CN113409167A - Water quality abnormity analysis method and device - Google Patents
Water quality abnormity analysis method and device Download PDFInfo
- Publication number
- CN113409167A CN113409167A CN202110952069.4A CN202110952069A CN113409167A CN 113409167 A CN113409167 A CN 113409167A CN 202110952069 A CN202110952069 A CN 202110952069A CN 113409167 A CN113409167 A CN 113409167A
- Authority
- CN
- China
- Prior art keywords
- water quality
- data
- sequence
- model
- data set
- 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 279
- 238000004458 analytical method Methods 0.000 title claims abstract description 43
- 230000002159 abnormal effect Effects 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 15
- 230000005856 abnormality Effects 0.000 claims description 39
- 238000012549 training Methods 0.000 claims description 35
- 238000012360 testing method Methods 0.000 claims description 29
- 238000012795 verification Methods 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 abstract description 2
- 238000013145 classification model Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/18—Water
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Pathology (AREA)
- Water Supply & Treatment (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Medicinal Chemistry (AREA)
- Food Science & Technology (AREA)
- Public Health (AREA)
- Biochemistry (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application discloses a water quality abnormity analysis method and a device. The method comprises the steps of collecting historical water quality section data and establishing a water quality characteristic section data set; calculating the correlation characteristics of the historical water quality characteristics and the target water quality characteristics in the section data set, and constructing a water quality abnormity model according to the historical water quality characteristics and the correlation characteristics; and collecting water quality data at the current moment, and inputting the water quality data at the current moment into a water quality abnormity model for water quality abnormity analysis. The water quality abnormity model capable of accurately finding water quality abnormity is constructed, the water quality abnormity detection method is suitable for abnormity analysis of various water quality indexes of different cross sections of different watersheds, accurate judgment of water quality data abnormity is achieved, the rate of missing report and the rate of false report of abnormal data are reduced, and data support is provided for management work of water environment quality.
Description
Technical Field
The application relates to the field of water quality abnormity alarm, in particular to a water quality abnormity analysis method and device.
Background
The water environment monitoring data is used as the real reflection of the water environment quality. The method can be used for timely and accurately finding the abnormality in the data, and is beneficial to finding the pollution in the water environment and providing a guiding function for water environment management. The method for processing the water quality data abnormity is to establish a fixed threshold or a dynamic threshold for the index. When the variation range of the data is within the threshold value again, the data is determined to be normal. And if the data is not in the threshold range, determining that the data is abnormal, and thus early warning is performed.
Considering that factors influencing the water environment are complex, and numerical differences among watersheds, sections and various indexes are large. The abnormal data monitoring method based on the threshold class needs to establish a corresponding threshold for each index, has large workload and cannot be well popularized and applied, and the method based on the threshold class does not consider the change of the water environment, so that the report omission and the report error of data abnormality can be caused.
Disclosure of Invention
The application provides a water quality abnormity analysis method, which comprises the following steps:
collecting historical water quality section data and establishing a water quality characteristic section data set;
calculating the correlation characteristics of the historical water quality characteristics and the target water quality characteristics in the section data set, and constructing a water quality abnormity model according to the historical water quality characteristics and the correlation characteristics;
and collecting water quality data at the current moment, and inputting the water quality data at the current moment into a water quality abnormity model for water quality abnormity analysis.
The method for analyzing the water quality abnormality, wherein the correlation characteristics of the historical water quality characteristics and the target water quality characteristics in the profile data set are calculated, specifically comprises the following substeps:
preprocessing the historical water quality characteristics to form a characteristic sequence;
calculating a gray correlation coefficient and a Pearson coefficient between the characteristic sequence and the target water quality sequence;
and calculating the correlation characteristics according to the grey correlation coefficient and the Pearson coefficient.
The water quality abnormality analysis method comprises the following steps of:
constructing a model parameter network, taking the collected historical water quality data sequence and the associated characteristic sequence as an input data set, and taking the water quality index data at the current moment as an output data set;
dividing an input data set into a training data set, a testing data set and a verification data set, and training a model parameter network by using the training data set, the testing data set and the verification data set to obtain a primary water quality abnormity model;
calculating a prediction result sequence of the primary water quality abnormity model to the verification data set, and calculating a difference sequence of the output sequence of the verification data set;
and establishing a final water quality abnormity model according to the difference sequence.
The water quality abnormality analysis method described above, wherein the final water quality abnormality model is established according to the difference sequence, specifically includes the following substeps:
carrying out approximate normal distribution test on the difference sequence;
if the test is not satisfied, returning to reconstruct the parameter net training model;
if the difference meets the verification requirement, calculating the difference change range to obtain the interval value of the normal water quality data;
and training a final water quality abnormal model according to the collected historical water quality data sequence and the interval value of the normal water quality data, and outputting the water quality abnormal condition.
The water quality abnormality analysis method described above, wherein the range of variation of the difference is calculated to obtain the interval value of the normal water quality data, specifically:
initializing a difference value variation range
；
Secondly, setting the mean value of the difference sequence as a, and calculating the number l of the difference sequence in the interval [ a-t, a + t ];
(iii) let the difference sequence length be L, when L is less than or equal to L0.95, t + =0.001 a;
and fourthly, obtaining the interval value of the normal water quality data as [ a-t, a + t ].
The application also provides a quality of water anomaly analysis device, includes:
the data acquisition module is used for acquiring historical water quality section data and establishing a water quality characteristic section data set; collecting water quality data at the current moment;
the correlation characteristic calculation module is used for calculating the correlation characteristics of the historical water quality characteristics and the target water quality characteristics in the section data set;
the water quality abnormity model building module is used for building a water quality abnormity model according to the historical water quality characteristics and the correlation characteristics;
and the water quality abnormity analysis module inputs the water quality data at the current moment into the water quality abnormity model to perform water quality abnormity analysis.
The water quality abnormality analysis apparatus as described above, wherein the correlation characteristic calculation module is specifically configured to: preprocessing the historical water quality characteristics to form a characteristic sequence; calculating a gray correlation coefficient and a Pearson coefficient between the characteristic sequence and the target water quality sequence; and calculating the correlation characteristics according to the grey correlation coefficient and the Pearson coefficient.
The water quality abnormality analysis device described above, wherein the water quality abnormality model building module specifically includes:
the model parameter network construction submodule is used for constructing a model parameter network, the collected historical water quality data sequence and the associated characteristic sequence are used as an input data set, and the water quality index data at the current moment are used as an output data set;
the water quality abnormity model training submodule is used for dividing an input data set into a training, testing and verifying data set, and training a model parameter network by using the training set, the testing set and the verifying data set to obtain a primary water quality abnormity model;
the final water quality abnormity model construction submodule is used for calculating a prediction result sequence of the primary water quality abnormity model to the verification data set and calculating a difference sequence of the primary water quality abnormity model and an output sequence of the verification data set; and establishing a final water quality abnormity model according to the difference sequence.
The water quality abnormality analysis apparatus as described above, wherein the final water quality abnormality model construction sub-module specifically includes:
the approximate normal distribution test unit is used for carrying out approximate normal distribution test on the difference sequence; if the test is not satisfied, returning to reconstruct the parameter net training model; if the verification is met, triggering a difference value change range calculation unit;
the difference value change range calculation module unit is used for calculating the difference value change range and obtaining the interval value of the normal water quality data;
and the final water quality abnormal model constructing subunit is used for training a final water quality abnormal model according to the collected historical water quality data sequence and the interval value of the normal water quality data and outputting the water quality abnormal condition.
The water quality abnormality analysis apparatus as described above, wherein the difference variation range calculation module unit is specifically configured to: initializing a difference value variation range
(ii) a Let the mean value of the difference sequence be a, calculate the difference sequence in the interval [ a-t, a + t]The number of (c) is l; (iii) let the difference sequence length be L, when L is less than or equal to L0.95, t + =0.001 a; fourthly, obtaining the interval value of the normal water quality data as [ a-t, a + t]。
The beneficial effect that this application realized is as follows: the water quality abnormity model capable of accurately finding water quality abnormity is constructed, the water quality abnormity detection method is suitable for abnormity analysis of various water quality indexes of different cross sections of different watersheds, accurate judgment of water quality data abnormity is achieved, the rate of missing report and the rate of false report of abnormal data are reduced, and data support is provided for management work of water environment quality.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings can be obtained by those skilled in the art according to the drawings.
