CN113866375A - Intelligent online monitoring method and system for effluent nitrogenous substances - Google Patents

Intelligent online monitoring method and system for effluent nitrogenous substances Download PDF

Info

Publication number
CN113866375A
CN113866375A CN202111091217.4A CN202111091217A CN113866375A CN 113866375 A CN113866375 A CN 113866375A CN 202111091217 A CN202111091217 A CN 202111091217A CN 113866375 A CN113866375 A CN 113866375A
Authority
CN
China
Prior art keywords
nitrogen
data
water
mse
prediction model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111091217.4A
Other languages
Chinese (zh)
Inventor
黄明智
牛国强
李小勇
易晓辉
石义静
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.)
South China Normal University
Original Assignee
South China Normal University
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 South China Normal University filed Critical South China Normal University
Priority to CN202111091217.4A priority Critical patent/CN113866375A/en
Publication of CN113866375A publication Critical patent/CN113866375A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/18—Water
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/18—Water
    • G01N33/1806—Biological oxygen demand [BOD] or chemical oxygen demand [COD]
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/18—Water
    • G01N33/1826—Organic contamination in water
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Analytical Chemistry (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Molecular Biology (AREA)
  • Immunology (AREA)
  • Biochemistry (AREA)
  • Medicinal Chemistry (AREA)
  • Food Science & Technology (AREA)
  • Biophysics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Emergency Medicine (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

The invention relates to an intelligent online monitoring method and system for effluent nitrogen-containing substances. The method comprises the following steps: collecting historical data of input variables and output variables for the predictive model; establishing a prediction model of the nitrogen-containing substance concentration based on the graph convolution neural network based on the input variable and the output variable; training the prediction model by using a momentum random gradient descent method; and acquiring current input variable data from the water body at the water inlet end, and inputting the current input variable data into the trained prediction model to obtain a prediction result of the output variable of the water outlet end. The device comprises a water quality parameter measuring module, a display device connected with the water quality parameter measuring module and a central processing device respectively connected with the water quality parameter measuring module and the display device, and the central processing device implements the method. The invention can automatically adjust the neural network parameters according to the change of the effluent quality parameters, so that the model can be learned on line, and the total nitrogen and ammonia nitrogen concentration of the effluent can be rapidly monitored in real time.

Description

Intelligent online monitoring method and system for effluent nitrogenous substances
Technical Field
The invention relates to an intelligent online monitoring method and system for effluent nitrogen-containing substances, and belongs to the technical field of water treatment. The method and the system can be applied to urban sewage treatment plants and relevant environmental monitoring departments and are used for rapid real-time online monitoring of key water quality parameters, namely total nitrogen and ammonia nitrogen.
Background
In order to ensure that a sewage plant is always in a stable and safe operation state, some key indexes, such as Chemical Oxygen Demand (COD), Total Suspended Solids (TSS), Total Phosphorus (TP), Total Nitrogen (TN), ammonia nitrogen (SNH) and the like, need to be monitored in real time in the sewage treatment process. The process performance, the effluent quality and the economic benefit of sewage treatment can be reflected by monitoring the indexes, and the sewage treatment process is optimized and controlled according to the monitoring result. In recent years, with the continuous operation of energy conservation and emission reduction of sewage plants, the concentrations of COD and TSS of effluent of the sewage plants are greatly reduced, and the pollution of TN and SNH of the effluent is increasingly serious. Excessive discharge of nitrogen (N) into the receiving water body can cause water bloom and water body eutrophication, and meanwhile, nitrogen is also an important index for evaluating the nutrition state of the receiving water body, so that online monitoring of TN and SNH of effluent of a sewage treatment plant becomes a key for solving the problem of water body eutrophication.
The concentration of TN and SNH of the current town sewage plant is mainly determined in a special laboratory through a national standard method, the national standard method has high measurement precision, but the experimental steps are complicated, the chemical reaction time is long, and the concentration of TN and SNH cannot be reflected in time. Some sewage plants have used precision instruments for measuring TN and SNH, wherein the commonly used precision instruments include an ammonia nitrogen on-line monitor and a total nitrogen on-line detector. Although these instruments have high sensitivity and can accurately measure the concentration of a water sample, the price and the later maintenance cost of the detectors are high, and the measurement process is very time-consuming and can not meet the requirement of measuring the TN and SNH concentration in real time.
Disclosure of Invention
The invention provides an intelligent online monitoring method and device for effluent nitrogen-containing substances, and aims to at least solve one of the technical problems in the prior art.
The technical scheme of the invention relates to an intelligent online monitoring method for effluent nitrogenous substances, which comprises the following steps:
s1, acquiring historical data of input variables and output variables of the prediction model from the field platform and/or the simulation platform through water quality parameter measurement modules arranged at the water inlet end and the water outlet end;
s2, establishing a prediction model of nitrogen-containing substance concentration based on the graph convolution neural network based on the input variable and the output variable;
s3, training the prediction model of the nitrogen-containing substance concentration based on the graph convolution neural network by using a momentum random gradient descent method;
and S4, acquiring current input variable data from the water body at the water inlet end on line through the water quality parameter measuring module, removing abnormal data, and inputting the abnormal data to the trained prediction model to obtain a prediction result of the output variable at the water outlet end.
Further, the input variables comprise dissolved oxygen, nitrate nitrogen, total influent suspended solids, influent chemical oxygen demand, total influent nitrogen and influent ammonia nitrogen concentration,
the output variable comprises the concentration of effluent ammonia nitrogen and effluent total nitrogen.
Further, in the step S1, the on-site platform includes a sewage treatment unit of a sewage plant, and the simulation platform includes an activated sludge model No. 1.
Further, the step S2 includes: and dividing the data groups of the input variables and the output variables into a training set and a testing set according to the ratio of 4:1, wherein the training data and the testing data are normalized before being input into the prediction model.
Further, the step S3 further includes: and obtaining the optimal convolution kernel number of the convolution layer in the convolution neural network (GCN) by adopting an iterative optimization method.
Further, the step S3 further includes the following steps:
s31, selecting nine candidate convolution kernels, wherein the value of each convolution kernel is a multiple of 2, and configuring the nine candidate convolution kernels into a row vector N (i), wherein i is the sequence of elements in the row vector;
s32, providing an initial error of the training of the prediction model based on the graph convolution neural network as MSE _ MAX, and setting the current convolution kernel number as N (i), wherein the sum of the mean square errors of two corresponding output variables in the training process is MSE (i);
s33, ensuring that the initialization parameters of each iteration of the convolution kernel number of the prediction model based on the graph convolution neural network are the same;
s34, when MSE (i) < MSE _ MAX, replacing the value of MSE _ MAX with MSE (i), and marking the current N (i) as desired _ N (i);
s35, when all the iterations of the nine candidate convolution kernels are completed, outputting the current MSE _ MAX as MSE (i) minimum value, and outputting the desired _ N (i) bit optimal convolution kernel number.
Further, the step S4 further includes: and importing the data generated by the solid platform and/or the simulation platform into a statistical table, and then removing abnormal data by a statistical method.
Further, the method also comprises the following steps: s5, setting an early warning value for the concentration of total nitrogen and ammonia nitrogen, and sending prompt information and an alarm on display equipment when monitoring that the current predicted value exceeds the early warning value; and S6, storing the prediction result data in a python file format.
The invention also relates to a computer-readable storage medium, on which program instructions are stored, which program instructions, when executed by a processor, implement the above-mentioned method.
The technical scheme of the invention also relates to an intelligent online monitoring system for effluent nitrogen-containing substances, which comprises: an online dissolved oxygen monitor; nitrate nitrogen on-line monitoring instrument; the display device is connected with the dissolved oxygen online monitor and the nitrate nitrogen online monitor; a central processing device comprising the computer-readable storage medium. Wherein the central processing unit is connected with the dissolved oxygen on-line monitor, the nitrate nitrogen on-line monitor and the display device.
The invention has the beneficial effects that:
the capability of efficiently extracting multidimensional data features by a graph convolution neural network is fully utilized, and a prediction model of the concentration of nitrogen-containing substances (total nitrogen and ammonia nitrogen) in the water body based on the GCN network is established; the GCN network parameters can be automatically adjusted according to the change of the effluent quality parameters of the sewage plant, so that the model can be used for online learning, and the total nitrogen and ammonia nitrogen concentrations of the sewage plant can be rapidly monitored in real time. The scheme of the invention can also be used for related environmental monitoring departments, provides basis for implementing water quality pollution prevention and control policies, and prevents serious pollution.
Drawings
Fig. 1 is a block diagram of the overall architecture of a system in an embodiment in accordance with the invention.
Fig. 2 is an overall flow diagram of a method in an embodiment in accordance with the invention.
Figure 3 is a block diagram of a GCN module according to an embodiment of the present invention.
FIG. 4 is a graph of GCN and CNN model training according to an embodiment of the present invention.
FIG. 5 is another training diagram of GCN and CNN models according to an embodiment of the present invention.
Detailed Description
The conception, the specific structure and the technical effects of the present invention will be clearly and completely described in conjunction with the embodiments and the accompanying drawings to fully understand the objects, the schemes and the effects of the present invention.
Before further detailed description of the embodiments of the present invention, terms and expressions referred to in the embodiments of the present invention will be described, and the terms and expressions referred to in the embodiments of the present invention are applicable to the following explanations:
adam: a momentum random gradient descent method;
BOD: biochemical oxygen demand, biological oxygen demand;
BSM 1: benchmark Simulation Model 1, Simulation reference Model 1;
CNN: a convolutional neural networks;
COD: chemical oxygen demand, chemical oxygen demand;
DO: dissolved oxygen;
GCN: graph convolution network graph convolution neural network;
SNH: ammonia nitrogen;
TN: total nitrogen;
TP: total phosphorus;
TSS: total suspended solids.
Referring to fig. 1, in some embodiments, an intelligent online monitoring system for effluent nitrogen-containing substances according to the present invention is divided into a hardware part and a software part. The hardware part can comprise a water quality parameter measuring module, a display device connected with the water quality parameter measuring module and a central processing device respectively connected with the water quality parameter measuring module and the display device. In some embodiments, the water quality parameter measuring module is used for acquiring auxiliary variables in the sewage treatment process and consists of a dissolved oxygen online monitor and a nitrate nitrogen online monitor. The central processing apparatus may include an ARM embedded computing device, which may be autonomously equipped according to different requirements. The water quality parameter measuring device and the central processing device can be in data communication through a USB interface. Preferably, the running environment of the ARM embedded computing device is a python platform.
At the heart of the online monitoring system is a software component, which implements the method according to the invention. In the software part, data acquired by the water quality parameter measurement module is processed and then used as input of a neural network prediction model, so that a GCN (generalized negative feedback network) -based prediction model of total nitrogen and ammonia nitrogen concentration of a sewage plant is established. In addition, the software part also has the functions of inquiring historical data and alarming when the threshold is out of limit.
Referring to fig. 2, in some embodiments, a method according to the present invention includes the steps of:
s1, acquiring historical data of input variables and output variables of the prediction model from the field platform and/or the simulation platform through water quality parameter measurement modules arranged at the water inlet end and the water outlet end;
s2, establishing a prediction model of nitrogen concentration based on a graph convolution neural network (GCN) based on the input variable and the output variable;
s3, training the prediction model of the nitrogen concentration based on the graph convolution neural network (GCN) by using a momentum random gradient descent method (Adam);
and S4, acquiring current input variable data from the water body at the water inlet end on line through the water quality parameter measuring module, removing abnormal data, and inputting the abnormal data to the trained prediction model to obtain a prediction result of the output variable at the water outlet end.
The above steps are described separately below by way of further examples.
For step S1, not only the on-site input and output variables may be obtained from the water quality parameter measurement module, but also historical data of the activated sludge model No. 1 (BSM1) and the BSM1 model that continuously run for two weeks in sunny days, rainy days, and heavy rain days, respectively, may be obtained, thereby providing data support for the subsequent training of the prediction model. The BSM1 model adopted in the embodiment is called as a simulation reference model, is proposed by the European Union scientific and technical Cooperation Organization (COST), is a simulation test platform for different sewage control schemes, enables each control scheme to be simulated under the same condition to ensure fairness, and can also be used for generating simulation data.
For step S2, SO, SNO, TSS may be usedinf、CODinf、TNinf、SNHinf、SNHeffAnd TNeffAnd taking the first 500 groups of historical data of the eight water quality parameters as modeling data, taking the first 400 groups of the modeling data as a training set and taking the last 100 groups of the modeling data as a test set according to the ratio of 4:1 between the training set and the test set. The network structure of the tested GCN model is shown in fig. 3, in which multiple sets of water quality parameters are used as network associations to form the input side of the GCN model, and then the right prediction and estimation values are obtained through a two-layer convolution network. Specifically, TSSinfAssociating SNO with SO and TN respectivelyinfAssociating, TNinfRespectively react with SO and CODinfAnd SNHinfAnd (4) correlating, thereby improving the prediction accuracy of the model.
For step S3, the GCN model may be trained by using a momentum stochastic gradient descent (Adam) method and training set data, and when the training is completed, the structure of the model is fixed, resulting in a trained GCN model, and the training process is as shown in fig. 4 and fig. 5.
In a preferred embodiment, the optimal number of convolution kernels for a convolution layer in a GCN can be obtained in an iterative optimization manner through the following five steps.
In the first step, nine candidate convolution kernels are selected empirically, and the nine candidate convolution kernels are set as a row vector N ═ 8,16,32,64,128,256,512,1024,2048, where N (i) is the current convolution kernel and i is the order of elements in the row vector. Specifically, the convolution kernel refers to the formula:
2c>2(a-2) ①
Figure BDA0003267438550000051
in the formula 2cFor the optimum number of convolution kernels, a ═ 6 is the number of input layer nodes, b ═ 2 is the number of output layer nodes, and d is a constant between 0 and 8. And the range of the optimal convolution kernel number obtained by comprehensively considering the two formulas is 23-211.
And secondly, setting the initial error of GCN training as MSE _ MAX, setting the MSE _ MAX to 1000 (generally, a larger value is set arbitrarily, and the value is only 1000 + 10000), and recording the sum of Mean Square Errors (MSE) of two corresponding output variables when the current convolution kernel number is N (i) training as MSE (i).
And thirdly, before iteration optimization begins, inputting a 'rand (' state ', 0)' instruction in a python command line to ensure that the initialization parameters of the GCN at each iteration are the same.
And fourthly, when MSE (i) < MSE _ MAX, replacing the value of MSE _ MAX with MSE (i), and marking the current N (i) as desired _ N (i).
And fifthly, when all the iterations of the nine candidate convolution kernels are finished, the current MSE _ MAX corresponds to the MSE (i) minimum value, the desired _ N (i) corresponds to the optimal convolution kernel number, and finally the optimal convolution kernel number is determined to be 64.
For step S4, importing the data generated by the BSM1 model into an excel table through a USB interface, and then removing the abnormal data through a statistical method. And importing the processed data into a GCN model, and starting to predict the concentration of total nitrogen and ammonia nitrogen, wherein the GCN model preferably runs in a python platform.
Furthermore, the method according to the invention may further comprise the steps of:
s5, setting an early warning value for the concentration of total nitrogen and ammonia nitrogen, enabling a predicted value and the early warning value to be displayed on a software interface at the same time, and when the predicted value exceeds the early warning value, displaying red color on the predicted value and giving an alarm;
s6, storing the predicted data in a py (or python) file format in software, and conveniently inquiring the historical data.
It should be recognized that the method steps in embodiments of the present invention may be embodied or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The method may use standard programming techniques. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Further, the operations of processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable interface, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and the like. Aspects of the invention may be embodied in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or write storage medium, RAM, ROM, or the like, such that it may be read by a programmable computer, which when read by the storage medium or device, is operative to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention may also include the computer itself when programmed according to the methods and techniques described herein.
A computer program can be applied to input data to perform the functions described herein to transform the input data to generate output data that is stored to non-volatile memory. The output information may also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on a display.
The above description is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiment, and any modifications, equivalent substitutions, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention as long as the technical effects of the present invention are achieved by the same means. The invention is capable of other modifications and variations in its technical solution and/or its implementation, within the scope of protection of the invention.

Claims (10)

1. An intelligent online monitoring method for effluent nitrogenous substances is characterized by comprising the following steps:
s1, acquiring historical data of input variables and output variables of the prediction model from the field platform and/or the simulation platform through water quality parameter measurement modules arranged at the water inlet end and the water outlet end;
s2, establishing a prediction model of nitrogen concentration based on a graph convolution neural network (GCN) based on the input variable and the output variable;
s3, training the prediction model of the nitrogen concentration based on the graph convolution neural network (GCN) by using a momentum random gradient descent method (Adam);
and S4, acquiring current input variable data from the water body at the water inlet end on line through the water quality parameter measuring module, removing abnormal data, and inputting the abnormal data to the trained prediction model to obtain a prediction result of the output variable at the water outlet end.
2. The method of claim 1, wherein,
the input variables include dissolved oxygen (SO), nitrate nitrogen (SNO), total suspended solids in influent water (TSS)inf) Chemical Oxygen Demand (COD) of inlet waterinf) Total Nitrogen (TN) of the feed waterinf) And influent ammonia nitrogen (SNH)inf) The concentration of (a) in (b),
the output variable comprises effluent ammonia nitrogen (SNH)eff) And Total Nitrogen (TN) of effluenteff) The concentration of (c).
3. The method according to claim 1 or 2, wherein, in said step S1,
the on-site platform includes a sewage treatment unit of a sewage plant, and the simulation platform includes an activated sludge number 1 simulation model (BSM 1).
4. The method according to claim 2, wherein the step S2 includes:
dividing the data groups of the input variable and the output variable into a training set and a testing set according to the ratio of 4:1 respectively,
and respectively carrying out normalization processing on the training data and the test data before inputting the training data and the test data into the prediction model.
5. The method according to claim 1, wherein the step S3 further comprises:
and obtaining the optimal convolution kernel number of the convolution layer in the convolution neural network (GCN) by adopting an iterative optimization method.
6. The method according to claim 5, wherein the step S3 further comprises:
s31, selecting nine candidate convolution kernels, wherein the value of each convolution kernel is a multiple of 2, and configuring the nine candidate convolution kernels into a row vector N (i), wherein i is the sequence of elements in the row vector;
s32, providing an initial error of training of the prediction model based on the graph convolutional neural network (GCN) as MSE _ MAX, and setting the sum of the mean square errors of two corresponding output variables during training as MSE (i);
s33, ensuring that the initialization parameters of each iteration of the convolution kernel number of the prediction model based on the graph convolution neural network (GCN) are the same;
s34, when MSE (i) < MSE _ MAX, replacing the value of MSE _ MAX with MSE (i), and marking the current N (i) as desired _ N (i);
s35, when all the iterations of the nine candidate convolution kernels are completed, outputting the current MSE _ MAX as MSE (i) minimum value, and outputting the desired _ N (i) bit optimal convolution kernel number.
7. The method according to claim 1 or 3, wherein the step S4 further comprises:
and importing the data generated by the solid platform and/or the simulation platform into a statistical table, and then removing abnormal data by a statistical method.
8. The method of claim 1, wherein the method further comprises the steps of:
s5, setting an early warning value for the concentration of total nitrogen and ammonia nitrogen, and sending prompt information and an alarm on display equipment when monitoring that the current predicted value exceeds the early warning value;
and S6, storing the prediction result data in a python file format.
9. A computer readable storage medium having stored thereon program instructions which, when executed by a processor, implement the method of any one of claims 1 to 8.
10. The utility model provides an go out water nitrogen containing thing intelligence on-line monitoring system which characterized in that includes:
an online dissolved oxygen monitor;
nitrate nitrogen on-line monitoring instrument;
the display device is connected with the dissolved oxygen online monitor and the nitrate nitrogen online monitor;
a central processing device comprising the computer-readable storage medium of claim 8, the central processing device being connected to the dissolved oxygen on-line monitor, the nitrate nitrogen on-line monitor, and the display device.
CN202111091217.4A 2021-09-17 2021-09-17 Intelligent online monitoring method and system for effluent nitrogenous substances Pending CN113866375A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111091217.4A CN113866375A (en) 2021-09-17 2021-09-17 Intelligent online monitoring method and system for effluent nitrogenous substances

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111091217.4A CN113866375A (en) 2021-09-17 2021-09-17 Intelligent online monitoring method and system for effluent nitrogenous substances

Publications (1)

Publication Number Publication Date
CN113866375A true CN113866375A (en) 2021-12-31

Family

ID=78996444

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111091217.4A Pending CN113866375A (en) 2021-09-17 2021-09-17 Intelligent online monitoring method and system for effluent nitrogenous substances

Country Status (1)

Country Link
CN (1) CN113866375A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117637063A (en) * 2024-01-10 2024-03-01 广东工业大学 Water quality measurement method, device, equipment and storage medium
CN117637063B (en) * 2024-01-10 2024-05-31 广东工业大学 Water quality measurement method, device, equipment and storage medium

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107664682A (en) * 2016-07-30 2018-02-06 复凌科技（上海）有限公司 A kind of water quality hard measurement Forecasting Methodology of ammonia nitrogen
CN107664683A (en) * 2016-07-30 2018-02-06 复凌科技（上海）有限公司 A kind of water quality hard measurement Forecasting Methodology of total nitrogen
CN108564553A (en) * 2018-05-07 2018-09-21 南方医科大学 Low-dose CT image noise suppression method based on convolutional neural networks
CN110346358A (en) * 2019-07-16 2019-10-18 山东润通科技有限公司 A kind of ammonia nitrogen Quick testing instrument of convolutional neural networks (CNN) prediction
CN111000551A (en) * 2019-12-05 2020-04-14 常州市第一人民医院 Heart disease risk diagnosis method based on deep convolutional neural network model
CN111553468A (en) * 2020-05-15 2020-08-18 南京大学 Method for accurately predicting effluent quality of sewage treatment plant
CN111651762A (en) * 2020-04-21 2020-09-11 浙江大学 Convolutional neural network-based PE (provider edge) malicious software detection method
CN112016574A (en) * 2020-10-22 2020-12-01 北京科技大学 Image classification method based on feature fusion
CN112183279A (en) * 2020-09-21 2021-01-05 中国人民解放军国防科技大学 Communication radiation source individual identification method based on IQ graph characteristics
WO2021082809A1 (en) * 2019-10-29 2021-05-06 山东科技大学 Training optimization method for foreign exchange time series prediction

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107664682A (en) * 2016-07-30 2018-02-06 复凌科技（上海）有限公司 A kind of water quality hard measurement Forecasting Methodology of ammonia nitrogen
CN107664683A (en) * 2016-07-30 2018-02-06 复凌科技（上海）有限公司 A kind of water quality hard measurement Forecasting Methodology of total nitrogen
CN108564553A (en) * 2018-05-07 2018-09-21 南方医科大学 Low-dose CT image noise suppression method based on convolutional neural networks
CN110346358A (en) * 2019-07-16 2019-10-18 山东润通科技有限公司 A kind of ammonia nitrogen Quick testing instrument of convolutional neural networks (CNN) prediction
WO2021082809A1 (en) * 2019-10-29 2021-05-06 山东科技大学 Training optimization method for foreign exchange time series prediction
CN111000551A (en) * 2019-12-05 2020-04-14 常州市第一人民医院 Heart disease risk diagnosis method based on deep convolutional neural network model
CN111651762A (en) * 2020-04-21 2020-09-11 浙江大学 Convolutional neural network-based PE (provider edge) malicious software detection method
CN111553468A (en) * 2020-05-15 2020-08-18 南京大学 Method for accurately predicting effluent quality of sewage treatment plant
CN112183279A (en) * 2020-09-21 2021-01-05 中国人民解放军国防科技大学 Communication radiation source individual identification method based on IQ graph characteristics
CN112016574A (en) * 2020-10-22 2020-12-01 北京科技大学 Image classification method based on feature fusion

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
林永泽: ""基于图卷积的时空水质预测方法研究"", 中国知网中国知识基础设施工程，工程科技Ⅰ辑，环境科学与资源利用 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117637063A (en) * 2024-01-10 2024-03-01 广东工业大学 Water quality measurement method, device, equipment and storage medium
CN117637063B (en) * 2024-01-10 2024-05-31 广东工业大学 Water quality measurement method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
Côte et al. Dynamic modelling of the activated sludge process: improving prediction using neural networks
CN109508811A (en) Parameter prediction method is discharged based on principal component analysis and the sewage treatment of shot and long term memory network
CN108469507B (en) Effluent BOD soft measurement method based on self-organizing RBF neural network
CN113837356B (en) Intelligent sewage treatment prediction method based on fused neural network
Bernal et al. Financial market time series prediction with recurrent neural networks
CN103728431A (en) Industrial sewage COD (chemical oxygen demand) online soft measurement method based on ELM (extreme learning machine)
CN110320335B (en) Multi-element robust soft measurement method for effluent quality index of sewage treatment
CN110824914B (en) Intelligent wastewater treatment monitoring method based on PCA-LSTM network
CN113837364B (en) Sewage treatment soft measurement method and system based on residual network and attention mechanism
CN103235096A (en) Sewage water quality detection method and apparatus
CN111784061B (en) Training method, device and equipment for power grid engineering cost prediction model
CN108595892A (en) Soft-measuring modeling method based on time difference model
CN112735541A (en) Sewage treatment water quality prediction method based on simple circulation unit neural network
CN104914227A (en) Multi-gaussian kernel self-optimization relevance vector machine based wastewater quality soft-measurement method
Huang et al. Prediction of effluent parameters of wastewater treatment plant based on improved least square support vector machine with PSO
CN113866375A (en) Intelligent online monitoring method and system for effluent nitrogenous substances
CN115700324A (en) Tile temperature early warning method and device and electronic equipment
Han et al. Intelligent modeling approach to predict effluent quality of wastewater treatment process
Chen et al. Modeling of wastewater treatment process using recurrent neural network
Juuso et al. Intelligent analysers and dynamic simulation in a biological water treatment process
Chang et al. Soft Sensor of the Key Effluent Index in the Municipal Wastewater Treatment Process Based on Transformer
KR101025337B1 (en) Dynamic-mass balance model based a real-time effluent prediction system for a continuous type of biological wastewater treatment plants
Nawaz et al. Development of Smart AnAmmOx System and Its Agile Operation and Decision Support for Pilot-Scale WWTP
Liu et al. ANN-based prediction of ammonia nitrogen for wastewater discharge indicators under carbon neutral trend
Juuso Hybrid models in dynamic simulation of a biological water treatment process

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20211231