CN107977724A - A kind of water quality hard measurement Forecasting Methodology of permanganate index - Google Patents
A kind of water quality hard measurement Forecasting Methodology of permanganate index Download PDFInfo
- Publication number
- CN107977724A CN107977724A CN201610920985.9A CN201610920985A CN107977724A CN 107977724 A CN107977724 A CN 107977724A CN 201610920985 A CN201610920985 A CN 201610920985A CN 107977724 A CN107977724 A CN 107977724A
- Authority
- CN
- China
- Prior art keywords
- water quality
- index
- model
- permanganate index
- permanganate
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Abstract
Embodiment of the present invention is related to environmental monitoring, discloses a kind of water quality hard measurement Forecasting Methodology of permanganate index.Including:Obtain the data value of multiple water quality monitoring indexs in water environment to be measured, the data value that each water quality monitoring index is acquired has multiple, at least one in multiple water quality monitoring indexs is permanganate index;Several water quality monitoring indexs are chosen from each water quality monitoring index in addition to permanganate index, the data value of selected water quality monitoring index is formed into set of data samples, set of data samples is divided into training set and test set, training set is trained using algorithm of support vector machine, obtains permanganate index soft-sensing model;Using test set, permanganate index soft-sensing model is tested, obtains test result;The foundation and model measurement of model are repeated, until the test result obtained meets preset condition, the permanganate index soft-sensing model of preset condition will be met as final soft-sensing model.Gained forecast result of model is accurate, reduces the water quality hard measurement forecast cost of permanganate index.
Description
Technical field
The present invention relates to the water quality hard measurement Predicting Technique of environmental monitoring, more particularly to permanganate index.
Background technology
It is well known that China's water resource is very rare, occupancy volume per person only accounts for the 1/4 of world average level, while seriously
Water environment pollution problem, such as water pollution, body eutrophication, city black and odorous water, underground water pollution.Ask water resource
Topic is further prominent.In rural area, China nearly 96%, about 80~9,000,000,000 t/a country sewage is not administered, serious rural environment
Pollution and the pollution of river ocean current domain, in city, black and odorous water already becomes a kind of urban disease, and all cities are escaped by luck almost without one.State
Interior major part river is subject to different degrees of pollution.Alleviate nervous water resource, increasing sewage purification, mitigate water environment pollution quarter
Do not allow to delay.
It is urgent with water environment protection and pollution control, it is particularly important that the water quality information that water quality monitoring provides, water quality prison
Survey is the important foundation of water environment protection and pollution control, its importance concern grasp water resource quality situation and to water,
The effective monitorings such as sewage disposal, blowdown.On the one hand, the water quality situation of polluted water body is required for by permanganate index, ammonia
The monitoring of the key water quality index such as nitrogen, total nitrogen (TN), total phosphorus (TP) provides water quality multidate information accurately and timely, on the other hand,
Timely and effectively Wastewater Treatment Parameters monitor, and are of great importance to sewage disposal system, and the discharge of sewage has to comply with national dirt
Relevant regulations in water discharge standard, this requires we must TN, TP, permanganate index, ammonia nitrogen in detection process water outlet
Deng key parameter.Therefore strengthening water environment protection and pollution control needs water quality monitoring work to develop in advance.
The monitoring of the key water quality index such as permanganate index, ammonia nitrogen, TN, TP, control, process for water treatment
Optimization and diagnosis play an important role, but this kind of water quality index is difficult to measure or be not easy on-line measurement, current main someone
Work test in laboratory and detection water quality automatically analyze instrument (water quality on-line detector).
Water quality on-line automatic analyzer, as permanganate index on-line computing model, TN on-line detectors, permanganate are online
Detector etc., in China, than later, the measuring accuracy and reliability of home products, there are a certain distance, are deposited with foreign countries for development
In single varieties, the defects of precision is low, and measurement period is long is measured, is not fully achieved and meets measurement demand, at saprobia
The water quality parameter of reason process can not measure exactly.It is but difficult, expensive there are repair and maintenance using external product
The problems such as, limit its application in water environment protection and pollution control field.
Monitoring resolving ideas has following two at present:
(1) direct measuring instrumentss are improved:According to the mistake of traditional detection technique thinking of development, in the form of hardware development of new
Journey measuring instrumentss.But it is typical non-linear, changeable since sewage disposal system is a complicated biochemistry treatment system
Amount, unstable, Correction for Large Dead Time System, disturbing factor is numerous and uncertain, directly research and development, improvement on-line monitoring instrument, and difficulty is big, and
Monitoring cost (disposable input and reagent expense) is higher, it is difficult to reduces.
(2) measurement indirectly:Using the thinking measured indirectly, believe using easy acquisition and with the relevant measurement of measured variable
Breath, estimates measured variable by calculating.Hard measurement is the concentrated reflection of this thought, and hard measurement is applied to water environment protection
And, it can be achieved that small investment, the purpose monitored in real time in pollution control.
The content of the invention
The purpose of embodiment of the present invention is the water quality hard measurement Forecasting Methodology for providing a kind of permanganate index, is protecting
Demonstrate,prove permanganate index water quality hard measurement prediction accuracy while, reduce permanganate index water quality hard measurement prediction into
This.
In order to solve the above technical problems, embodiments of the present invention provide a kind of water quality hard measurement of permanganate index
Forecasting Methodology, including:
The acquisition and analysis of data:Obtain the data value of multiple water quality monitoring indexs in water environment to be measured, each water process
The data value that monitoring index is acquired has multiple, at least one in multiple water quality monitoring indexs refers to for permanganate
Number;
The foundation of model:Several water quality prison is chosen from each water quality monitoring index in addition to the permanganate index
Index is surveyed, the data value of selected water quality monitoring index is formed into set of data samples, the set of data samples is divided into training
Collection and test set, are trained the training set using algorithm of support vector machine, obtain permanganate index soft-sensing model;
Model measurement:Utilize the test set, the test tested by Multi simulation running, to the soft survey of the permanganate index
Amount model is tested, and obtains test result;
The foundation of the model and the model measurement are repeated, until the test result obtained meets preset condition,
The permanganate index soft-sensing model of the preset condition will be met as final soft-sensing model.
In terms of existing technologies, the main distinction and its effect are embodiment of the present invention:In permanganate index
Hard measurement prediction in, with the method for repeatedly modeling and testing, from numerous water quality monitoring indexs, choose and arrive and water ring to be measured
The more particularly suitable index in border so that the model finally obtained can more predict permanganic acid in water environment to be measured accurate stable
The value of salt index.Solve in the prior art, modeled using same group of water process monitoring index, the model obtained cannot be accurate
Meet the permanganate index prediction of water environment to be measured, expand the application scenarios of embodiment of the present invention.In addition, further limit
The data got are divided into training set and test set, both data values can be different data values so that, can during test
Using outer test is collected, greatly improve the effect convincingness of permanganate index soft-sensing model.
As a further improvement, before the modeling procedure, further include:Correlation analysis:Referred to using each water quality monitoring
Target data value, carries out correlation analysis, obtains each water quality monitoring index in addition to the permanganate index and described
Correlation between permanganate index;Correspondingly, in described several water quality monitoring indexs of selection, the correlation is utilized
Just, several water quality monitoring indexs are chosen.
Utilize correlation analysis so that can be chosen during index for selection according to analysis result so that selection is provided with preferably
Foundation, improve the efficiency for obtaining satisfactory soft-sensing model.
As a further improvement, after the model measurement, and before the model measurement, further include:Intersected by ten foldings and tested
Demonstrate,prove and the permanganate index soft-sensing model obtained is optimized;It is described that permanganate index soft-sensing model is surveyed
In examination, the permanganate index soft-sensing model after optimization is tested.
Model optimization is carried out using ten folding cross validations so that the error of model is greatly lowered, and greatly improves mould
Type accuracy, by above-mentioned algorithm of support vector machine and ten folding cross validations, makes the final mask of acquisition more precise and stable.
As a further improvement, described select according to each test result in final soft-sensing model, the model measurement
The test result of middle acquisition includes:Time complexity, accuracy rate and the stabilization of the permanganate index soft-sensing model
Property.The content of test result is further limited, improves the validity of selected final soft-sensing model.
As a further improvement, in the obtaining step, if the data value got belongs to:Permanganic acid index, total nitrogen,
Total phosphorus or ammonia nitrogen, then give up.Due to the direct testing cost mistake of this four indexs of permanganate index, total nitrogen, total phosphorus or ammonia nitrogen
Height, does not use water quality hard measurement forecast cost of this four indexs as input, further reduction permanganate index.
Brief description of the drawings
Fig. 1 is the hard measurement Forecasting Methodology flow chart of the permanganate index in first embodiment according to the present invention;
Fig. 2 is high obtained by permanganate index value and hard measurement in the actual water outlet in first embodiment according to the present invention
The schematic diagram to when relative error of manganate exponential quantity;
Fig. 3 is the hard measurement Forecasting Methodology flow chart of the permanganate index in second embodiment according to the present invention.
Embodiment
To make the purpose, technical scheme and advantage of embodiment of the present invention clearer, below in conjunction with attached drawing to this hair
Bright each embodiment is explained in detail.However, it will be understood by those skilled in the art that in each implementation of the invention
In mode, many ins and outs are proposed in order to make reader more fully understand the application.It is but even if thin without these technologies
Section and many variations based on following embodiment and modification, can also realize the application technical solution claimed.
The first embodiment of the present invention is related to a kind of water quality hard measurement Forecasting Methodology of permanganate index.Its flow is such as
It is specific as follows shown in Fig. 1:
Step 101, the data value of multiple water quality monitoring indexs in water environment to be measured is obtained.
Specifically, the water quality monitoring index in present embodiment can be following index:Permanganate index, water temperature,
PH, dissolved oxygen, electrical conductivity, turbidity, flow velocity etc..Certainly, in practical applications, other water quality monitoring indexs can also be chosen, no
It is limited to These parameters.More specifically, at least one in the water quality monitoring index obtained is permanganate index.
More specifically, above-mentioned water quality monitoring index will be divided into two classes, it is input pointer and output-index respectively, exports
Index refers to water quality monitoring index permanganate index, and the data value of permanganate index is as output data sample;Input pointer
Including other water quality monitoring indexs in addition to permanganate index, the data value of these indexs is as input sample of data.
It should be noted that the data value that each water quality monitoring index is acquired have it is multiple.The nearly stage can generally be selected
Data value of the historical data as each index.
It is noted that acceptable further garbled data in this step, such as:If the data value category got
In:Total nitrogen, total phosphorus or ammonia nitrogen, then give up.These three indexs of total nitrogen, total phosphorus or ammonia nitrogen can not thus be used, due to total nitrogen,
The direct testing cost of these three indexs of total phosphorus or ammonia nitrogen is excessive, does not use these three indexs further to be reduced high as input
The water quality hard measurement forecast cost of mangaic acid salt index.
Step 102, using the data value of each water quality monitoring index, correlation analysis is carried out, is obtained except permanganate refers to
The correlation between each water quality monitoring index and permanganate index outside number.
Specifically, correlation analysis formula is following formula (1):
Wherein, correlation coefficient r represents the degree in close relations between two variables x and y.
It is noted that in practical applications, correlation analysis can not also be carried out, directly chosen using experience, but this
Embodiment is also the increase in the step of correlation analysis, can allow and be chosen during index for selection according to analysis result, be made
It must choose and be provided with preferable foundation, accelerate to obtain the speed of satisfactory soft-sensing model.
Step 103, several water quality monitoring indexs are chosen from each water quality monitoring index in addition to permanganate index
Combination, forms set of data samples.
Specifically, the basis for selecting in present embodiment can be the correlation analysis of step 102 as a result, as chosen
It is several indexs of correlation more than 30%, and the data value of selected water quality monitoring index is formed into set of data samples.
In practical application, rule of thumb the larger mandatory parameter of some correlations can also be set, and ginseng is not selected without correlation
Number.
Specifically, correlation results are represented with correlation coefficient r, and the value of r is between -1 and+1, i.e. -1≤r≤+ 1.Its
Property is as follows:
Work as r>When 0, two variable positive correlations, r are represented<When 0, two variables are negative correlation;
When | r | when=1, two variables of expression are fairly linear correlation, are functional relation;
As r=0, without linear relationship between two variables of expression;
When 0<|r|<When 1, represent that there are a degree of linear correlation for two variables.And | r | closer 1, two variable top-stitchings
Sexual intercourse is closer;| r | closer to 0, represent that the linear correlation of two variables is weaker.It can generally be divided by three-level:|r|<0.4 is
It is low linearly related;0.4≤|r|<0.7 is related for conspicuousness;0.7≤|r|<1 is related for highly linear.
More specifically, the index quantity chosen also does not limit, any number of index can be chosen.
Step 104, set of data samples is divided into two classes:One kind is used as training set, and one kind is used as test set.
Specifically, the data value included in the training set after present embodiment division can be more than what is included in test set
Data value.Wherein, various principles can be used during division.
It is noted that the set of data samples used in follow-up modeling procedure is training set;Used in testing procedure
Set of data samples be test set.The data value of training set and test set is further limited as different data values so that test
When, the outer test of collection can be utilized, greatly improves the effect convincingness of permanganate index soft-sensing model.
Step 105, training set is trained using algorithm of support vector machine, obtains the hard measurement mould of permanganate index
Type.
Specifically, support vector machines (Support Vector Machine, SVM) is Vapni and his research group
In a kind of new sorting technique for two category classification problems that nineteen ninety-five proposes according to statistical theory.SVM passes through construction
Function (nonlinear function) by input data space reflection to higher-dimension feature space, then in this high-dimensional feature space
In based on structural risk minimization construction optimal separating hyper plane so that the anticipation error of classification is minimum.
More specifically, support vector machines divides following steps in present embodiment:
1. it is vectorial (i.e. sample set) to input training sample:(Xi,yi) (i=1,2 ..., N, X ∈ Rn,y∈Rn);
2. specify the type of kernel function;
3. solving the optimal solution of target function type (13) using QUADRATIC PROGRAMMING METHOD FOR, optimal lagrange multipliers are obtained;
4. using a supporting vector in sample storehouse, substitute into formula (14), lvalue f (X) is its predicted value, be can obtain
Deviation b*。
Specifically for two class linear separabilities the problem of, if linear separability sample set { (Xi,yi), i=1,2 ... N }, Xi
∈Rd, yi∈ { 1, -1 } is the category label of sample, yiFor sample class, if yi=1, then Xi∈X+;If yi=-1, that
Xi∈X-.The condition of the two classes subset linear separability is that there are a vector W*With constant b*, and they meet following formula (1)
Constraints:
yi(<Xi·W*>+b*) >=1, i=1 ..., N (1)
And vector W*With minimum norm
Discriminant function at this time is:
F (X)=W*·X+b* (3)
Under the conditions of linear restriction formula (1), quadratic form is minimized, referring to formula (2).Method for solving with lagrange (i.e.:Draw
Ge Lang) multiplier method, lagrange equations are:
Wherein ai>=0 is lagrange multipliers.Partial differential is asked to W and b, obtains following condition:
So as to obtain relational expression (6) and (7):
Substitution formula obtains in (4)
Wherein H (a) is the rewriting of L (W, a, b).Solve this formula and obtain ai *>=0, i=1,2 ..., N, substitutes into formula (6) and obtains:
The a of optimal solutioni *It must meet:
ai *|yi(<W*·Xi>+b*) -1 |=0, i=1,2 ..., N (10)
Optimal solution a can be tried to achieve by Novel Algorithmi *And W*.Then a supporting vector X is choseni, seek b*:
b*=yi-<Xi·W*> (11)
Optimal discriminant function has following form:
When for Nonlinear Mapping when, object function is changed into:
Anticipation function is:
Wherein, k is kernel function, such as formula (15).Kernel function for Radial basis kernel function (Radial Basis Function,
RBF), most general Radial basis kernel function is Gaussian radial basis function.
K (X, Y)=exp-γ * | X-Y |2} (15)
Step 106, optimized using ten folding proof methods to obtaining permanganate index soft-sensing model, after being optimized
Permanganate index water quality soft-sensing model.
Specifically, sample set is randomly divided into ten parts in this step, in turn will wherein 9 parts do training 1 part test, 10
Then secondary result average carries out 10 times of cross validations of 20 times and averages as the estimation to arithmetic accuracy.
Step 107, the soft-sensing model of the permanganate index after being optimized is tested using test set, obtained
Obtain test result.
Specifically, after input test collection, trained Lagrange multiplier a is utilized*, deviation b*And kernel function, root
Anticipation function f (X) is solved according to formula (14), test result is obtained according to the comparison of each predicted value of acquisition and test set.
Test result includes in present embodiment:Time complexity, accuracy rate and the stability of soft-sensing model.In order to obtain
More preferably prediction model, so be required for being considered in these areas, could obtain that run time is short, accuracy rate is high, steady
Qualitative good prediction model.Certainly, in practical applications, test result may also contain more items, such as:Involved in model
Index quantity.
Step 108, whether the test result for judging to obtain meets preset condition;If so, then perform step 109;If it is not, then
Return to step 103.
Specifically, can be with the basis for estimation in present embodiment step 107 test result whether meet it is default
Condition.For example whether accuracy rate is higher than 90%, when being higher than 90% due to accuracy rate, prediction model is considered than calibrated
True, certain accuracy rate can be higher than 95%, and corresponding prediction model is with regard to successful.Again for example, the index quantity being related to is
It is no suitable, during due to actual prediction, if involved index quantity is fewer, the stability of model is influenced, conversely, then influence should
The time complexity of model.
Certainly, if it is decided that test result can't meet preset condition, and the model that may be obtained is accurate not enough, that
Modeling procedure is just repeated, continuously improves the combination of involved index.Specifically, step 103 is performed every time to 106
Afterwards, the corresponding soft-sensing model for obtaining a permanganate index.
Such as in practical application, it is predetermined to need to find permanganate index soft-sensing model of the accuracy more than 95%.
Model for the first time, have chosen 14 water quality index, after the permanganate index soft-sensing model test obtained to first time, obtain
The accuracy obtained is 90%;Carry out second to model, have chosen 7 water quality index again, to second of permanganic acid obtained
After the test of salt index soft-sensing model, the accuracy of acquisition is 93%;Third time modeling is carried out again, have chosen 3 water quality again
Index, after the permanganate index soft-sensing model test obtained to third time, the accuracy of acquisition is 97% to have reached standard
Requirement of the exactness more than 95%.
It should also be noted that, in modeling procedure is performed a plurality of times, the water quality monitoring selected by arbitrarily training twice refers to
Mark combination does not repeat.
Step 109, using test result meet preset condition permanganate index soft-sensing model as final soft
Measurement model.
Specifically, test of the present inventor to final soft-sensing model as shown in Fig. 2, wherein it should be noted that
Figure center line 1 represents the actual measured value of permanganate index, and line 2 represents the permanganate carried out using final soft-sensing model
Exponential forecasting value, line 3 represent relative error between the two.
Present embodiment in terms of existing technologies, in the hard measurement prediction of permanganate index, with repeatedly building
Mould and the method tested, from numerous water quality monitoring indexs, the index more particularly suitable with water environment to be measured is arrived in selection so that final
The model of acquisition can more predict the value of permanganate index in water environment to be measured accurate stable.Solves the prior art
In, modeled using same group of water process monitoring index, the model obtained cannot closely conform to the water to be measured of various different conditions
Environment, expands the application scenarios of embodiment of the present invention.Further, since using ten folding cross validations, reduce and obtain preferably prediction
The time of model.
The step of various methods divide above, be intended merely to describe it is clear, can be merged into when realizing a step or
Some steps are split, are decomposed into multiple steps, as long as including identical logical relation, all protection domain in this patent
It is interior;To either adding inessential modification in algorithm in flow or introducing inessential design, but its algorithm is not changed
Core design with flow is all in the protection domain of the patent.
Second embodiment of the present invention is related to a kind of water quality hard measurement Forecasting Methodology of permanganate index.Its flow is such as
It is specific as follows shown in Fig. 3:
Step 201, the acquisition and analysis of data.
Specifically, the data value of multiple water quality monitoring indexs in water environment to be measured, each water quality monitoring index quilt are obtained
The data value got has multiple, at least one in multiple water quality monitoring indexs is permanganate index.
Step 202, selecting index.
Specifically, several water quality monitorings are chosen from each water quality monitoring index in addition to permanganate index to refer to
Mark.
Step 203, the preparation of set of data samples.
Specifically, the data value of selected water quality monitoring index is formed into set of data samples, meanwhile, by set of data samples
It is divided into training set and test set.
Step 204, the foundation of model.
Specifically, training set is trained using algorithm of support vector machine, obtains permanganate index hard measurement mould
Type.
Step 205, model measurement.
Specifically, using test set, permanganate index soft-sensing model is tested, obtains test result.
Step 206, whether the test result for judging to obtain meets preset condition;If so, then perform step 207;If it is not, then
Return to step 202.
Step 207, the permanganate index soft-sensing model of preset condition will be met as final soft-sensing model.
In terms of existing technologies, the main distinction and its effect are present embodiment:In the soft of permanganate index
In measurement prediction, with the method for repeatedly modeling and testing, from numerous water quality monitoring indexs, choose and arrive with water environment to be measured more
For suitable index so that the model finally obtained can more predict permanganate in water environment to be measured accurate stable and refer to
Several values.Solve in the prior art, modeled using same group of water process monitoring index, the model obtained cannot closely conform to
The permanganate index prediction of water environment to be measured, expands the application scenarios of embodiment of the present invention.Obtained in addition, further limiting
To data be divided into training set and test set, both data values can be different data values so that during test, Ke Yili
With the outer test of collection, greatly improve the effect convincingness of permanganate index soft-sensing model.
It will be understood by those skilled in the art that the respective embodiments described above are to realize the specific embodiment of the present invention,
And in practical applications, can to it, various changes can be made in the form and details, without departing from the spirit and scope of the present invention.
Claims (6)
- A kind of 1. water quality hard measurement Forecasting Methodology of permanganate index, it is characterised in that including:The acquisition and analysis of data:The data value of multiple water quality monitoring indexs in water environment to be measured is obtained, each water quality monitoring refers to Marking the data value that is acquired has multiple, at least one in multiple water quality monitoring indexs is permanganate index;The foundation of model:Several water quality monitorings are chosen from each water quality monitoring index in addition to the permanganate index to refer to Mark, set of data samples is formed by the data value of selected water quality monitoring index, by the set of data samples be divided into training set and Test set, is trained the training set using algorithm of support vector machine, obtains permanganate index soft-sensing model;Model measurement:Using the test set, the permanganate index soft-sensing model is tested, obtains test knot Fruit;The foundation of the model and the model measurement are repeated, until the test result obtained meets preset condition, will be accorded with The permanganate index soft-sensing model of the preset condition is closed as final soft-sensing model.
- 2. the water quality hard measurement Forecasting Methodology of permanganate index according to claim 1, it is characterised in that the model Before test, and after the model measurement, further include:By ten folding cross validations to the permanganate index hard measurement mould that is obtained Type optimizes;It is described that permanganate index soft-sensing model is tested, to permanganate index soft-sensing model after optimization into Row test.
- 3. the water quality hard measurement Forecasting Methodology of permanganate index according to claim 1, it is characterised in that the model Foundation before, further include:Correlation analysis:Using the data value of each water quality monitoring index, correlation analysis is carried out, acquisition removes the permanganate The correlation between each water quality monitoring index and the permanganate index outside index;Correspondingly, in described several water quality monitoring indexs of selection, using the height of the correlation, several water quality prison is chosen Survey index.
- 4. the water quality hard measurement Forecasting Methodology of permanganate index according to claim 1, it is characterised in that the model The test result obtained in test includes:The time complexity of the permanganate index soft-sensing model, accuracy rate and Stability.
- 5. the water quality hard measurement Forecasting Methodology of permanganate index according to claim 1, it is characterised in that the data Acquisition and analysis in, if the data value got belongs to:Permanganate index, total nitrogen, total phosphorus or ammonia nitrogen, then give up.
- 6. the water quality hard measurement Forecasting Methodology of permanganate index as claimed in any of claims 1 to 5, its feature It is, the data value included in the training set is more than the data value included in the test set.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610920985.9A CN107977724A (en) | 2016-10-21 | 2016-10-21 | A kind of water quality hard measurement Forecasting Methodology of permanganate index |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610920985.9A CN107977724A (en) | 2016-10-21 | 2016-10-21 | A kind of water quality hard measurement Forecasting Methodology of permanganate index |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107977724A true CN107977724A (en) | 2018-05-01 |
Family
ID=62004498
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610920985.9A Withdrawn CN107977724A (en) | 2016-10-21 | 2016-10-21 | A kind of water quality hard measurement Forecasting Methodology of permanganate index |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107977724A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109934419A (en) * | 2019-04-11 | 2019-06-25 | 苏州热工研究院有限公司 | A kind of nuclear power plant's intake marine organisms amount variation prediction technique |
CN110132629A (en) * | 2019-06-06 | 2019-08-16 | 浙江清华长三角研究院 | A method of utilizing SVM prediction rural domestic sewage treatment facility operation validity |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103235096A (en) * | 2013-04-16 | 2013-08-07 | 广州铁路职业技术学院 | Sewage water quality detection method and apparatus |
CN103942457A (en) * | 2014-05-09 | 2014-07-23 | 浙江师范大学 | Water quality parameter time series prediction method based on relevance vector machine regression |
-
2016
- 2016-10-21 CN CN201610920985.9A patent/CN107977724A/en not_active Withdrawn
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103235096A (en) * | 2013-04-16 | 2013-08-07 | 广州铁路职业技术学院 | Sewage water quality detection method and apparatus |
CN103942457A (en) * | 2014-05-09 | 2014-07-23 | 浙江师范大学 | Water quality parameter time series prediction method based on relevance vector machine regression |
Non-Patent Citations (1)
Title |
---|
谢福民: "基于支持向量机的软测量方法及其应用研究", 《中国优秀硕士学位论文全文数据库(信息科技辑)》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109934419A (en) * | 2019-04-11 | 2019-06-25 | 苏州热工研究院有限公司 | A kind of nuclear power plant's intake marine organisms amount variation prediction technique |
CN110132629A (en) * | 2019-06-06 | 2019-08-16 | 浙江清华长三角研究院 | A method of utilizing SVM prediction rural domestic sewage treatment facility operation validity |
CN110132629B (en) * | 2019-06-06 | 2020-03-10 | 浙江清华长三角研究院 | Method for predicting operation effectiveness of rural domestic sewage treatment facility by using support vector machine |
WO2020244265A1 (en) * | 2019-06-06 | 2020-12-10 | 浙江清华长三角研究院 | Method for predicting operation effectiveness of rural domestic sewage treatment facility using support vector machine |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111104981B (en) | Hydrological prediction precision evaluation method and system based on machine learning | |
CN107229768B (en) | Slopereliability parameter acquiring method and device based on fuzzy classification technology | |
CN108399248A (en) | A kind of time series data prediction technique, device and equipment | |
CN111400371A (en) | Voltage correlation verification-based user variable relationship identification method | |
CN103136539A (en) | Grounding grid corrosion rate level prediction method | |
CN109948522A (en) | A kind of X-ray hand osseous maturation degree interpretation method based on deep neural network | |
Xiong et al. | The order statistics correlation coefficient and PPMCC fuse non-dimension in fault diagnosis of rotating petrochemical unit | |
CN101853290A (en) | Meteorological service performance evaluation method based on geographical information system (GIS) | |
US20220122739A1 (en) | Ai-based condition classification system for patients with novel coronavirus | |
CN109767054A (en) | Efficiency cloud appraisal procedure and edge efficiency gateway based on deep neural network algorithm | |
CN113406558B (en) | Ammeter misalignment detection method and device based on linear regression and electronic equipment | |
CN105468926A (en) | Underground water type drinking water source pollution source analysis method | |
CN203772781U (en) | Characteristic variable-based sewage total phosphorus measuring device | |
CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
CN116432123A (en) | Electric energy meter fault early warning method based on CART decision tree algorithm | |
CN107977724A (en) | A kind of water quality hard measurement Forecasting Methodology of permanganate index | |
CN107665288A (en) | A kind of water quality hard measurement Forecasting Methodology of COD | |
CN105243503A (en) | Coastal zone ecological safety assessment method based on space variables and logistic regression | |
CN117078114B (en) | Water quality evaluation method and system for water-bearing lakes under influence of diversion engineering | |
CN109019717A (en) | A kind of heat-engine plant desulfurized waste water intelligent processing method and system | |
CN107664683A (en) | A kind of water quality hard measurement Forecasting Methodology of total nitrogen | |
CN109033524A (en) | A kind of chemical process concentration variable On-line Estimation method based on robust mixed model | |
Jiang et al. | Empirical research of hot topic recognition and its evolution path method for scientific and technological literature | |
CN117170221A (en) | Artificial intelligence control system for sewage treatment | |
CN107665363A (en) | A kind of water quality hard measurement Forecasting Methodology of total phosphorus |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180501 |