CN109725119A - Water quality information processing method, system, storage medium and computer equipment - Google Patents
Water quality information processing method, system, storage medium and computer equipment Download PDFInfo
- Publication number
- CN109725119A CN109725119A CN201811524359.3A CN201811524359A CN109725119A CN 109725119 A CN109725119 A CN 109725119A CN 201811524359 A CN201811524359 A CN 201811524359A CN 109725119 A CN109725119 A CN 109725119A
- Authority
- CN
- China
- Prior art keywords
- water quality
- total amount
- bacteria total
- prediction value
- content
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 333
- 230000010365 information processing Effects 0.000 title claims abstract description 35
- 238000003672 processing method Methods 0.000 title claims abstract description 23
- 238000003860 storage Methods 0.000 title claims abstract description 11
- 241000894006 Bacteria Species 0.000 claims abstract description 300
- 239000000126 substance Substances 0.000 claims abstract description 42
- 238000001514 detection method Methods 0.000 claims abstract description 36
- 230000036541 health Effects 0.000 claims abstract description 34
- 230000008859 change Effects 0.000 claims abstract description 29
- 238000012544 monitoring process Methods 0.000 claims abstract description 13
- 244000052616 bacterial pathogen Species 0.000 claims abstract description 9
- 244000052769 pathogen Species 0.000 claims description 119
- 230000001717 pathogenic effect Effects 0.000 claims description 119
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 87
- 238000003062 neural network model Methods 0.000 claims description 87
- 201000010099 disease Diseases 0.000 claims description 85
- 239000006227 byproduct Substances 0.000 claims description 81
- 230000001580 bacterial effect Effects 0.000 claims description 77
- 230000007246 mechanism Effects 0.000 claims description 60
- 230000006872 improvement Effects 0.000 claims description 45
- 238000012549 training Methods 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 24
- 238000000034 method Methods 0.000 claims description 12
- 238000012806 monitoring device Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 5
- 230000000721 bacterilogical effect Effects 0.000 claims description 3
- 238000011269 treatment regimen Methods 0.000 abstract 2
- 230000000694 effects Effects 0.000 description 9
- 238000009360 aquaculture Methods 0.000 description 7
- 244000144974 aquaculture Species 0.000 description 7
- 239000003651 drinking water Substances 0.000 description 6
- 235000020188 drinking water Nutrition 0.000 description 6
- HEDRZPFGACZZDS-UHFFFAOYSA-N Chloroform Chemical compound ClC(Cl)Cl HEDRZPFGACZZDS-UHFFFAOYSA-N 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- QTBSBXVTEAMEQO-UHFFFAOYSA-N Acetic acid Chemical compound CC(O)=O QTBSBXVTEAMEQO-UHFFFAOYSA-N 0.000 description 3
- 241000251468 Actinopterygii Species 0.000 description 3
- 206010017553 Furuncle Diseases 0.000 description 3
- 241000252498 Ictalurus punctatus Species 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000005660 chlorination reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- 238000004659 sterilization and disinfection Methods 0.000 description 3
- 241000607516 Aeromonas caviae Species 0.000 description 2
- 241000607528 Aeromonas hydrophila Species 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 2
- 241000607473 Edwardsiella <enterobacteria> Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 235000017845 Persicaria vulgaris Nutrition 0.000 description 2
- 244000170788 Persicaria vulgaris Species 0.000 description 2
- 206010040047 Sepsis Diseases 0.000 description 2
- 241000607598 Vibrio Species 0.000 description 2
- 241000700605 Viruses Species 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- DIKBFYAXUHHXCS-UHFFFAOYSA-N bromoform Chemical compound BrC(Br)Br DIKBFYAXUHHXCS-UHFFFAOYSA-N 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 125000004772 dichloromethyl group Chemical group [H]C(Cl)(Cl)* 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 210000000936 intestine Anatomy 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 230000007115 recruitment Effects 0.000 description 2
- 208000013223 septicemia Diseases 0.000 description 2
- HFFLGKNGCAIQMO-UHFFFAOYSA-N trichloroacetaldehyde Chemical compound ClC(Cl)(Cl)C=O HFFLGKNGCAIQMO-UHFFFAOYSA-N 0.000 description 2
- 238000004457 water analysis Methods 0.000 description 2
- ARGCQEVBJHPOGB-UHFFFAOYSA-N 2,5-dihydrofuran Chemical class C1OCC=C1 ARGCQEVBJHPOGB-UHFFFAOYSA-N 0.000 description 1
- 208000035143 Bacterial infection Diseases 0.000 description 1
- 241000195493 Cryptophyta Species 0.000 description 1
- 208000004232 Enteritis Diseases 0.000 description 1
- 206010015150 Erythema Diseases 0.000 description 1
- 241000233866 Fungi Species 0.000 description 1
- 108010034145 Helminth Proteins Proteins 0.000 description 1
- 206010034647 Peristalsis visible Diseases 0.000 description 1
- 241000589516 Pseudomonas Species 0.000 description 1
- 241001482311 Trionychidae Species 0.000 description 1
- 208000025865 Ulcer Diseases 0.000 description 1
- 206010061577 Ulcer haemorrhage Diseases 0.000 description 1
- 241000607594 Vibrio alginolyticus Species 0.000 description 1
- 241000544286 Vibrio anguillarum Species 0.000 description 1
- 241000607618 Vibrio harveyi Species 0.000 description 1
- 206010047400 Vibrio infections Diseases 0.000 description 1
- IKHGUXGNUITLKF-XPULMUKRSA-N acetaldehyde Chemical compound [14CH]([14CH3])=O IKHGUXGNUITLKF-XPULMUKRSA-N 0.000 description 1
- 208000022362 bacterial infectious disease Diseases 0.000 description 1
- 201000005008 bacterial sepsis Diseases 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- JPOXNPPZZKNXOV-UHFFFAOYSA-N bromochloromethane Chemical class ClCBr JPOXNPPZZKNXOV-UHFFFAOYSA-N 0.000 description 1
- FMWLUWPQPKEARP-UHFFFAOYSA-N bromodichloromethane Chemical compound ClC(Cl)Br FMWLUWPQPKEARP-UHFFFAOYSA-N 0.000 description 1
- 229950005228 bromoform Drugs 0.000 description 1
- 230000000711 cancerogenic effect Effects 0.000 description 1
- 231100000315 carcinogenic Toxicity 0.000 description 1
- LFHISGNCFUNFFM-UHFFFAOYSA-N chloropicrin Chemical class [O-][N+](=O)C(Cl)(Cl)Cl LFHISGNCFUNFFM-UHFFFAOYSA-N 0.000 description 1
- QPJDMGCKMHUXFD-UHFFFAOYSA-N cyanogen chloride Chemical compound ClC#N QPJDMGCKMHUXFD-UHFFFAOYSA-N 0.000 description 1
- 230000014670 detection of bacterium Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000013505 freshwater Substances 0.000 description 1
- 229910052736 halogen Inorganic materials 0.000 description 1
- 150000002367 halogens Chemical class 0.000 description 1
- 244000000013 helminth Species 0.000 description 1
- 230000003116 impacting effect Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000000968 intestinal effect Effects 0.000 description 1
- 150000002500 ions Chemical class 0.000 description 1
- 150000002576 ketones Chemical class 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- WSFSSNUMVMOOMR-NJFSPNSNSA-N methanone Chemical compound O=[14CH2] WSFSSNUMVMOOMR-NJFSPNSNSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002703 mutagenesis Methods 0.000 description 1
- 231100000350 mutagenesis Toxicity 0.000 description 1
- 230000008855 peristalsis Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- QQONPFPTGQHPMA-UHFFFAOYSA-N propylene Natural products CC=C QQONPFPTGQHPMA-UHFFFAOYSA-N 0.000 description 1
- -1 propylene halide nitrile Chemical class 0.000 description 1
- 230000008929 regeneration Effects 0.000 description 1
- 238000011069 regeneration method Methods 0.000 description 1
- 210000000697 sensory organ Anatomy 0.000 description 1
- 235000015170 shellfish Nutrition 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001954 sterilising effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 229940029273 trichloroacetaldehyde Drugs 0.000 description 1
- 231100000397 ulcer Toxicity 0.000 description 1
- 208000022534 visible peristalsis Diseases 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Purification Treatments By Anaerobic Or Anaerobic And Aerobic Bacteria Or Animals (AREA)
Abstract
The application relates to a water quality information processing method, a system, a storage medium and computer equipment, which are used for acquiring water quality detection parameters of a target water body; predicting the change condition of the total amount of bacteria according to the physical and chemical parameters and the total amount of bacteria to obtain a predicted value of the total amount of bacteria and a predicted value of the content of specific pathogenic bacteria of the target water body; and when the predicted value of the total amount of the bacteria and/or the predicted value of the content of the specific pathogenic bacteria exceed the water quality health standard, determining a corresponding water quality treatment strategy according to the predicted value of the total amount of the bacteria and/or the predicted value of the content of the specific pathogenic bacteria. The water quality condition can be predicted in advance by predicting the total amount of bacteria and the content of specific pathogenic bacteria in the water body, and a corresponding water quality treatment strategy is provided when the water quality condition exceeds the water quality health standard, so that the aim of monitoring the water quality condition in real time can be fulfilled, and the safety influence and property loss caused by water quality information lag can be reduced to a certain extent.
Description
Technical field
This application involves water quality monitoring technical fields, are situated between more particularly to a kind of water quality information processing method, system, storage
Matter and computer equipment.
Background technique
With the improvement of living standards, people are also higher and higher to the attention degree of water quality safety, such as: in people's daily life
The water quality safety etc. of the water quality safety and other application scenarios (fishery, aquaculture etc.) of used drinking water usually comes
It says, it can be using the bacteria total amount in water body as a measurement standard of water quality safety.
The prior art obtains water body sample in order to guarantee water quality safety, by carrying out water body sampling, and passes through laboratory pair
Water body sample carries out water analysis, to obtain the water quality health information of water body.However, since water analysis needs to spend
Regular hour leads to not the real-time water quality information for obtaining water body, and the case where be easy to appear information delay, i.e., when detection water
When body bacteria total amount is exceeded, corresponding water body produces security implication to the public or fishery, aquaculture etc., causes certain
Loss.
Summary of the invention
Based on this, it is necessary in view of the problems of the existing technology, provide one kind can with look-ahead water quality condition and
Water quality information processing method, system, storage medium and the computer equipment of water quality Management strategy are provided when necessary.
A kind of water quality information processing method, comprising:
The water quality detection parameter of object water body is obtained, the water quality detection parameter includes: that the physical-chemical parameters and bacterium are total
Amount；
According to the physical-chemical parameters and the bacteria total amount, the situation of change of the bacteria total amount is carried out pre-
It surveys, obtains the bacteria total amount predicted value and special pathogen content prediction value of the object water body；
When the bacteria total amount predicted value and/or the special pathogen content prediction value exceed water quality health standards,
Corresponding water quality Management strategy is determined according to the bacteria total amount predicted value and/or the special pathogen content prediction value.
The special pathogen is the corresponding pathogenic bacteria of different application environment in one of the embodiments,.
It is total to the bacterium in one of the embodiments, according to the physical-chemical parameters and the bacteria total amount
The situation of change of amount predicted, obtain the object water body bacteria total amount predicted value and special pathogen content prediction
Value, comprising:
It is total to the bacterium by water quality ecological mechanism model according to the physical-chemical parameters and the bacteria total amount
The situation of change of amount is predicted, and obtains the object water body according to the bacteria total amount and situation of change prediction result
Bacteria total amount predicted value；
According to the bacteria total amount predicted value, is predicted, obtained by content of the neural network model to special pathogen
To the special pathogen content prediction value of the object water body.
In one of the embodiments, include any one of the following terms:
First item: carrying out parameter calibration and Verification to water quality ecological mechanism model according to sample data, and by bacterium
The water quality ecological mechanism model is added in regrowth parameter, and the sample data includes the physical-chemical parameters and corresponding bacterium
Total amount delta data；
Section 2: being training number with the corresponding special cause of disease bacterial content of special pathogen type and different bacterium total amount
According to being trained to the neural network model；
When the neural network model is worked as according to the special pathogen content prediction value that current bacteria total amount obtains with described
The error of the corresponding special cause of disease bacterial content of reality of preceding bacteria total amount within a preset range when, determine the neural network model instruction
Practice and completes.
In one of the embodiments, according to the bacteria total amount predicted value and/or the special pathogen content prediction
Value determines corresponding water quality Management strategy, comprising:
According to the bacteria total amount predicted value and/or the special pathogen content prediction value, pass through water quality ecological mechanism
Model and neural network model are to the bacteria total amount predicted value and/or the corresponding water of the special pathogen content prediction value
Matter administers situation and carries out forecast assessment, and determines corresponding water quality Management strategy according to forecast assessment result.
In one of the embodiments, according to the bacteria total amount predicted value and/or the special pathogen content prediction
Value, by water quality ecological mechanism model and neural network model to the bacteria total amount predicted value and/or the special cause of disease
The corresponding water quality of bacterial content predicted value administers situation and carries out forecast assessment, and determines that corresponding water quality is controlled according to forecast assessment result
Reason strategy, including any one of the following terms:
First item: when the bacteria total amount predicted value and the special pathogen content prediction value all exceed water quality health
When standard, according to the bacteria total amount predicted value and default Management strategy, by the water quality ecological mechanism model to improvement
The regrowth situation of bacterium afterwards is predicted, bacteria total amount re prediction value is obtained, and the bacteria total amount re prediction value is
The bacteria total amount predicted value is corresponding, administer after bacteria total amount predicted value；
According to the bacteria total amount re prediction value, by the neural network model to corresponding special cause of disease bacterial content
It is predicted, obtains corresponding special cause of disease bacterial content re prediction value, the special cause of disease bacterial content re prediction value is institute
State special pathogen content prediction value it is corresponding, administer after special cause of disease bacterial content predicted value；
According to the default Management strategy, the harmful side product content after improvement is carried out by the neural network model
Prediction, obtains corresponding harmful side product content prediction value；
When the bacteria total amount re prediction value, the special cause of disease bacterial content re prediction value and harmful by-product
When object content prediction value reaches preset standard, determine that the default Management strategy is the water quality Management strategy；
Section 2: when the bacteria total amount predicted value exceeds water quality health standards, according to the bacteria total amount predicted value
And default Management strategy, it is predicted by regrowth situation of the water quality ecological mechanism model to the bacterium after improvement,
Obtain bacteria total amount re prediction value；
According to the default Management strategy, the harmful side product content after improvement is carried out by the neural network model
Prediction, obtains corresponding harmful side product content prediction value；
When the bacteria total amount re prediction value and the harmful side product content prediction value reach preset standard, really
The fixed default Management strategy is the water quality Management strategy；
Section 3: when the special pathogen content prediction value exceeds water quality health standards, according to the bacteria total amount
Predicted value and default Management strategy are carried out by regrowth situation of the water quality ecological mechanism model to the bacterium after improvement
Prediction, obtains bacteria total amount re prediction value；
According to the bacteria total amount re prediction value, by the neural network model to corresponding special cause of disease bacterial content
It is predicted, obtains corresponding special cause of disease bacterial content re prediction value；
According to the default Management strategy, the harmful side product content after improvement is carried out by the neural network model
Prediction, obtains corresponding harmful side product content prediction value；
When the special cause of disease bacterial content re prediction value and the harmful side product content prediction value reach pre- bidding
On time, determine that the default Management strategy is the water quality Management strategy.
The neural network model is obtained by following steps training in one of the embodiments:
Using different default Management strategies and corresponding harmful side product content as training data, to the neural network
Model is trained；
When the harmful side product content prediction value that the neural network model is obtained according to current Management strategy is worked as with described
The error of the corresponding practical harmful side product content of preceding Management strategy within a preset range when, determine the neural network model instruction
Practice and completes.
