CN106124718A - The Dissolved Oxygen in Water concentration prediction method that many strategy artificial bee colonies optimize - Google Patents
The Dissolved Oxygen in Water concentration prediction method that many strategy artificial bee colonies optimize Download PDFInfo
- Publication number
- CN106124718A CN106124718A CN201610489055.2A CN201610489055A CN106124718A CN 106124718 A CN106124718 A CN 106124718A CN 201610489055 A CN201610489055 A CN 201610489055A CN 106124718 A CN106124718 A CN 106124718A
- Authority
- CN
- China
- Prior art keywords
- support vector
- vector machine
- dissolved oxygen
- individuality
- individual
- 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.)
- Granted
Links
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
- G01N33/1806—Water biological or chemical oxygen demand (BOD or COD)
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Computational Linguistics (AREA)
- Biochemistry (AREA)
- Medicinal Chemistry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Emergency Medicine (AREA)
- Pathology (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Analytical Chemistry (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Food Science & Technology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of Dissolved Oxygen in Water concentration prediction method that many strategy artificial bee colonies optimize.The present invention uses support vector machine as the forecast model of Dissolved Oxygen in Water concentration, utilizes many strategy artificial bee colony algorithm that parameter ε in the penalty factor of support vector machine, radially base nuclear parameter g and insensitive loss function is optimized design.In many strategy artificial bee colony algorithm, merge multiple search strategy, and during optimizing, selected search strategy adaptively according to current Evolution States carry out optimizing, thus improve the optimization ability of algorithm.The present invention can improve the precision of prediction of Dissolved Oxygen in Water concentration.
Description
Technical field
The present invention relates to Dissolved Oxygen in Water concentration prediction field, especially relate to the water that a kind of many strategy artificial bee colonies optimize
Body dissolved oxygen concentration Forecasting Methodology.
Background technology
Dissolved Oxygen in Water is the necessary material that aquaculture product is depended on for existence.In water body, the concentration of dissolved oxygen directly reflects
The quality of breeding water body.The prediction of dissolved oxygen concentration helps lend some impetus to the healthy aquaculture of aquatic products, improves the production efficiency of cultivation.
As can be seen here, the concentration holding dissolved oxygen real-time dynamicly has important practical significance in aquaculture industry.But support
Growing the concentration change of dissolved oxygen in pond is an extremely complex physics, chemistry and bioprocess.Traditional dissolved oxygen concentration is pre-
Survey method often also exists the problem that precision of prediction is the highest, forecast error is bigger.
In recent years, many research worker utilize the method for intelligence computation to predict the concentration of dissolved oxygen, and achieve certain
Effect.Such as, Guo Lianxi etc. utilize fuzzy neural network to predict dissolved oxygen in fish pond concentration (Guo Lianxi, Deng Changhui. based on
The Prediction model for dissolved oxygen in fish pond [J] of fuzzy neural network. aquatic product journal, 2006,30 (2): 225-229.).Miao Xinying uses
Genetic algorithm optimizes design neutral net, and utilizes the neutral net after optimizing design to predict the concentration of dissolved oxygen in fish pond
(Miao Xinying, Ge Tingyou, Gao Hui, etc. Prediction model for dissolved oxygen in fish pond [J] based on artificial neural network and genetic algorithms. ocean, Dalian
College journal, 2011,26 (3): 264-267.).Li Daoliang etc. have invented a kind of Aquatic product based on least square method supporting vector machine
Cultivation dissolved oxygen concentration on-line prediction method (patent No.: 201110047876.8).Han Honggui etc. have invented a kind of based on from group
Knit the dissolved oxygen model predictive control method (patent No.: 201310000516.1) of radial base neural net.
Numerous achievements in research show Dissolved Oxygen in Water concentration prediction method based on intelligence computation be one the most potential
Technology.In recent years, artificial bee colony algorithm has become a study hotspot in intelligence computation, and it has had been applied to dissolve
In the concentration prediction of oxygen, and achieve certain precision of prediction (Su Caihong, Xiang Na, woods Makin. god based on ABC optimized algorithm
[J] is predicted through network water dissolution oxygen. Computer Simulation, 2013,30 (11): 325-329.).But, Traditional Man ant colony algorithm
In Dissolved Oxygen in Water concentration prediction, easily occur that convergence rate is slow, it was predicted that the shortcoming that precision is the highest.
Summary of the invention
The present invention is directed to Traditional Man ant colony algorithm in Dissolved Oxygen in Water concentration prediction, easily occur that convergence rate is slow, in advance
Survey the shortcoming that precision is the highest, propose a kind of Dissolved Oxygen in Water concentration prediction method that many strategy artificial bee colonies optimize.Energy of the present invention
Enough improve the precision of prediction of Dissolved Oxygen in Water concentration.
Technical scheme: a kind of Dissolved Oxygen in Water concentration prediction method that many strategy artificial bee colonies optimize, including
Following steps:
Step 1, gathers water sample in needs estimation range continuously for LD days, and then detection gathers the water quality index of water sample: temperature
Degree, nitrite, ammonia nitrogen, total nitrogen, nitrate, dissolved oxygen, and using the water quality index data that collect as sample data set;So
The water quality index sample data set that rear normalized is collected, and the training data being set to support vector machine by front 70%
Collection, rear 30% is set to test data set;
Step 2, user initializes prediction span natural law ND, population scale Popsize, and individual maximum does not improves number of times
Limit, maximum evaluation number of times MAX_FEs;
Step 3, current evolution algebraically t=0, Evaluation: Current number of times FEs=0, and make the optimization design ginseng of support vector machine
Several several D=3;
Step 4, randomly generates initial populationWherein: individual subscript i=1,
2 ..., Popsize, andRepresent population PtIn i-th individual, it randomly generates formula and is:
Wherein dimension subscript j=1,2,3;Illustrate the value of 3 optimal design parameter of support vector machine, i.e.It is
The penalty factor of support vector machine,It is radial direction base nuclear parameter g of support vector machine,It is the insensitive of support vector machine
Parameter ε in loss function;Rand (0,1) is the function producing random real number between [0,1], LOjAnd UPjBe respectively support to
The lower bound of the region of search of the jth optimal design parameter of amount machine and the upper bound;
Step 5, calculates population PtIn each individualityAdaptive valueWherein individual subscript i=1,2 ...,
Popsize, individualAdaptive valueComputational methods be: utilize individualityAs the training parameter of support vector machine,
And use training dataset Training Support Vector Machines, wherein the input variable of support vector machine is the water quality index of normalized a day
Data: temperature, nitrite, ammonia nitrogen, total nitrogen, nitrate, dissolved oxygen;After support vector machine is output as normalized ND days
Dissolved Oxygen in Water concentration value;Then the support vector machine trained mean square error NE in test data set is calculatedi, then order
BodyAdaptive value
Step 6, makes population PtIn all individualities do not improve number of timesWherein individual subscript i=1,2 ...,
Popsize, and make Evaluation: Current number of times FEs=FEs+Popsize;
Step 7, preserves population PtIn optimum individual Bestt;
Step 8, makes strategy factor STU=0.6;
Step 9, employs honeybee to perform its search operation;
Step 10, according to population PtThe adaptive value of middle individuality calculates the select probability of each individuality;
Step 11, observes honeybee according to population PtIn the select probability of each individuality select that individual how tactful perform adaptability
Search operation generates new individual, then perform to select operation and update individuality do not improve number of times, specifically comprise the following steps that
Step 11.1, makes enumerator i=1, makes strategy factor list UList for sky;
Step 11.2, according to population PtIn each individuality select probability use roulette policy selection go out individualityAnd
Order is new individual
Step 11.3, randomly generates positive integer RJ between [1, D];
Step 11.4, produces a Gauss number GU=normrnd (STU, 0.2), if the value of GU is beyond [0,1]
Between scope, then use same method to regenerate gaussian random real number GU, until between the value of GU is without departing from [0,1]
Scope, wherein normrnd (STU, 0.2) is expressed as with STU as average, and 0.2 is the Gauss number generation function of standard deviation;
Step 11.5, order strategy sequence number STI=floor (GU × 3) %3, wherein floor is downward bracket function, and % is
Complementation symbol;
Step 11.6, if STI is equal to 0, forwards step 11.7 to;Otherwise judge whether STI is equal to 1, if STI is equal to
1, then forward step 11.12 to, otherwise forward step 11.15 to;
Step 11.7, randomly generates an integer RI1 between [1, Popsize], and make random weights RK=rand (0,
1);
Step 11.8, makes average
Step 11.9, makes standard deviation
Step 11.10, with MeanU as average, STDV is that standard deviation produces a gaussian random real number Val, if Val
Value is beyond [LORJ,UPRJScope between], then use same method to regenerate gaussian random real number Val, until Val
Value without departing from [LORJ,UPRJScope between], then makes
Step 11.11, forwards step 11.16 to;
Step 11.12, randomly generates two unequal integer RI2 and RI3 between [1, Popsize];
Step 11.13, order
Step 11.14, forwards step 11.16 to;
Step 11.15, order
Step 11.16, calculates new individual UtAdaptive value Fit (Ut);
Step 11.17, if new individual UtThan individualityMore excellent, then GU is added in strategy factor list UList;
Step 11.18, at individualityWith new individual UtBetween perform select operation and update individualityDo not improve number of times
Step 11.19, makes enumerator i=i+1;
Step 11.20, if enumerator i is less than or equal to Popsize, then forwards step 11.2 to, otherwise forwards step to
11.21;
Step 11.21, calculative strategy is because of meansigma methods MeanLU of data in sublist UList;
Step 11.22, makes STU=0.9 × STU+0.1 × MeanLU, then goes to step 12;
Step 12, makes Evaluation: Current number of times FEs=FEs+Popsize × 2;
Step 13, search bee performs its search operation;
Step 14, preserves population PtIn optimum individual Bestt;
Step 15, current evolution algebraically t=t+1;
Step 16, repeats step 9 to step 15 until Evaluation: Current number of times FEs terminates after reaching MAX_FEs, will perform
The optimum individual Best obtained in journeytAs the training parameter of support vector machine, and train support vector with training dataset
Machine, then by the water quality index data of normalized a day: temperature, nitrite, ammonia nitrogen, total nitrogen, nitrate, dissolved oxygen input
To the support vector machine trained, calculate the Dissolved Oxygen in Water concentration value after the most measurable ND days of the output of support vector machine.
The present invention uses support vector machine as the forecast model of Dissolved Oxygen in Water concentration, utilizes many strategy artificial bee colonies to calculate
Method is optimized design to parameter ε in the penalty factor of support vector machine, radially base nuclear parameter g and insensitive loss function.?
In many strategy artificial bee colony algorithm, merge multiple search strategy, and adapted to according to current Evolution States during optimizing
Select to property search strategy to carry out optimizing, thus improve the optimization ability of algorithm.Compared with congenic method, the present invention can
Improve the precision of prediction of Dissolved Oxygen in Water concentration.
Accompanying drawing explanation
Fig. 1 is the flow chart of the present invention.
Detailed description of the invention
Below by embodiment, and combine accompanying drawing, technical scheme is described in further detail.
Embodiment:
Step 1, in determining the region needing to predict Dissolved Oxygen in Water concentration, and continuous LD=55 days the determined regions of collection
Water sample, then detection gather water sample water quality index: temperature, nitrite, ammonia nitrogen, total nitrogen, nitrate, dissolved oxygen, and will
The water quality index data collected are as sample data set;Then the water quality index sample data that normalized is collected
Collection, and the training dataset being set to support vector machine by front 70%, rear 30% is set to test data set;
Step 2, user initializes prediction span natural law ND=2, population scale Popsize=50, and individual maximum is not improved
Number of times Limit=100, maximum evaluation number of times MAX_FEs=300000;
Step 3, current evolution algebraically t=0, Evaluation: Current number of times FEs=0, and make the optimization design ginseng of support vector machine
Several several D=3;
Step 4, randomly generates initial populationWherein: individual subscript i=1,
2 ..., Popsize, andRepresent population PtIn i-th individual, it randomly generates formula and is:
Wherein dimension subscript j=1,2,3;Illustrate the value of 3 optimal design parameter of support vector machine, i.e.It is
The penalty factor of support vector machine,It is radial direction base nuclear parameter g of support vector machine,It is the insensitive of support vector machine
Parameter ε in loss function;Rand (0,1) is the function producing random real number between [0,1], wherein LO=[0 0 0], UP=
[10,000 1 1], LOjAnd UPjIt is respectively lower bound and the upper bound of the region of search of the jth optimal design parameter of support vector machine;
Step 5, calculates population PtIn each individualityAdaptive valueWherein individual subscript i=1,2 ...,
Popsize, individualAdaptive valueComputational methods be: utilize individualityTraining as support vector machine is joined
Number, and use training dataset Training Support Vector Machines, wherein the input variable of support vector machine is the water quality of normalized a day
Achievement data: temperature, nitrite, ammonia nitrogen, total nitrogen, nitrate, dissolved oxygen;Support vector machine is output as normalized 2 days
After Dissolved Oxygen in Water concentration value;Then the support vector machine trained mean square error NE in test data set is calculatedi, then
Order individualityAdaptive value
Step 6, makes population PtIn all individualities do not improve number of timesWherein individual subscript i=1,2 ...,
Popsize, and make Evaluation: Current number of times FEs=FEs+Popsize;
Step 7, preserves population PtIn optimum individual Bestt;
Step 8, makes strategy factor STU=0.6;
Step 9, employs honeybee to perform its search operation;
Step 10, according to population PtThe adaptive value of middle individuality calculates the select probability of each individuality;
Step 11, observes honeybee according to population PtIn the select probability of each individuality select that individual how tactful perform adaptability
Search operation generates new individual, then perform to select operation and update individuality do not improve number of times, specifically comprise the following steps that
Step 11.1, makes enumerator i=1, makes strategy factor list UList for sky;
Step 11.2, according to population PtIn each individuality select probability use roulette policy selection go out individualityAnd
Order is new individual
Step 11.3, randomly generates positive integer RJ between [1, D];
Step 11.4, produces a Gauss number GU=normrnd (STU, 0.2), if the value of GU is beyond [0,1]
Between scope, then use same method to regenerate gaussian random real number GU, until between the value of GU is without departing from [0,1]
Scope, wherein normrnd (STU, 0.2) is expressed as with STU as average, and 0.2 is the Gauss number generation function of standard deviation;
Step 11.5, order strategy sequence number STI=floor (GU × 3) %3, wherein floor is downward bracket function, and % is
Complementation symbol;
Step 11.6, if STI is equal to 0, forwards step 11.7 to;Otherwise judge whether STI is equal to 1, if STI is equal to
1, then forward step 11.12 to, otherwise forward step 11.15 to;
Step 11.7, randomly generates an integer RI1 between [1, Popsize], and make random weights RK=rand (0,
1);
Step 11.8, makes average
Step 11.9, makes standard deviation
Step 11.10, with MeanU as average, STDV is that standard deviation produces a gaussian random real number Val, if Val
Value is beyond [LORJ,UPRJScope between], then use same method to regenerate gaussian random real number Val, until Val
Value without departing from [LORJ,UPRJScope between], then makes
Step 11.11, forwards step 11.16 to;
Step 11.12, randomly generates two unequal integer RI2 and RI3 between [1, Popsize];
Step 11.13, order
Step 11.14, forwards step 11.16 to;
Step 11.15, order
Step 11.16, calculates new individual UtAdaptive value Fit (Ut);
Step 11.17, if new individual UtThan individualityMore excellent, then GU is added in strategy factor list UList;
Step 11.18, at individualityWith new individual UtBetween perform select operation and update individualityDo not improve number of times
Step 11.19, makes enumerator i=i+1;
Step 11.20, if enumerator i is less than or equal to Popsize, then forwards step 11.2 to, otherwise forwards step to
11.21;
Step 11.21, calculative strategy is because of meansigma methods MeanLU of data in sublist UList;
Step 11.22, makes STU=0.9 × STU+0.1 × MeanLU, then goes to step 12;
Step 12, makes Evaluation: Current number of times FEs=FEs+Popsize × 2;
Step 13, search bee performs its search operation;
Step 14, preserves population PtIn optimum individual Bestt;
Step 15, current evolution algebraically t=t+1;
Step 16, repeats step 9 to step 15 until Evaluation: Current number of times FEs terminates after reaching MAX_FEs, will perform
The optimum individual Best obtained in journeytAs the training parameter of support vector machine, and train support vector with training dataset
Machine, then by the water quality index data of normalized a day: temperature, nitrite, ammonia nitrogen, total nitrogen, nitrate, dissolved oxygen input
To the support vector machine trained, calculate the Dissolved Oxygen in Water concentration value after the most measurable 2 days of the output of support vector machine.
Specific embodiment described herein is only to present invention spirit explanation for example.Technology neck belonging to the present invention
Described specific embodiment can be made various amendment or supplements or use similar mode to replace by the technical staff in territory
Generation, but without departing from the spirit of the present invention or surmount scope defined in appended claims.
Claims (1)
1. the Dissolved Oxygen in Water concentration prediction method that the artificial bee colony of strategy more than a kind optimizes, it is characterised in that: comprise the following steps:
Step 1, continuous LD days collection water samples in needs estimation range, the then water quality index of detection collection water sample: temperature, Asia
Nitrate, ammonia nitrogen, total nitrogen, nitrate, dissolved oxygen, and using the water quality index data that collect as sample data set;Then return
One change processes the water quality index sample data set collected, and the training dataset being set to support vector machine by front 70%,
Rear 30% is set to test data set;
Step 2, user initializes prediction span natural law ND, population scale Popsize, and individual maximum does not improves number of times Limit,
Big evaluation number of times MAX_FEs;
Step 3, current evolution algebraically t=0, Evaluation: Current number of times FEs=0, and make the optimal design parameter of support vector machine
Number D=3;
Step 4, randomly generates initial populationWherein: individual subscript i=1,2 ...,
Popsize, andRepresent population PtIn i-th individual, it randomly generates formula and is:
Wherein dimension subscript j=1,2,3;Illustrate the value of 3 optimal design parameter of support vector machine, i.e.Be support to
The penalty factor of amount machine,It is radial direction base nuclear parameter g of support vector machine,It it is the insensitive loss letter of support vector machine
Parameter ε in number;Rand (0,1) is the function producing random real number between [0,1], LOjAnd UPjIt is respectively support vector machine
The lower bound of the region of search of jth optimal design parameter and the upper bound;
Step 5, calculates population PtIn each individualityAdaptive valueWherein individual subscript i=1,2 ...,
Popsize, individualAdaptive valueComputational methods be: utilize individualityAs the training parameter of support vector machine,
And use training dataset Training Support Vector Machines, wherein the input variable of support vector machine is the water quality index of normalized a day
Data: temperature, nitrite, ammonia nitrogen, total nitrogen, nitrate, dissolved oxygen;After support vector machine is output as normalized ND days
Dissolved Oxygen in Water concentration value;Then the support vector machine trained mean square error NE in test data set is calculatedi, then order
BodyAdaptive value
Step 6, makes population PtIn all individualities do not improve number of timesWherein individual subscript i=1,2 ...,
Popsize, and make Evaluation: Current number of times FEs=FEs+Popsize;
Step 7, preserves population PtIn optimum individual Bestt;
Step 8, makes strategy factor STU=0.6;
Step 9, employs honeybee to perform its search operation;
Step 10, according to population PtThe adaptive value of middle individuality calculates the select probability of each individuality;
Step 11, observes honeybee according to population PtIn the select probability of each individuality select and individual perform the many decision searches of adaptability
Operation generates new individual, then perform to select operation and update individuality do not improve number of times, specifically comprise the following steps that
Step 11.1, makes enumerator i=1, makes strategy factor list UList for sky;
Step 11.2, according to population PtIn each individuality select probability use roulette policy selection go out individualityAnd make new
Individual
Step 11.3, randomly generates positive integer RJ between [1, D];
Step 11.4, produces a Gauss number GU=normrnd (STU, 0.2), if between the value of GU is beyond [0,1]
Scope, then use same method to regenerate gaussian random real number GU, until the value of GU is without departing from the model between [0,1]
Enclosing, wherein normrnd (STU, 0.2) is expressed as with STU as average, and 0.2 is the Gauss number generation function of standard deviation;
Step 11.5, order strategy sequence number STI=floor (GU × 3) %3, wherein floor is downward bracket function, and % is remainder
Operative symbol;
Step 11.6, if STI is equal to 0, forwards step 11.7 to;Otherwise judge whether STI is equal to 1, if STI is equal to 1, then
Forward step 11.12 to, otherwise forward step 11.15 to;
Step 11.7, randomly generates an integer RI1 between [1, Popsize], and makes random weights RK=rand (0,1);
Step 11.8, makes average
Step 11.9, makes standard deviation
Step 11.10, with MeanU as average, STDV is that standard deviation produces a gaussian random real number Val, if the value of Val surpasses
Go out [LORJ,UPRJScope between], then use same method to regenerate gaussian random real number Val, until the value of Val
Without departing from [LORJ,UPRJScope between], then makes
Step 11.11, forwards step 11.16 to;
Step 11.12, randomly generates two unequal integer RI2 and RI3 between [1, Popsize];
Step 11.13, order
Step 11.14, forwards step 11.16 to;
Step 11.15, order
Step 11.16, calculates new individual UtAdaptive value Fit (Ut);
Step 11.17, if new individual UtThan individualityMore excellent, then GU is added in strategy factor list UList;
Step 11.18, at individualityWith new individual UtBetween perform select operation and update individualityDo not improve number of times
Step 11.19, makes enumerator i=i+1;
Step 11.20, if enumerator i is less than or equal to Popsize, then forwards step 11.2 to, otherwise forwards step 11.21 to;
Step 11.21, calculative strategy is because of meansigma methods MeanLU of data in sublist UList;
Step 11.22, makes STU=0.9 × STU+0.1 × MeanLU, then goes to step 12;
Step 12, makes Evaluation: Current number of times FEs=FEs+Popsize × 2;
Step 13, search bee performs its search operation;
Step 14, preserves population PtIn optimum individual Bestt;
Step 15, current evolution algebraically t=t+1;
Step 16, repeats step 9 to step 15 until Evaluation: Current number of times FEs terminates after reaching MAX_FEs, during performing
The optimum individual Best obtainedtAs the training parameter of support vector machine, and carry out Training Support Vector Machines with training dataset, so
After by the water quality index data of normalized a day: temperature, nitrite, ammonia nitrogen, total nitrogen, nitrate, dissolved oxygen are input to instruction
The support vector machine perfected, calculates the Dissolved Oxygen in Water concentration value after the most measurable ND days of the output of support vector machine.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610489055.2A CN106124718B (en) | 2016-06-27 | 2016-06-27 | The Dissolved Oxygen in Water concentration prediction method of more tactful artificial bee colony optimization |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610489055.2A CN106124718B (en) | 2016-06-27 | 2016-06-27 | The Dissolved Oxygen in Water concentration prediction method of more tactful artificial bee colony optimization |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106124718A true CN106124718A (en) | 2016-11-16 |
CN106124718B CN106124718B (en) | 2017-12-05 |
Family
ID=57285036
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610489055.2A Active CN106124718B (en) | 2016-06-27 | 2016-06-27 | The Dissolved Oxygen in Water concentration prediction method of more tactful artificial bee colony optimization |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106124718B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106959360A (en) * | 2017-03-18 | 2017-07-18 | 江西理工大学 | The rare-earth mining area farmland water pH value flexible measurement method developed using backward difference |
CN110610261A (en) * | 2019-08-23 | 2019-12-24 | 广东奥博信息产业股份有限公司 | Water body dissolved oxygen prediction method based on neural network |
CN111310788A (en) * | 2020-01-15 | 2020-06-19 | 广东奥博信息产业股份有限公司 | Water body pH value prediction method based on parameter optimization |
CN112505270A (en) * | 2020-10-23 | 2021-03-16 | 中国水利水电科学研究院 | Optimization method for improving dissolved oxygen in stagnant temperature layer of reservoir |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10142195A (en) * | 1996-11-15 | 1998-05-29 | Matsushita Electric Ind Co Ltd | Bod sensing device |
CN101158674A (en) * | 2007-11-15 | 2008-04-09 | 天津市市政工程设计研究院 | Method for predicting chlorophyll a concentration in water based on BP nerval net |
JP4884448B2 (en) * | 2008-10-20 | 2012-02-29 | ソマール株式会社 | Drug addition control management method and drug addition control management device |
CN103778482A (en) * | 2014-02-12 | 2014-05-07 | 中国农业大学 | Aquaculture dissolved oxygen short-term prediction method based on multi-scale analysis |
CN104573813A (en) * | 2014-12-18 | 2015-04-29 | 东北大学 | Self-adaption artificial swarm optimization method based on historical information in running process |
-
2016
- 2016-06-27 CN CN201610489055.2A patent/CN106124718B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10142195A (en) * | 1996-11-15 | 1998-05-29 | Matsushita Electric Ind Co Ltd | Bod sensing device |
CN101158674A (en) * | 2007-11-15 | 2008-04-09 | 天津市市政工程设计研究院 | Method for predicting chlorophyll a concentration in water based on BP nerval net |
JP4884448B2 (en) * | 2008-10-20 | 2012-02-29 | ソマール株式会社 | Drug addition control management method and drug addition control management device |
CN103778482A (en) * | 2014-02-12 | 2014-05-07 | 中国农业大学 | Aquaculture dissolved oxygen short-term prediction method based on multi-scale analysis |
CN104573813A (en) * | 2014-12-18 | 2015-04-29 | 东北大学 | Self-adaption artificial swarm optimization method based on historical information in running process |
Non-Patent Citations (2)
Title |
---|
李少博等: "关于水产养殖水溶解氧的预测仿真研究", 《计算机仿真》 * |
李明河等: "基于LM算法的溶解氧神经网络预测控制", 《农业机械学报》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106959360A (en) * | 2017-03-18 | 2017-07-18 | 江西理工大学 | The rare-earth mining area farmland water pH value flexible measurement method developed using backward difference |
CN106959360B (en) * | 2017-03-18 | 2019-03-29 | 江西理工大学 | The rare-earth mining area farmland water pH value flexible measurement method to develop using backward difference |
CN110610261A (en) * | 2019-08-23 | 2019-12-24 | 广东奥博信息产业股份有限公司 | Water body dissolved oxygen prediction method based on neural network |
CN110610261B (en) * | 2019-08-23 | 2023-02-28 | 广东奥博信息产业股份有限公司 | Water body dissolved oxygen prediction method based on neural network |
CN111310788A (en) * | 2020-01-15 | 2020-06-19 | 广东奥博信息产业股份有限公司 | Water body pH value prediction method based on parameter optimization |
CN111310788B (en) * | 2020-01-15 | 2023-06-09 | 广东奥博信息产业股份有限公司 | Water pH value prediction method based on parameter optimization |
CN112505270A (en) * | 2020-10-23 | 2021-03-16 | 中国水利水电科学研究院 | Optimization method for improving dissolved oxygen in stagnant temperature layer of reservoir |
Also Published As
Publication number | Publication date |
---|---|
CN106124718B (en) | 2017-12-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103577694B (en) | Aquaculture water quality short-time combination forecast method on basis of multi-scale analysis | |
Ding et al. | Evaluation of salt-tolerant germplasm and screening of the salt-tolerance traits of sweet sorghum in the germination stage | |
CN103218669B (en) | A kind of live fish cultivation water quality comprehensive forecasting method of intelligence | |
CN106124718A (en) | The Dissolved Oxygen in Water concentration prediction method that many strategy artificial bee colonies optimize | |
Roadknight et al. | Modeling complex environmental data | |
CN103886218B (en) | Storehouse, the lake algal bloom Forecasting Methodology compensated with neutral net and support vector machine based on polynary non-stationary time series | |
CN107358294A (en) | A kind of water demand prediction method based on Elman neutral nets | |
CN105631517A (en) | Photovoltaic power generation power short term prediction method based on mind evolution Elman neural network | |
CN103150609A (en) | Modeling method for short time traffic flow predicting model | |
CN101533000A (en) | Method for constructing water eutrophication risk analysis model | |
Da-Rocha et al. | Pulse vs. optimal stationary fishing: The Northern Stock of hake | |
CN110414115A (en) | A kind of wavelet neural network tomato yield prediction technique based on genetic algorithm | |
CN109308544A (en) | Based on to sdpecific dispersion-shot and long term memory network cyanobacterial bloom prediction technique | |
CN105930685B (en) | The rare-earth mining area underground water ammonia nitrogen concentration Forecasting Methodology of Gauss artificial bee colony optimization | |
An et al. | A simulator-based planning framework for optimizing autonomous greenhouse control strategy | |
CN114444755A (en) | Wind power short-term power prediction method and device and readable storage medium | |
CN104598657B (en) | A kind of gene die body reconstructing method based on memetic algorithms | |
Chen et al. | A water-saving irrigation decision-making model for greenhouse tomatoes based on genetic optimization TS fuzzy neural network | |
Costache et al. | Integrating aquaponics production systems into the Romanian green procurement network | |
Concepcion II et al. | Metaheuristic optimization of ammonia factor as a eutrophication pollution emission descriptor for trophic state stability | |
CN104598770B (en) | Wheat aphid quantitative forecasting technique and system based on human evolution's gene expression programming | |
CN113052379A (en) | Tomato water demand prediction method based on BAS-RBF | |
Beni et al. | Application of machine learning to predict of energy use efficiency and damage assessment of almond and walnut production | |
Caballero-Anthony et al. | Linking Climate Change Adaptation and Food Security in ASEAN | |
CN106959360B (en) | The rare-earth mining area farmland water pH value flexible measurement method to develop using backward difference |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |