AI analog input module is connected with an ambient thermometer, an ambient hygrometer, a barometer and an anemometer;
the fourth DI digital quantity input module is connected with the smoke detection alarm;
realizing the information sensing and acquisition of temperature, humidity, atmospheric pressure, wind speed and smoke detection alarm of the methane system.
The full-running state cloud real-time database of the biogas system comprises a cloud computing integrated machine, wherein the cloud computing integrated machine is communicated with a running state sensing system of a pretreatment unit of the biogas system, an anaerobic fermentation unit information acquisition system of the biogas system, a biogas output and distribution running state sensing system, a sewage treatment unit running state sensing system and a biogas system environment information sensing system through a tera-megaswitch;
the cloud computing all-in-one machine is provided with a real-time production database, a historical data query database and a data table of the real-time production database and the historical data query database; the two databases are synchronized by Golden Gate software.
And (3) producing a daily data table of the database in real time, wherein each table only retains 1 day of data. The historical data query library designs a day data table and a month data table, and stores the day data into the month table of the corresponding date through the ETL.
The system comprises a biogas system, an intelligent expert system, a PLC (programmable logic controller), an automatic feeding and discharging system, an automatic material total solid concentration allocation system, a PH value automatic control system, an automatic stirring system, an automatic sewage disposal system and an anaerobic fermentation unit automatic warming system, wherein the optimal control system of the biogas system is based on a full-running state information perception system of the biogas system;
the PLC, the automatic feeding and discharging system, the automatic material total solid concentration allocation system, the PH value automatic control system, the automatic stirring system, the automatic sewage discharging system and the anaerobic fermentation unit automatic temperature increasing system are optimally controlled according to the optimal control result of the intelligent expert module.
The control method based on the optimal control system comprises the following steps:
step one, selecting the running state characteristic V of a methane system i ；
Constructing a deep belief network DBN;
step three, historical operation state characteristics V of the methane system i Inputting a DBN, carrying out greedy training on the DBN layer by layer, and then adjusting DBN parameters by using a back propagation BP algorithm to finish the training of the DBN;
inputting real-time data of the biogas system into the DBN after training in the step three to generate an optimal control variable
And fifthly, completing control according to the optimal control variable in the fourth step.
Wherein,,
V i ＝[LT YCL ,T YCL ,TS YCL ,LT YY ,T YY-S ,T YY-Z ,T YY-X ,PH YY ,TS YY ,COD YY ,BOD YY ,VFA YY ,CH4 YY ,CO2 YY ,L ZQ ,W ZQ ,P ZQ ,T HJ ,RH HJ ,P HJ ,S HJ ]；LT YCL for the level value of the pretreatment unit, T YCL For the temperature value of the pretreatment unit, TS YCL For the material TS concentration value, LT of the pretreatment unit YY For the liquid level value of the anaerobic fermentation unit, T YY-S For the upper temperature value, T, of the anaerobic fermentation unit YY-Z Is the middle temperature value of the anaerobic fermentation unit, T YY-X For the lower temperature value, PH, of the anaerobic fermentation unit YY For pH value, TS of anaerobic fermentation unit YY Is the material TS concentration value and COD of the anaerobic fermentation unit YY BOD, the chemical oxygen demand of anaerobic fermentation unit YY For biochemical oxygen demand value of anaerobic fermentation unit, VFA YY Is the volatile organic acid value, CH4 of the anaerobic fermentation unit YY Is CH 4 Concentration value, CO2 YY Is CO 2 Concentration value, L ZQ Is the methane flow value, W ZQ Is the moisture value and P of the biogas ZQ Is the methane pressure value, T HJ Is the ambient temperature value, RH HJ Is the ambient humidity value, P HJ Is the ambient atmospheric pressure value, S HJ Is an ambient wind speed value;
the specific method of the first step comprises the following steps:
step 1.1, reconstructing a time sequence v of the operation state of the biogas system by adopting a C-C method phase space i Setting v i Is a delay time t of (2) i And embedding dimension m i And take t i =1 and m i =3600, and running state data v of methane system i Uniformly expressed as v i ＝[v i (t),v i (t-1),…,v i (t-(3600-1))]；
Step 1.2, select V i Is the characteristic data of the methane system,
V i ＝[LT YCL ,T YCL ,TS YCL ,LT YY ,T YY-S ,T YY-Z ,T YY-X ,PH YY ,TS YY ,COD YY ,BOD YY ,VFA YY ,CH4 YY ,CO2 YY ,L ZQ ,W ZQ ,P ZQ ,T HJ ,RH HJ ,P HJ ,S HJ ]v is set up i The feature data is expressed as a 21 x 3600 historical running data time series vector.
The specific method of the fifth step comprises the following steps:
step 5.1, controlling the optimal temperature value of the variable fermentation unit according to the optimal control of the step four
The PLC controller adopts a PID control algorithm to control a heating system of the biogas system, so that the anaerobic fermentation unit is kept at an optimal temperature value;
step 5.2, controlling the variable fermentation unit optimally according to the fourth step
The PLC controller controls the feeding and discharging system by adopting a PID control algorithm, so that the TS concentration value of the anaerobic fermentation unit is kept at the optimal TS concentration value;
step 5.3, controlling the variable fermentation unit optimally according to the fourth step
The PLC controller adopts a PID control algorithm to control a PH value allocation system, so that the PH value of the anaerobic fermentation unit is kept at the optimal PH concentration value;
step 5.4, controlling the optimal stirring interval time of the variable fermentation unit according to the optimal control of the step four
The PLC controller controls the stirring time of the stirring system regularly.
The invention has the beneficial effects that:
the invention effectively solves the difficult problem that the biogas system with complex operation mechanism and difficult excavation of operation rule is difficult to realize optimal biogas production control, and by adopting the full-state information sensing and real-time optimal control integrated design method, the operation rule of the biogas system can be effectively excavated and insight by adopting a deep learning method based on historical data, and the biogas production process can be optimally controlled in real time based on an intelligent expert system, so that the biogas production rate and the total biogas production amount of the biogas system can be effectively improved.
Drawings
FIG. 1 is a diagram of a full state information sensing and real-time optimal control integrated design method structure of a biogas system;
FIG. 2 is a diagram of a full state information sensing method of a biogas system;
FIG. 3 is a diagram of a full state cloud real-time database architecture of a biogas system;
FIG. 4 is a diagram of a full state cloud real-time database table design for a biogas system;
FIG. 5 is a diagram of a deep learning-based intelligent expert system of the biogas system;
FIG. 6 is a block diagram of an optimal control system for a biogas system.
Detailed Description
The invention will be further described with reference to the drawings and examples.
The invention mainly comprises the following steps: the system comprises a full-state sensing system of the biogas system, a full-state cloud real-time database of the biogas system, an intelligent expert system of the biogas system based on deep learning and a real-time optimal control system of the biogas system. The whole technical scheme structure diagram is shown in figure 1.
The full operation state information sensing system of the methane system comprises: the system comprises an operation state sensing system of a pretreatment unit of the biogas system, an anaerobic fermentation unit information sensing system of the biogas system, a biogas transmission and distribution operation state sensing system, a sewage treatment unit operation state sensing system and a biogas system environment information sensing system. The technical scheme structure is shown in figure 2.
The pretreatment unit operation state sensing system of the biogas system comprises: the intelligent control system comprises a first CPU module, wherein the first CPU module is connected with a first AI analog input module, the first AI analog input module is connected with a first ultrasonic water level meter, a first temperature transmitter and a first total solid concentration detector, and the first CPU module is used for realizing information sensing and acquisition of the water level, the temperature and the total solid concentration of a preprocessing unit. The first CPU module adopts Siemens PLC S7-300 CPU.
The anaerobic fermentation unit operation state sensing system of the biogas system comprises: the system comprises a second CPU module (Siemens PLC S7-300 CPU), a second AI analog quantity input module, a first DI digital quantity input module, a second ultrasonic water level meter, a second temperature transmitter, a PH value detector, a Total Solid (TS) concentration detector, a first Chemical Oxygen Demand (COD) value detector, a first Biochemical Oxygen Demand (BOD) value detector, a first volatile organic acid (VFA) detector, an oxidation-reduction potentiometer (ORP) and an overload limit switch, and can realize the information sensing and acquisition of the liquid level of an anaerobic fermentation unit, the temperature, the PH value, the TS concentration and the overload alarm of the middle lower part of the upper part.