A kind of water quality information processing system, comprising: water monitoring device, data transmission device and water quality management platform；
The water monitoring device is used to obtain the water quality detection parameter of object water body, the water quality detection ginseng by monitoring
Number includes: the physical-chemical parameters and bacteria total amount；
The data transmission device is used to the water quality detection parameter that the water monitoring device obtains being transmitted to the water
Matter manages platform；
The water quality management platform is used for according to the physical-chemical parameters and the bacteria total amount, total to the bacterium
The situation of change of amount predicted, obtain the object water body bacteria total amount predicted value and special pathogen content prediction
Value；When the bacteria total amount predicted value and/or the special pathogen content prediction value exceed water quality health standards, according to institute
It states bacteria total amount predicted value and/or the special pathogen content prediction value determines corresponding water quality Management strategy.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device realizes the step of above-mentioned water quality information processing method when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of above-mentioned water quality information processing method is realized when row.
Above-mentioned water quality information processing method, system, storage medium and computer equipment obtain the water quality detection of object water body
Parameter, water quality detection parameter include: the physical-chemical parameters and bacteria total amount；It is right according to the physical-chemical parameters and bacteria total amount
The situation of change of bacteria total amount predicted, obtain object water body bacteria total amount predicted value and special pathogen content prediction
Value；It is pre- according to bacteria total amount when bacteria total amount predicted value and/or special pathogen content prediction value exceed water quality health standards
Measured value and/or special pathogen content prediction value determine corresponding water quality Management strategy.Pass through the bacteria total amount in prediction water body
And special cause of disease bacterial content, it can be with look-ahead water quality condition, and provided when water quality condition exceeds water quality health standards
Corresponding water quality Management strategy, so as to play the purpose of similar real-time monitoring water quality condition, and can be to a certain degree
It is upper to reduce security implication and property loss as caused by water quality information lag.
Detailed description of the invention
Fig. 1 is the flow diagram of water quality information processing method in one embodiment；
Fig. 2 is the overall flow figure of water quality information processing method in one embodiment；
Fig. 3 is the structural schematic diagram of water quality information processing unit in one embodiment；
Fig. 4 is the structural schematic diagram of water quality information processing system in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
In one embodiment, as shown in Figure 1, providing a kind of water quality information processing method, being applied in this way can be with
Be explained for the water quality management platform of water quality information processing, method includes the following steps:
Step S100 obtains the water quality detection parameter of object water body.
Water quality detection parameter includes the physical-chemical parameters and bacteria total amount, and the physical-chemical parameters can indicate impurity in water body
Type and quantity, be the important yardstick for judging water pollution degree.Wherein, physical parameter includes the physical index of sense organ,
Such as temperature, coloration, turbidity, transparency and other physical water quality indicators, such as total solid, suspended solid, stationarity
Solid, conductivity (resistivity) etc..Chemical parameters include pH value, hardness, basicity, various ions, general organic substance etc. in addition,
Bacteria total amount is the pollution level for indicating water body from bacteriological angle, including total number of bacteria, total coliform number, various cause of diseases
Bacterium, virus etc..
The water quality detection parameter that water quality management platform obtains can be the water quality detection parameter being collected in advance, be also possible to
The water quality detection parameter acquired in real time, the water quality detection parameter can be through water quality monitoring equipment and the detection of bacterium sensor
It obtains, alternatively, it is also possible to be can be by the parameter of equipment monitoring, the parameter of the type by artificial including some other
The parameter that sampling analysis obtains.
Step S200 predicts the situation of change of bacteria total amount, obtains according to the physical-chemical parameters and bacteria total amount
To the bacteria total amount predicted value and special pathogen content prediction value of object water body；
Water quality management platform after obtaining water quality detection parameter, according in water quality detection parameter the physical-chemical parameters and
Bacteria total amount can predict the following growing state of bacterium in conjunction with the growing state of bacterium, that is, predict bacteria total amount
Situation of change obtains corresponding bacteria total amount predicted value and special pathogen content prediction value.
Step S300, when bacteria total amount predicted value and/or special pathogen content prediction value exceed water quality health standards,
Corresponding water quality Management strategy is determined according to bacteria total amount predicted value and/or special pathogen content prediction value.
When water quality management platform passes through the step S200 bacteria total amount predicted value predicted and/or special cause of disease bacterial content
It when predicted value exceeds water quality health standards, that is, indicates within following correspondence period, it may appear that water quality is beyond health standards
Situation.Therefore, water quality management platform can be determined in view of bacteria total amount predicted value and/or special pathogen content prediction value and be corresponded to
Water quality Management strategy, related personnel can according to the actual situation according to the water quality Management strategy carry out water quality improvement, so as to
To carry out water quality improvement in advance, bacteria total amount and/or the exceeded situation of special cause of disease bacterial content are avoided the occurrence of.
The present embodiment, can be with look-ahead water quality shape by bacteria total amount and special cause of disease bacterial content in prediction water body
Condition, and corresponding water quality Management strategy is provided when water quality condition exceeds water quality health standards, it is similar real so as to play
When monitor water quality condition purpose, and can reduce to a certain extent as water quality information lag caused by security implication and
Property loss.
In one embodiment, special pathogen is the corresponding pathogenic bacteria of different application environment, specifically can be various water
Produce the corresponding pathogenic bacteria of breeding environment.
The cause of disease of aquaculture creature disease is caused mainly to have bacterium, virus, fungi, helminth and some algae etc.,
Wherein the common symptom of fish caused by bacterium has gill rot, white skin, red skin, perpendicular squama, bacterial septicemia, bacillary enteritis, furuncle
Sore, stigmatosis etc., the common bacteriosis of shell-fish have red leg, gill rot, blind, crust ulcer, fluorescence disease etc., and soft-shelled turtle class is common
Bacteriosis has Edwardsiella disease, shothole disease, Red neck disease, ulcer bleeding disease, and frog common bacterial disease has Edward
Bacterium disease, red leg disease, streptococcosis etc..Specifically, the cause of disease of gill rot is columnar fiber bacterium, and the cause of disease of red skin is Pseudomonas
Bacterium, the cause of disease for erecting squama is the dotted pseudomonad of water type, and the cause of disease of fresh water fish bacterial sepsis is Aeromonas hydrophila, bacillary intestines
Scorching cause of disease is Aeromonas hydrophila, Aeromonas caviae and visible peristalsis visible intestinal peristalsis Aeromonas punctata, and the cause of disease of printing is dotted gas unit cell
Bacterium subspecies, the cause of disease of furuncle sore are that the dotted production gas list packet Jun , Channel-catfish class intestines septicemia Shi You Channel-catfish Edwardsiella Gan Ran Channel-catfish class of furuncle sore type is drawn
It rises, vibriosis: vibrio frequent species have Vibrio anguillarum, vibrio parahaemolytious, vibrio alginolyticus, Vibrio harveyi etc..
In addition, the content due to special pathogen possibly can not normally be obtained by monitoring on-line, it is therefore possible to use people
The mode of work sampling analysis obtains the content of special pathogen, and the special pathogen content data is uploaded to water quality management and is put down
Platform.
In one embodiment, this method further include: parameter rate is carried out to water quality ecological mechanism model according to sample data
Fixed and Verification, and water quality ecological mechanism model is added in bacterial preoxidation parameter, sample data includes the physical-chemical parameters
And corresponding bacteria total amount delta data.
Water quality ecological mechanism model can be using existing mechanism model, and according to the physical-chemical parameters and corresponding
Bacteria total amount delta data is adjusted the model parameter of the mechanism model, so that the mechanism model has according to physico
Learn the ability of parameter prediction bacteria total amount situation of change.
Specifically, the parameter that parameter calibration first will assume substitutes into mechanism model, and obtaining corresponding calculated result, (bacterium is total
Measure predicted value), then calculated result and real data (practical bacteria total amount) are compared, if calculated result and real data
Error within a preset range, it may be considered that parameter at this time is qualified parameter；If calculated result and real data
Error exceed preset range, then parameter is adjusted, and parameter adjusted is substituted into mechanism model again, is counted again
It calculates, then is compared, until the error of calculated result and real data is within a preset range.It further include parameter after parameter calibration
Verifying, it can the mechanism model after parameter calibration is verified using new sample data, when the meter of mechanism model output
When calculating the error of result and real data within a preset range, determines that the mechanism model has and predicted according to the physical-chemical parameters
The ability of bacteria total amount situation of change.
In addition, bacterial preoxidation parameter is indicated after to sterilization processing is carried out containing germy object, the regeneration of bacterium
The parameters such as long rate can make the mechanism model have by the way that water quality ecological mechanism model is added in bacterial preoxidation parameter
Predict the ability of bacterial preoxidation situation.
In one embodiment, this method further include: with special pathogen type and the corresponding spy of different bacterium total amount
Different cause of disease bacterial content is training data, is trained to neural network model；When neural network model is according to current bacteria total amount
The error of the obtained special cause of disease bacterial content of special pathogen content prediction value reality corresponding with current bacteria total amount is default
When in range, determine that neural network model training is completed.
Specifically, training sample is obtained first, includes bacteria total amount and corresponding special pathogen in the training sample
Content, using bacteria total amount as the input of neural network model, using corresponding special cause of disease bacterial content as neural network model
Output, which is trained, until the spy that is predicted according to the bacteria total amount of the neural network model
The error of different pathogen content prediction value and the special cause of disease bacterial content within a preset range, to construct bacteria total amount and special
The correlation of different cause of disease bacterial content.
The present embodiment is by the corresponding special cause of disease bacterial content of special pathogen type and different bacterium total amount to nerve
Network model is trained, which is predicted according to bacteria total amount to obtain accurate spy
Different pathogen content prediction value.
In one embodiment, according to the physical-chemical parameters and bacteria total amount, the situation of change of bacteria total amount is carried out
Prediction, obtains the bacteria total amount predicted value and special pathogen content prediction value of object water body, comprising the following steps: according to object
Physicochemical parameter and bacteria total amount are predicted by situation of change of the water quality ecological mechanism model to bacteria total amount, and root
The bacteria total amount predicted value of object water body is obtained according to bacteria total amount and situation of change prediction result；It is predicted according to bacteria total amount
Value, is predicted, the special cause of disease bacterial content for obtaining object water body is pre- by content of the neural network model to special pathogen
Measured value.
After the water quality detection parameter for obtaining object water body, according to the physical-chemical parameters in water quality detection parameter and carefully
Bacterium total amount, the water quality ecological mechanism model after being passed through using parameter calibration and Verification predicted, so as to obtain compared with
Determine that the bacteria total amount is pre- by comparison bacteria total amount predicted value and water quality health standards for accurate bacteria total amount predicted value
Whether measured value is exceeded, and then can be administered in advance in the case where bacteria total amount predicted value is exceeded.
Further, bacteria total amount predicted value is obtained according to water quality ecological mechanism model, passes through trained neural network
Model predicts the content of special pathogen, so as to obtain accurately special pathogen content prediction value, from
And can be administered in advance in the case where special pathogen content prediction value is exceeded, prevent or reduce special pathogen pair
Property loss caused by aquaculture.
It should be noted that the detecting step due to pathogen special in water body is complicated, time-consuming, cause detection difficulty compared with
Greatly, therefore the prior art typically first carries out conventional bacteria total amount detection, just detects one by one to various pathogenic bacteria when necessary.
And the present embodiment can be predicted by trained neural network model and be obtained compared with subject to according to bacteria total amount predicted value
True special pathogen content prediction value, so as to reduce the testing process of special pathogen, and can be in special cause of disease
Bacterial content predicted value is administered in advance when exceeded, and special cause of disease bacterial content is avoided exceeded situation occur.
In one embodiment, it is determined according to bacteria total amount predicted value and/or special pathogen content prediction value corresponding
Water quality Management strategy, comprising: according to bacteria total amount predicted value and/or special pathogen content prediction value, pass through water quality ecological machine
Model and neural network model is managed to administer bacteria total amount predicted value and/or the corresponding water quality of special pathogen content prediction value
Situation carries out forecast assessment, and determines corresponding water quality Management strategy according to forecast assessment result.
In one embodiment, neural network model is obtained by following steps training: with different default Management strategies
And corresponding harmful side product content is training data, is trained to neural network model；When neural network model according to
The harmful side product content prediction value practical harmful side product content corresponding with current Management strategy that current Management strategy obtains
Error within a preset range when, determine neural network model training complete.
Specifically, training sample is obtained first, includes different Management strategies and different Management strategies in the training sample
Harmful side product content after corresponding improvement, using different Management strategies as the input of neural network model, with different improvement
Output of the harmful side product content as neural network model after the corresponding improvement of strategy, instructs the neural network model
Practice, until corresponding harmful side product content prediction value and reality that the neural network model is predicted according to different Management strategies
The error of the harmful side product content on border within a preset range, thus construct output (the harmful side product content after improvement) with
Input the correlation of (different Management strategies).
For using cholorination as water quality administration way, chlorination of drinking water disinfection by-products includes haloform, mainly
Refer to chloroform, bromodichloromethane, two bromochloromethanes and bromoform, the frequency that wherein chloroform occurs is most, content
Highest.Chlorination Disinfection By-products are in addition to haloform, and there are also halogen acetic acid, halogenated ketone, propylene halide nitrile, trichloronitromethane, water
Close trichloroacetaldehyde, cyanogen chloride, formaldehyde, acetaldehyde, 2.4.6-trichlorophenol etc., in addition, chlorination drinking water can also generate the chloro- 4- of 3-
- 2 (5H)-furans of (dichloromethyl) -5- hydroxyl and E-2- chloro- 3- (dichloromethyl) -4- oxygen-butadienoic acid.These substances are right
Human body is harmful, can carcinogenic or mutagenesis.Therefore, also particularly important for the prediction of harmful side product content.
The present embodiment is trained neural network model by the corresponding harmful side product information of different Management strategies, makes
Obtaining the neural network model can be predicted according to different Management strategies to obtain the nocuousness after accurate water quality is administered
By-products content predicted value, to facilitate the decision of staff's progress Management strategy.
In one embodiment, raw by water quality according to bacteria total amount predicted value and/or special pathogen content prediction value
State mechanism model and neural network model are to bacteria total amount predicted value and/or the corresponding water quality of special pathogen content prediction value
It administers situation and carries out forecast assessment, and corresponding water quality Management strategy is determined according to forecast assessment result, comprising the following steps:
When bacteria total amount predicted value and special pathogen content prediction value all exceed water quality health standards, according to bacterium
Prediction of Total value and default Management strategy are carried out by regrowth situation of the water quality ecological mechanism model to the bacterium after improvement
Prediction, obtains bacteria total amount re prediction value, bacteria total amount re prediction value be bacteria total amount predicted value is corresponding, administer after
The predicted value of bacteria total amount；According to bacteria total amount re prediction value, corresponding special pathogen is contained by neural network model
Amount is predicted, obtains corresponding special cause of disease bacterial content re prediction value, special cause of disease bacterial content re prediction value is special
Pathogen content prediction value is corresponding, administer after special cause of disease bacterial content predicted value；According to default Management strategy, pass through mind
The harmful side product content after improvement is predicted through network model, obtains corresponding harmful side product content prediction value；When
Bacteria total amount re prediction value, special cause of disease bacterial content re prediction value and harmful side product content prediction value reach pre- bidding
On time, determine that default Management strategy is water quality Management strategy.
In another embodiment, according to bacteria total amount predicted value and/or special pathogen content prediction value, pass through water quality
Ecological mechanism model and neural network model are to bacteria total amount predicted value and/or the corresponding water of special pathogen content prediction value
Matter administers situation and carries out forecast assessment, and determines corresponding water quality Management strategy according to forecast assessment result, comprising the following steps:
When bacteria total amount predicted value exceeds water quality health standards, according to bacteria total amount predicted value and default improvement plan
Slightly, it is predicted by regrowth situation of the water quality ecological mechanism model to the bacterium after improvement, it is secondary pre- to obtain bacteria total amount
Measured value；According to default Management strategy, the harmful side product content after improvement is predicted by neural network model, is obtained pair
The harmful side product content prediction value answered；When bacteria total amount re prediction value and harmful side product content prediction value reach default
When standard, determine that default Management strategy is water quality Management strategy.
In yet another embodiment, according to bacteria total amount predicted value and/or special pathogen content prediction value, pass through water quality
Ecological mechanism model and neural network model are to bacteria total amount predicted value and/or the corresponding water of special pathogen content prediction value
Matter administers situation and carries out forecast assessment, and determines corresponding water quality Management strategy according to forecast assessment result, comprising the following steps:
When special pathogen content prediction value exceeds water quality health standards, according to bacteria total amount predicted value and default control
Reason strategy, is predicted by regrowth situation of the water quality ecological mechanism model to the bacterium after improvement, obtains bacteria total amount two
Secondary predicted value；According to bacteria total amount re prediction value, corresponding special cause of disease bacterial content is carried out by neural network model pre-
It surveys, obtains corresponding special cause of disease bacterial content re prediction value；According to default Management strategy, by neural network model to improvement
Harmful side product content afterwards is predicted, corresponding harmful side product content prediction value is obtained；When special cause of disease bacterial content two
When secondary predicted value and harmful side product content prediction value reach preset standard, determine that default Management strategy is that water quality administers plan
Slightly.
In one embodiment, when determining that default Management strategy is water quality Management strategy, used preset standard can be with
It is specific parameter value, such as: the preset standard value of bacteria total amount is set as As, and the preset standard value of special cause of disease bacterial content is
Bs, the preset standard value of harmful side product content are Cs, then: when bacteria total amount re prediction value A is marked in advance lower than (or being equal to)
When quasi- value As, determine that bacteria total amount re prediction value reaches preset standard；When special cause of disease bacterial content re prediction value B is lower than
When (or being equal to) preset standard value Bs, determine that special cause of disease bacterial content re prediction value reaches preset standard；Work as harmful side product
When content prediction value C is lower than (or being equal to) preset standard value Cs, determine that harmful side product content prediction value reaches preset standard.
In one embodiment, for different water body objects, corresponding preset standard may be different.Such as: for
For daily life drinking water, the preset standard value of harmful side product content can be set more lower, thus
Prevent harmful by-products from doing harm to huamn body.And for the water body of aquaculture, special cause of disease bacterial content is preset
Standard value can be set more lower, to prevent special pathogen from impacting to aquaculture products, in turn result in wealth
Produce loss.
In one embodiment, it is also possible to control using the objective function for carrying out regulation effect assessment as determining preset
Reason strategy is the judgment criteria of water quality Management strategy.
For example, following table is the corresponding bacteria total amount re prediction value of different Management strategies, special cause of disease bacterial content is secondary pre-
Measured value and harmful side product content prediction value:
The assessment of regulation effect can be then carried out by following objective function:
Mi=Ai*X+Bi*Y+Ci*Z
Wherein, M is regulation effect assessment result, and X is that the regulation effect of bacterium assesses parameter, and Y is controlling for special pathogen
Recruitment evaluation parameter is managed, Z is that the regulation effect of harmful by-products assesses parameter, and i indicates serial number, is positive integer.Regulation effect is commented
Estimating parameter can be understood as weight parameter, furthermore it is possible to which the value for defining M is smaller, the regulation effect of the Management strategy is better.
It further, can be to the different classes of regulation effect in above-mentioned objective function for different water body objects
Assessment parameter is adjusted.Such as: for daily life drinking water, it can suitably increase controlling for harmful by-products
Manage recruitment evaluation parameter；For the water body of aquaculture, it can suitably increase the regulation effect assessment ginseng of special pathogen
Number.
In one embodiment, as shown in Fig. 2, providing a kind of water quality information processing method, method includes the following steps:
(1) water quality ecological mechanism model is obtained, the neural network model for carrying out water quality information processing is constructed；
(2) parameter calibration and Verification are carried out to water quality ecological mechanism model according to sample data, and by bacteriological aftergrowth
Water quality ecological mechanism model is added in long parameter, and sample data includes the physical-chemical parameters and corresponding bacteria total amount variation number
According to；
(3) right using the corresponding special cause of disease bacterial content of special pathogen type and different bacterium total amount as training data
Neural network model is trained, until the special pathogen content prediction that neural network model is obtained according to current bacteria total amount
It is worth the error of the special cause of disease bacterial content of reality corresponding with current bacteria total amount within a preset range；
(4) using different default Management strategies and corresponding harmful side product content as training data, to neural network
Model is trained, until harmful side product content prediction value that neural network model is obtained according to current Management strategy and current
The error of the corresponding practical harmful side product content of Management strategy is within a preset range；
(5) when water quality ecological mechanism model is adjusted by step (2), by step (3), (4) to neural network
Model is trained, and determines that the adjustment of water quality ecological mechanism model is completed, after the completion of neural network model training, obtains object water
The water quality detection parameter of body；
(6) variation according to the physical-chemical parameters and bacteria total amount, by water quality ecological mechanism model to bacteria total amount
Situation is predicted, and obtains the bacteria total amount predicted value of object water body according to bacteria total amount and situation of change prediction result；
It according to bacteria total amount predicted value, is predicted, is obtained pair by content of the neural network model to special pathogen
As the special pathogen content prediction value of water body；
(7) judge whether bacteria total amount predicted value and/or special pathogen content prediction value are exceeded；If so, executing step
Suddenly (8), if not, it is determined that object water body is healthy water body；
(8) according to bacteria total amount predicted value and/or special pathogen content prediction value, by water quality ecological mechanism model with
And neural network model is administered situation to bacteria total amount predicted value and/or the corresponding water quality of special pathogen content prediction value and is carried out
Forecast assessment, and corresponding water quality Management strategy is determined according to forecast assessment result；
(9) output/display/push bacteria total amount predicted value and/or the exceeded message of special pathogen content prediction value and
Corresponding water quality Management strategy.
It should be understood that although each step in the flow chart of Fig. 1-2 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 1-2
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 3, providing a kind of water quality information processing unit, which includes: that parameter obtains
Module 100, content prediction module 200 and policy development module 300.
Parameter acquisition module 100 is used to obtain the water quality detection parameter of object water body, and water quality detection parameter includes: physico
Learn parameter and bacteria total amount；
Content prediction module 200 is used for according to the physical-chemical parameters and bacteria total amount, to the situation of change of bacteria total amount
It is predicted, obtains the bacteria total amount predicted value and special pathogen content prediction value of object water body；
Policy development module 300 is used to exceed water quality when bacteria total amount predicted value and/or special pathogen content prediction value
When health standards, corresponding water quality Management strategy is determined according to bacteria total amount predicted value and/or special pathogen content prediction value.
Specific about water quality information processing unit limits the limit that may refer to above for water quality information processing method
Fixed, details are not described herein.Modules in above-mentioned water quality information processing unit can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In one embodiment, as shown in figure 4, providing a kind of water quality information processing system, which includes: water quality monitoring
Device 410, data transmission device 420 and water quality management platform 430.
Water monitoring device 410 includes water quality monitoring equipment and bacterium sensor, for obtaining object water by monitoring
The water quality detection parameter of body, the water quality detection parameter include: the physical-chemical parameters and bacteria total amount；
Data transmission device 420 is used to the water quality detection parameter that water monitoring device 410 obtains being transmitted to water quality management
Platform 430；
Water quality management platform 430 is used for according to the physical-chemical parameters and bacteria total amount, to the situation of change of bacteria total amount
It is predicted, obtains the bacteria total amount predicted value and special pathogen content prediction value of object water body；When bacteria total amount is predicted
When value and/or special pathogen content prediction value exceed water quality health standards, according to bacteria total amount predicted value and/or special cause of disease
Bacterial content predicted value determines corresponding water quality Management strategy.
Restriction about water quality management platform 420 may refer to the restriction above for water quality information processing method,
This is repeated no more.
The course of work of water quality information processing system includes real-time live monitoring, data transmission, pattern die in the present embodiment
Core links, this system such as quasi-, early-warning and predicting, intelligence control, processing scheme optimization and system feedback make full use of Internet of Things skill
Art and advantage are carried out the intelligent supervision of water body bacteria total amount based on Internet of Things and environment big data, pass through water quality monitoring
Equipment and bacterium sensor real-time collecting the physical-chemical parameters and bacteria total amount are driving parameter structure with the environmental data being collected into
Complex model is built, near real-time prediction is carried out to the following change of water quality, especially bacteria total amount and special cause of disease bacterial content, to will
The exceeded event of the bacterium of appearance provides warning information, and provides corresponding solution by the method for model optimization, to drop
The exceeded bring of low water body bacterium influences, and this system can effectively solve the problem that the exceeded incident of water body bacterium now lags, to endanger the public strong
Health and problem to culture fishery safety, thus it is possible to vary traditional Laboratory Monitoring, the status of post-processing are filled up at this
Blank of the field without early warning mechanism and optimization processing scheme, can be widely applied to rivers, lake, river mouth, seashore, fish pond, confession
Water, draining and drinking water related with water resource and public place.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor perform the steps of the water quality detection parameter for obtaining object water body, water when executing computer program
Quality detection parameter includes: the physical-chemical parameters and bacteria total amount；According to the physical-chemical parameters and bacteria total amount, to bacteria total amount
Situation of change predicted, obtain the bacteria total amount predicted value and special pathogen content prediction value of object water body；When thin
When bacterium Prediction of Total value and/or special pathogen content prediction value exceed water quality health standards, according to bacteria total amount predicted value and/
Or special pathogen content prediction value determines corresponding water quality Management strategy.
In one embodiment, it also performs the steps of when processor executes computer program according to the physical-chemical parameters
And bacteria total amount, it is predicted by situation of change of the water quality ecological mechanism model to bacteria total amount, and according to bacteria total amount
And situation of change prediction result obtains the bacteria total amount predicted value of object water body；According to bacteria total amount predicted value, pass through nerve
Network model predicts the content of special pathogen, obtains the special pathogen content prediction value of object water body.
In one embodiment, any one in the following terms is also realized when processor executes computer program:
First item: being adjusted, calibration and verifying according to model parameter of the sample data to water quality ecological mechanism model, and
Water quality ecological mechanism model is added in bacterial preoxidation parameter, sample data includes that the physical-chemical parameters and corresponding bacterium are total
Measure delta data；
Section 2: being training number with the corresponding special cause of disease bacterial content of special pathogen type and different bacterium total amount
According to being trained to neural network model；When the special cause of disease bacterial content that neural network model is obtained according to current bacteria total amount
The error of the special cause of disease bacterial content of predicted value reality corresponding with current bacteria total amount within a preset range when, determine neural network
Model training is completed.
In one embodiment, it also performs the steps of when processor executes computer program and is predicted according to bacteria total amount
Value and/or special pathogen content prediction value, it is pre- to bacteria total amount by water quality ecological mechanism model and neural network model
Measured value and/or the corresponding water quality of special pathogen content prediction value administer situation and carry out forecast assessment, and according to forecast assessment knot
Fruit determines corresponding water quality Management strategy.
In one embodiment, any one in the following terms is also realized when processor executes computer program:
First item: when bacteria total amount predicted value and special pathogen content prediction value all exceed water quality health standards,
Regrowth according to bacteria total amount predicted value and default Management strategy, by water quality ecological mechanism model to the bacterium after improvement
Situation predicted, obtains bacteria total amount re prediction value, bacteria total amount re prediction value be bacteria total amount predicted value it is corresponding,
The predicted value of bacteria total amount after improvement；According to bacteria total amount re prediction value, by neural network model to corresponding special
Cause of disease bacterial content is predicted, corresponding special cause of disease bacterial content re prediction value, special cause of disease bacterial content re prediction are obtained
Value be special pathogen content prediction value it is corresponding, administer after special cause of disease bacterial content predicted value；According to default improvement plan
Slightly, the harmful side product content after improvement is predicted by neural network model, obtains corresponding harmful side product content
Predicted value；When bacteria total amount re prediction value, special cause of disease bacterial content re prediction value and harmful side product content prediction value
When reaching preset standard, determine that default Management strategy is water quality Management strategy；
Section 2: it when bacteria total amount predicted value exceeds water quality health standards, according to bacteria total amount predicted value and presets
Management strategy is predicted by regrowth situation of the water quality ecological mechanism model to the bacterium after improvement, obtains bacteria total amount
Re prediction value；According to default Management strategy, the harmful side product content after improvement is predicted by neural network model,
Obtain corresponding harmful side product content prediction value；When bacteria total amount re prediction value and harmful side product content prediction value reach
When to preset standard, determine that default Management strategy is water quality Management strategy；
Section 3: when special pathogen content prediction value exceed water quality health standards when, according to bacteria total amount predicted value with
And default Management strategy, it is predicted, is obtained thin by regrowth situation of the water quality ecological mechanism model to the bacterium after improvement
Bacterium total amount re prediction value；According to bacteria total amount re prediction value, corresponding special pathogen is contained by neural network model
Amount is predicted, corresponding special cause of disease bacterial content re prediction value is obtained；According to default Management strategy, pass through neural network mould
Type predicts the harmful side product content after improvement, obtains corresponding harmful side product content prediction value；When special cause of disease
When bacterial content re prediction value and harmful side product content prediction value reach preset standard, determine that default Management strategy is water quality
Management strategy.
In one embodiment, it also performs the steps of when processor executes computer program with different default improvement
Tactful and corresponding harmful side product content is training data, is trained to neural network model；Work as neural network model
The harmful side product content prediction value practical harmful side product corresponding with current Management strategy obtained according to current Management strategy
The error of content within a preset range when, determine neural network model training complete.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of the water quality detection parameter for obtaining object water body when being executed by processor, water quality detection parameter includes:
The physical-chemical parameters and bacteria total amount；According to the physical-chemical parameters and bacteria total amount, the situation of change of bacteria total amount is carried out
Prediction, obtains the bacteria total amount predicted value and special pathogen content prediction value of object water body；When bacteria total amount predicted value and/
Or special pathogen content prediction value contains according to bacteria total amount predicted value and/or special pathogen when exceeding water quality health standards
Amount predicted value determines corresponding water quality Management strategy.
In one embodiment, it also performs the steps of when computer program is executed by processor and is joined according to physical chemistry
Several and bacteria total amount, is predicted, and total according to bacterium by situation of change of the water quality ecological mechanism model to bacteria total amount
Amount and situation of change prediction result obtain the bacteria total amount predicted value of object water body；According to bacteria total amount predicted value, pass through mind
It is predicted through content of the network model to special pathogen, obtains the special pathogen content prediction value of object water body.
In one embodiment, any one in the following terms is also realized when computer program is executed by processor:
First item: being adjusted, calibration and verifying according to model parameter of the sample data to water quality ecological mechanism model, and
Water quality ecological mechanism model is added in bacterial preoxidation parameter, sample data includes that the physical-chemical parameters and corresponding bacterium are total
Measure delta data；
Section 2: being training number with the corresponding special cause of disease bacterial content of special pathogen type and different bacterium total amount
According to being trained to neural network model；When the special cause of disease bacterial content that neural network model is obtained according to current bacteria total amount
The error of the special cause of disease bacterial content of predicted value reality corresponding with current bacteria total amount within a preset range when, determine neural network
Model training is completed.
In one embodiment, it is also performed the steps of when computer program is executed by processor pre- according to bacteria total amount
Measured value and/or special pathogen content prediction value, by water quality ecological mechanism model and neural network model to bacteria total amount
Predicted value and/or the corresponding water quality of special pathogen content prediction value administer situation and carry out forecast assessment, and according to forecast assessment
As a result corresponding water quality Management strategy is determined.
In one embodiment, any one in the following terms is also realized when computer program is executed by processor:
First item: when bacteria total amount predicted value and special pathogen content prediction value all exceed water quality health standards,
Regrowth according to bacteria total amount predicted value and default Management strategy, by water quality ecological mechanism model to the bacterium after improvement
Situation predicted, obtains bacteria total amount re prediction value, bacteria total amount re prediction value be bacteria total amount predicted value it is corresponding,
The predicted value of bacteria total amount after improvement；According to bacteria total amount re prediction value, by neural network model to corresponding special
Cause of disease bacterial content is predicted, corresponding special cause of disease bacterial content re prediction value, special cause of disease bacterial content re prediction are obtained
Value be special pathogen content prediction value it is corresponding, administer after special cause of disease bacterial content predicted value；According to default improvement plan
Slightly, the harmful side product content after improvement is predicted by neural network model, obtains corresponding harmful side product content
Predicted value；When bacteria total amount re prediction value, special cause of disease bacterial content re prediction value and harmful side product content prediction value
When reaching preset standard, determine that default Management strategy is water quality Management strategy；
Section 2: it when bacteria total amount predicted value exceeds water quality health standards, according to bacteria total amount predicted value and presets
Management strategy is predicted by regrowth situation of the water quality ecological mechanism model to the bacterium after improvement, obtains bacteria total amount
Re prediction value；According to default Management strategy, the harmful side product content after improvement is predicted by neural network model,
Obtain corresponding harmful side product content prediction value；When bacteria total amount re prediction value and harmful side product content prediction value reach
When to preset standard, determine that default Management strategy is water quality Management strategy；
Section 3: when special pathogen content prediction value exceed water quality health standards when, according to bacteria total amount predicted value with
And default Management strategy, it is predicted, is obtained thin by regrowth situation of the water quality ecological mechanism model to the bacterium after improvement
Bacterium total amount re prediction value；According to bacteria total amount re prediction value, corresponding special pathogen is contained by neural network model
Amount is predicted, corresponding special cause of disease bacterial content re prediction value is obtained；According to default Management strategy, pass through neural network mould
Type predicts the harmful side product content after improvement, obtains corresponding harmful side product content prediction value；When special cause of disease
When bacterial content re prediction value and harmful side product content prediction value reach preset standard, determine that default Management strategy is water quality
Management strategy.
In one embodiment, it also performs the steps of when computer program is executed by processor and default is controlled with different
Reason strategy and corresponding harmful side product content are training data, are trained to neural network model；When neural network mould
Type is according to harmful side product content prediction value practical harmful by-product corresponding with current Management strategy that current Management strategy obtains
The error of object content within a preset range when, determine neural network model training complete.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, computer program can be stored in a non-volatile computer and can be read
In storage medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the application
To any reference of memory, storage, database or other media used in provided each embodiment, may each comprise non-
Volatibility and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM (PROM),
Electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include arbitrary access
Memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms, such as static
RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhanced SDRAM
(ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) directly RAM (RDRAM), straight
Connect memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (10)
1. a kind of water quality information processing method characterized by comprising
The water quality detection parameter of object water body is obtained, the water quality detection parameter includes: the physical-chemical parameters and bacteria total amount；
According to the physical-chemical parameters and the bacteria total amount, the situation of change of the bacteria total amount is predicted, is obtained
To the bacteria total amount predicted value and special pathogen content prediction value of the object water body；
When the bacteria total amount predicted value and/or the special pathogen content prediction value exceed water quality health standards, according to
The bacteria total amount predicted value and/or the special pathogen content prediction value determine corresponding water quality Management strategy.
2. water quality information processing method according to claim 1, which is characterized in that the special pathogen is different application
The corresponding pathogenic bacteria of environment.
3. water quality information processing method according to claim 2, which is characterized in that according to the physical-chemical parameters and
The bacteria total amount predicts the situation of change of the bacteria total amount, obtains the bacteria total amount prediction of the object water body
Value and special pathogen content prediction value, comprising:
According to the physical-chemical parameters and the bacteria total amount, by water quality ecological mechanism model to the bacteria total amount
Situation of change is predicted, and obtains the bacterium of the object water body according to the bacteria total amount and situation of change prediction result
Prediction of Total value；
According to the bacteria total amount predicted value, is predicted by content of the neural network model to special pathogen, obtain institute
State the special pathogen content prediction value of object water body.
4. water quality information processing method according to claim 3, which is characterized in that including any one of the following terms:
First item: carrying out parameter calibration and Verification to water quality ecological mechanism model according to sample data, and by bacteriological aftergrowth
The water quality ecological mechanism model is added in long parameter, and the sample data includes the physical-chemical parameters and corresponding bacteria total amount
Delta data；
Section 2: right using the corresponding special cause of disease bacterial content of special pathogen type and different bacterium total amount as training data
The neural network model is trained；
The special pathogen content prediction value that is obtained according to current bacteria total amount when the neural network model and described current thin
The error of the special cause of disease bacterial content of the corresponding reality of bacterium total amount within a preset range when, determine that the neural network model has been trained
At.
5. water quality information processing method according to claim 1, which is characterized in that according to the bacteria total amount predicted value
And/or the special pathogen content prediction value determines corresponding water quality Management strategy, comprising:
According to the bacteria total amount predicted value and/or the special pathogen content prediction value, pass through water quality ecological mechanism model
And neural network model controls the bacteria total amount predicted value and/or the corresponding water quality of the special pathogen content prediction value
It manages situation and carries out forecast assessment, and corresponding water quality Management strategy is determined according to forecast assessment result.
6. water quality information processing method according to claim 5, which is characterized in that according to the bacteria total amount predicted value
And/or the special pathogen content prediction value, by water quality ecological mechanism model and neural network model to the bacterium
Prediction of Total value and/or the corresponding water quality improvement situation progress forecast assessment of the special pathogen content prediction value, and according to
Forecast assessment result determines any one of corresponding water quality Management strategy, including the following terms:
First item: when the bacteria total amount predicted value and the special pathogen content prediction value all exceed water quality health standards
When, according to the bacteria total amount predicted value and default Management strategy, by the water quality ecological mechanism model to improvement after
The regrowth situation of bacterium is predicted, obtains bacteria total amount re prediction value, the bacteria total amount re prediction value is described
Bacteria total amount predicted value is corresponding, administer after bacteria total amount predicted value；
According to the bacteria total amount re prediction value, corresponding special cause of disease bacterial content is carried out by the neural network model
Prediction, obtains corresponding special cause of disease bacterial content re prediction value, and the special cause of disease bacterial content re prediction value is the spy
Different pathogen content prediction value is corresponding, administer after special cause of disease bacterial content predicted value；
According to the default Management strategy, the harmful side product content after improvement is carried out by the neural network model pre-
It surveys, obtains corresponding harmful side product content prediction value；
When the bacteria total amount re prediction value, the special cause of disease bacterial content re prediction value and the harmful side product contain
When amount predicted value reaches preset standard, determine that the default Management strategy is the water quality Management strategy；
Section 2: when the bacteria total amount predicted value exceeds water quality health standards, according to the bacteria total amount predicted value and
Default Management strategy, is predicted by regrowth situation of the water quality ecological mechanism model to the bacterium after improvement, is obtained
Bacteria total amount re prediction value；
According to the default Management strategy, the harmful side product content after improvement is carried out by the neural network model pre-
It surveys, obtains corresponding harmful side product content prediction value；
When the bacteria total amount re prediction value and the harmful side product content prediction value reach preset standard, institute is determined
Stating default Management strategy is the water quality Management strategy；
Section 3: it when the special pathogen content prediction value exceeds water quality health standards, is predicted according to the bacteria total amount
Value and default Management strategy are carried out pre- by regrowth situation of the water quality ecological mechanism model to the bacterium after improvement
It surveys, obtains bacteria total amount re prediction value；
According to the bacteria total amount re prediction value, corresponding special cause of disease bacterial content is carried out by the neural network model
Prediction, obtains corresponding special cause of disease bacterial content re prediction value；
According to the default Management strategy, the harmful side product content after improvement is carried out by the neural network model pre-
It surveys, obtains corresponding harmful side product content prediction value；
When the special cause of disease bacterial content re prediction value and the harmful side product content prediction value reach preset standard,
Determine that the default Management strategy is the water quality Management strategy.
7. water quality information processing method according to claim 6, which is characterized in that the neural network model passes through following
Step training obtains:
Using different default Management strategies and corresponding harmful side product content as training data, to the neural network model
It is trained；
When the harmful side product content prediction value that the neural network model is obtained according to current Management strategy is currently controlled with described
When managing the error of the corresponding practical harmful side product content of strategy within a preset range, determine that the neural network model has been trained
At.
8. a kind of water quality information processing system characterized by comprising water monitoring device, data transmission device and water quality
Manage platform；
The water monitoring device is used to obtain the water quality detection parameter of object water body, the water quality detection parameter packet by monitoring
It includes: the physical-chemical parameters and bacteria total amount；
The data transmission device is used to the water quality detection parameter that the water monitoring device obtains being transmitted to the water quality pipe
Platform；
The water quality management platform is used for according to the physical-chemical parameters and the bacteria total amount, to the bacteria total amount
Situation of change is predicted, the bacteria total amount predicted value and special pathogen content prediction value of the object water body are obtained；When
When the bacteria total amount predicted value and/or the special pathogen content prediction value exceed water quality health standards, according to described thin
Bacterium Prediction of Total value and/or the special pathogen content prediction value determine corresponding water quality Management strategy.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the processor realizes water quality information processing side described in any one of claims 1 to 7 when executing the computer program
The step of method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of water quality information processing method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811524359.3A CN109725119B (en) | 2018-12-13 | 2018-12-13 | Water quality information processing method, system, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811524359.3A CN109725119B (en) | 2018-12-13 | 2018-12-13 | Water quality information processing method, system, storage medium and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109725119A true CN109725119A (en) | 2019-05-07 |
| CN109725119B CN109725119B (en) | 2021-04-23 |
Family
ID=66295685
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811524359.3A Active CN109725119B (en) | 2018-12-13 | 2018-12-13 | Water quality information processing method, system, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109725119B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111595799A (en) * | 2020-06-05 | 2020-08-28 | 重庆铂源检测技术有限公司 | Water quality analysis method and system |
| CN111938425A (en) * | 2020-07-20 | 2020-11-17 | 上海纯米电子科技有限公司 | Heating method, heating device, electric kettle and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101775434A (en) * | 2010-04-02 | 2010-07-14 | 天津大学 | Method for quick predicting total bacterial count of potable water network based on BP (Back Propagation) neural network |
| CN102565296A (en) * | 2011-12-11 | 2012-07-11 | 天津大学 | On-line early warning system and early warning method for quality of raw water of water reclamation plant |
| CN102707026A (en) * | 2012-06-06 | 2012-10-03 | 天津大学 | Water reclamation plant raw water quality online early warning system and control method thereof |
| CN102807301A (en) * | 2012-07-31 | 2012-12-05 | 天津大学 | Outlet water quality online monitoring and real-time forecasting system of water reclamation plant and control method thereof |
| CN103018416A (en) * | 2012-12-05 | 2013-04-03 | 天津大学 | Water quality on-line monitoring and prediction method for water supply pipe network |
| CN103018418A (en) * | 2012-12-16 | 2013-04-03 | 天津大学 | Landscape water quality online early warning system |
| CN103136601A (en) * | 2013-03-14 | 2013-06-05 | 天津大学 | Regeneration water factory effluent residual chorine risk prediction method |
| CN106354940A (en) * | 2016-08-30 | 2017-01-25 | 天津大学 | Landscape water quality simulation and early warning method based on water quality model uncertainty input |
-
2018
- 2018-12-13 CN CN201811524359.3A patent/CN109725119B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101775434A (en) * | 2010-04-02 | 2010-07-14 | 天津大学 | Method for quick predicting total bacterial count of potable water network based on BP (Back Propagation) neural network |
| CN102565296A (en) * | 2011-12-11 | 2012-07-11 | 天津大学 | On-line early warning system and early warning method for quality of raw water of water reclamation plant |
| CN102707026A (en) * | 2012-06-06 | 2012-10-03 | 天津大学 | Water reclamation plant raw water quality online early warning system and control method thereof |
| CN102807301A (en) * | 2012-07-31 | 2012-12-05 | 天津大学 | Outlet water quality online monitoring and real-time forecasting system of water reclamation plant and control method thereof |
| CN103018416A (en) * | 2012-12-05 | 2013-04-03 | 天津大学 | Water quality on-line monitoring and prediction method for water supply pipe network |
| CN103018418A (en) * | 2012-12-16 | 2013-04-03 | 天津大学 | Landscape water quality online early warning system |
| CN103136601A (en) * | 2013-03-14 | 2013-06-05 | 天津大学 | Regeneration water factory effluent residual chorine risk prediction method |
| CN106354940A (en) * | 2016-08-30 | 2017-01-25 | 天津大学 | Landscape water quality simulation and early warning method based on water quality model uncertainty input |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111595799A (en) * | 2020-06-05 | 2020-08-28 | 重庆铂源检测技术有限公司 | Water quality analysis method and system |
| CN111938425A (en) * | 2020-07-20 | 2020-11-17 | 上海纯米电子科技有限公司 | Heating method, heating device, electric kettle and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109725119B (en) | 2021-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Groenendaal et al. | Development of the Dutch Johne’s disease control program supported by a simulation model | |
| CN107169610A (en) | Aquaculture dissolved oxygen prediction method and device | |
| CN113126490B (en) | Intelligent frequency conversion oxygenation control method and device | |
| CN109725119A (en) | Water quality information processing method, system, storage medium and computer equipment | |
| NO345829B1 (en) | C-fish – fish welfare control | |
| CN117084200B (en) | Aquaculture dosing control system applying big data analysis | |
| CN105069220A (en) | Back-propagation (BP) neural network immune genetic algorithm based microbial fermentation optimization method | |
| Lukas et al. | Bulk tank somatic cell counts analyzed by statistical process control tools to identify and monitor subclinical mastitis incidence | |
| CN104898723B (en) | Aquaculture pond pH value intelligence control system | |
| CN118071177B (en) | Sewage treatment simulation regulation and control method and system | |
| CN118235723B (en) | Cow intelligent monitoring platform and device based on wisdom pasture | |
| CN110045771A (en) | A kind of fishpond water quality intelligent monitor system | |
| CN109711590B (en) | Fishery water quality analysis monitoring method, device and system | |
| CN109825549A (en) | The risk assessment of fresh milk staphylococcus aureus and quick early warning system | |
| Marks et al. | Factors influencing the dynamics of a collapsed blue swimmer crab (Portunus armatus) population and its lack of recovery | |
| CN110197704A (en) | A kind of self-organizing BP neural network water outlet total phosphorus prediction technique based on limited Boltzmann machine | |
| CN117763352A (en) | Dosage optimization control method based on VSM-GRU total phosphorus prediction model | |
| CN116562469A (en) | Fresh water fish pathogen transmission prediction method, device, equipment and storage medium | |
| CN117877739A (en) | Quantitative evaluation method for infectious disease prevention and control strategy based on dynamics | |
| CN103679538A (en) | Field immune effect evaluation method for porcine circovirus 2 vaccine | |
| CN109781951A (en) | A kind of fishpond water quality monitoring system and monitoring method | |
| CN116502903A (en) | Method for evaluating suitability of bottom-sowing scallop breeding area site selection based on analytic hierarchy process | |
| CN116452358A (en) | Intelligent agriculture management system based on Internet of things | |
| CN116313046A (en) | Traditional Chinese medicine clinical auxiliary decision-making system based on data analysis | |
| CN109359624A (en) | The prediction technique and prediction meanss of laying hen foraging behaviour neural network based |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |