CN110597934A - Method and device for generating water quality information map - Google Patents
Method and device for generating water quality information map Download PDFInfo
- Publication number
- CN110597934A CN110597934A CN201910717544.2A CN201910717544A CN110597934A CN 110597934 A CN110597934 A CN 110597934A CN 201910717544 A CN201910717544 A CN 201910717544A CN 110597934 A CN110597934 A CN 110597934A
- Authority
- CN
- China
- Prior art keywords
- water quality
- prediction model
- data
- prediction
- map
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 324
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000012544 monitoring process Methods 0.000 claims abstract description 88
- 238000013441 quality evaluation Methods 0.000 claims abstract description 34
- 238000012549 training Methods 0.000 claims description 27
- 230000008569 process Effects 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 15
- 238000001303 quality assessment method Methods 0.000 claims description 10
- ZAMOUSCENKQFHK-UHFFFAOYSA-N Chlorine atom Chemical compound [Cl] ZAMOUSCENKQFHK-UHFFFAOYSA-N 0.000 claims description 9
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 claims description 9
- 239000000460 chlorine Substances 0.000 claims description 9
- 229910052801 chlorine Inorganic materials 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 9
- -1 conductivity Substances 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 7
- 230000015654 memory Effects 0.000 claims description 6
- 230000006403 short-term memory Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 230000007787 long-term memory Effects 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims 1
- 230000008859 change Effects 0.000 abstract description 8
- 238000010219 correlation analysis Methods 0.000 abstract description 4
- 230000007613 environmental effect Effects 0.000 abstract description 2
- 239000006185 dispersion Substances 0.000 description 9
- 238000012545 processing Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000002159 abnormal effect Effects 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 4
- 238000010606 normalization Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000001988 toxicity Effects 0.000 description 2
- 231100000419 toxicity Toxicity 0.000 description 2
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000008961 swelling Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Databases & Information Systems (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Public Health (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for generating a water quality information map. The method comprises the steps of setting a plurality of monitoring points on a map, then obtaining water quality information data of the monitoring points, constructing a water quality prediction model, obtaining water quality prediction data of the monitoring points according to the water quality information data and the water quality prediction model, displaying the water quality prediction data on the map, and generating a water quality information map to predict the water quality of a monitoring area. The water quality monitoring method comprises the steps of establishing a nonlinear relation water quality prediction model containing a plurality of parameters through water quality evaluation information monitoring data and combining correlation analysis and influence relation among multiple parameters of water quality, predicting water quality change in advance based on the water quality prediction model, and visually displaying a prediction result on a water quality information map so as to eliminate water quality risk hidden danger in advance and effectively guarantee water quality safety. Can be widely applied to the water quality monitoring fields such as environmental water affairs, water conservancy monitoring and the like.
Description
Technical Field
The invention relates to the field of water quality prediction, in particular to a method and a device for generating a water quality information map.
Background
Nowadays, people have higher and higher requirements on the quality of supplied water, and the guarantee of water quality safety is always a problem worthy of research. Generally speaking, the water quality evaluation parameters mainly related to the water quality monitoring in real time include pH, turbidity, residual chlorine, ammonia nitrogen, conductivity, water temperature, biotoxicity index and the like. How to reveal the influence relationship among water quality factors according to the existing monitoring data by combining with the correlation analysis among multiple parameters of a water body, and meanwhile, the determination of the nonlinear relationship among the multiple parameters is one of the difficulties and the key points of water quality data prediction modeling, the modeling difficulty is larger and more complex when the parameters are more, and larger uncertainty is brought to the final modeling result. In addition, the existing water quality monitoring can only display the current water quality monitoring information of monitoring points, and the large-scale water quality change trend of a monitoring area cannot be predicted so as to prevent.
Therefore, it is necessary to provide a water quality prediction model in combination with water quality evaluation parameters, and generate a water quality information map according to the prediction result to predict the water quality of the monitored area.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art. Therefore, the invention aims to provide a method and a device for establishing a water quality prediction model by combining water quality evaluation parameters and generating a water quality information map according to the prediction result.
The technical scheme adopted by the invention is as follows:
in a first aspect, the present invention provides a method for generating a water quality information map, comprising:
setting a plurality of monitoring points on a map;
acquiring water quality information data of the monitoring points, wherein the water quality information data comprises: time series data for water quality assessment parameters, the water quality assessment parameters including one or more of: pH, turbidity, residual chlorine, ammonia nitrogen, conductivity, water temperature and biotoxicity index;
and (3) carrying out monitoring point water quality prediction: constructing a water quality prediction model, and obtaining water quality prediction data of the monitoring point according to the water quality information data and the water quality prediction model, wherein the water quality prediction model comprises: a water quality grey prediction model and an information prediction model;
and displaying the water quality prediction data on the map to generate the water quality information map.
Further, the water quality gray prediction model is a differential equation of n-order x variables, and the process of constructing the water quality gray prediction model specifically comprises the following steps:
acquiring water quality information data of the monitoring points;
establishing a water quality variable selection model according to the water quality information data;
and establishing the water quality gray prediction model according to the water quality variable selection model.
Further, the process of monitoring point water quality prediction is as follows:
constructing the information prediction model based on the long-term and short-term memory neural network;
acquiring time sequence data of the water quality evaluation parameters of the monitoring points as a prediction training sample set;
acquiring a water quality evaluation parameter grey prediction value output by the water quality grey prediction model;
inputting the grey predicted value of the water quality evaluation parameter as a test sample set into the information prediction model;
performing parameter training on the information prediction model according to the prediction training sample set and the test sample set to obtain a trained information prediction model;
and obtaining the water quality prediction data of the monitoring point according to the output of the information prediction model.
Further, the method further comprises the step of carrying out data preprocessing on the prediction training sample set and the test sample set.
Further, the method also comprises the following steps: and when the water quality prediction data exceeds the water quality index evaluation standard range, performing abnormity alarm.
In a second aspect, the present invention also provides an apparatus for generating a water quality information map, comprising:
and a monitoring point setting module: the monitoring system is used for setting a plurality of monitoring points on a map;
the module for acquiring the data of the monitoring points comprises: the monitoring point water quality information data acquisition device is used for acquiring the water quality information data of the monitoring point, wherein the water quality information data comprises: time series data for water quality assessment parameters, the water quality assessment parameters including one or more of: pH, turbidity, residual chlorine, ammonia nitrogen, conductivity, water temperature, biotoxicity index and the like;
a monitoring point water quality prediction module is carried out: the water quality prediction model is used for constructing a water quality prediction model and obtaining water quality prediction data of the monitoring point according to the water quality information data and the water quality prediction model, and the water quality prediction model comprises: a water quality grey prediction model and an information prediction model;
a water quality information map generation module: and the water quality prediction data is displayed on the map to generate the water quality information map.
In a third aspect, the invention also provides a water quality information map generated by the method for generating a water quality information map according to any one of the first aspect.
In a fourth aspect, the present invention provides an apparatus for generating a water quality information map, comprising:
at least one processor, and a memory communicatively coupled to the at least one processor;
wherein the processor is adapted to perform the method of any of the first aspects by invoking a computer program stored in the memory.
In a fifth aspect, the present invention provides a computer-readable storage medium having stored thereon computer-executable instructions for causing a computer to perform the method of any of the first aspects.
The invention has the beneficial effects that:
according to the invention, a plurality of monitoring points are set on a map, then water quality information data of the monitoring points are obtained, a water quality prediction model is constructed, water quality prediction data of the monitoring points are obtained according to the water quality information data and the water quality prediction model, the water quality prediction data are displayed on the map, and a water quality information map is generated to predict the water quality of a monitoring area. The water quality monitoring method comprises the steps of establishing a nonlinear relation water quality prediction model containing a plurality of parameters through water quality evaluation information monitoring data and combining correlation analysis and influence relation among multiple parameters of water quality, predicting water quality change in advance based on the water quality prediction model, and visually displaying a prediction result on a water quality information map so as to eliminate water quality risk hidden danger in advance and effectively guarantee water quality safety.
Can be widely applied to the water quality monitoring fields such as environmental water affairs, water conservancy monitoring and the like.
Drawings
FIG. 1 is a flow chart of an embodiment of a method for generating a water quality information map according to the present invention;
FIG. 2 is a schematic diagram of a training process of a water quality gray prediction model according to an embodiment of the method for generating a water quality information map;
FIG. 3 is a schematic process diagram of an information prediction model according to an embodiment of the method for generating a water quality information map according to the present invention;
FIG. 4 is a block diagram of a water quality prediction model according to an embodiment of the method for generating a water quality information map of the present invention;
fig. 5 is a block diagram showing a configuration of an apparatus for generating a water quality information map according to an embodiment of the present invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will be made with reference to the accompanying drawings. It is obvious that the drawings in the following description are only some examples of the invention, and that for a person skilled in the art, other drawings and embodiments can be derived from them without inventive effort.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
The first embodiment is as follows:
an embodiment of the present invention provides a method for generating a water quality information map, and fig. 1 is a flowchart illustrating an implementation of the method for generating a water quality information map according to the embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
s1: a plurality of monitoring points are set on a map, wherein the distribution of the monitoring points needs to be adjusted according to actual monitoring requirements, so that the monitoring range of the monitoring points can completely cover the map range to be monitored.
S2: acquiring water quality information data of each monitoring point, wherein in the embodiment, the water quality information data comprises: and the time sequence data of the water quality evaluation parameters refers to collecting real-time measurement values selected as the water quality evaluation parameters at certain time intervals according to time continuity.
Wherein, the water quality evaluation parameters are a series of parameters influencing water quality obtained in the actual research process, and comprise one or more of the following parameters: pH, turbidity, residual chlorine, ammonia nitrogen, conductivity, water temperature, biotoxicity index and the like.
S3: and (3) carrying out monitoring point water quality prediction: a water quality prediction model is constructed, and water quality prediction data of a monitoring point is obtained according to the water quality information data and the water quality prediction model, wherein in the embodiment, the water quality prediction model comprises the following steps: a water quality grey prediction model and an information prediction model.
S4: and displaying the water quality prediction data on a map to generate a water quality information map, wherein the water quality prediction data of the monitoring points can be uploaded to a server in a wireless or wired transmission mode and acquired by a water quality information map system.
The water quality information map can visually display the water quality prediction data of each monitoring point, the water quality monitoring information is obtained through the map of the monitored water area range, the water quality prediction data is presented in the form of an electronic map, the monitoring points can be automatically positioned, the water quality prediction result can be searched and inquired, and a user can conveniently know the water quality prediction conditions of the area where the water quality prediction data is located and the area concerned in real time.
S5: and when the water quality prediction data exceeds the water quality index evaluation standard range, performing abnormity alarm. The water quality prediction data can be visually displayed on the water quality information map, so that the water quality prediction data can be compared and analyzed with a water quality index evaluation standard range, if the water quality index evaluation standard range is exceeded, the possibility of occurrence of a water quality risk event is prompted, and when the water quality exceeding event is predicted, related personnel are informed by an alarm, so that related measures can be taken in time, and the occurrence of the water quality risk event is prevented. Alternative alarm modes include, but are not limited to, the following: screen reminding, short message, mail and the like.
In a specific embodiment, the water quality index evaluation standard range is set as follows, and an abnormal alarm is prompted when the water quality index evaluation standard range is exceeded.
For example: pH: 6.5-8.5;
turbidity: less than 1.0 NTU;
comprehensive toxicity index of water quality: greater than 60 (index value range 0-100).
Where NTU refers to the scattering turbidity unit, indicating that the instrument measures the scattered light intensity at a 90 angle to the incident light. Specifically, in step S3, a method of constructing the water quality gray prediction model is as follows.
Specifically, in step S3, a method of constructing the water quality gray prediction model is as follows.
Some water quality evaluation parameters can change along with the passage of time on the way that water flows through a water supply pipe network, particularly the water quality at the tail end of some pipe networks, and the parameter change is more obvious, so that a water quality gray prediction model of the embodiment can be established according to the water quality evaluation parameters and is recorded as GM (n, x), the water quality gray prediction model is an n-order differential equation with x variables, and the process of constructing the water quality gray prediction model specifically comprises the following steps:
s311: acquiring water quality information data of a monitoring point;
s312: establishing a water quality variable selection model according to the water quality information data;
s313: and selecting a model according to the water quality variable to establish a water quality gray prediction model.
In this embodiment, the water quality variable selection model may be selected as follows: an Adaptive _ Lasso variable selection model (a self-Adaptive LASSO estimation algorithm) is adopted, and water quality evaluation parameters which are high in correlation degree and can be used for water quality monitoring are gradually screened through significance test of a model coefficient, wherein the water quality evaluation parameters can be one or more of water quality evaluation parameters such as pH, turbidity, residual chlorine, ammonia nitrogen, conductivity, water temperature and biotoxicity index.
In this embodiment, a standard multiple linear regression model is established as the water quality variable selection model, and is expressed as:
Y＝Xβ+ε (1)
wherein Y is an interpreted variable of dimension n x 1,is an explanatory variable data matrix of n x p, epsilon is a residual vector, beta (beta)1,β2,...,βp)TIs an unknown parameter model in p x 1 dimension.
Let ε be an independently distributed random variable with N samples, each being (x)1,y1)，(x2,y2)…(xn,yn) Acquiring water quality information data of a monitoring point, and after data preprocessing is completed, establishing a water quality Adaptive _ Lasso variable selection model, which is expressed as:
wherein the content of the first and second substances,is an Adaptive _ Lasso estimate, λ represents a non-negative regularization parameter,for the penalty term, i.e. the weight change,in order to be the weight, the weight is,is an initial estimation value of the jth parameter, and is generally a coefficient obtained by a common least square method.
On the basis of the water quality variable selection model, a water quality gray prediction model, i.e., GM (n, x), is established, and the process of deriving GM (1,1) will be described as an example.
Assuming that the selected water quality evaluation parameter is one, the time series data is expressed as: x(0)＝{X(0)(i) I is 1,2, … … n, and is a non-negative and monotonous original sequence data, and in order to ensure the feasibility of performing water quality gray prediction, the original sequence data needs to be subjected to a grade ratio test, and the grade ratio of the original sequence data is calculated and expressed as:
where λ (k) denotes the step ratio, if all step ratios fall within the soluble coverage Θ (e)-2/(n+1),e2/(n+2)) In the interior, a water quality gray prediction model can be established, otherwise, for X(0)Performing a translational change such that: y is(0)＝X(0)+ C, where C is the translation value.
The process of establishing the GM (1,1) model is as follows:
1) to X(0)Performing an accumulation to obtain an accumulation sequence, which is expressed as:
X(1)＝{X(1)(k)},k＝1,2,……n (5)
2) to X(1)The following differential equation of heterogeneity was established to obtain the GM (1,1) model, expressed as:
3) solving the differential equation to obtain the following predicted values:
4) since the GM (1,1) model obtains the first accumulated value, the data obtained by the GM (1,1) model is usedIs reduced intoNamely X(0)The water quality gray prediction model is expressed as:
after the model is established, residual error detection is needed to judge whether the model meets the general requirements, and the residual error is expressed as:
in this embodiment, if all | epsilon (k) | <0.1, it is considered that a higher requirement is reached; if all | ε (k) | <0.2|, the general requirement is considered to be met.
Fig. 2 is a schematic diagram of a training process of the water quality gray prediction model in this embodiment. The method specifically comprises the following steps:
s321: and constructing a water quality gray prediction model obtained in the process.
S322: acquiring water quality information data of each monitoring point, preprocessing the water quality information data, and training the preprocessed data through a variable selection model to be used as a gray prediction training sample set, wherein the method specifically comprises the following steps: and acquiring time series data of the water quality evaluation parameters of the target area, performing data preprocessing on the data, cleaning and removing invalid data to obtain original available training data serving as a gray prediction training sample set.
S323: and performing parameter training on the water quality gray prediction model according to the gray prediction training sample set to obtain the trained water quality gray prediction model. The method specifically comprises the following steps: and training the grey prediction training sample set through the water quality grey prediction model to optimize parameters of the water quality grey prediction model, verifying whether the parameters are reasonable or not, and optimizing the parameters to obtain relatively optimal model parameter values.
Further, in step S3, the information prediction model is constructed as follows.
In this embodiment, the information prediction model is optionally based on a long-term short-term memory neural network (LSTM) model, and performs water quality analysis prediction according to the self water quality evaluation parameter time-series data of the same monitoring point. It is understood that the present embodiment may also adopt other neural network models to implement the information prediction model.
LSTM, known as Long Short-Term Memory, is a time-recursive Neural Network suitable for processing and predicting important events with relatively Long intervals and delays in time series, and is essentially a special RNN Network, a Recurrent Neural Network (rcn), generally, RNN includes the following three characteristics:
1) an output can be generated at each time node, and the connection between the hidden units is cyclic;
2) the method can generate an output at each time node, and the output at the time node is only circularly connected with a hidden unit of the next time node;
3) contains hidden units with cyclic links and is capable of processing sequence data and outputting a single prediction.
RNNs, when dealing with long term dependencies (nodes that are far apart in time series), suffer from gradient vanishing (high probability) or gradient swelling (low probability) problems due to the multiple multiplication of the jacobian matrix involved in calculating the connections between the far apart nodes. It is therefore necessary to select a threshold RNN network, of which the LSTM is one. LSTM avoids the problems of gradient explosion and gradient disappearance in standard RNNs and learns faster by allowing the weighting coefficients between connections to be changed at different times and allowing the network to forget what information has currently accumulated.
In this embodiment, as shown in fig. 3, a process diagram of the information prediction model is shown.
S331: and constructing an information prediction model based on the long-term and short-term memory neural network and initializing the information prediction model.
S332: and acquiring time series data of the water quality evaluation parameters of each monitoring point, and performing data preprocessing on the time series data to serve as a prediction training sample set.
Optionally, in a specific embodiment, the pH value is taken as a water quality evaluation parameter to be measured, and other water quality evaluation parameters are taken as parameters to be selected, and then the data is preprocessed according to requirements. When other water quality evaluation parameters (such as turbidity, residual chlorine, ammonia nitrogen, biological toxicity index and the like) are selected for prediction, the steps are similar to the steps for predicting by selecting the pH value.
The data preprocessing in this embodiment includes: outlier processing, null processing, data normalization, etc., advantageously results in normalized valid data, such as in one embodiment:
abnormal value processing: performing emptying treatment or smoothing treatment on the obviously abnormal values, such as the values with pH higher than 14 or pH lower than 0, which belong to abnormal values;
and (4) null value processing: optionally, an algorithm such as inputter or lagrange is used to interpolate the null value.
Data normalization: and adopting dispersion standardization treatment.
S333: and correspondingly, when the information prediction model selects the pH value as the water quality evaluation parameter, the input of the water quality grey prediction model also selects the pH value as the water quality evaluation parameter.
S334: and (4) taking the grey prediction value of the water quality evaluation parameter as a test sample set, and inputting the test sample set into the information prediction model.
S335: and performing data preprocessing on the prediction training sample set and the test sample set, and then performing parameter training on the information prediction model to obtain the trained information prediction model. Fitting is carried out on the data of the test sample set and the data of the prediction training sample set, the fitting times are determined according to requirements, and insufficient fitting degree or overfitting needs to be prevented.
S336: and obtaining water quality prediction data of the monitoring point according to the output of the information prediction model. Because different water quality evaluation parameters are selected and different dimensions are often provided, the difference between numerical values is large, and the result of data analysis is influenced without processing. Therefore, in order to eliminate the influence of dimension and value range differences between indexes, data standardization processing is required, for example, data is scaled to exist in a designated area, which is convenient for comprehensive analysis.
Optionally, in this embodiment, the data is subjected to dispersion normalization, that is, after the original data is subjected to linear transformation, the data is mapped between [0 and 1 ]. It should be noted that the input data is subjected to dispersion standardization processing, and during output, corresponding dispersion standardization reduction needs to be performed to meet the characteristics of actual data. The specific operation is as follows:
dispersion standardization treatment:
X*＝(Xoriginal value-Xmin)/(Xmax-Xmin) (10)
Dispersion normalized reduction:
Xoriginal value＝X*(Xmax-Xmin)+Xmin (11)
Wherein, X*The value after dispersion standardization is in the range of 0,1]，XOriginal valueFor any sample data, XmaxIs the maximum value of the sample data, XminIs the minimum value of sample data, Xmax-XminIs a very poor sample data.
In one embodiment, the LSTM model is optionally constructed with Keras, a high-level neural network API, written by Python, and based on the tenserflow, thano, and CNTK backend implementations.
As shown in fig. 4, a block diagram of the water quality prediction model according to the present embodiment is shown. It can be seen that the water quality prediction model in this embodiment includes: a water quality grey prediction model and an information prediction model (LSTM model). The water quality grey prediction model and the information prediction model are established and connected, parameters of the two models are verified in the training process, and the output of the water quality grey prediction model is used as a test sample set of the information prediction model to jointly form the water quality prediction model.
Wherein, construct quality of water grey prediction model, include: time sequence data of monitoring points based on water quality evaluation parameters are obtained, a sample set which can be originally used for gray prediction training is obtained, then a model is selected through Adaptive _ Lasso variables to process the time sequence set, and a group of correlated water quality gray prediction models are established for characteristic indexes.
Wherein, constructing an information prediction model (LSTM model) comprises: acquiring time series data of water quality evaluation parameters of monitoring points as a prediction training sample set, using a water quality evaluation parameter grey prediction value output by a water quality grey prediction model as a test sample set, performing data preprocessing (such as dispersion standardization) on the prediction training sample set and the test sample set, and then training an information prediction model.
And verifying whether the parameters of the water quality prediction model reach the optimal values, otherwise, adjusting and retraining the parameters until the parameters are optimal, and then performing anti-dispersion standardization on the output data and outputting the data as the water quality prediction data of the monitoring points.
In the embodiment, a plurality of monitoring points are set on the map, then water quality information data of the monitoring points are obtained, a water quality prediction model is constructed, water quality prediction data of the monitoring points are obtained according to the water quality information data and the water quality prediction model, the water quality prediction data are displayed on the map, and a water quality information map is generated to predict the water quality.
Example two:
the embodiment provides a device for generating a water quality information map, which is used for executing the method shown in the first embodiment. As shown in fig. 5, the block diagram of the apparatus for generating a water quality information map according to the present embodiment includes:
setting a monitoring point module 10: the monitoring system is used for setting a plurality of monitoring points on a map;
monitor point data acquisition module 20: the monitoring point water quality information data acquisition device is used for acquiring the water quality information data of the monitoring point, wherein the water quality information data comprises: time series data for water quality assessment parameters, the water quality assessment parameters including one or more of: pH, turbidity, residual chlorine, ammonia nitrogen, conductivity, water temperature and biotoxicity index;
monitoring point water quality prediction module 30: the water quality prediction model is used for constructing a water quality prediction model and obtaining water quality prediction data of the monitoring point according to the water quality information data and the water quality prediction model, and the water quality prediction model comprises: a water quality grey prediction model and an information prediction model;
the water quality information map generation module 40: and the water quality prediction data is displayed on the map to generate the water quality information map.
Example three:
the embodiment provides a water quality information map, which is generated by the method as described in the first embodiment, and has a water quality prediction function and an alarm function, the water quality prediction is realized based on a water quality prediction model, the water quality prediction result of a monitoring point can be displayed on the map, and when a water quality exceeding event is predicted, an alarm is provided to inform relevant personnel, so that the water quality safety is effectively guaranteed.
In addition, the present invention also provides an apparatus for generating a water quality information map, comprising:
at least one processor, and a memory communicatively coupled to the at least one processor; wherein the processor is configured to perform the method according to embodiment one by calling the computer program stored in the memory.
In addition, the present invention also provides a computer-readable storage medium, which stores computer-executable instructions for causing a computer to perform the method according to the first embodiment.
According to the invention, through water quality evaluation information monitoring data, in combination with correlation analysis and influence relation among multiple parameters of water quality, a nonlinear relation water quality prediction model containing multiple parameters is established, water quality change can be predicted in advance based on the water quality prediction model, and the prediction result is visually displayed on a water quality information map, so that water quality risk hidden danger can be eliminated in advance, and water quality safety is effectively guaranteed.
The above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same, although the present invention is described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (9)
1. A method for generating a water quality information map, comprising:
setting a plurality of monitoring points on a map;
acquiring water quality information data of the monitoring points, wherein the water quality information data comprises: time series data for water quality assessment parameters, the water quality assessment parameters including one or more of: pH, turbidity, residual chlorine, ammonia nitrogen, conductivity, water temperature and biotoxicity index;
and (3) carrying out monitoring point water quality prediction: constructing a water quality prediction model, and obtaining water quality prediction data of the monitoring point according to the water quality information data and the water quality prediction model, wherein the water quality prediction model comprises: a water quality grey prediction model and an information prediction model;
and displaying the water quality prediction data on the map to generate the water quality information map.
2. The method for generating the water quality information map according to claim 1, wherein the water quality gray prediction model is a differential equation with n-order and x-variable, and the process of constructing the water quality gray prediction model specifically comprises:
acquiring water quality information data of the monitoring points;
establishing a water quality variable selection model according to the water quality information data;
and establishing the water quality gray prediction model according to the water quality variable selection model.
3. The method for generating the water quality information map according to claim 2, wherein the process of predicting the water quality of the monitoring point comprises the following steps:
constructing the information prediction model based on the long-term and short-term memory neural network;
acquiring time sequence data of the water quality evaluation parameters of the monitoring points as a prediction training sample set;
acquiring a water quality evaluation parameter grey prediction value output by the water quality grey prediction model;
inputting the grey predicted value of the water quality evaluation parameter as a test sample set into the information prediction model;
performing parameter training on the information prediction model according to the prediction training sample set and the test sample set to obtain a trained information prediction model;
and obtaining the water quality prediction data of the monitoring point according to the output of the information prediction model.
4. The method of claim 3, further comprising preprocessing data of the predictive training sample set and the test sample set.
5. The method for generating a water quality information map according to any one of claims 1 to 4, further comprising an abnormality alarm: and when the water quality prediction data exceeds the water quality index evaluation standard range, performing abnormity alarm.
6. An apparatus for generating a water quality information map, comprising:
and a monitoring point setting module: the monitoring system is used for setting a plurality of monitoring points on a map;
the module for acquiring the data of the monitoring points comprises: the monitoring point water quality information data acquisition device is used for acquiring the water quality information data of the monitoring point, wherein the water quality information data comprises: time series data for water quality assessment parameters, the water quality assessment parameters including one or more of: pH, turbidity, residual chlorine, ammonia nitrogen, conductivity, water temperature and biotoxicity index;
a monitoring point water quality prediction module is carried out: the water quality prediction model is used for constructing a water quality prediction model and obtaining water quality prediction data of the monitoring point according to the water quality information data and the water quality prediction model, and the water quality prediction model comprises: a water quality grey prediction model and an information prediction model;
a water quality information map generation module: and the water quality prediction data is displayed on the map to generate the water quality information map.
7. A water quality information map generated by the method of generating a water quality information map according to any one of claims 1 to 5.
8. An apparatus for generating a water quality information map, comprising:
at least one processor; and a memory communicatively coupled to the at least one processor;
wherein the processor is adapted to perform the method of any one of claims 1 to 5 by invoking a computer program stored in the memory.
9. A computer-readable storage medium having stored thereon computer-executable instructions for causing a computer to perform the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910717544.2A CN110597934A (en) | 2019-08-05 | 2019-08-05 | Method and device for generating water quality information map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910717544.2A CN110597934A (en) | 2019-08-05 | 2019-08-05 | Method and device for generating water quality information map |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110597934A true CN110597934A (en) | 2019-12-20 |
Family
ID=68853535
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910717544.2A Pending CN110597934A (en) | 2019-08-05 | 2019-08-05 | Method and device for generating water quality information map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110597934A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111524030A (en) * | 2020-04-22 | 2020-08-11 | 常州市环境科学研究院 | Plain river network area water environment monitoring early warning and safety guarantee management system |
| CN114417740A (en) * | 2022-03-30 | 2022-04-29 | 青岛杰瑞工控技术有限公司 | Deep sea breeding situation sensing method |
| CN115879600A (en) * | 2022-11-15 | 2023-03-31 | 广东省水利水电科学研究院 | River surge health evaluation and analysis method, system, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101825622A (en) * | 2010-04-02 | 2010-09-08 | 浙江浙大中控信息技术有限公司 | Water quality prediction method and device |
| CN104792959A (en) * | 2015-05-08 | 2015-07-22 | 博乐宝科技有限公司 | Electronic map system for displaying water quality information and display method of electronic map system |
| CN107679657A (en) * | 2017-09-28 | 2018-02-09 | 黑龙江省科学院火山与矿泉研究所 | Water quality prediction method for mineral spring |
| CN107688871A (en) * | 2017-08-18 | 2018-02-13 | 中国农业大学 | A kind of water quality prediction method and device |
-
2019
- 2019-08-05 CN CN201910717544.2A patent/CN110597934A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101825622A (en) * | 2010-04-02 | 2010-09-08 | 浙江浙大中控信息技术有限公司 | Water quality prediction method and device |
| CN104792959A (en) * | 2015-05-08 | 2015-07-22 | 博乐宝科技有限公司 | Electronic map system for displaying water quality information and display method of electronic map system |
| CN107688871A (en) * | 2017-08-18 | 2018-02-13 | 中国农业大学 | A kind of water quality prediction method and device |
| CN107679657A (en) * | 2017-09-28 | 2018-02-09 | 黑龙江省科学院火山与矿泉研究所 | Water quality prediction method for mineral spring |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111524030A (en) * | 2020-04-22 | 2020-08-11 | 常州市环境科学研究院 | Plain river network area water environment monitoring early warning and safety guarantee management system |
| CN114417740A (en) * | 2022-03-30 | 2022-04-29 | 青岛杰瑞工控技术有限公司 | Deep sea breeding situation sensing method |
| CN115879600A (en) * | 2022-11-15 | 2023-03-31 | 广东省水利水电科学研究院 | River surge health evaluation and analysis method, system, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110597934A (en) | Method and device for generating water quality information map | |
| Russo et al. | Air quality prediction using optimal neural networks with stochastic variables | |
| CN111476278B (en) | Intelligent gas concentration detection system | |
| Tang et al. | Methodologies for uncertainty management in prognostics | |
| CN115169479A (en) | Remote monitoring method, system and storage medium for sewage treatment process | |
| Human et al. | Shewhart-type control charts for variation in phase I data analysis | |
| Vigier et al. | An application of OWA operators in fuzzy business diagnosis | |
| McCulloch et al. | Calibrating agent-based models using uncertainty quantification methods | |
| CN115099512A (en) | Freshwater fish culture intelligent management system and management method | |
| CN112215410B (en) | Power load prediction method based on improved deep learning | |
| CN114418183A (en) | Livestock and poultry health sign big data internet of things detection system | |
| CN113240006A (en) | Method and device for monitoring wastewater discharge, electronic equipment and storage medium | |
| CN117540336A (en) | Time sequence prediction method and device and electronic equipment | |
| Scandol | Use of quality control methods to monitor the status of fish stocks | |
| Eo et al. | Deep learning framework with essential pre-processing techniques for improving mixed-gas concentration prediction | |
| CN112819244B (en) | Meteorological factor-based RF-HW water quality index hybrid prediction method | |
| CN114390376B (en) | Fire big data remote detection and early warning system | |
| CN114841416A (en) | Long-short term memory network-based prediction method for amino acid nitrogen in soy sauce fermentation process | |
| Wooldredge | Path Analysis | |
| CN114417242A (en) | Big data detection system for livestock and poultry activity information | |
| CN113468823A (en) | Optical module damage detection method and system based on machine learning | |
| Yu et al. | Dynamic Sampling Policy for In Situ and Online Measurements Data Fusion in a Policy Network | |
| CN112836842A (en) | Watershed water environment quality prediction method and system based on source-sink risk analysis | |
| JP7481691B2 (en) | Quality evaluation device, teaching data creation method, quality evaluation processing program, and quality evaluation method | |
| Rosqvist | Simulation and multi‐attribute utility modelling of life cycle profit |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191220 |
|
| RJ01 | Rejection of invention patent application after publication |