CN117786584A - Big data analysis-based method and system for monitoring and early warning of water source pollution in animal husbandry - Google Patents
Big data analysis-based method and system for monitoring and early warning of water source pollution in animal husbandry Download PDFInfo
- Publication number
- CN117786584A CN117786584A CN202410210815.6A CN202410210815A CN117786584A CN 117786584 A CN117786584 A CN 117786584A CN 202410210815 A CN202410210815 A CN 202410210815A CN 117786584 A CN117786584 A CN 117786584A
- Authority
- CN
- China
- Prior art keywords
- data
- nitrogen
- phosphorus concentration
- monitoring
- point
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 99
- 238000000034 method Methods 0.000 title claims abstract description 71
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 65
- 238000007405 data analysis Methods 0.000 title claims abstract description 30
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims abstract description 168
- 230000008859 change Effects 0.000 claims abstract description 127
- 238000005070 sampling Methods 0.000 claims abstract description 96
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims abstract description 85
- 229910052698 phosphorus Inorganic materials 0.000 claims abstract description 85
- 239000011574 phosphorus Substances 0.000 claims abstract description 85
- 229910052757 nitrogen Inorganic materials 0.000 claims abstract description 84
- YUWBVKYVJWNVLE-UHFFFAOYSA-N [N].[P] Chemical compound [N].[P] YUWBVKYVJWNVLE-UHFFFAOYSA-N 0.000 claims abstract description 64
- 230000002159 abnormal effect Effects 0.000 claims abstract description 42
- 238000013528 artificial neural network Methods 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000012216 screening Methods 0.000 claims description 14
- 238000010606 normalization Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 abstract description 16
- 238000000746 purification Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000005856 abnormality Effects 0.000 description 5
- 238000004140 cleaning Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 244000144972 livestock Species 0.000 description 2
- 238000011946 reduction process Methods 0.000 description 2
- 239000010865 sewage Substances 0.000 description 2
- 239000002351 wastewater Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 125000001477 organic nitrogen group Chemical group 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
Classifications
-
- 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
- Y02A20/20—Controlling water pollution; Waste water treatment
Landscapes
- Investigating Or Analyzing Non-Biological Materials By The Use Of Chemical Means (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a method and a system for monitoring and early warning of pollution of water sources in animal husbandry based on big data analysis. The method utilizes the difference of the significant change points between different sampling periods to determine the change significance degree of each significant change point. And further analyzing the data value and the data change trend of each data point on the nitrogen-phosphorus concentration curve, obtaining the significant coefficient of each data point by combining the corresponding change significant degree, determining abnormal data points and adjusting the data values of the abnormal data points to obtain the optimized nitrogen-phosphorus concentration curve. And obtaining characteristic data of the nitrogen and phosphorus concentration through dimension reduction for network training. And carrying out pollution grade identification and early warning by using the trained pollution early warning neural network. According to the invention, the influence of abnormal data points in the acquired data is eliminated, so that the referential property of the feature data after the dimension reduction is improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a system for monitoring and early warning of pollution of water sources in animal husbandry based on big data analysis.
Background
In the large-scale cultivation process of the animal husbandry, the daily wastewater for cleaning contains a large amount of organic phosphorus and organic nitrogen, and ecological balance can be influenced if the purification treatment is improper or the wastewater is directly discharged, so that ecological pollution is caused to the water environment, and therefore, the pollution of the water source around the animal husbandry needs to be monitored and pre-warned to a certain extent, and the pollution of the water source around the animal husbandry by the water for the animal husbandry is avoided.
In the existing pollution monitoring and early warning method, nitrogen and phosphorus concentration data acquired by a water quality monitoring device can be identified through a neural network, so that the pollution level is determined. In the practical application process, in order to more accurately evaluate the treatment of water source pollution in the current animal husbandry, corresponding water quality monitoring data exist in a plurality of positions such as a water source position, a purification area position and the like, so that the condition that the water quality monitoring data are more complex in dimension is caused, the data condition is unfavorable for training and identifying a neural network, certain dimension reduction processing is needed for the collected water quality monitoring data, and characteristic data are extracted for training and identifying the neural network. The existing data dimension reduction method does not consider common change characteristics among water quality monitoring data in different periods, abnormal data points in the data acquisition process cannot be identified, the reference degree of the characteristic data acquired after dimension reduction is poor, and the trained pollution early warning neural network cannot perform accurate pollution monitoring early warning.
Disclosure of Invention
In order to solve the technical problem that the prior data dimension reduction method directly reduces the dimension of water quality monitoring data at different positions, so that the reference degree of characteristic data obtained by dimension reduction is poor, the invention aims to provide a water source pollution monitoring and early warning method and system for animal husbandry based on big data analysis, and the adopted technical scheme is as follows:
the invention provides a big data analysis-based method for monitoring and early warning water source pollution in animal husbandry, which comprises the following steps:
acquiring nitrogen and phosphorus concentration curves at a plurality of monitoring positions of a water source of animal husbandry under continuous preset sampling periods in a historical big database;
each of the nitrogen-phosphorus concentration curves comprises a significant change point; obtaining the variation significance degree of each significant change point under each sampling period according to the difference of the significant change points corresponding to the same monitoring position between each sampling period and other sampling periods;
acquiring the change trend consistency of each data point on the nitrogen-phosphorus concentration curve in a preset neighborhood range, and acquiring the concentration data deviation degree between each data point and the data points which are at the same monitoring position in different sampling periods and correspond to the same monitoring time; obtaining a significant coefficient of each data point according to the consistency of the variation trend, the deviation degree of the concentration data and the variation significance degree of a significant variation point of the data point on the nitrogen-phosphorus concentration curve;
screening abnormal data points according to the significant coefficient, and adjusting the nitrogen and phosphorus concentration data values of the abnormal data points to obtain an optimized nitrogen and phosphorus concentration curve; reducing the dimension of all optimized nitrogen and phosphorus concentration curves in each sampling period to obtain nitrogen and phosphorus concentration characteristic data;
training the pollution early warning neural network by taking the nitrogen and phosphorus concentration characteristic data as training data; and obtaining the pollution level of the real-time nitrogen and phosphorus concentration characteristic data in the real-time sampling period according to the trained pollution early warning neural network and feeding back an early warning signal.
Further, the method for acquiring the significant change point comprises the following steps:
and acquiring a first derivative of each data point on the nitrogen-phosphorus concentration curve, and taking the data point with the largest absolute value of the first derivative and earliest time sequence as the significant change point.
Further, the obtaining formula of the variation significance degree includes:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein->Is->Sample period ∈>Said degree of significance of the change at a significant change point, < >>Is->A sequence of said significant change points of all monitored positions at a sampling period, +.>Is->Sequences of said significant change points of all monitoring positions at other sampling periods +.>Solving a function for the DTW distance, +.>For normalization function->To divide->The number of other sampling periods than the number of sampling periods, < >>Is->Sample period ∈>Nitrogen-phosphorus concentration corresponding to the marked change point, < >>Is the firstThe>Nitrogen-phosphorus concentration corresponding to the marked change point, < >>Is->Sample period ∈>Monitoring time corresponding to the obvious change point, +.>Is->The>The monitoring time corresponding to the significant change point.
Further, the method for obtaining the consistency of the variation trend comprises the following steps:
constructing a neighborhood range on the nitrogen-phosphorus concentration curve by taking each data point as a central point, dividing the neighborhood range into a first sub-neighborhood range and a second sub-neighborhood range by the central point, and sequentially performing straight line fitting on the data points in the neighborhood range, the first sub-neighborhood range and the second sub-neighborhood range to respectively obtain a first fitting straight line, a second fitting straight line and a third fitting straight line; obtaining a first slope difference between the second fitting straight line and the first fitting straight line, obtaining a second slope difference between the third fitting straight line and the first fitting straight line, taking the sum of the first slope difference and the second slope difference as the fluctuation degree of the variation trend in the neighborhood range, and carrying out negative correlation and normalization processing on the fluctuation degree of the variation trend to obtain the consistency of the variation trend.
Further, the concentration data deviation degree acquisition method includes:
for one data point, acquiring the average nitrogen and phosphorus concentration of the data point corresponding to the same monitoring position and the same monitoring time in different sampling periods, and taking the difference between the nitrogen and phosphorus concentration of the data point and the average nitrogen and phosphorus concentration as the deviation degree of the concentration data.
Further, the method for obtaining the significant coefficient comprises the following steps:
taking the ratio of the deviation degree of the concentration data to the consistency of the variation trend as the data variation degree of each data point; normalizing the change significance degree of a significant change point of a data point on the nitrogen-phosphorus concentration curve to obtain a significant weight; normalizing the product of the saliency weight and the degree of change of the data to obtain the saliency coefficient of each data point.
Further, the method for adjusting the data value of the abnormal data point comprises the following steps:
and under the same monitoring position, taking the mean value of the nitrogen and phosphorus concentrations of non-abnormal data points in different sampling periods and the same time sequence position at the monitoring moment of the abnormal data points as an adjusting value, and taking the adjusting value as a nitrogen and phosphorus concentration data value adjusted by the corresponding abnormal data point.
Further, the method for obtaining the characteristic data of the nitrogen and phosphorus concentration comprises the following steps:
performing principal component analysis on the optimized nitrogen-phosphorus concentration curve to obtain a principal component direction; obtaining the projection duty ratio of each data point on each optimized nitrogen-phosphorus concentration curve in the main component direction, accumulating and normalizing the projection duty ratio of all data points on each optimized nitrogen-phosphorus concentration curve, and obtaining the screening index of each optimized nitrogen-phosphorus concentration curve; and taking the optimized nitrogen-phosphorus concentration curve with the screening index larger than a preset screening threshold value as the nitrogen-phosphorus concentration characteristic data.
Further, the training the pollution early warning neural network by using the nitrogen and phosphorus concentration characteristic data as training data comprises the following steps:
forming a characteristic matrix under a corresponding sampling period by the nitrogen and phosphorus concentration characteristics in one sampling period; and training the pollution early warning neural network by taking the pollution level in the corresponding sampling period as the tag data of the feature matrix and taking the feature data and the tag data as training data.
The invention provides a big data analysis-based stock raising water source pollution monitoring and early warning system, which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes any one step of the big data analysis-based stock raising water source pollution monitoring and early warning method when executing the computer program.
The invention has the following beneficial effects:
in the embodiment of the invention, the nitrogen and phosphorus concentration curves of a plurality of monitoring positions under continuous preset sampling periods are acquired from the historical large database, and support is provided for the training data quantity of the early warning neural network. The significant change points can be used as characteristic points for representing the nitrogen-phosphorus concentration curve, and the possibility of data abnormality of each monitoring position in each sampling period can be estimated by analyzing the difference of the significant change points among the sampling periods and utilizing the significant degree of change. The method further combines the data point change trend of the nitrogen and phosphorus concentration curve, obtains a significant coefficient through common change characteristics, screens out abnormal data points by using the significant coefficient, wherein the abnormal data points are data points which obviously do not accord with the water quality change rule of the water source in animal husbandry, and therefore the nitrogen and phosphorus concentration data values at the positions of the abnormal data points need to be adjusted to obtain an optimized nitrogen and phosphorus concentration curve. The influence of abnormal data on the dimension reduction process can be avoided by optimizing the dimension reduction of the nitrogen-phosphorus concentration curve, so that nitrogen-phosphorus concentration characteristic data with stronger references are obtained, a pollution early warning neural network with high accuracy is obtained, and the pollution level in a real-time state is identified, so that pollution of peripheral water sources in the animal husbandry is monitored and early warned.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an animal husbandry water source pollution monitoring and early warning method based on big data analysis according to an embodiment of the present invention.
Detailed Description
In order to further explain the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects thereof of the method and system for monitoring and early warning pollution of water sources in animal husbandry based on big data analysis, which are provided by the invention, with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
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 invention provides a concrete scheme of a water source pollution monitoring and early warning method and a system for animal husbandry based on big data analysis, which are specifically described below with reference to the accompanying drawings.
An embodiment of a method and a system for monitoring and early warning of water source pollution in animal husbandry based on big data analysis:
referring to fig. 1, a flowchart of an animal husbandry water source pollution monitoring and early warning method based on big data analysis according to an embodiment of the present invention is shown, where the method includes:
step S1: and acquiring nitrogen and phosphorus concentration curves at a plurality of monitoring positions of the water source of the animal husbandry under continuous preset sampling periods in a historical large database.
In order to provide training data for the pollution early warning neural network, the collected nitrogen and phosphorus concentration data needs to be extracted from a historical large database. It should be noted that, because the data is collected from the historical database, the water pollution level in the livestock farm under the corresponding period is known, that is, the nitrogen and phosphorus concentration curves at a plurality of monitoring positions under one sampling period are one set of monitoring data, and each set of monitoring data corresponds to a known pollution level.
In one embodiment of the invention, one sampling period is set to 12 hours, and the sampling frequency is set to be once every five minutes, because continuous time series data are collected, the data points collected in one sampling period form a nitrogen-phosphorus concentration curve. It should be noted that the data change between sampling periods needs to be analyzed in the subsequent data processing, and thus, for each sampling period, 14 sampling periods preceding in time are selected as sampling periods to be analyzed.
In an embodiment of the invention, the monitoring locations include a purified sewage discharge port location, and a plurality of locations in the purification area. It should be noted that, in the purification area, water quality monitoring points can be uniformly set according to the number of the set water quality monitoring sensors, and also can be set randomly, and the monitoring positions can be set automatically according to the actual implementation scene without limitation.
Step S2: each nitrogen-phosphorus concentration curve comprises a significant change point; and obtaining the variation significance degree of each significant change point under each sampling period according to the difference of the significant change points corresponding to the same monitoring position between each sampling period and other sampling periods.
At each monitoring position, because a certain sewage treatment means exists at the monitoring position and a certain self-cleaning effect can be generated through water body flow, certain change characteristics exist on a nitrogen and phosphorus concentration curve at a certain monitoring position in one sampling period. In order to conveniently analyze the change characteristics on the nitrogen and phosphorus concentration curve, firstly, the obvious change points on the curve are obtained, the obvious change points are used as the characteristic points for representing the change of the nitrogen and phosphorus concentration curve, and the obvious change points can be used as references for analysis during the subsequent analysis of the change of the curve.
Preferably, in one embodiment of the present invention, the method for acquiring the significant change point includes:
the first derivative of each data point on the nitrogen-phosphorus concentration curve is obtained, and the larger the absolute value of the derivative is, the larger the change rate of the position of the point is, so that the data point with the largest absolute value of the first derivative and earliest time sequence is taken as a significant change point. I.e., the significant change point characterizes the data point on the entire curve that produced the earliest maximum change.
The positions of the significant change points on the nitrogen-phosphorus concentration curves corresponding to different monitoring positions and the represented change degrees are different. For the entire sampling period, the significant change points of all monitored locations can characterize the nitrogen and phosphorus concentration change characteristics of the water purification process at that sampling period. If the purification process of the livestock farm is stable, the characteristic of the change of the nitrogen and phosphorus concentration among different sampling periods does not have larger change; if noise is generated in the collected data to cause abnormality in some data points, the data points change the change characteristics of the nitrogen-phosphorus concentration curve, and further influence the change characteristics of the nitrogen-phosphorus concentration in the whole sampling period. Therefore, the difference of the corresponding obvious change points of the same monitoring position between each sampling period and other sampling periods can be analyzed, and the change obvious degree of each obvious change point under each sampling period is obtained, namely the change obvious degree characterizes the data referenceability of the corresponding nitrogen-phosphorus concentration curve, and the larger the change obvious degree is, the larger the probability of being influenced by noise on the curve is.
Preferably, in one embodiment of the present invention, the obtaining formula of the variation significance level includes:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein->Is->Sample period ∈>Degree of change significance of a significant change point, +.>Is->Sequence of significant change points of all monitored positions at each sampling period, +.>Is->A sequence of significant change points for all monitored positions at each other sampling period,solving a function for the DTW distance, +.>For normalization function->To divide->The number of other sampling periods than the number of sampling periods, < >>Is->Sample period ∈>Nitrogen-phosphorus concentration corresponding to the marked change point, < >>Is->The>Nitrogen-phosphorus concentration corresponding to the marked change point, < >>Is->Sample period ∈>Monitoring time corresponding to the obvious change point, +.>Is->The>The monitoring time corresponding to the significant change point.
In the change significance formula, the change characteristics of the nitrogen and phosphorus concentration in the whole sampling period are represented by a sequence formed by significant change points of all monitoring positions in the sampling period, and the difference of corresponding sequences between different sampling periods is measured by using a DTW distance, namely, the larger the DTW distance is, the larger the change difference of the nitrogen and phosphorus concentration between two sampling periods is indicated. The rate of change of the difference at the point of significant change is further characterized by the ratio of the concentration difference to the actual difference, i.eThe larger the difference is, the more the obvious change points of the same monitoring position under different sampling periods are, the further the difference of the change characteristics of the nitrogen and phosphorus concentration between two sampling periods can be obtained by combining with the DTW distance, the difference of the change characteristics of the nitrogen and phosphorus concentration between one sampling period and other sampling periods can be obtained by averaging, the larger the difference is, the larger the change is, the larger the degree of influence of noise is, the more unreliable the data is, and the significant degree of change is, compared with the data of the same monitoring position under other sampling periods.
Step S3: the method comprises the steps of obtaining the consistency of the change trend of each data point on a nitrogen-phosphorus concentration curve in a preset neighborhood range, and obtaining the deviation degree of concentration data between each data point and the data points which are at the same monitoring position in different sampling periods and correspond to the same monitoring time; and obtaining the significance coefficient of each data point according to the consistency of the variation trend, the deviation degree of the concentration data and the variation significance degree of the significance change point on the nitrogen-phosphorus concentration curve of the data point.
Because the water flow can generate a certain self-cleaning effect in the flowing movement process, the nitrogen and phosphorus concentration curve shows a fixed change trend in a local range, namely the change trend is generated by the self-cleaning of the water flow. Therefore, the uniformity of the variation trend of each data point on the nitrogen and phosphorus concentration curve in a preset neighborhood range is obtained, the larger the uniformity of the variation trend is, the more uniform the local variation trend of the data point in the neighborhood range is, and the variation trend generated by the self-cleaning of water flow is only; otherwise, the smaller the consistency of the variation trend is, the larger the influence probability of the abnormal data points in the local range is, so that variation trend fluctuation is generated on the normal variation trend, and the consistency of the variation trend is reduced. Normally, the data values of the data points on the nitrogen and phosphorus concentration curves at different sampling periods of the same monitoring position are also close to the same concentration value, so that the degree of deviation of concentration data between each data point and the data points corresponding to the same monitoring position and the same monitoring time in different sampling periods is obtained, the larger the degree of deviation is, the more the data points are different data points, and the lower the data reference is. Therefore, by combining the consistency of the variation trend, the deviation degree of the concentration data and the variation significance degree of the significant variation point on the nitrogen-phosphorus concentration curve of each data point, the significance coefficient of each data point can be obtained, namely the significance coefficient can represent the abnormality degree of the corresponding data point, and the greater the abnormality degree is, the lower the data referential of the corresponding data point is.
Preferably, the method for acquiring the consistency of the variation trend in one embodiment of the present invention includes:
and on the nitrogen-phosphorus concentration curve, constructing a neighborhood range by taking each data point as a central point, dividing the neighborhood range into a first sub-neighborhood range and a second sub-neighborhood range by the central point, and sequentially performing straight line fitting on the data points in the neighborhood range, the first sub-neighborhood range and the second sub-neighborhood range to respectively obtain a first fitting straight line, a second fitting straight line and a third fitting straight line. The first fitting straight line represents the overall change trend of the neighborhood range, and the second fitting straight line and the third fitting straight line represent the change trend of half data points in the neighborhood range respectively. Therefore, a first slope difference between the second fitting straight line and the first fitting straight line is obtained, a second slope difference between the third fitting straight line and the first fitting straight line is obtained, if the variation trend of the data points in the neighborhood range is consistent, the first slope difference and the second slope difference are smaller values, and therefore the sum value of the first slope difference and the second slope difference is used as the variation trend fluctuation degree in the neighborhood range, the variation trend fluctuation degree is subjected to negative correlation and normalization processing, and the variation trend consistency is obtained. In one embodiment of the invention, the trend consistency is formulated as:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Is->Sample period ∈>The first +.on the nitrogen-phosphorus concentration curve corresponding to the significant change point>Trend consistency of data points, +.>Is->Slope of first fitted line in neighborhood range corresponding to data point, +.>Slope of the second fit line, +.>Slope of the third fit line, +.>Is an exponential function based on natural constants. In other embodiments of the present invention, other basic mathematical operations such as function mapping may be used to implement negative correlation mapping and normalization, which are not described and limited herein.
In one embodiment of the invention, the size of the neighborhood range is set to 7, i.e. the neighborhood range is divided into two sub-neighborhood ranges of size 3 centered on the center point.
It should be noted that, if there are some areas in the neighborhood of a certain data point, for example, there are no data points in the starting point and the end point of the curve, the interpolation is performed on the positions without data points, and the specific interpolation algorithm is a technical means well known to those skilled in the art, which is not limited and described herein.
Preferably, in one embodiment of the present invention, the concentration data deviation degree acquisition method includes:
for one data point, the average nitrogen and phosphorus concentration of the data point which is at the same monitoring position in different sampling periods and corresponds to the same monitoring time is obtained, and the difference between the nitrogen and phosphorus concentration of the data point and the average nitrogen and phosphorus concentration is taken as the deviation degree of concentration data.
Preferably, in one embodiment of the present invention, the method for obtaining the significant coefficient includes:
the ratio of the deviation degree of the concentration data and the consistency of the change trend is taken as the data change degree of each data point. That is, the greater the deviation degree of the density data and the smaller the consistency of the variation trend, the greater the degree of variation of the data corresponding to the data point, and the greater the probability that the data point is an abnormal data point. And normalizing the change significance degree of the significant change point on the nitrogen-phosphorus concentration curve of the data point to obtain the significance weight. The product of the significance weight and the degree of change of the data is normalized to obtain a significance coefficient for each data point. That is, the larger the saliency weight is, the larger the probability of noise influence occurs on the corresponding curve is, so that the saliency degree of each data point can be obtained by weighting the data change degree according to the saliency weight. The greater the significance level indicates the more distinct data points corresponding to the data points, the lower the data content reference level.
In one embodiment of the invention, the significant coefficient is formulated as:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein->Is->Sample period ∈>The first +.on the nitrogen-phosphorus concentration curve corresponding to the significant change point>Significant coefficient of data points,/>Is->Sample period ∈>Degree of change significance of a significant change point, +.>Is->Sample period ∈>The first +.on the nitrogen-phosphorus concentration curve corresponding to the significant change point>Concentration data deviation degree of data points, +.>Is->Sample period ∈>The first +.on the nitrogen-phosphorus concentration curve corresponding to the significant change point>Trend consistency of data points. />Is a normalization function. In one embodiment of the present invention, the normalization function may be implemented by using a plurality of basic mathematical means such as pole difference normalization and hyperbolic tangent function mapping method, which are not limited and described herein.
Step S4: screening abnormal data points according to the significant coefficient, and adjusting the nitrogen and phosphorus concentration data values of the abnormal data points to obtain an optimized nitrogen and phosphorus concentration curve; and (3) reducing the dimension of all the optimized nitrogen and phosphorus concentration curves in each sampling period to obtain nitrogen and phosphorus concentration characteristic data.
Because the significant coefficient can represent the data referenceable degree of one data point, the abnormal data point is screened out according to the significant coefficient, and then the nitrogen and phosphorus concentration data value of the abnormal data point is required to be adjusted to ensure the referenceability of the dimension reduction result, so that an optimized nitrogen and phosphorus concentration curve is obtained. That is, the influence of noise and other abnormal data does not exist on the optimized nitrogen-phosphorus concentration curve, the reference of the whole data is stronger, and the nitrogen-phosphorus concentration characteristic data obtained by dimension reduction has better reference.
Preferably, the method for adjusting the data value of an outlier data point in one embodiment of the present invention comprises:
and under the same monitoring position, taking the mean value of the nitrogen and phosphorus concentrations of non-abnormal data points in the same time sequence position in different sampling periods and the abnormal data point monitoring time as an adjusting value, and taking the adjusting value as a nitrogen and phosphorus concentration data value adjusted by the corresponding abnormal data point. It should be noted that, because in one embodiment of the present invention, 14 consecutive sampling periods are selected as the analysis period of a certain sampling period, the average value of the nitrogen and phosphorus concentrations of the non-abnormal data points in the 14 sampling periods, which are at the same monitoring position as the abnormal data point in the sampling period and at the same time sequence position at the monitoring time, needs to be selected as the adjustment value.
Preferably, the method for obtaining characteristic data of nitrogen and phosphorus concentration in one embodiment of the present invention includes:
performing principal component analysis on the optimized nitrogen-phosphorus concentration curve to obtain a principal component direction; the projection ratio of each data point on each optimized nitrogen and phosphorus concentration curve in the main component direction is obtained, the larger the projection ratio is, the more important the corresponding data content is, the projection ratio of all data points on each optimized nitrogen and phosphorus concentration curve is accumulated and normalized, and the screening index of each optimized nitrogen and phosphorus concentration curve is obtained. And taking the optimized nitrogen-phosphorus concentration curve with the screening index larger than the preset screening threshold value as nitrogen-phosphorus concentration characteristic data. In one embodiment of the invention, the screening threshold is set to 0.95. It should be noted that, the principal component analysis method is a dimension reduction method well known to those skilled in the art, and the specific algorithm is a well known technique and will not be described herein.
Step S5: training the pollution early warning neural network by taking the nitrogen and phosphorus concentration characteristic data as training data; and obtaining the pollution level of the real-time nitrogen and phosphorus concentration characteristic data in the real-time sampling period according to the trained pollution early warning neural network and feeding back an early warning signal.
Because the data are collected in the historical database, each group of data corresponds to a known pollution level, and therefore the pollution early-warning neural network with high accuracy can be obtained by training the pollution early-warning neural network by taking the characteristic data of the nitrogen and phosphorus concentration as training data. Similar to step S1 to step S4, the data in the real-time sampling period and the corresponding continuous sampling period are selected, the data collected in the real-time sampling period are processed and analyzed, the real-time nitrogen and phosphorus concentration characteristic data are screened out, the real-time nitrogen and phosphorus concentration characteristic data are input into the pollution early-warning neural network, the pollution level is output, and if the pollution level is greater than the preset early-warning level threshold, the early-warning signal is fed back.
Preferably, training the pollution early warning neural network using the characteristic data of the nitrogen and phosphorus concentration as training data in one embodiment of the present invention includes:
forming a characteristic matrix under a corresponding sampling period by using the nitrogen and phosphorus concentration characteristics in one sampling period; and training the pollution early warning neural network by taking the pollution level in the corresponding sampling period as the tag data of the feature matrix and taking the feature data and the tag data as training data. In one embodiment of the invention, the pollution early warning neural network selects a fully connected neural network structure, the pollution levels are set to be four levels, the pollution levels are respectively pollution-free, light pollution, medium pollution and heavy pollution, and early warning signals are fed back when the pollution levels reach the light pollution and above. It should be noted that the fully-connected neural network structure and the training method are all technical means well known to those skilled in the art, and are not described herein.
In summary, the embodiment of the invention collects the nitrogen and phosphorus concentration curves at a plurality of monitoring positions of the animal husbandry water source under continuous sampling periods, and determines the variation significance degree of each significant variation point by utilizing the difference of the significant variation points among different sampling periods. Further analyzing the data value and the data change trend of each data point on the nitrogen-phosphorus concentration curve, and obtaining the significant coefficient of each data point by combining the corresponding change significant degree, further determining abnormal data points and adjusting the data values of the abnormal data points to obtain the optimized nitrogen-phosphorus concentration curve. And obtaining characteristic data of the nitrogen and phosphorus concentration through dimension reduction for network training. And carrying out pollution grade identification and early warning by using the trained pollution early warning neural network. According to the invention, by eliminating the influence of abnormal data points in the acquired data, the referential property of the feature data after dimension reduction is improved, and the pollution monitoring and early warning accuracy of the neural network is improved.
The invention provides a big data analysis-based stock raising water source pollution monitoring and early warning system, which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes any one step of the big data analysis-based stock raising water source pollution monitoring and early warning method when executing the computer program.
An embodiment of a method for processing water source data of animal husbandry based on big data analysis:
when the pollution data of the water source is collected in the animal husbandry farm, in order to more accurately evaluate the treatment of the current animal husbandry on the water source pollution, corresponding water quality monitoring data exist in a plurality of positions such as the water source position, the purification area position and the like, so that the condition that the water quality monitoring data are more complex in dimension is caused, certain dimension reduction treatment is needed to be carried out on the collected water quality monitoring data, and the characteristic data are extracted for data analysis. The existing data dimension reduction method does not consider common change characteristics among water quality monitoring data in different periods, and can not identify abnormal data points in the data acquisition process, so that the reference degree of the feature data acquired after dimension reduction is poor. In order to solve the technical problem, a method for processing data of a water source of animal husbandry based on big data analysis is provided, and the method comprises the following steps:
step S1: and acquiring nitrogen and phosphorus concentration curves at a plurality of monitoring positions of the water source of the animal husbandry under continuous preset sampling periods in a historical large database.
Step S2: each nitrogen-phosphorus concentration curve comprises a significant change point; and obtaining the variation significance degree of each significant change point under each sampling period according to the difference of the significant change points corresponding to the same monitoring position between each sampling period and other sampling periods.
Step S3: the method comprises the steps of obtaining the consistency of the change trend of each data point on a nitrogen-phosphorus concentration curve in a preset neighborhood range, and obtaining the deviation degree of concentration data between each data point and the data points which are at the same monitoring position in different sampling periods and correspond to the same monitoring time; and obtaining the significance coefficient of each data point according to the consistency of the variation trend, the deviation degree of the concentration data and the variation significance degree of the significance change point on the nitrogen-phosphorus concentration curve of the data point.
Step S4: screening abnormal data points according to the significant coefficient, and adjusting the nitrogen and phosphorus concentration data values of the abnormal data points to obtain an optimized nitrogen and phosphorus concentration curve; and (3) reducing the dimension of all the optimized nitrogen and phosphorus concentration curves in each sampling period to obtain nitrogen and phosphorus concentration characteristic data.
Because the steps S1 to S4 have been described in detail in the embodiments of the method and the system for monitoring and early warning pollution of water sources in animal husbandry based on big data analysis, they are not described in detail herein.
The embodiment of the invention has the beneficial effects that: according to the embodiment of the invention, the significant change points can be taken as the characteristic points for representing the nitrogen-phosphorus concentration curve, and the possibility of data abnormality at each monitoring position in each sampling period can be estimated by analyzing the difference of the significant change points among the sampling periods and utilizing the significant change degree. The method further combines the data point change trend of the nitrogen and phosphorus concentration curve, obtains a significant coefficient through common change characteristics, screens out abnormal data points by using the significant coefficient, wherein the abnormal data points are data points which obviously do not accord with the water quality change rule of the water source in animal husbandry, and therefore the nitrogen and phosphorus concentration data values at the positions of the abnormal data points need to be adjusted to obtain an optimized nitrogen and phosphorus concentration curve. The influence of abnormal data on the dimension reduction process can be avoided by reducing the dimension of the optimized nitrogen-phosphorus concentration curve, so that nitrogen-phosphorus concentration characteristic data with stronger reference property is obtained.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (10)
1. The utility model provides a water source pollution monitoring and early warning method of animal husbandry based on big data analysis which is characterized in that the method comprises the following steps:
acquiring nitrogen and phosphorus concentration curves at a plurality of monitoring positions of a water source of animal husbandry under continuous preset sampling periods in a historical big database;
each of the nitrogen-phosphorus concentration curves comprises a significant change point; obtaining the variation significance degree of each significant change point under each sampling period according to the difference of the significant change points corresponding to the same monitoring position between each sampling period and other sampling periods;
acquiring the change trend consistency of each data point on the nitrogen-phosphorus concentration curve in a preset neighborhood range, and acquiring the concentration data deviation degree between each data point and the data points which are at the same monitoring position in different sampling periods and correspond to the same monitoring time; obtaining a significant coefficient of each data point according to the consistency of the variation trend, the deviation degree of the concentration data and the variation significance degree of a significant variation point of the data point on the nitrogen-phosphorus concentration curve;
screening abnormal data points according to the significant coefficient, and adjusting the nitrogen and phosphorus concentration data values of the abnormal data points to obtain an optimized nitrogen and phosphorus concentration curve; reducing the dimension of all optimized nitrogen and phosphorus concentration curves in each sampling period to obtain nitrogen and phosphorus concentration characteristic data;
training the pollution early warning neural network by taking the nitrogen and phosphorus concentration characteristic data as training data; and obtaining the pollution level of the real-time nitrogen and phosphorus concentration characteristic data in the real-time sampling period according to the trained pollution early warning neural network and feeding back an early warning signal.
2. The method for monitoring and early warning pollution of water sources in animal husbandry based on big data analysis according to claim 1, wherein the method for acquiring the significant change points comprises the following steps:
and acquiring a first derivative of each data point on the nitrogen-phosphorus concentration curve, and taking the data point with the largest absolute value of the first derivative and earliest time sequence as the significant change point.
3. The method for monitoring and early warning of pollution of water sources in animal husbandry based on big data analysis according to claim 1, wherein the formula for obtaining the variation significance comprises the following steps:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein->Is->Sample period ∈>Said degree of significance of the change at a significant change point, < >>Is->A sequence of said significant change points of all monitored positions at a sampling period, +.>Is->Sequences of said significant change points of all monitoring positions at other sampling periods +.>Solving a function for the DTW distance, +.>For normalization function->To divide->The number of other sampling periods than the number of sampling periods, < >>Is->Sample period ∈>Nitrogen-phosphorus concentration corresponding to the marked change point, < >>Is->The>Nitrogen-phosphorus concentration corresponding to the marked change point, < >>Is->Sample period ∈>Monitoring time corresponding to the obvious change point, +.>Is->The>The monitoring time corresponding to the significant change point.
4. The method for monitoring and early warning pollution of water sources in animal husbandry based on big data analysis according to claim 1, wherein the method for acquiring the consistency of the variation trend comprises the following steps:
constructing a neighborhood range on the nitrogen-phosphorus concentration curve by taking each data point as a central point, dividing the neighborhood range into a first sub-neighborhood range and a second sub-neighborhood range by the central point, and sequentially performing straight line fitting on the data points in the neighborhood range, the first sub-neighborhood range and the second sub-neighborhood range to respectively obtain a first fitting straight line, a second fitting straight line and a third fitting straight line; obtaining a first slope difference between the second fitting straight line and the first fitting straight line, obtaining a second slope difference between the third fitting straight line and the first fitting straight line, taking the sum of the first slope difference and the second slope difference as the fluctuation degree of the variation trend in the neighborhood range, and carrying out negative correlation and normalization processing on the fluctuation degree of the variation trend to obtain the consistency of the variation trend.
5. The method for monitoring and early warning pollution of water sources in animal husbandry based on big data analysis according to claim 1, wherein the method for acquiring the deviation degree of concentration data comprises the following steps:
for one data point, acquiring the average nitrogen and phosphorus concentration of the data point corresponding to the same monitoring position and the same monitoring time in different sampling periods, and taking the difference between the nitrogen and phosphorus concentration of the data point and the average nitrogen and phosphorus concentration as the deviation degree of the concentration data.
6. The method for monitoring and early warning pollution of water sources in animal husbandry based on big data analysis according to claim 1, wherein the method for obtaining the significant coefficient comprises the following steps:
taking the ratio of the deviation degree of the concentration data to the consistency of the variation trend as the data variation degree of each data point; normalizing the change significance degree of a significant change point of a data point on the nitrogen-phosphorus concentration curve to obtain a significant weight; normalizing the product of the saliency weight and the degree of change of the data to obtain the saliency coefficient of each data point.
7. A method for monitoring and pre-warning pollution of water sources in animal husbandry based on big data analysis according to claim 1, wherein the method for adjusting the data value of the abnormal data points comprises the following steps:
and under the same monitoring position, taking the mean value of the nitrogen and phosphorus concentrations of non-abnormal data points in different sampling periods and the same time sequence position at the monitoring moment of the abnormal data points as an adjusting value, and taking the adjusting value as a nitrogen and phosphorus concentration data value adjusted by the corresponding abnormal data point.
8. The method for monitoring and early warning pollution of water sources in animal husbandry based on big data analysis according to claim 1, wherein the method for obtaining characteristic data of nitrogen and phosphorus concentration comprises the following steps:
performing principal component analysis on the optimized nitrogen-phosphorus concentration curve to obtain a principal component direction; obtaining the projection duty ratio of each data point on each optimized nitrogen-phosphorus concentration curve in the main component direction, accumulating and normalizing the projection duty ratio of all data points on each optimized nitrogen-phosphorus concentration curve, and obtaining the screening index of each optimized nitrogen-phosphorus concentration curve; and taking the optimized nitrogen-phosphorus concentration curve with the screening index larger than a preset screening threshold value as the nitrogen-phosphorus concentration characteristic data.
9. A method for monitoring and early warning pollution of water sources in animal husbandry based on big data analysis according to claim 1, wherein the training of the pollution early warning neural network by using the characteristic data of nitrogen and phosphorus concentration as training data comprises the following steps:
forming a characteristic matrix under a corresponding sampling period by the nitrogen and phosphorus concentration characteristics in one sampling period; and training the pollution early warning neural network by taking the pollution level in the corresponding sampling period as the tag data of the feature matrix and taking the feature data and the tag data as training data.
10. The utility model provides an animal husbandry water source pollution monitoring and early warning system based on big data analysis, includes memory, processor and the computer program that stores in the memory and can run on the processor, characterized in that the step of an animal husbandry water source pollution monitoring and early warning method based on big data analysis according to any one of claims 1~9 is realized to the processor when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410210815.6A CN117786584B (en) | 2024-02-27 | 2024-02-27 | Big data analysis-based method and system for monitoring and early warning of water source pollution in animal husbandry |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410210815.6A CN117786584B (en) | 2024-02-27 | 2024-02-27 | Big data analysis-based method and system for monitoring and early warning of water source pollution in animal husbandry |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117786584A true CN117786584A (en) | 2024-03-29 |
| CN117786584B CN117786584B (en) | 2024-04-30 |
Family
ID=90380044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410210815.6A Active CN117786584B (en) | 2024-02-27 | 2024-02-27 | Big data analysis-based method and system for monitoring and early warning of water source pollution in animal husbandry |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117786584B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118130743A (en) * | 2024-05-08 | 2024-06-04 | 冠珹餐饮管理(沈阳)有限公司 | Water quality monitoring data processing method and system based on cloud computing |
| CN118130743B (en) * | 2024-05-08 | 2024-07-12 | 冠珹餐饮管理(沈阳)有限公司 | Water quality monitoring data processing method and system based on cloud computing |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015176565A1 (en) * | 2014-05-22 | 2015-11-26 | 袁志贤 | Method for predicting faults in electrical equipment based on multi-dimension time series |
| WO2022160682A1 (en) * | 2021-01-27 | 2022-08-04 | 力合科技（湖南）股份有限公司 | Water quality monitoring data analysis method and apparatus, device, and storage medium |
| CN114965924A (en) * | 2022-05-16 | 2022-08-30 | 蚌埠碧水蓝环境科技有限公司 | Sewage pollutant concentration detection system |
| WO2022217839A1 (en) * | 2021-04-14 | 2022-10-20 | 江南大学 | Air quality prediction method based on deep spatiotemporal similarity |
| WO2022252505A1 (en) * | 2021-06-02 | 2022-12-08 | 杭州安脉盛智能技术有限公司 | Device state monitoring method based on multi-index cluster analysis |
| CN116089846A (en) * | 2023-04-03 | 2023-05-09 | 北京智蚁杨帆科技有限公司 | New energy settlement data anomaly detection and early warning method based on data clustering |
| US20230264355A1 (en) * | 2020-07-28 | 2023-08-24 | Kawasaki Jukogyo Kabushiki Kaisha | State monitoring device, state abnormality determination method, and state abnormality determination program |
| CN117148784A (en) * | 2023-10-27 | 2023-12-01 | 山东山森数控技术有限公司 | Operation fault analysis method for multi-axis multi-channel numerical control system |
| CN117194928A (en) * | 2023-11-07 | 2023-12-08 | 湖南中云图地理信息科技有限公司 | GNSS-based geographic deformation monitoring system |
| CN117196353A (en) * | 2023-11-07 | 2023-12-08 | 山东省济宁生态环境监测中心(山东省南四湖东平湖流域生态环境监测中心) | Environmental pollution assessment and monitoring method and system based on big data |
| CN117390573A (en) * | 2023-12-12 | 2024-01-12 | 深圳前海慧联科技发展有限公司 | Wind turbine generator operation abnormality early warning method based on time sequence prediction |
| CN117451963A (en) * | 2023-12-22 | 2024-01-26 | 深圳市瑞盛环保科技有限公司 | High-efficient detecting system of ammonia nitrogen waste water |
| CN117476140A (en) * | 2023-12-28 | 2024-01-30 | 沧州市生态环境监控中心(沧州市机动车污染防治监控中心) | Atmospheric environmental pollution treatment method based on multidimensional data analysis of Internet of things |
| CN117522632A (en) * | 2023-12-25 | 2024-02-06 | 阳光学院 | Water quality index prediction method based on deep learning |
| CN117591978A (en) * | 2023-11-30 | 2024-02-23 | 中科广化检测技术服务(深圳)有限公司 | Environment pollution detection method, system, equipment and storage medium |
-
2024
- 2024-02-27 CN CN202410210815.6A patent/CN117786584B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015176565A1 (en) * | 2014-05-22 | 2015-11-26 | 袁志贤 | Method for predicting faults in electrical equipment based on multi-dimension time series |
| US20230264355A1 (en) * | 2020-07-28 | 2023-08-24 | Kawasaki Jukogyo Kabushiki Kaisha | State monitoring device, state abnormality determination method, and state abnormality determination program |
| WO2022160682A1 (en) * | 2021-01-27 | 2022-08-04 | 力合科技（湖南）股份有限公司 | Water quality monitoring data analysis method and apparatus, device, and storage medium |
| WO2022217839A1 (en) * | 2021-04-14 | 2022-10-20 | 江南大学 | Air quality prediction method based on deep spatiotemporal similarity |
| WO2022252505A1 (en) * | 2021-06-02 | 2022-12-08 | 杭州安脉盛智能技术有限公司 | Device state monitoring method based on multi-index cluster analysis |
| CN114965924A (en) * | 2022-05-16 | 2022-08-30 | 蚌埠碧水蓝环境科技有限公司 | Sewage pollutant concentration detection system |
| CN116089846A (en) * | 2023-04-03 | 2023-05-09 | 北京智蚁杨帆科技有限公司 | New energy settlement data anomaly detection and early warning method based on data clustering |
| CN117148784A (en) * | 2023-10-27 | 2023-12-01 | 山东山森数控技术有限公司 | Operation fault analysis method for multi-axis multi-channel numerical control system |
| CN117194928A (en) * | 2023-11-07 | 2023-12-08 | 湖南中云图地理信息科技有限公司 | GNSS-based geographic deformation monitoring system |
| CN117196353A (en) * | 2023-11-07 | 2023-12-08 | 山东省济宁生态环境监测中心(山东省南四湖东平湖流域生态环境监测中心) | Environmental pollution assessment and monitoring method and system based on big data |
| CN117591978A (en) * | 2023-11-30 | 2024-02-23 | 中科广化检测技术服务(深圳)有限公司 | Environment pollution detection method, system, equipment and storage medium |
| CN117390573A (en) * | 2023-12-12 | 2024-01-12 | 深圳前海慧联科技发展有限公司 | Wind turbine generator operation abnormality early warning method based on time sequence prediction |
| CN117451963A (en) * | 2023-12-22 | 2024-01-26 | 深圳市瑞盛环保科技有限公司 | High-efficient detecting system of ammonia nitrogen waste water |
| CN117522632A (en) * | 2023-12-25 | 2024-02-06 | 阳光学院 | Water quality index prediction method based on deep learning |
| CN117476140A (en) * | 2023-12-28 | 2024-01-30 | 沧州市生态环境监控中心(沧州市机动车污染防治监控中心) | Atmospheric environmental pollution treatment method based on multidimensional data analysis of Internet of things |
Non-Patent Citations (2)
| Title |
|---|
| B. VERSTEEG;A. BEGEN;CISCO;T. VANCAENEGEM;ALCATEL-LUCENT;Z. VAX; MICROSOFT CORPORATION;: "Unicast-Based Rapid Acquisition of Multicast RTP Sessions draft-ietf-avt-rapid-acquisition-for-rtp-05", IETF, 16 November 2009 (2009-11-16) * |
| 史斌;姜继平;王鹏;: "基于高频在线水质数据异常的突发污染预警", 中国环境科学, no. 11, 20 November 2017 (2017-11-20) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118130743A (en) * | 2024-05-08 | 2024-06-04 | 冠珹餐饮管理(沈阳)有限公司 | Water quality monitoring data processing method and system based on cloud computing |
| CN118130743B (en) * | 2024-05-08 | 2024-07-12 | 冠珹餐饮管理(沈阳)有限公司 | Water quality monitoring data processing method and system based on cloud computing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117786584B (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115933787B (en) | Indoor multi-terminal intelligent control system based on indoor environment monitoring | |
| CN117196353B (en) | Environmental pollution assessment and monitoring method and system based on big data | |
| CN116228176B (en) | Sewage treatment data efficient management system based on data processing | |
| CN110045771B (en) | Intelligent monitoring system for water quality of fishpond | |
| CN116400126B (en) | Low-voltage power box with data processing system | |
| CN112906738B (en) | Water quality detection and treatment method | |
| CN110728320A (en) | Water quality monitoring and early warning method and system based on combination of self-coding and clustering | |
| CN111339499B (en) | Sewage treatment plant running state evaluation method based on time trajectory similarity | |
| CN117633697B (en) | Intelligent live pig monitoring method and system based on Internet of things | |
| CN117314016A (en) | Hydraulic engineering on-line monitoring method based on BIM technology | |
| CN114266457A (en) | Method for detecting different loss inducement of distribution line | |
| CN117786584B (en) | Big data analysis-based method and system for monitoring and early warning of water source pollution in animal husbandry | |
| CN113702612B (en) | River bank pollution detection and investigation site selection method and system based on artificial intelligence | |
| CN116523174A (en) | Sewage treatment plant working condition assessment method and system based on self-organizing neural network | |
| CN114149076B (en) | Intelligent debugging system of anaerobic ammonia oxidation sewage treatment system | |
| CN114997470A (en) | Short-term power load prediction method based on LSTM neural network | |
| CN117540327B (en) | Enterprise environment autonomous management data acquisition and processing system | |
| CN118171135B (en) | Aquaculture environment monitoring method based on multi-source data fusion | |
| CN117196881B (en) | Intelligent cultivation information management system based on big data | |
| CN115481904B (en) | Intelligent constructed wetland based wastewater treatment efficiency management system | |
| CN116307361B (en) | Quick adjustment and control method for aquaculture environmental factors | |
| CN117290559B (en) | Water treatment agent content monitoring method and system | |
| CN117648657B (en) | Urban planning multi-source data optimization processing method | |
| CN117829381B (en) | Agricultural greenhouse data optimization acquisition system based on Internet of things | |
| CN115267101A (en) | Water quality monitoring system and method based on three parameters |
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 |