CN111701444B - Method for treating organic waste gas by using biotrickling filter based on convolutional neural network - Google Patents

Method for treating organic waste gas by using biotrickling filter based on convolutional neural network Download PDF

Info

Publication number
CN111701444B
CN111701444B CN202010621251.7A CN202010621251A CN111701444B CN 111701444 B CN111701444 B CN 111701444B CN 202010621251 A CN202010621251 A CN 202010621251A CN 111701444 B CN111701444 B CN 111701444B
Authority
CN
China
Prior art keywords
parameters
gas
network model
filter processing
biotrickling filter
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
Application number
CN202010621251.7A
Other languages
Chinese (zh)
Other versions
CN111701444A (en
Inventor
杨百忍
吴梦蕾
商青青
周琦
耿安琪
于广成
杨帅
张可慧
李方
谈超逸
张庆凯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui Chenze Intellectual Property Service Co ltd
Original Assignee
Yancheng Institute of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Yancheng Institute of Technology filed Critical Yancheng Institute of Technology
Priority to CN202010621251.7A priority Critical patent/CN111701444B/en
Publication of CN111701444A publication Critical patent/CN111701444A/en
Application granted granted Critical
Publication of CN111701444B publication Critical patent/CN111701444B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01D—SEPARATION
    • B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
    • B01D53/34—Chemical or biological purification of waste gases
    • B01D53/74—General processes for purification of waste gases; Apparatus or devices specially adapted therefor
    • B01D53/84—Biological processes
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01D—SEPARATION
    • B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
    • B01D53/34—Chemical or biological purification of waste gases
    • B01D53/38—Removing components of undefined structure
    • B01D53/44—Organic components
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01D—SEPARATION
    • B01D2257/00—Components to be removed
    • B01D2257/70—Organic compounds not provided for in groups B01D2257/00 - B01D2257/602
    • B01D2257/708—Volatile organic compounds V.O.C.'s
    • 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
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
    • Y02A50/20—Air quality improvement or preservation, e.g. vehicle emission control or emission reduction by using catalytic converters

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Chemical & Material Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Molecular Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Environmental & Geological Engineering (AREA)
  • Biophysics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Analytical Chemistry (AREA)
  • General Chemical & Material Sciences (AREA)
  • Oil, Petroleum & Natural Gas (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Treating Waste Gases (AREA)

Abstract

The invention discloses a method for treating organic waste gas by a biotrickling filter based on a convolutional neural network, which belongs to the technical field of volatile organic compound treatment and comprises the following steps: s10, constructing a biotrickling filter processing network model based on the convolutional neural network; s20, training the biotrickling filter processing network model by using the training sample; and S30, inputting the real-time parameters of the bio-trickling filter into the trained bio-trickling filter processing network model, and giving a parameter matching scheme by the trained bio-trickling filter processing network model, wherein the parameter matching scheme is the basis for the operation of the bio-trickling filter. The bio-trickling filter treatment network of the invention adjusts the real-time concentration of organic pollutants at the air inlet and the liquid output parameter of the liquid sprayer according to the parameter index of the prefabricated exhaust gas, so that the bio-trickling filter tower can fully exert the treatment capacity of the biological purification system, and simultaneously saves the energy for operating the spray pump.