The biogas transmission and distribution unit operation state sensing system comprises: comprising the following steps: a third CPU module (Siemens PLC S7-300 CPU), a third AI analog quantity input module, a second DI digital quantity input module, and a CH 4 Concentration detector, CO 2 Concentration detector, O 2 Concentration detector, H 2 S concentration detector, marsh gas flowmeter, marsh gas moisture detector, marsh gas pressure gauge, marsh gas leakage alarm, CH of marsh gas transmission and distribution unit can be realized 4 、CO 2 、O 2 And H 2 S concentration, methane flow, water content, pressure and methane leakage alarm information sensing and acquisition.
Sewage treatment unit running state perception system: comprising the following steps: the system comprises a fourth CPU module (Siemens PLC S7-300CPU module), a fourth AI analog quantity input module, a third DI digital quantity input module, a sewage thermometer, a sewage flowmeter, a sewage level meter, a second Chemical Oxygen Demand (COD) value detector, a second Biochemical Oxygen Demand (BOD) value detector, a second volatile organic acid (VFA) detector, a suspended matter (SS) value detector and a smoke detection alarm, and realizes information sensing and acquisition of sewage flow, temperature, liquid level and COD, BOD, VFA, SS.
The methane system environment information acquisition system comprises: comprising the following steps: the fifth CPU module (Siemens PLC S7-300 CPU), the fifth AI analog input module, the fourth DI digital input module, the ambient thermometer, the ambient hygrometer, the barometer, the anemometer and the smoke detection alarm can realize the information sensing and collection of the temperature, the humidity, the atmospheric pressure, the wind speed and the smoke detection alarm of the biogas system.
The full-running state cloud real-time database of the biogas system mainly comprises: cloud computing all-in-one tera-megaswitch. The cluster architecture adopts a Hadoop architecture, the bottom database adopts a PI real-time database, and streaming technology data is used for warehousing. The real-time database is deployed on a distributed architecture of cloud computing, and real-time warehousing of mass data is realized through parallel distributed computing and multi-copy technology of the cloud computing. Meanwhile, the RAID6 technology is adopted to realize data physical protection, and the SnapShot and SnapRestore technology adopting the Net App storage mechanism is adopted to realize data logic protection.
The full-running state cloud real-time database of the biogas system comprises a full-state information real-time production database and a historical data query database of the biogas system, the two databases are synchronized through Golden Gate software, and the database architecture is shown in figure 3.
The system also comprises a real-time production database of the full-state information of the methane system and a data table of a historical data query database. And (3) producing a daily data table of the database in real time, wherein each table only retains 1 day of data. The historical data query library designs a day data table and a month data table, and stores the day data into the month table of the corresponding date through the ETL. The database table is shown in fig. 4.
The system comprises a biogas system, an intelligent expert system, a PLC (programmable logic controller), an automatic feeding and discharging system, an automatic material total solid concentration allocation system, a PH value automatic control system, an automatic stirring system, an automatic sewage disposal system and an anaerobic fermentation unit automatic warming system, wherein the optimal control system of the biogas system is based on a full-running state information perception system of the biogas system;
the PLC, the automatic feeding and discharging system, the automatic material total solid concentration allocation system, the PH value automatic control system, the automatic stirring system, the automatic sewage discharging system and the anaerobic fermentation unit automatic temperature increasing system are optimally controlled according to the optimal control result of the intelligent expert module.
The control method based on the optimal control system, as shown in FIG. 5, comprises
Step one, extracting the operating state characteristics of a methane system, and selecting the operating state characteristics V of the methane system i ；
V i ＝[LT YCL ,T YCL ,TS YCL ,LT YY ,T YY-S ,T YY-Z ,T YY-X ,PH YY ,TS YY ,COD YY ,BOD YY ,VFA YY ,CH4 YY ,CO2 YY ,L ZQ ,W ZQ ,P ZQ ,T HJ ,RH HJ ,P HJ ,S HJ ]；
Wherein: LT (LT) YCL For the level value of the pretreatment unit, T YCL For the temperature value of the pretreatment unit, TS YCL For the material TS concentration value, LT of the pretreatment unit YY For the liquid level value of the anaerobic fermentation unit, T YY-S For the upper temperature value, T, of the anaerobic fermentation unit YY-Z Is the middle temperature value of the anaerobic fermentation unit, T YY-X For the lower temperature value, PH, of the anaerobic fermentation unit YY For pH value, TS of anaerobic fermentation unit YY Is the material TS concentration value and COD of the anaerobic fermentation unit YY BOD, the chemical oxygen demand of anaerobic fermentation unit YY For biochemical oxygen demand value of anaerobic fermentation unit, VFA YY Is the volatile organic acid value, CH4 of the anaerobic fermentation unit YY Is CH 4 Concentration value, CO2 YY Is CO 2 Concentration value, L ZQ Is the methane flow value, W ZQ Is the moisture value and P of the biogas ZQ Is the methane pressure value, T HJ Is the ambient temperature value, RH HJ Is the ambient humidity value, P HJ Is the ambient atmospheric pressure value, S HJ Is an ambient wind speed value;
constructing a Deep Belief Network (DBN);
the DBN is based on a limited Boltzmann machine (RBM), and the network layer number and the node number of each layer of the DBN are determined;
training a Deep Belief Network (DBN);
historical operating state characteristic V of methane system i Inputting a DBN, carrying out greedy training on the DBN layer by layer, and then adjusting DBN parameters by using a back propagation BP algorithm to finish the training of the DBN;
step four, outputting an optimal control variable of the biogas system;
inputting real-time data of the biogas system into the DBN after training in the third step to generate an optimal control variable
Wherein,,
is the optimal material TS concentration value of the pretreatment unit, < >>
For the optimal liquid level value of the anaerobic fermentation unit, +.>
For the optimal upper temperature value of the anaerobic fermentation unit, < >>
Is the optimal middle temperature value of the anaerobic fermentation unit +.>
For the optimal lower temperature of the anaerobic fermentation unit +.>
For the optimal pH value of the anaerobic fermentation unit +.>
Is the optimal material TS concentration value of the anaerobic fermentation unit, < + >>
For the optimal chemical oxygen demand value of the anaerobic fermentation unit +.>
Is the optimal biochemical oxygen demand value of the anaerobic fermentation unit +.>
Is the optimal volatile organic acid value of the anaerobic fermentation unit, < >>
The optimal stirring interval time of the anaerobic fermentation unit;
in the first step, the operation state feature extraction is performed as follows:
step 1.1, extracting characteristic variables of running states:
V i ＝[LT YCL ,T YCL ,TS YCL ,LT YY ,T YY-S ,T YY-Z ,T YY-X ,PH YY ,TS YY ,COD YY ,BOD YY ,VFA YY ,CH4 YY ,CO2 YY ,L ZQ ,W ZQ ,P ZQ ,T HJ ,RH HJ ,P HJ ,S HJ ]；
wherein: LT (LT) YCL For the level value of the pretreatment unit, T YCL For the temperature value of the pretreatment unit, TS YCL For the material TS concentration value, LT of the pretreatment unit YY For the liquid level value of the anaerobic fermentation unit, T YY-S For the upper temperature value, T, of the anaerobic fermentation unit YY-Z Is the middle temperature value of the anaerobic fermentation unit, T YY-X For the lower temperature value, PH, of the anaerobic fermentation unit YY For pH value, TS of anaerobic fermentation unit YY Is the material TS concentration value and COD of the anaerobic fermentation unit YY BOD, the chemical oxygen demand of anaerobic fermentation unit YY For biochemical oxygen demand value of anaerobic fermentation unit, VFA YY Is the volatile organic acid value, CH4 of the anaerobic fermentation unit YY Is CH 4 Concentration value, CO2 YY Is CO 2 Concentration value, L ZQ Is the methane flow value, W ZQ Is the moisture value and P of the biogas ZQ Is the methane pressure value, T HJ Is the ambient temperature value, RH HJ Is the ambient humidity value, P HJ Is the ambient atmospheric pressure value, S HJ Is an ambient wind speed value;
step 1.2, C-C methodPhase space reconstruction biogas system running state time sequence v i Setting v i Is a delay time t of (2) i And embedding dimension m i And take t i =1 and m i =3600, and running state data v of methane system i Uniformly expressed as v i ＝[v i (t),v i (t-1),…,v i (t-(3600-1))]；
Step 1.3 according to step 1.2, V i Is characteristic data V of a methane system i The feature data is expressed as a 21×3600 historical running data time series vector;
in the second step, the deep belief network DBN is constructed, which specifically includes the following steps:
step 2.1, constructing a RBM-based 5-layer DBN, which comprises 1 input layer, 3 hidden layers and 1 decision layer;
step 2.2, designating the number of nodes of the input layer of the DBN as 21×3600; the number of nodes of the first hidden layer is 1000; the number of nodes of the second hidden layer is 1000; the number of nodes of the third hidden layer is 2000; the number of nodes of the decision layer is 11.
step 3.1, training the 5 layers of the DBN layer by using a contrast divergence CD algorithm, and calculating output values of 3 hidden layers and 1 decision layer and weights and biases among the layers;
and 3.2, adjusting the whole DBN by using a BP algorithm, optimizing DBN parameters, and completing the global training of the DBN.
Step five, real-time optimal control of the methane system, as shown in figure 6,
step 5.1 controlling the optimal temperature value of the variable fermentation unit according to the optimal control of the step four
The PLC controller adopts a PID control algorithm to control a heating system of the biogas system, so that the anaerobic fermentation unit is kept at an optimal temperature value; />
Step 5.2: controlling the variable fermentation unit optimally according to the fourth step
The PLC controller controls the feeding and discharging system by adopting a PID control algorithm, so that the TS concentration value of the anaerobic fermentation unit is kept at the optimal TS concentration value;
step 5.3: controlling the variable fermentation unit optimally according to the fourth step
The PLC controller adopts a PID control algorithm to control a PH value allocation system, so that the PH value of the anaerobic fermentation unit is kept at the optimal PH concentration value;
step 5.4: optimal stirring interval time of fermentation unit according to optimal control variable of step four
The PLC controller controls the stirring time of the stirring system regularly.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (8)
1. A control method of an optimal control system of a biogas system of a full-running state information sensing system of the biogas system is characterized in that,
the full-running state information sensing system of the methane system comprises a full-running state cloud real-time database of the methane system, wherein the full-running state cloud real-time database of the methane system is communicated with a running state sensing system of a pretreatment unit of the methane system, an anaerobic fermentation unit information acquisition system of the methane system, a methane transmission and distribution running state sensing system, a sewage treatment unit running state sensing system and a methane system environment information sensing system;
the system comprises a methane system, an intelligent expert system, a PLC controller, an automatic feeding and discharging system, an automatic material total solid concentration allocation system, a PH value automatic control system, an automatic stirring system, an automatic sewage disposal system and an anaerobic fermentation unit automatic temperature increasing system, wherein the methane system optimal control system of the methane system is a full-running state information perception system of the methane system;
the PLC, the automatic feeding and discharging system, the automatic material total solid concentration allocation system, the PH value automatic control system, the automatic stirring system, the automatic sewage discharging system and the anaerobic fermentation unit automatic temperature increasing system are optimally controlled according to the optimal control result of the intelligent expert module;
the control method of the optimal control system comprises the following steps:
step one, selecting the running state characteristic V of a methane system i ；
Constructing a deep belief network DBN;
step three, historical operation state characteristics V of the methane system i Inputting a DBN, carrying out greedy training on the DBN layer by layer, and then adjusting DBN parameters by using a back propagation BP algorithm to finish the training of the DBN;
inputting real-time data of the biogas system into the DBN after training in the step three to generate an optimal control variable
Step five, completing control according to the optimal control variable in the step four;
wherein,,
V i ＝[LT YCL ,T YCL ,TS YCL ,LT YY ,T YY-S ,T YY-Z ,T YY-X ,PH YY ,TS YY ,COD YY ,BOD YY ,VFA YY ,CH4 YY ,CO2 YY ,
L ZQ ,W ZQ ,P ZQ ,T HJ ,RH HJ ,P HJ ,S HJ ]；LT YCL for the level value of the pretreatment unit, T YCL For the temperature value of the pretreatment unit, TS YCL For the material TS concentration value, LT of the pretreatment unit YY For the liquid level value of the anaerobic fermentation unit, T YY-S For the upper temperature value, T, of the anaerobic fermentation unit YY-Z Is the middle temperature value of the anaerobic fermentation unit, T YY-X For the lower temperature value, PH, of the anaerobic fermentation unit YY For pH value, TS of anaerobic fermentation unit YY Is the material TS concentration value and COD of the anaerobic fermentation unit YY BOD, the chemical oxygen demand of anaerobic fermentation unit YY For biochemical oxygen demand value of anaerobic fermentation unit, VFA YY Is the volatile organic acid value, CH4 of the anaerobic fermentation unit YY Is CH 4 Concentration value, CO2 YY Is CO 2 Concentration value, L ZQ Is the methane flow value, W ZQ Is the moisture value and P of the biogas ZQ Is the methane pressure value, T HJ Is the ambient temperature value, RH HJ Is the ambient humidity value, P HJ Is the ambient atmospheric pressure value, S HJ Is an ambient wind speed value;
the specific method of the first step comprises the following steps:
step 1.1, reconstructing a time sequence v of the operation state of the biogas system by adopting a C-C method phase space i Setting v i Is a delay time t of (2) i And embedding dimension m i And take t i =1 and m i =3600, and running state data v of methane system i Uniformly expressed as v i ＝[v i (t),v i (t-1),...,v i (t-(3600-1))]；
Step 1.2, select V i Is the characteristic data of the methane system,
V i ＝[LT YCL ,T YCL ,TS YCL ,LT YY ,T YY-S ,T YY-Z ,T YY-X ,PH YY ,TS YY ,COD YY ,BOD YY ,VFA YY ,CH4 YY ,CO2 YY ,L ZQ ,W ZQ ,P ZQ ,T HJ ,RH HJ ,P HJ ,S HJ ]v is set up i The feature data is expressed as a 21 x 3600 historical running data time series vector.
2. The control method of an optimal control system of a biogas system of a full-operation state information sensing system of a biogas system according to claim 1, wherein the operation state sensing system of a pretreatment unit of the biogas system comprises a first CPU module, the first CPU module is connected with a first AI analog input module, the first AI analog input module is connected with a first ultrasonic water level gauge, a first temperature transmitter and a first total solid concentration detector, and the first CPU module is used for sensing and collecting information of the water level, the temperature and the total solid concentration of the pretreatment unit.
3. The control method of an optimal control system of a biogas system of a full-operation state information sensing system of the biogas system according to claim 1, wherein the anaerobic fermentation unit operation state sensing system of the biogas system comprises a second CPU module, and the second CPU module is connected with a second AI analog quantity input module and a first DI digital quantity input module;
the second AI analog input module is connected with a second ultrasonic water level meter, a second temperature transmitter, a PH value detector, a second total solid concentration detector, a first chemical oxygen demand value detector, a first biochemical oxygen demand value detector, a first volatile organic acid detector and an oxidation reduction potentiometer;
the first DI digital quantity input module is connected with the overload limit switch;
the information sensing and acquisition of the liquid level of the anaerobic fermentation unit, the temperature and the PH value of the middle and lower parts of the upper part and the total solid concentration and overload alarm are realized.
4. The control method of an optimal control system of a biogas system of a full-operation state information sensing system of the biogas system according to claim 1, wherein the biogas output and distribution unit operation state sensing system comprises a third CPU module, and the third CPU module is connected with a third AI analog quantity input module and a second DI digital quantity input module;
the third AI analog input module and CH 4 Concentration detector, CO 2 Concentration detector, O 2 Concentration detector, H 2 S concentration detector and methane flowThe meter, the methane moisture detector and the methane pressure meter are connected;
the second DI digital quantity input module is connected with the biogas leakage alarm;
CH for realizing biogas transmission and distribution unit 4 、CO 2 、O 2 And H 2 S concentration, methane flow, moisture, pressure and methane leakage alarm information sensing and acquisition.
5. The control method of an optimal control system of a biogas system of a full-operation state information sensing system of the biogas system according to claim 1, wherein the sewage treatment unit operation state sensing system comprises a fourth CPU module, and the fourth CPU module is connected with a fourth AI analog quantity input module and a third DI digital quantity input module;
the fourth AI analog input module is connected with a sewage thermometer, a sewage flowmeter, a sewage level meter, a second chemical oxygen demand value detector, a second biochemical oxygen demand value detector, a second volatile organic acid detector and a suspended matter value detector;
the third DI digital quantity input module is connected with the smoke detection alarm;
realizing the information sensing and collection of sewage flow, temperature, liquid level, chemical oxygen demand, biochemical oxygen demand, volatile organic acid and suspended matters.
6. The control method of the optimal control system of the biogas system of the full-operation state information sensing system of the biogas system according to claim 1, wherein the biogas system environment information acquisition system comprises a fifth CPU module, and the fifth CPU module is connected with a fifth AI analog quantity input module and a fourth DI digital quantity input module;
the fifth AI analog input module is connected with an ambient thermometer, an ambient hygrometer, a barometer and an anemometer;
the fourth DI digital quantity input module is connected with the smoke detection alarm;
realizing the information sensing and acquisition of temperature, humidity, atmospheric pressure, wind speed and smoke detection alarm of the methane system.
7. The control method of an optimal control system of a biogas system of a full operation state information sensing system of the biogas system according to claim 1, wherein the full operation state cloud real-time database of the biogas system comprises a cloud computing integrated machine, and the cloud computing integrated machine is communicated with an operation state sensing system of a pretreatment unit of the biogas system, an anaerobic fermentation unit information acquisition system of the biogas system, a biogas transmission and distribution operation state sensing system, a sewage treatment unit operation state sensing system and a biogas system environment information sensing system through a tera-switch;
the cloud computing all-in-one machine is provided with a real-time production database, a historical data query database and a data table of the real-time production database and the historical data query database; the two databases are synchronized by Golden Gate software;
producing a daily data table of a database in real time, wherein each table only retains 1 day of data; the historical data query library designs a day data table and a month data table, and stores the day data into the month table of the corresponding date through the ETL.
8. The control method according to claim 1, wherein the specific method of the fifth step includes:
step 5.1, controlling the optimal temperature value of the variable fermentation unit according to the optimal control of the step four
The PLC controller adopts a PID control algorithm to control a heating system of the biogas system, so that the anaerobic fermentation unit is kept at an optimal temperature value;
step 5.2, controlling the variable fermentation unit optimally according to the fourth step
The PLC controller controls the feeding and discharging system by adopting a PID control algorithm, so that the TS concentration value of the anaerobic fermentation unit is kept at the optimal TS concentration value;
step 5.3 according to the steps ofOptimally controlled variable fermentation unit
The PLC controller adopts a PID control algorithm to control a PH value allocation system, so that the PH value of the anaerobic fermentation unit is kept at the optimal PH concentration value;
step 5.4, controlling the optimal stirring interval time of the variable fermentation unit according to the optimal control of the step four
The PLC controller controls the stirring time of the stirring system regularly. />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810378406.1A CN108319150B (en) | 2018-04-25 | 2018-04-25 | Full-running state information sensing and optimal control system and method for biogas system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810378406.1A CN108319150B (en) | 2018-04-25 | 2018-04-25 | Full-running state information sensing and optimal control system and method for biogas system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108319150A CN108319150A (en) | 2018-07-24 |
| CN108319150B true CN108319150B (en) | 2023-05-23 |
Family
ID=62895347
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810378406.1A Active CN108319150B (en) | 2018-04-25 | 2018-04-25 | Full-running state information sensing and optimal control system and method for biogas system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108319150B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109184933B (en) * | 2018-09-10 | 2020-07-31 | 山东交通学院 | Cooperative optimization control method and system for methane internal combustion generator set |
| CN109401961A (en) * | 2018-10-16 | 2019-03-01 | 上海量能生物科技有限公司 | Biological culture system with artificial intelligence |
| CN109456887A (en) * | 2018-10-16 | 2019-03-12 | 上海量能生物科技有限公司 | Biological culture system based on Internet of Things |
| CN109184931B (en) * | 2018-11-13 | 2024-01-19 | 山东交通学院 | Active control system and method for methane internal combustion generator set |
| CN111176121A (en) * | 2020-02-06 | 2020-05-19 | 山东大学 | Vehicle control unit optimization system and method based on cloud platform |
| CN112479360B (en) * | 2020-11-06 | 2022-07-12 | 深圳市深能环保东部有限公司 | Method for identifying and adjusting abnormity of anaerobic treatment process of domestic garbage leachate |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202054663U (en) * | 2011-05-24 | 2011-11-30 | 武汉凯迪水务水处理有限公司 | Dissolved oxygen automatic control system for sewage water biological pool |
| US8417391B1 (en) * | 2011-12-15 | 2013-04-09 | Restore Nv | Automated demand response energy management system |
| CN103305413A (en) * | 2012-03-15 | 2013-09-18 | 北京愿景宏能源环保科技发展有限公司 | Biogas fermentation gas supply engineering control system |
| CN203950194U (en) * | 2014-07-16 | 2014-11-19 | 南京宏博环保实业有限公司 | A kind of biogas real-time monitoring system |
| WO2017188858A1 (en) * | 2016-04-28 | 2017-11-02 | Schlumberger Canada Limited | Reservoir performance system |
-
2018
- 2018-04-25 CN CN201810378406.1A patent/CN108319150B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202054663U (en) * | 2011-05-24 | 2011-11-30 | 武汉凯迪水务水处理有限公司 | Dissolved oxygen automatic control system for sewage water biological pool |
| US8417391B1 (en) * | 2011-12-15 | 2013-04-09 | Restore Nv | Automated demand response energy management system |
| CN103305413A (en) * | 2012-03-15 | 2013-09-18 | 北京愿景宏能源环保科技发展有限公司 | Biogas fermentation gas supply engineering control system |
| CN203950194U (en) * | 2014-07-16 | 2014-11-19 | 南京宏博环保实业有限公司 | A kind of biogas real-time monitoring system |
| WO2017188858A1 (en) * | 2016-04-28 | 2017-11-02 | Schlumberger Canada Limited | Reservoir performance system |
Non-Patent Citations (4)
| Title |
|---|
| 厌氧发酵工艺的BP神经网络建模与粒子群算法优化;赵孝文,等;《应用能源技术》(第3期);8-12 * |
| 宁夏农村沼气工程物联网智能监控系统构建;单臣玉;程志;崔耀东;闫吉春;;宁夏农林科技(第03期);56-58 * |
| 沼气工程物联网构建及应用分析;《中国沼气》;第33卷(第1期);65-69 * |
| 粒子群优化的神经网络PID沼气干发酵温度控制;刘浩;沈星;曲浩丽;王鹏军;;计算机工程与设计(03);784-788 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108319150A (en) | 2018-07-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108319150B (en) | Full-running state information sensing and optimal control system and method for biogas system | |
| Qdais et al. | Modeling and optimization of biogas production from a waste digester using artificial neural network and genetic algorithm | |
| Wang et al. | Optimization of fermentative hydrogen production process using genetic algorithm based on neural network and response surface methodology | |
| Zhao et al. | Modified Anaerobic Digestion Model No. 1 for modeling methane production from food waste in batch and semi-continuous anaerobic digestions | |
| Sewsynker-Sukai et al. | Artificial neural networks: an efficient tool for modelling and optimization of biofuel production (a mini review) | |
| Mu et al. | A kinetic approach to anaerobic hydrogen-producing process | |
| Wang et al. | Application of desirability function based on neural network for optimizing biohydrogen production process | |
| Münch et al. | Mathematical modelling of prefermenters—I. Model development and verification | |
| Enitan et al. | Optimization of biogas generation using anaerobic digestion models and computational intelligence approaches | |
| Darwesh et al. | Experimental studies on the contribution of solar energy as a source for heating biogas digestion units | |
| Zhao et al. | Optimization of hydrogen production in a granule-based UASB reactor | |
| Saghouri et al. | Modeling and optimization of biomethane production from solid-state anaerobic co-digestion of organic fraction municipal solid waste and other co-substrates | |
| Zhou et al. | Anaerobic digestion of different organic wastes for biogas production and its operational control performed by the modified ADM1 | |
| Dhussa et al. | Nonlinear Autoregressive Exogenous modeling of a large anaerobic digester producing biogas from cattle waste | |
| CN107557293A (en) | Electromagnetism reinforced anaerobic digests gas production system and its regulation and control method | |
| Wang et al. | Machine learning framework for intelligent aeration control in wastewater treatment plants: Automatic feature engineering based on variation sliding layer | |
| Wu et al. | Kinetics study of fermentative hydrogen production from liquid swine manure supplemented with glucose under controlled pH | |
| Robles et al. | A fuzzy-logic-based controller for methane production in anaerobic fixed-film reactors | |
| Lin et al. | Prediction of wastewater treatment system based on deep learning | |
| Huang et al. | Modeling of acetate-type fermentation of sugar-containing wastewater under acidic pH conditions | |
| Bala | System dynamics modelling and simulation of biogas production systems | |
| Zhang et al. | A study of the kinetics and the effect of trace elements on mixed anaerobic fermentative biogas production by ternary quadratic general rotary unitized design | |
| Feng et al. | Application of the initial rate method in anaerobic digestion of kitchen waste | |
| Ji et al. | Evaluation of methane production features and kinetics of Bougainvillea spectabilis Willd waste under mesophilic conditions | |
| CN208044320U (en) | The full running state information perception of bionethanation system and optimal control system |
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 | ||
| CB02 | Change of applicant information |
Address after: 250023 No. 5 Jiao Tong Road, Tianqiao District, Shandong, Ji'nan Applicant after: Shandong Jiaotong University Address before: No. 5001, Haitang Road, Science Park, Changqing University, Changqing District, Jinan City, Shandong Province Applicant before: Shandong Jiaotong University |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |