CN113571135A - Water age detection method based on parallel first-level model - Google Patents
Water age detection method based on parallel first-level model Download PDFInfo
- Publication number
- CN113571135A CN113571135A CN202110609532.5A CN202110609532A CN113571135A CN 113571135 A CN113571135 A CN 113571135A CN 202110609532 A CN202110609532 A CN 202110609532A CN 113571135 A CN113571135 A CN 113571135A
- Authority
- CN
- China
- Prior art keywords
- residual chlorine
- water
- consumption rate
- chlorine
- method based
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 121
- 238000001514 detection method Methods 0.000 title claims abstract description 22
- ZAMOUSCENKQFHK-UHFFFAOYSA-N Chlorine atom Chemical compound [Cl] ZAMOUSCENKQFHK-UHFFFAOYSA-N 0.000 claims abstract description 102
- 239000000460 chlorine Substances 0.000 claims abstract description 102
- 229910052801 chlorine Inorganic materials 0.000 claims abstract description 102
- 238000002474 experimental method Methods 0.000 claims abstract description 13
- 238000012417 linear regression Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 7
- 230000008859 change Effects 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 14
- 230000004913 activation Effects 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000007476 Maximum Likelihood Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000012217 deletion Methods 0.000 claims description 3
- 230000037430 deletion Effects 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 2
- 239000003651 drinking water Substances 0.000 abstract description 4
- 235000020188 drinking water Nutrition 0.000 abstract description 4
- 238000011161 development Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 230000003321 amplification Effects 0.000 description 3
- 238000003199 nucleic acid amplification method Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/10—Analysis or design of chemical reactions, syntheses or processes
-
- 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
Landscapes
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Analytical Chemistry (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Theoretical Computer Science (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Crystallography & Structural Chemistry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Physics & Mathematics (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Treatment Of Water By Oxidation Or Reduction (AREA)
Abstract
The invention relates to a water age detection method based on a parallel primary model, which comprises the following steps: collecting the water temperature and residual chlorine of the water outlet of the water supply and outlet equipment, and recording the collecting time; developing a three-factor orthogonal experiment according to the collected water temperature, time and residual chlorine and the initial chlorine concentration to determine the decay rate of the residual chlorine in the water outlet equipment, wherein the decay rate of the residual chlorine comprises the rapid consumption rate of the residual chlorine and the slow consumption rate of the residual chlorine; establishing an arrhenius relation model of the decay rate of the residual chlorine and the water temperature; establishing a parallel primary model according to the Arrhenius relation model to simulate the change conditions of residual chlorine and water age in the water body; and processing the parallel primary model by utilizing linear regression estimation, and performing approximate estimation on the water age of the water outlet equipment under the condition that the current residual chlorine, the initial residual chlorine and the water temperature are known. The intelligent water age detection system can realize intelligent and accurate detection of the water age of drinking water in a town water supply system.
Description
Technical Field
The invention relates to the technical field of water age detection, in particular to a water age detection method based on a parallel first-level model.
Background
Water is not only a life line of the whole national economy but also one of the basic substances on which human beings rely for survival and development. The water supply problem is one of the key problems related to the sustainable development of China. With the acceleration of the urbanization progress of China and the rapid development of national economy, the urban water supply of China enters the rapid development period, and in order to meet the basic requirements of industrial production and resident life, the water supply industry develops from the original direction of ensuring sufficient water supply and toward improving the water supply safety, improving the water quality and carrying out modern management. Various water storage devices (such as water tanks, water tanks and the like) in the urban water supply system are indispensable important facilities for guaranteeing the life, development, production and construction of urban people. As one of the urban infrastructure, the normal operation and water quality safety of the urban water supply system relate to the safety and stability of the whole society. In recent years, the water quality in the water storage facility has been increasingly considered.
Conventional methods for calculating the water age are more, for example, a large number of experiments predict the update time of water tanks in each cell to calculate the water age, but the experiment is greatly influenced by peripheral interference, and the generated result error is large and is not representative.
Disclosure of Invention
The invention aims to provide a water age detection method based on a parallel primary model, which can realize intelligent and accurate detection of the water age of drinking water in a town water supply system.
The technical scheme adopted by the invention for solving the technical problems is as follows: the water age detection method based on the parallel primary model comprises the following steps:
(1) collecting the water temperature and residual chlorine of the water outlet of the water supply and outlet equipment, and recording the collecting time;
(2) developing a three-factor orthogonal experiment according to the collected water temperature, time and residual chlorine and the initial chlorine concentration to determine the decay rate of the residual chlorine in the water outlet equipment, wherein the decay rate of the residual chlorine comprises the rapid consumption rate of the residual chlorine and the slow consumption rate of the residual chlorine;
(3) establishing an arrhenius relation model of the decay rate of the residual chlorine and the water temperature;
(4) establishing a parallel primary model according to the Arrhenius relation model to simulate the change conditions of residual chlorine and water age in the water body;
(5) and processing the parallel primary model by utilizing linear regression estimation, and performing approximate estimation on the water age of the water outlet equipment under the condition that the current residual chlorine, the initial residual chlorine and the water temperature are known.
And (3) preprocessing zero point supplement and abnormal point deletion are carried out on the collected water temperature and residual chlorine between the step (1) and the step (2).
The step (2) is specifically as follows: and calculating the residual chlorine consumption rate of each group of data in each time interval in the three-factor orthogonal experiment by adopting a difference-by-difference method, judging a rapid attenuation stage and a slow attenuation stage of the residual chlorine according to the residual chlorine consumption rate, and calculating the rapid residual chlorine consumption rate and the slow residual chlorine consumption rate by adopting an averaging method.
And (3) enhancing the decay rate of the residual chlorine and the water temperature.
The Arrhenius relationship model established in the step (3) is as follows:wherein k isbfFor fast consumption rate of residual chlorine, kbsThe slow consumption rate of residual chlorine, temp. the water temperature of water outlet equipment, R is gas constant, Af=exp(nf),As=exp(ns),nfAnd nsIs a constant coefficient, Ef=-R×mfIndicating the activation energy of the fast reaction, Es=-R×msRepresents the activation energy of the slow reaction, mfAnd msIs a constant coefficient.
The parallel first-level model established in the step (4) is as follows: c ═ C0zexp(-kbft)+C0(1-z)exp(-kbst), wherein C is the residual chlorine concentration at the current moment, C0Is the initial residual chlorine concentration, z is the ratio of the chlorine consumption of the rapid reaction to the total chlorine consumption, t is time, kbfFor fast consumption rate of residual chlorine, kbsThe slow consumption rate of residual chlorine.
The linear regression estimation in the step (5) is maximum likelihood estimation or least square estimation.
Advantageous effects
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects: according to the invention, based on monitoring parameters acquired by a data acquisition unit installed in water storage equipment in a water supply coverage area, orthogonal experiments are utilized to carry out research, and a relation model between the monitoring parameters and the water age is mastered, so that a water tank water age algorithm based on a parallel first-level model is built, and the intelligent and accurate detection of the water age of drinking water in a town water supply system can be realized.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The invention will be further illustrated with reference to the following specific examples. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and such equivalents may fall within the scope of the present invention as defined in the appended claims.
The embodiment of the invention relates to a water age detection method based on a parallel primary model, which comprises the following steps: collecting the water temperature and residual chlorine of the water outlet of the water supply and outlet equipment, and recording the collecting time; developing a three-factor orthogonal experiment according to the collected water temperature, time and residual chlorine and the initial chlorine concentration to determine the decay rate of the residual chlorine in the water outlet equipment, wherein the decay rate of the residual chlorine comprises the rapid consumption rate of the residual chlorine and the slow consumption rate of the residual chlorine; establishing an arrhenius relation model of the decay rate of the residual chlorine and the water temperature; establishing a parallel primary model according to the Arrhenius relation model to simulate the change conditions of residual chlorine and water age in the water body; and processing the parallel primary model by utilizing linear regression estimation, and performing approximate estimation on the water age of the water outlet equipment under the condition that the current residual chlorine, the initial residual chlorine and the water temperature are known.
As shown in fig. 1, the method comprises the following specific steps:
step 1, installing residual chlorine detection equipment and water temperature detection equipment in an area covered by water supply equipment according to the practical application scene of the water outlet equipment in the area covered by the water supply equipment, wherein the collected parameters comprise: water temperature temp. and residual chlorine C.
Step 2, preprocessing the acquired data by adopting a data preprocessing method to complete zero supplement and abnormal point deletion in the data;
and 3, developing a three-factor orthogonal experiment according to the collected water temperature, time and residual chlorine and the initial chlorine concentration, specifically: and calculating the residual chlorine consumption rate of each group of data in each time interval in the three-factor orthogonal experiment by adopting a difference-by-difference method, judging the fast attenuation stage and the slow attenuation stage of the residual chlorine according to the magnitude value of the residual chlorine consumption rate, and calculating the fast residual chlorine consumption rate and the slow residual chlorine consumption rate by adopting an averaging method. When the fast attenuation stage and the slow attenuation stage of the residual chlorine are judged, the judgment can be realized by setting a reasonable threshold, namely when the consumption rate of the residual chlorine exceeds the threshold, the fast attenuation stage is realized, and when the consumption rate of the residual chlorine does not exceed the threshold, the slow attenuation stage is realized.
And 4, because data with larger difference is needed during initial training of the model with the residual chlorine consumption rate changing along with the temperature, in order to improve the model precision, a data enhancement technology is needed to map the original data to a high-dimensional space so as to amplify useful information and obtain high-precision processing data. The data enhancement technique needs to follow the following principles:
(1) because of multi-source signal input, the data of all signal sources need to be amplified by a uniform method;
(2) the data cannot be distorted;
(3) the amplification of the data must be within a reasonable range;
(4) the amplification is carried out in a uniform data amplification interval;
based on the principle, the data enhancement processing is carried out on the residual chlorine rapid consumption rate, the residual chlorine slow consumption rate and the water temperature data obtained after the three-factor orthogonal experiment, and the main realization process is as follows:
(1) respectively calculating the weight values of the multi-source information by adopting an entropy weight method according to the input parameters;
(2) the enhancement of the data is accomplished using the following equation:
Bij=xij/wj
in the formula: b isijObtaining an enhancement matrix; x is the number ofijThe method comprises the following steps of (1) taking elements in original data, wherein i is the row number of the original data, and j is the column number of the original data; w is ajThe weight value of each column corresponds to the original data.
The method is adopted to enhance the original data, and the smaller data is amplified to a certain height space, so that more reasonable data information can be obtained, and the establishment of a relation model between the residual chlorine consumption rate and the water temperature is conveniently completed.
Step 5, according to each group of residual chlorine fast consumption rate k after data enhancementbfSlow consumption rate kbsAnd the water temperature Temp can establish two dependent variables as lnk respectivelybfAnd lnkbsThe independent variable isFirst order linear equation of (1):
in the formula: temp is the water temperature in the water tank, DEG C; m isf,nf,ms,nsIs a constant coefficient; k is a radical ofbfFor a rapid consumption rate of residual chlorine, h-1;kbsThe slow consumption rate of residual chlorine, h-1;
An arrhenius (Arrhennius) relationship model for the rate of decay of residual chlorine and the water temperature temp. was determined by two first order linear equations in equation (1):
in the formula: r is a gas constant, J/(K.mol); efActivation energy for fast reaction, kJ/mol; esActivation energy of slow reaction, kJ/mol; a. thefIs a constant independent of temperature, h-1;AsIs a constant independent of temperature, h-1。
Step 6, establishing a parallel primary model to simulate the attenuation condition of the residual chlorine in the water body, wherein the model assumes that the reaction of the residual chlorine in the water body occurs at two reaction rates, namely a fast reaction rate and a slow reaction rate, and the reaction model is as follows:
C=C0zexp(-kbft)+C0(1-z)exp(-kbst) (4)
in the formula: c is the residual chlorine concentration at the current moment, mg/L; c0Initial chlorine concentration, mg/L; z is the ratio of the chlorine consumption of the rapid reaction to the total chlorine consumption; t is time, h.
And 7, processing the parallel primary model by utilizing linear regression estimation, and carrying out approximate estimation on the water age of the current water outlet equipment to the maximum extent under the condition that the current residual chlorine, the initial residual chlorine and the water temperature are known, wherein the linear regression estimation can be maximum likelihood estimation or least square estimation.
According to the invention, the relation model of the monitoring parameters and the water age is mastered by developing research through orthogonal experiments according to the monitoring parameters acquired by the data acquisition unit arranged in the water storage equipment in the water supply coverage area, so that the water age algorithm of the water tank based on the parallel first-level model is built, and the intelligent and accurate detection of the water age of the drinking water in the urban water supply system can be realized.
Claims (7)
1. A water age detection method based on a parallel first-level model is characterized by comprising the following steps:
(1) collecting the water temperature and residual chlorine of the water outlet of the water supply and outlet equipment, and recording the collecting time;
(2) developing a three-factor orthogonal experiment according to the collected water temperature, time and residual chlorine and the initial chlorine concentration to determine the decay rate of the residual chlorine in the water outlet equipment, wherein the decay rate of the residual chlorine comprises the rapid consumption rate of the residual chlorine and the slow consumption rate of the residual chlorine;
(3) establishing an arrhenius relation model of the decay rate of the residual chlorine and the water temperature;
(4) establishing a parallel primary model according to the Arrhenius relation model to simulate the change conditions of residual chlorine and water age in the water body;
(5) and processing the parallel primary model by utilizing linear regression estimation, and performing approximate estimation on the water age of the water outlet equipment under the condition that the current residual chlorine, the initial residual chlorine and the water temperature are known.
2. The water age detection method based on the parallel primary model according to claim 1, further comprising a pretreatment of zero point supplement and abnormal point deletion for the collected water temperature and residual chlorine between the step (1) and the step (2).
3. The water age detection method based on the parallel primary model according to claim 1, wherein the step (2) is specifically as follows: and calculating the residual chlorine consumption rate of each group of data in each time interval in the three-factor orthogonal experiment by adopting a difference-by-difference method, judging a rapid attenuation stage and a slow attenuation stage of the residual chlorine according to the residual chlorine consumption rate, and calculating the rapid residual chlorine consumption rate and the slow residual chlorine consumption rate by adopting an averaging method.
4. The water age detection method based on the parallel first-order model as claimed in claim 1, further comprising enhancing the decay rate of residual chlorine and the water temperature between the step (2) and the step (3).
5. The water age detection method based on the parallel primary model according to claim 1, wherein the arrhenius relationship model established in the step (3) is:wherein k isbfFor fast consumption rate of residual chlorine, kbsThe slow consumption rate of residual chlorine, temp. the water temperature of water outlet equipment, R is gas constant, Af=exp(nf),As=exp(ns),nfAnd nsIs a constant coefficient, Ef=-R×mfIndicating the activation energy of the fast reaction, Es=-R×msRepresents the activation energy of the slow reaction, mfAnd msIs a constant coefficient.
6. The water age detection method based on the parallel primary model according to claim 1, wherein the parallel primary model established in the step (4) is: c ═ C0zexp(-kbft)+C0(1-z)exp(-kbst), wherein C is the residual chlorine concentration at the current moment, C0Is the initial residual chlorine concentration, z is the ratio of the chlorine consumption of the rapid reaction to the total chlorine consumption, t is time, kbfFor fast consumption rate of residual chlorine, kbsThe slow consumption rate of residual chlorine.
7. The water age detection method based on the parallel first-order model according to claim 1, wherein the linear regression estimation in the step (5) is maximum likelihood estimation or least square estimation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110609532.5A CN113571135A (en) | 2021-06-01 | 2021-06-01 | Water age detection method based on parallel first-level model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110609532.5A CN113571135A (en) | 2021-06-01 | 2021-06-01 | Water age detection method based on parallel first-level model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113571135A true CN113571135A (en) | 2021-10-29 |
Family
ID=78160981
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110609532.5A Pending CN113571135A (en) | 2021-06-01 | 2021-06-01 | Water age detection method based on parallel first-level model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113571135A (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100875372B1 (en) * | 2007-12-31 | 2008-12-22 | 한국수자원공사 | A device for consecutive measuring residual chlorine in water distribution system |
CN102707027A (en) * | 2012-06-12 | 2012-10-03 | 浙江大学 | Method for determining chlorine demand for rapid reaction in chlorine residual decay after chlorination |
-
2021
- 2021-06-01 CN CN202110609532.5A patent/CN113571135A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100875372B1 (en) * | 2007-12-31 | 2008-12-22 | 한국수자원공사 | A device for consecutive measuring residual chlorine in water distribution system |
CN102707027A (en) * | 2012-06-12 | 2012-10-03 | 浙江大学 | Method for determining chlorine demand for rapid reaction in chlorine residual decay after chlorination |
Non-Patent Citations (1)
Title |
---|
王旭冕: "城市供水系统水质安全性与余氯控制的研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》, pages 160 - 22 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104376380B (en) | A kind of ammonia nitrogen concentration Forecasting Methodology based on recurrence self organizing neural network | |
CN111291937A (en) | Method for predicting quality of treated sewage based on combination of support vector classification and GRU neural network | |
CN104965971B (en) | A kind of ammonia nitrogen concentration flexible measurement method based on fuzzy neural network | |
CN101630376B (en) | Soft-sensing modeling method and soft meter of multi-model neural network in biological fermentation process | |
CN112001527B (en) | Industrial production process target data prediction method of multi-feature fusion depth neural network | |
CN102854296A (en) | Sewage-disposal soft measurement method on basis of integrated neural network | |
CN106249724B (en) | A kind of polynary molten steel quality forecast Control Algorithm of blast furnace and system | |
CN105510546A (en) | Intelligent biochemical oxygen demand (BOD) detection method based on self-organizing recursion radial basis function (RBF) neural network | |
CN103606006A (en) | Sludge volume index (SVI) soft measuring method based on self-organized T-S fuzzy nerve network | |
CN102262147A (en) | Soft measurement method and system for effluent chemical oxygen demand (COD) of waste water treatment system | |
CN104199389B (en) | The optimization method of golden hydrometallurgy replacement process | |
CN108088974B (en) | Soft measurement method for effluent nitrate nitrogen in anaerobic simultaneous denitrification methanogenesis process | |
CN110866659A (en) | On-line prediction method for caustic ratio in dissolution process of high-pressure pipeline in Bayer-process alumina production | |
CN115169733B (en) | Deep learning-based method for predicting resuspension amount of internal solitary waves on deep sea sediment | |
CN104951803A (en) | Soft measurement method applied to dry point of aviation kerosene of atmospheric-pressure distillation tower and based on dynamic moving window LSSVM (least squares support vector machine) | |
CN105445344A (en) | Temperature compensation method of system for detecting heavy metals in water environment | |
CN105320987A (en) | Satellite telemetry data intelligent interpretation method based on BP neural network | |
CN109711435A (en) | A kind of support vector machines on-Line Voltage stability monitoring method based on genetic algorithm | |
CN102542126A (en) | Soft measurement method based on half supervision learning | |
CN114169242A (en) | Intelligent control algorithm for analyzing ecological oxygenation of river channel based on parameter uncertainty | |
CN103952724B (en) | For the optimization weight Relative Principal Component Analysis Algorithm of aluminium cell condition trouble diagnosis | |
CN106706491B (en) | Intelligent detection method for membrane bioreactor-MBR water permeability | |
CN115371642A (en) | Geological statistics inversion method for hydrogeological parameter dynamic change characteristics | |
CN112819087B (en) | Method for detecting abnormality of BOD sensor of outlet water based on modularized neural network | |
CN111204867B (en) | Membrane bioreactor-MBR membrane pollution intelligent decision-making method |
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 |