Description

Method for treating organic waste gas by using biotrickling filter based on convolutional neural network
Technical Field
The invention belongs to the technical field of volatile organic compound treatment, and particularly relates to a method for treating organic waste gas by using a biotrickling filter based on a convolutional neural network.
Background
The biological trickling filter is the most commonly used device for treating VOCs waste gas by a biological method, and organic pollutants are degraded into CO through the metabolism process of microorganisms attached to the surface of a filler in the trickling filter2And water and inorganic salt, and the waste gas is used as nutrition or energy to generate new microbial cytoplasm to form stable and balanced micro-ecological environment, and can continuously metabolize and convert pollutants in the waste gas.
However, in the process of treating organic waste gas by the prior art biological trickling filtration method, the liquid output of each seasoning section sprayer in the biological trickling filtration tower is always unchanged regardless of the concentration of organic pollutants, the treatment capacity of a biological purification system cannot be fully exerted, and simultaneously, a great deal of energy waste is caused.
Therefore, there is an urgent need for a method for treating organic waste gas by using a bio-trickling filter which can match the concentration of organic pollutants with the amount of liquid discharged from a sprayer in the bio-trickling filter to reduce the residual concentration of organic pollutants in an exhaust port.
Disclosure of Invention
The invention aims to provide a method for treating organic waste gas by using a biological trickling filter, which can match the concentration of organic pollutants with the liquid output of a sprayer in the biological trickling filter so as to reduce the residual concentration of organic waste gas at an exhaust port, and adopts the following technical scheme:
a method for treating organic waste gas by a biotrickling filter based on a convolutional neural network comprises the following steps:
s10, constructing a biotrickling filter processing network model based on the convolutional neural network;
s20, training the biotrickling filter processing network model by using a training sample;
s30, inputting the real-time parameters of the biotrickling filter into the trained biotrickling filter processing network model, and giving a parameter matching scheme by the trained biotrickling filter processing network model, wherein the parameter matching scheme is the basis for the operation of the biotrickling filter.
Further, the training samples include the following parameters: the parameters of mixed gas entering the air inlet of the biological trickling filter tower, the parameters of a spray pump, the parameters of working liquid, the parameters of a liquid distributor and the parameters of exhaust gas of an exhaust port; the real-time parameters of the bio-trickling filter are consistent with the training samples.
Further, the parameters of the mixed gas entering the air inlet of the biological trickling filter comprise: gas inflow, gas temperature, gas pressure and organic pollutant concentration in the mixed gas; the spray pump parameters comprise the flow of the working fluid extracted by the spray pump; the working fluid parameters comprise working fluid temperature and PH value; the liquid distributor parameters comprise liquid outlet amounts of the liquid sprayers respectively corresponding to the upper section of the packing, the middle section of the packing and the lower section of the packing; the parameters of the exhaust gas of the exhaust port comprise the residual concentration of the organic pollutants.
Further, the structure of the model of the biotrickling filter processing network is shown in fig. 2.
Further, the training process of the bio-trickling filter processing network model in step S20 is as follows:
s21, obtaining parameters in the training sample, wherein the parameters in the training sample are used for generating a basis for the biotrickling filter processing network model to provide a parameter matching scheme;
s22, inputting each parameter in the parameters in the training sample into the biotrickling filter processing network model;
s23, selecting the optimal matching parameters among all parameters by the biotrickling filter processing network model through a genetic algorithm to form a parameter matching scheme;
s24, the bio-trickling filter processing network model sends the parameter matching scheme to the bio-trickling filter.
Further, the bio-trickling filter gas inlet is provided with a gas flow meter for measuring the gas inlet flow and the gas temperature, a gas pressure sensor for measuring the gas pressure, and a first gas sensor for measuring the concentration of organic pollutants in the mixed gas.
Furthermore, a liquid flow meter for measuring the flow of the extracted working liquid by the spray pump, a temperature sensor for measuring the temperature of the working liquid and a PH meter for measuring the PH value are arranged on the liquid inlet of the spray pump; the liquid sprayer outlets corresponding to the upper section filler, the middle section filler and the lower section filler are respectively provided with a flowmeter for measuring the liquid amount; the exhaust port is provided with a second gas sensor for measuring the residual concentration of the organic pollutants.
Further, the convolutional neural network comprises an input layer, convolutional layers and pooling layers, wherein the number of convolutional layers is 16, the convolutional layers with the convolutional kernel size of 3 x 3 and the maximum pooling layer with the number of layers of 5.
Further, the training samples comprise 80% of training samples and 20% of testing training samples.
Has the advantages that:
the invention provides a method for treating organic waste gas by a biotrickling filter based on a convolutional neural network, wherein a biotrickling filter treatment network model adjusts the real-time concentration of organic pollutants at an air inlet and the liquid output parameter of a liquid sprayer according to the parameter index of prefabricated exhaust gas, so that the biotrickling filter can fully exert the treatment capacity of a biological purification system, and simultaneously, the energy for operating a spray pump is saved.
Drawings
FIG. 1 is a flow chart of a method for treating organic waste gas by using a biotrickling filter based on a convolutional neural network
FIG. 2 is a schematic view of a model of a biotrickling filter processing network
Wherein, 100-a biological trickling filter; 101-an exhaust gas intake system; 102-a tank body; 103-a fan; 104-a first conduit; 105-a second conduit; 107-gas-liquid mass transfer box; 109-an air inlet pipe; 111-a venturi tube; 113-a third conduit; 115-an air inlet; 117-vent; 119-a liquid inlet pipe; 121-a circulation pump; 123-a first space; 125-a second space; 127-a connecting section; 129-first inlet end; 131-a first drain end; 133-a first expanding section; 135-a constriction section; 136-a second expanding section; 137-a delivery pump; 141-a tower body; 143-stock solution section; 144-a gas distribution section; 145-filler section; 147-a spray system; 148-a liquid distributor; 151-a packing frame; 153-upper section packing; 155-middle section packing; 157-lower section packing; 159-spray pump; 161-spray pipes; 162-a second inlet end; 163-gas distributor; 164-a second drain; 165-a packing turnup system; 167-stirring shaft; 169-an aerator pipe; 171-an aeration head; 173-activated sludge.
Detailed Description
Example 1
A method for treating organic waste gas by a biotrickling filter based on a convolutional neural network comprises the following steps:
s10, constructing a biotrickling filter processing network model based on the convolutional neural network; the structure of the model of the biotrickling filter processing network is shown in figure 2.
In this embodiment, the convolutional neural network includes an input layer, convolutional layers, and pooling layers, where the number of convolutional layers is 16, the convolutional layer with a convolutional kernel size of 3 × 3, and the maximum pooling layer with the number of layers being 5.
S20, training the biotrickling filter processing network model by using the training sample;
in this embodiment, the training samples include the following parameters: parameters of the mixed gas entering the gas inlet 115 of the biotrickling filter 100, parameters of the spray pump 159, parameters of the working fluid, parameters of the liquid distributor 148 and parameters of the gas discharged from the gas outlet 117; the real-time parameters of the bio-trickling filter 100 are consistent with the training samples.
Wherein, the mixed gas parameters entering the air inlet of the bio-trickling filter 100 include: gas inflow, gas temperature, gas pressure and organic pollutant concentration in the mixed gas; spray pump 159 parameters include the flow rate at which the spray pump draws the working fluid; the working fluid parameters comprise working fluid temperature and PH value; the parameters of the liquid distributor 148 comprise the liquid outlet amount of the liquid sprayer corresponding to the upper section packing 153, the middle section packing 155 and the lower section packing 157 respectively; the exhaust gas parameters of the exhaust port 117 include the remaining concentration of organic contaminants.
The training process of the biotrickling filter processing network model in the step S20 is as follows:
s21, obtaining parameters in the training sample, wherein the parameters in the training sample are used for generating a bio-trickling filter processing network model and providing a basis of a parameter matching scheme;
s22, inputting each parameter in the parameters in the training sample into the biotrickling filter processing network model;
s23, selecting the optimal matching parameters among all parameters by the biotrickling filter processing network model through a genetic algorithm to form a parameter matching scheme;
s24, the bio-trickling filter processing network model sends the parameter matching scheme to the bio-trickling filter 100.
The gas inlet of the bio-trickling filter 100 is provided with a gas flow meter for measuring the gas inlet flow and the gas temperature, a gas pressure sensor for measuring the gas pressure, and a first gas sensor for measuring the concentration of organic pollutants in the mixed gas.
In the present embodiment, the training samples include 80% of the training samples and 20% of the test training samples.
And S30, inputting the real-time parameters of the bio-trickling filter 100 into the trained bio-trickling filter processing network model, and giving a parameter matching scheme by the trained bio-trickling filter processing network model, wherein the parameter matching scheme is the basis for the operation of the bio-trickling filter 100.
In this embodiment, the liquid inlet of the spray pump 159 is provided with a liquid flow meter for measuring the flow rate of the extracted working liquid by the spray pump, a temperature sensor for measuring the temperature of the working liquid and a PH meter for measuring the PH value; flow meters for measuring liquid quantities are respectively arranged at the liquid sprayer outlets corresponding to the upper section packing 153, the middle section packing 155 and the lower section packing 157; the exhaust port 117 is provided with a second gas sensor that measures the remaining concentration of organic contaminants.
In this embodiment, a bio-trickling filter 100 is included, comprising: the tower comprises a tower body 141, a spraying system 147, a gas-liquid mass transfer box 107, a circulating pump 121 and a packing turning system 165.
The tank body 102 has a cavity therein for containing the working fluid, and the cavity is divided into a first space 123 and a second space 125 by the working fluid. The working fluid is placed in the second space 125.
One end of the air inlet pipe 109 is a connecting section 127, and the other end of the air inlet pipe 109 is connected with the first pipeline 104 of the fan 103 in the waste gas inlet system 101. A fan 103 of the waste gas inlet system 101 introduces a mixed gas of organic waste gas and air, the fan 103 is connected with an air inlet pipe 109 through a first pipeline 104, and the mixed gas is sent into the box body 102 in a positive pressure mode, so that conveying power of working gas in the gas-liquid mass transfer box 107 is provided.
The inlet pipe 119 includes a first inlet end 129 and a first discharge end 131. Wherein, the first inlet end 129 is connected with the box body 102 and extends into the working fluid, and the cavity of the first inlet end 129 is communicated with the second space 125. The first drain 131 is located in the first space 123. The liquid inlet pipe 119 may further be provided with a delivery pump 137, and the liquid inlet pipe 119 is in matching connection with the delivery pump 137. The transfer pump 137 is responsible for extracting the working fluid to provide power for transferring the working fluid.
The number of the venturi tubes 111 is one, and the venturi tubes 111 are located in the box body 102, and the venturi tubes 111 have a first diameter-expanding section 133, a contracting section 135, and a second diameter-expanding section 136 connected in this order. The lumen of the venturi tube 111 communicates with the lumen of the liquid inlet pipe 119 and the lumen of the air inlet pipe 109.
The first diameter-expanding section 133 and the second diameter-expanding section 136 are respectively positioned in the first space 123 and the second space 125, the first liquid discharge end 131 is connected with the first diameter-expanding section 133, and the lumen of the first liquid discharge end 131 is communicated with the lumen of the first diameter-expanding section 133. The connecting section 127 of the air inlet pipe 109 is connected with the contraction section 135, and the lumen of the connecting section 127 of the air inlet pipe 109 is communicated with the lumen of the contraction section 135. The exhaust gas from the venturi 111 enters the bottom of the bio-trickling filter 100.
The tower body 141 is provided with a liquid storage section 143, a filler section 145 for fixing the filler, and a gas distribution section 144 which are connected in sequence, and the tower body 141 is further provided with a gas inlet 115 and a gas outlet 117. The gas inlet 115 of the column body 141 is connected with the gas-liquid mass transfer tank 107 through a third pipe 113. The gas discharged from the gas-liquid mass transfer tank 107 enters the column body 141 through the third pipe 113. The gas discharge port 117 is located at the top of the column body 141 for discharging the gas after being purified.
Wherein the liquid storage section 143 is located at the bottom of the bio-trickling filter 100. The liquid storage section 143 is used for collecting and storing the sprayed working fluid, and the working fluid in the tank body 102 is the same as the working fluid in the liquid storage section 143. Certainly, activated sludge 173 can be added into the working fluid in the liquid storage section 143 according to construction requirements, so that waste gas subjected to mass transfer enhancement by the gas-liquid mass transfer tank 107 can be pretreated when entering the liquid storage section 143, and microorganisms are kept in an aerobic state all the time.
Wherein, the filler section 145 comprises an upper section of filler 153, a middle section of filler 155 and a lower section of filler 157. The packing is placed on a packing holder 151 and the packing holder 151 is fixed to the side wall of the column body 141. The filler of the lower section filler 157 is a large-particle-size ceramsite filler with uniform particle size, the middle section filler 155 is a medium-particle-size ceramsite filler with uniform particle size, and the upper section filler 153 is a small-particle-size semi-flexible filler with uniform particle size. By the filling, the radial concentration of the malodorous gas is the same and the axial concentration change is uniform while the low resistance of the biological trickling filter 100 is kept; meanwhile, the load of the filler for treating the waste gas is kept uniform; in addition, the particle size of the filler is changed from small to large from top to bottom in sequence, so that the middle filler 155 receives dead microorganisms brought by the working fluid flowing down from the upper filler 153, and when the lower filler 157 receives dead microorganisms brought by the working fluid from the upper filler 153 and the middle filler 155, the particle size of the middle filler 155 is larger than that of the upper filler 153, the gap of the middle filler 155 is larger than that of the upper filler 153, the particle size of the lower filler 157 is large, and the gap of the lower filler 157 is larger than that of the middle filler 155 and the upper filler 153, so that the middle filler is not easy to block.
Wherein the chamber of the gas distribution section 144 may communicate with the first space 123 via the third conduit 113. The gas distribution section 144 is provided with a gas distributor 163, and the third conduit 113 communicates with the gas distributor 163 so as to uniformly distribute the gas within the column body 141 through the gas distributor 163.
The spraying system 147 comprises a spraying pump 159, a spraying pipe 161 and a liquid distributor 148, wherein the spraying pump 159 and the spraying pipe 161 are matched with each other and used for extracting the working liquid in the liquid storage section 143. The spraying system 147 is disposed outside the tower body 141, and a part of the spraying system extends into the tower body 141 to extract the working fluid in the fluid storage section 143.
The spray pipe 161 includes a second liquid inlet end 162 and a second liquid outlet end 164, the second liquid inlet end 162 extends into the liquid storage section 143, and the second liquid outlet end 164 extends into the side wall of the tower body 141 and is fixed above the packing frame 151. Each of the upper packing 153, the middle packing 155 and the lower packing 157 is provided with a spray pipe 161 separately. The second liquid discharge end 164 is distributed with a liquid distributor 148, and the working liquid is introduced into the circulating liquid inlet pipe 119 by a spray pump 159, and is uniformly sprayed on the packing by the liquid distributor 148, so that the water and the gas in the tower body 141 are uniformly distributed.
The second pipe 105 of the circulating pump 121 is used for connecting the liquid storage section 143 with the gas-liquid mass transfer tank 107 through the circulating pump 121. The liquid storage section 143 can be extracted and conveyed by the circulating pump 121, and after the working fluid in the liquid storage section 143 is left standing, the supernatant can be sent back to the gas-liquid mass transfer tank 107 through the second pipeline 105 of the circulating pump 121, and the rest is discharged.
The packing turning system 165 includes a turning motor and a stirring shaft 167 provided with a stirring paddle. The output pump of the pile turning motor is connected with the stirring shaft 167 and controls the rotation of the stirring paddle, and the rotation speed is not more than 1 r/min. The stirring shaft 167 extends from the top of the column body 141 into the packing section 145.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the technical scope of the present invention, so that any minor modifications, equivalent changes and modifications made to the above embodiment according to the technical spirit of the present invention are within the technical scope of the present invention.

Claims (7)

1. A method for treating organic waste gas by a biotrickling filter based on a convolutional neural network is characterized by comprising the following steps:
s10, constructing a biotrickling filter processing network model based on the convolutional neural network;
s20, training the biotrickling filter processing network model by using a training sample;
s30, inputting real-time parameters of the biotrickling filter into a trained biotrickling filter processing network model, and giving a parameter matching scheme by the trained biotrickling filter processing network model, wherein the parameter matching scheme is the basis for the operation of the biotrickling filter;
training the training sample to obtain the biotrickling filter processing network model comprises the following steps:
taking the numerical value corresponding to each parameter in the training sample as an input layer node;
converting each of the matched parameters in the training sample to a numerical value;
taking the obtained data corresponding to each matching parameter as an output layer node of the biotrickling filter processing network model;
and training according to the input layer nodes and the output layer nodes to obtain the biotrickling filter processing network model.
2. The convolutional neural network based biotrick filter processing method of claim 1, wherein the training sample comprises the following parameters: the parameters of mixed gas entering the air inlet of the biological trickling filter tower, the parameters of a spray pump, the parameters of working liquid, the parameters of a liquid distributor and the parameters of exhaust gas of an exhaust port; the real-time parameters of the bio-trickling filter are consistent with the training samples.
3. The method for treating organic waste gas by using the biotrickling filter based on the convolutional neural network as claimed in claim 2, wherein the mixed gas parameters entering the gas inlet of the biotrickling filter comprise: gas inflow, gas temperature, gas pressure and organic pollutant concentration in the mixed gas; the spray pump parameters comprise the flow of the working fluid extracted by the spray pump; the working fluid parameters comprise working fluid temperature and pH value; the liquid distributor parameters comprise liquid outlet amounts of the liquid sprayers respectively corresponding to the upper section of the packing, the middle section of the packing and the lower section of the packing; the parameters of the exhaust gas of the exhaust port comprise the residual concentration of the organic pollutants.
4. The method for treating organic waste gas by using the biotrickling filter based on the convolutional neural network as claimed in claim 3, wherein the training process of the biotrickling filter treatment network model in step S20 is as follows:
s21, obtaining parameters in the training sample, wherein the parameters in the training sample are used for generating a basis for the biotrickling filter processing network model to provide a parameter matching scheme;
s22, inputting each parameter in the parameters in the training sample into the biotrickling filter processing network model;
s23, selecting the optimal matching parameters among all parameters by the biotrickling filter processing network model through a genetic algorithm to form a parameter matching scheme;
s24, the bio-trickling filter processing network model sends the parameter matching scheme to the bio-trickling filter.
5. The method of claim 3, wherein the bio-trickling filter inlet is provided with a gas flow meter for measuring the inlet gas flow and the gas temperature, a gas pressure sensor for measuring the gas pressure, and a first gas sensor for measuring the concentration of organic pollutants in the mixed gas.
6. The method for treating organic waste gas by using the biotrickling filter based on the convolutional neural network as claimed in claim 5, wherein the liquid inlet of the spray pump is provided with a liquid flow meter for measuring the flow rate of the extracted working fluid by the spray pump, a temperature sensor for measuring the temperature of the working fluid and a pH meter for measuring the pH value; the liquid sprayer outlets corresponding to the upper section filler, the middle section filler and the lower section filler are respectively provided with a flowmeter for measuring the liquid amount; the exhaust port is provided with a second gas sensor for measuring the residual concentration of the organic pollutants.
7. The method of claim 1, wherein the convolutional neural network comprises an input layer, convolutional layers, a pooling layer, the number of convolutional layers is 16, convolutional layers with a convolutional kernel size of 3 x 3, and the number of pooling layers is 5 of the maximum pooling layer.
CN202010621251.7A 2020-07-01 2020-07-01 Method for treating organic waste gas by using biotrickling filter based on convolutional neural network Active CN111701444B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010621251.7A CN111701444B (en) 2020-07-01 2020-07-01 Method for treating organic waste gas by using biotrickling filter based on convolutional neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010621251.7A CN111701444B (en) 2020-07-01 2020-07-01 Method for treating organic waste gas by using biotrickling filter based on convolutional neural network

Publications (2)

Publication Number Publication Date
CN111701444A CN111701444A (en) 2020-09-25
CN111701444B true CN111701444B (en) 2022-02-08

Family

ID=72545337

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010621251.7A Active CN111701444B (en) 2020-07-01 2020-07-01 Method for treating organic waste gas by using biotrickling filter based on convolutional neural network

Country Status (1)

Country Link
CN (1) CN111701444B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112517631B (en) * 2020-11-27 2021-07-23 苏州精英环保有限公司 Intelligent normal-temperature desorption remediation equipment and method for volatile organic contaminated soil
US20220355242A1 (en) * 2021-05-07 2022-11-10 Taiwan Semiconductor Manufacturing Co., Ltd. System and method for removing volatile organic compounds from process gasses
CN114931854B (en) * 2022-05-31 2023-05-26 北京实力伟业环保科技有限公司 System and method for purifying waste gas by microorganisms
CN115414770B (en) * 2022-09-15 2023-12-01 杭州楚环科技股份有限公司 Garbage waste gas treatment method
CN116116181B (en) * 2023-04-18 2023-07-18 科扬环境科技有限责任公司 Model optimization-based waste gas and wastewater treatment method and device

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10118691A (en) * 1996-10-17 1998-05-12 Kurita Water Ind Ltd Apparatus for biological nitrification and denitrification treatment
CN104504238A (en) * 2014-11-21 2015-04-08 国家电网公司 Method for predicting nitrogen oxide emission concentration of coal-fired unit based on neural network
CN108445852A (en) * 2018-04-24 2018-08-24 江西永源节能环保科技股份有限公司 The control system of desulfurization off sulfide effect in a kind of processing of intelligent flue gas
CN108985381A (en) * 2018-07-25 2018-12-11 广东工业大学 The determination method, device and equipment of nitrogen oxide emission prediction model
CN109359428A (en) * 2018-11-27 2019-02-19 上海海事大学 A kind of modeling method of boiler combustion efficiency and emission of nitrogen and oxygen compounds

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10118691A (en) * 1996-10-17 1998-05-12 Kurita Water Ind Ltd Apparatus for biological nitrification and denitrification treatment
CN104504238A (en) * 2014-11-21 2015-04-08 国家电网公司 Method for predicting nitrogen oxide emission concentration of coal-fired unit based on neural network
CN108445852A (en) * 2018-04-24 2018-08-24 江西永源节能环保科技股份有限公司 The control system of desulfurization off sulfide effect in a kind of processing of intelligent flue gas
CN108985381A (en) * 2018-07-25 2018-12-11 广东工业大学 The determination method, device and equipment of nitrogen oxide emission prediction model
CN109359428A (en) * 2018-11-27 2019-02-19 上海海事大学 A kind of modeling method of boiler combustion efficiency and emission of nitrogen and oxygen compounds

Also Published As

Publication number Publication date
CN111701444A (en) 2020-09-25

Similar Documents

Publication Publication Date Title
CN111701444B (en) Method for treating organic waste gas by using biotrickling filter based on convolutional neural network
CN101293722B (en) Municipal sewage treatment system and equipment built on river
CN105439285B (en) A kind of regulation method of sewage treatment
CN101343108A (en) Method for coupling treatment of sewage water of waterpower cavitation and ozone
CN207159016U (en) A kind of energy saving and environment friendly Chemical Manufacture sewage disposal device
CN105330096B (en) A kind of sewage disposal external whole process deodoration system and application
CN207738599U (en) Plate type ceramic combined films complete set of equipments
CN207079138U (en) Stripping reflux formula integrated equipment for sewage treatment
CN205258202U (en) Pharmaceutical chemical engineering effluent treatment plant
CN218810832U (en) Distributed MABR sewage treatment plant
CN111470602A (en) Full-automatic dosing device and method for sewage treatment
CN214399977U (en) Integrated and enhanced AAO process accurate control system
CN207313378U (en) Micropollutant water repairs all-in-one machine
CN210481143U (en) Sewage treatment system based on MBR membrane process
CN209740811U (en) Multistage AO-MBR membrane jar device of integration
CN208104022U (en) A kind of circulating MBR process tank
CN206375789U (en) Sewage integrated treatment device
CN109626475B (en) Emission reduction type oil refining and chemical engineering integrated combination device
CN106006945A (en) Parasitic filler biofilter for domestic sewage treatment
CN207061979U (en) Anaerobic reactor big flow EGR
CN205011762U (en) Online hyperplasia expands equipment of banking up active fungus crowd among sewage treatment system with earth
CN211644988U (en) Integrated treatment device for domestic sewage
CN220351867U (en) Landfill leachate treatment device
CN208104029U (en) Vehicle-mounted integrated equipment for sewage treatment
CN216336831U (en) Multifunctional integrated MBBR sewage treatment test device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20230725

Address after: No. 43886, 4th Floor, GF District, Building 3, Phase 3, E-commerce Park, Wenshui Road, Shushan District, Hefei City, Anhui Province, 230000

Patentee after: Anhui Chenze Intellectual Property Service Co.,Ltd.

Address before: 224051 No. 1 hope road middle road, Ting Hu District, Yancheng City, Jiangsu

Patentee before: YANCHENG INSTITUTE OF TECHNOLOGY