FIG. 1 is a flow chart of a water quality abnormality analysis method according to an embodiment of the present disclosure;
fig. 2 is a schematic diagram of a water quality abnormality analysis apparatus according to a second embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
As shown in fig. 1, an embodiment of the present application provides a water quality abnormality analysis method, including:
the historical water quality section data are different water quality objects collected at the same time point or in the same time period before the current time, including water quality data, hydrological data, meteorological data, time data and the like, and a large amount of historical water quality section data are collected to construct water quality characteristic section numberA data set; for example, collecting water quality data n times before, including collecting t1Time point or (0-t)1) Water quality data A of time period1Hydrologic data B1Meteorological data C1Time data D1，t2Time point or (t)1~t2) Water quality data A of time period2Hydrologic data B2Meteorological data C2Time data D2，tnWater quality data A at time pointsnHydrologic data BnMeteorological data CnTime data DnThe constructed water quality characteristic section data set is W = { (A)1,B1,C1,D1),(A1,B1,C1,D1),…,(A1,B1,C1,D1)}。
the method comprises the following steps of calculating the correlation characteristics of historical water quality characteristics and target water quality characteristics in a section data set, and specifically comprises the following substeps:
step11, preprocessing the historical water quality characteristics to form a characteristic sequencek；
Specifically, time characteristics in historical water quality characteristics are converted into year, month, day and time characteristics, and characteristics such as water period characteristics and precipitation are added to form a characteristic sequencek；
Step12, calculating a gray correlation coefficient and a Pearson coefficient between the characteristic sequence and the target water quality sequence;
the gray correlation coefficient was calculated using the following formula
And Pearson's coefficient
：
Wherein the content of the first and second substances,
is a characteristic sequencekWith the target water quality sequencehThe gray correlation coefficient between the gray color components,
is a characteristic sequencekWith the target water quality sequencehThe gray correlation coefficient sequence between the two coefficients,
water quality sequence for purposehConstituting a grey correlation coefficient sequence;
is a characteristic sequencekWith the target water quality sequencehThe pearson coefficient in between is,
is a characteristic sequencekWith the target water quality sequencehA sequence of pearson coefficients in between,
water quality sequence for purposehConstituting a Pearson coefficient sequence.
Step13, calculating the correlation characteristics according to the grey correlation coefficient and the Pearson coefficient;
specifically, a gray correlation coefficient is calculated
And Pearson's coefficient
Weighted numerical valueS，
，Will be provided withSA feature of not less than 0.5 is taken as the associated feature.
In the embodiment of the application, a water quality abnormity model is established according to the historical water quality characteristics and the associated characteristics, and the method specifically comprises the following substeps:
step21, constructing a model parameter network, taking the collected historical water quality data sequence and the associated characteristic sequence as an input data set, and taking the water quality index data at the current moment as an output data set;
step22, dividing an input data set into training, testing and verifying data sets, and training a model parameter network by using the training sets, the testing sets and the verifying data sets to obtain a primary water quality abnormity model;
specifically, for each parameter combination, when the error of the test data set and the error of the training data set are not reduced any more and the errors of the two data sets are close, the model training is stopped, and the model with the minimum error of the verification data set is selected as the primary water quality abnormity model.
Step23, calculating a prediction result sequence of the primary water quality abnormity model to the verification data set, and calculating a difference sequence of the output sequence of the verification data set;
step24, establishing a final water quality abnormity model according to the difference sequence;
specifically, the method for establishing the final water quality abnormity model according to the difference sequence specifically comprises the following substeps:
step241, performing approximate normal distribution test on the difference sequence S, returning to execute Step21 when the test is not satisfied, reconstructing a parameter network training model, and executing Step242 if the test is satisfied;
step242, calculating a difference value change range t to obtain an interval value of normal water quality data;
wherein, calculate difference variation range, obtain the interval value of normal quality of water data, specifically do:
initializing a difference value variation range
；
Let the mean value of the difference sequence be a, calculate the difference sequence in the interval [ a-t, a + t]Number of (2)l；
Let the length of the difference sequence be L whenlAt less than or equal to L0.95, t + =0.001 a
And fourthly, obtaining the interval value of the normal water quality data as [ a-t, a + t ].
Step243, training a final water quality abnormity model according to the collected historical water quality data sequence and the interval value of the normal water quality data, and outputting the water quality abnormity condition;
specifically, the characteristics such as abnormal water quality data, abnormal hydrological data, abnormal meteorological data and abnormal time data are extracted from the historical water quality data sequence, the characteristics such as normal water quality data, normal hydrological data, normal meteorological data and normal time data are extracted from the normal water quality data, and a water quality characteristic vector set is constructed
Wherein, in the step (A),
is a water quality characteristic vector, and is characterized in that,
，
，
respectively representing the characteristics of abnormal water quality data, abnormal hydrological data, abnormal meteorological data and abnormal time data,
respectively representing the characteristics of normal water quality data, normal hydrological data, normal meteorological data and normal time data;
inputting the water quality characteristic vector set into a prediction model, training the prediction model to obtain different sub-classification models
Using the respective sub-classification models
Classifying the water quality characteristic vector set, and obtaining classification results
Estimating to obtain each sub-classification model
Set of weights of
(ii) a Calculating each sub-classification model by particle swarm optimization algorithm
Set of weights of
The optimal value corresponding to each weight in the weight; by individual sub-classification models
And the optimal value of its corresponding weight
And (4) determining the abnormal condition of the water quality in a combined manner.
specifically, after the water quality abnormality model is constructed by using the historical water quality data at the previous n moments, the water quality data at the n +1 th moment is collected and input into the water quality abnormality model, and then the water quality abnormality condition S is outputn+1Then comparing with the interval value of the normal water quality data, if:
wherein the content of the first and second substances,
，
respectively a predicted value and a real monitoring value of the water quality index n +1 moment model; if it isS n+1 Between a-t and a + t, the water quality is normal, ifS n+1 Less than a-t orS n+1 If the water quality is higher than a + t, the water quality is abnormal.
Example two
As shown in fig. 2, a water quality abnormality analysis apparatus 200 according to a first embodiment of the present application includes: the system comprises a data acquisition module 210, an associated characteristic calculation module 220, a water quality abnormity model construction module 230 and a water quality abnormity analysis module 240;
the data acquisition module 210 is used for acquiring historical water quality section data and establishing a water quality characteristic section data set; collecting water quality data at the current moment;
the correlation characteristic calculation module 220 is used for calculating the correlation characteristics of the historical water quality characteristics and the target water quality characteristics in the section data set;
a water quality abnormity model construction module 230 for constructing a water quality abnormity model according to the historical water quality characteristics and the associated characteristics;
and the water quality abnormity analysis module 240 inputs the water quality data at the current moment into the water quality abnormity model to perform water quality abnormity analysis.
The associated feature calculating module 220 is specifically configured to: preprocessing the historical water quality characteristics to form a characteristic sequence; calculating a gray correlation coefficient and a Pearson coefficient between the characteristic sequence and the target water quality sequence; and calculating the correlation characteristics according to the grey correlation coefficient and the Pearson coefficient.
The water quality abnormality model building module 230 specifically includes:
the model parameter network construction submodule 231 is used for constructing a model parameter network, taking the collected historical water quality data sequence and the associated characteristic sequence as an input data set, and taking the water quality index data at the current moment as an output data set;
the primary water quality abnormality model training submodule 232 is used for dividing an input data set into a training, testing and verifying data set, and training a model parameter network by using the training set, the testing set and the verifying data set to obtain a primary water quality abnormality model;
a final water quality abnormity model construction submodule 233 for calculating a prediction result sequence of the primary water quality abnormity model to the verification data set, and calculating a difference sequence with an output sequence of the verification data set; and establishing a final water quality abnormity model according to the difference sequence.
Specifically, the final water quality abnormality model construction submodule 233 specifically includes:
an approximate normal distribution test unit 2331 for performing an approximate normal distribution test on the difference sequence; if the test is not satisfied, returning to reconstruct the parameter net training model; if the verification is met, triggering a difference value change range calculation unit;
a difference variation range calculation module 2332, configured to calculate a difference variation range to obtain an interval value of the normal water quality data;
a final water quality abnormal model constructing subunit 2333, configured to train a final water quality abnormal model according to the collected historical water quality data sequence and the interval value of the normal water quality data, and output a water quality abnormal condition.
The difference variation range calculating module 2332 is specifically configured to: initializing a difference value variation range
(ii) a Let the mean value of the difference sequence be a, calculate the difference sequence in the interval [ a-t, a + t]The number of (c) is l; (iii) let the difference sequence length be L, when L is less than or equal to L0.95, t + =0.001 a; fourthly, obtaining the interval value of the normal water quality data as [ a-t, a + t]。
Corresponding to the above embodiments, an embodiment of the present invention provides a computer storage medium, including: at least one memory and at least one processor;
the memory is used for storing one or more program instructions;
the processor is used for running one or more program instructions to execute a water quality abnormity analysis method.
In accordance with the embodiments described above, embodiments of the present invention provide a computer-readable storage medium, where the computer storage medium includes one or more program instructions, and the one or more program instructions are used by a processor to execute a water quality abnormality analysis method.
The embodiment of the invention discloses a computer readable storage medium, wherein computer program instructions are stored in the computer readable storage medium, and when the computer program instructions are run on a computer, the computer is enabled to execute the water quality abnormity analysis method.
In an embodiment of the invention, the processor may be an integrated circuit chip having signal processing capability. The Processor may be a general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete Gate or transistor logic device, discrete hardware component.
The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The processor reads the information in the storage medium and completes the steps of the method in combination with the hardware.
The storage medium may be a memory, for example, which may be volatile memory or nonvolatile memory, or which may include both volatile and nonvolatile memory.
The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory.
The volatile Memory may be a Random Access Memory (RAM) which serves as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), SLDRAM (SLDRAM), and Direct Rambus RAM (DRRAM).
The storage media described in connection with the embodiments of the invention are intended to comprise, without being limited to, these and any other suitable types of memory.
Those skilled in the art will appreciate that the functionality described in the present invention may be implemented in a combination of hardware and software in one or more of the examples described above. When software is applied, the corresponding functionality may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
The above-mentioned embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made on the basis of the technical solutions of the present invention should be included in the scope of the present invention.
Claims (10)
1. A water quality abnormality analysis method is characterized by comprising the following steps:
collecting historical water quality section data and establishing a water quality characteristic section data set;
calculating the correlation characteristics of the historical water quality characteristics and the target water quality characteristics in the section data set, and constructing a water quality abnormity model according to the historical water quality characteristics and the correlation characteristics;
and collecting water quality data at the current moment, and inputting the water quality data at the current moment into a water quality abnormity model for water quality abnormity analysis.
2. The water quality abnormality analysis method according to claim 1, wherein the correlation characteristic between the historical water quality characteristic and the target water quality characteristic in the profile data set is calculated, and the method specifically comprises the following substeps:
preprocessing the historical water quality characteristics to form a characteristic sequence;
calculating a gray correlation coefficient and a Pearson coefficient between the characteristic sequence and the target water quality sequence;
and calculating the correlation characteristics according to the grey correlation coefficient and the Pearson coefficient.
3. The water quality abnormality analysis method according to claim 1, wherein a water quality abnormality model is constructed based on the historical water quality characteristics and the correlation characteristics, and the method specifically comprises the following substeps:
constructing a model parameter network, taking the collected historical water quality data sequence and the associated characteristic sequence as an input data set, and taking the water quality index data at the current moment as an output data set;
dividing an input data set into a training data set, a testing data set and a verification data set, and training a model parameter network by using the training data set, the testing data set and the verification data set to obtain a primary water quality abnormity model;
calculating a prediction result sequence of the primary water quality abnormity model to the verification data set, and calculating a difference sequence of the output sequence of the verification data set;
and establishing a final water quality abnormity model according to the difference sequence.
4. The water quality abnormality analysis method according to claim 3, wherein a final water quality abnormality model is established based on the difference sequence, and the method specifically comprises the following substeps:
carrying out approximate normal distribution test on the difference sequence;
if the test is not satisfied, returning to reconstruct the parameter net training model;
if the difference meets the verification requirement, calculating the difference change range to obtain the interval value of the normal water quality data;
and training a final water quality abnormal model according to the collected historical water quality data sequence and the interval value of the normal water quality data, and outputting the water quality abnormal condition.
5. The water quality abnormality analysis method according to claim 4, wherein the range of variation of the difference is calculated to obtain an interval value of normal water quality data, specifically:
initializing a difference value variation range
；
Let the mean value of the difference sequence be a, calculate the difference sequence in the interval [ a-t, a + t]Number of (2)l；
Let the length of the difference sequence be L whenlWhen L is less than or equal to 0.95, t + =0.001 a;
and fourthly, obtaining the interval value of the normal water quality data as [ a-t, a + t ].
6. A water quality abnormality analysis device is characterized by comprising:
the data acquisition module is used for acquiring historical water quality section data and establishing a water quality characteristic section data set; collecting water quality data at the current moment;
the correlation characteristic calculation module is used for calculating the correlation characteristics of the historical water quality characteristics and the target water quality characteristics in the section data set;
the water quality abnormity model building module is used for building a water quality abnormity model according to the historical water quality characteristics and the correlation characteristics;
and the water quality abnormity analysis module inputs the water quality data at the current moment into the water quality abnormity model to perform water quality abnormity analysis.
7. The water quality abnormality analysis apparatus according to claim 6, wherein the correlation characteristic calculation module is specifically configured to: preprocessing the historical water quality characteristics to form a characteristic sequence; calculating a gray correlation coefficient and a Pearson coefficient between the characteristic sequence and the target water quality sequence; and calculating the correlation characteristics according to the grey correlation coefficient and the Pearson coefficient.
8. The water quality abnormality analysis apparatus according to claim 6, wherein the water quality abnormality model building module specifically includes:
the model parameter network construction submodule is used for constructing a model parameter network, the collected historical water quality data sequence and the associated characteristic sequence are used as an input data set, and the water quality index data at the current moment are used as an output data set;
the water quality abnormity model training submodule is used for dividing an input data set into a training, testing and verifying data set, and training a model parameter network by using the training set, the testing set and the verifying data set to obtain a primary water quality abnormity model;
the final water quality abnormity model construction submodule is used for calculating a prediction result sequence of the primary water quality abnormity model to the verification data set and calculating a difference sequence of the primary water quality abnormity model and an output sequence of the verification data set; and establishing a final water quality abnormity model according to the difference sequence.
9. The water quality abnormality analysis apparatus according to claim 8, wherein the final water quality abnormality model construction submodule specifically includes:
the approximate normal distribution test unit is used for carrying out approximate normal distribution test on the difference sequence; if the test is not satisfied, returning to reconstruct the parameter net training model; if the verification is met, triggering a difference value change range calculation unit;
the difference value change range calculation module unit is used for calculating the difference value change range and obtaining the interval value of the normal water quality data;
and the final water quality abnormal model constructing subunit is used for training a final water quality abnormal model according to the collected historical water quality data sequence and the interval value of the normal water quality data and outputting the water quality abnormal condition.
10. A computer storage medium, comprising: at least one memory and at least one processor;
the memory is used for storing one or more program instructions;
a processor for executing one or more program instructions to perform a water quality abnormality analysis method as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110952069.4A CN113409167B (en) | 2021-08-19 | 2021-08-19 | Water quality abnormity analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110952069.4A CN113409167B (en) | 2021-08-19 | 2021-08-19 | Water quality abnormity analysis method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113409167A true CN113409167A (en) | 2021-09-17 |
| CN113409167B CN113409167B (en) | 2021-11-30 |
Family
ID=77688846
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110952069.4A Active CN113409167B (en) | 2021-08-19 | 2021-08-19 | Water quality abnormity analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113409167B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113781019A (en) * | 2021-11-12 | 2021-12-10 | 中国环境监测总站 | Method and device for automatically screening and fusing monitoring data |
| CN116308952A (en) * | 2023-03-08 | 2023-06-23 | 浪潮智慧科技有限公司 | Water quality monitoring method and device based on unmanned ship |
| CN116500240A (en) * | 2023-06-21 | 2023-07-28 | 江西索立德环保服务有限公司 | Soil environment quality monitoring method, system and readable storage medium |
| CN117524497A (en) * | 2023-10-26 | 2024-02-06 | 曙光云计算集团有限公司 | Data processing method, device, computer equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140012556A1 (en) * | 2012-07-06 | 2014-01-09 | Electronics And Telecommunications Research Institute | Apparatus and method for real time water quality prediction using hydrodynamic model |
| CN106872657A (en) * | 2017-01-05 | 2017-06-20 | 河海大学 | A kind of multivariable water quality parameter time series data accident detection method |
| CN109711590A (en) * | 2017-10-26 | 2019-05-03 | 中国电信股份有限公司 | Fishery water quality analyzing monitoring method, device and system |
| CN112651665A (en) * | 2021-01-14 | 2021-04-13 | 浙江鸿程计算机系统有限公司 | Surface water quality index prediction method and device based on graph neural network |
-
2021
- 2021-08-19 CN CN202110952069.4A patent/CN113409167B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140012556A1 (en) * | 2012-07-06 | 2014-01-09 | Electronics And Telecommunications Research Institute | Apparatus and method for real time water quality prediction using hydrodynamic model |
| CN106872657A (en) * | 2017-01-05 | 2017-06-20 | 河海大学 | A kind of multivariable water quality parameter time series data accident detection method |
| CN109711590A (en) * | 2017-10-26 | 2019-05-03 | 中国电信股份有限公司 | Fishery water quality analyzing monitoring method, device and system |
| CN112651665A (en) * | 2021-01-14 | 2021-04-13 | 浙江鸿程计算机系统有限公司 | Surface water quality index prediction method and device based on graph neural network |
Non-Patent Citations (1)
| Title |
|---|
| 冯民权 等: "BP 网络马尔可夫模型的水质预测研究———基于灰色关联分析", 《自然灾害学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113781019A (en) * | 2021-11-12 | 2021-12-10 | 中国环境监测总站 | Method and device for automatically screening and fusing monitoring data |
| CN116308952A (en) * | 2023-03-08 | 2023-06-23 | 浪潮智慧科技有限公司 | Water quality monitoring method and device based on unmanned ship |
| CN116308952B (en) * | 2023-03-08 | 2023-09-22 | 浪潮智慧科技有限公司 | Water quality monitoring method and device based on unmanned ship |
| CN116500240A (en) * | 2023-06-21 | 2023-07-28 | 江西索立德环保服务有限公司 | Soil environment quality monitoring method, system and readable storage medium |
| CN116500240B (en) * | 2023-06-21 | 2023-12-29 | 江西索立德环保服务有限公司 | Soil environment quality monitoring method, system and readable storage medium |
| CN117524497A (en) * | 2023-10-26 | 2024-02-06 | 曙光云计算集团有限公司 | Data processing method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113409167B (en) | 2021-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113409167B (en) | Water quality abnormity analysis method and device | |
| CN113496104B (en) | Precipitation prediction correction method and system based on deep learning | |
| CN111310968A (en) | LSTM neural network circulation hydrological forecasting method based on mutual information | |
| CN110686633B (en) | Landslide displacement prediction method and device and electronic equipment | |
| CN108399248A (en) | A kind of time series data prediction technique, device and equipment | |
| CN111288973B (en) | Method and device for obtaining flow rate of sea surface, computer equipment and storage medium | |
| CN115439654B (en) | Method and system for finely dividing weakly supervised farmland plots under dynamic constraint | |
| CN114037184A (en) | Method, apparatus, medium, device, and program product for predicting profit evaluation index | |
| CN115545334A (en) | Land use type prediction method, land use type prediction device, electronic device, and storage medium | |
| CN113487223B (en) | Risk assessment method and system based on information fusion | |
| CN117371337B (en) | Water conservancy model construction method and system based on digital twin | |
| CN114881343A (en) | Short-term load prediction method and device of power system based on feature selection | |
| WO2021104216A1 (en) | Method and device for evaluating device model trend similarity | |
| CN111275059B (en) | Image processing method and device and computer readable storage medium | |
| Pasaribu et al. | Rainfall forecast of merauke using autoregressive integrated moving average model | |
| CN114911788B (en) | Data interpolation method and device and storage medium | |
| CN116740586A (en) | Hail identification method, hail identification device, electronic equipment and computer readable storage medium | |
| CN116364203A (en) | Water quality prediction method, system and device based on deep learning | |
| CN113505039A (en) | Communication fault analysis method, device and system | |
| CN115310648A (en) | Medium-and-long-term wind power combination prediction method based on multi-meteorological variable model identification | |
| CN114169646A (en) | Water bloom prediction method, device, electronic equipment and computer readable storage medium | |
| Kesavavarthini et al. | Bias correction of CMIP6 simulations of precipitation over Indian monsoon core region using deep learning algorithms | |
| CN112949947A (en) | Power failure early warning method and system based on convolution long-term and short-term memory network | |
| CN113553754A (en) | Memory, fire risk prediction model construction method, system and device | |
| CN117671603B (en) | Multi-dimensional environment monitoring method for power transmission line of three-dimensional ranging device |
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 |