CN117196353B - Environmental pollution assessment and monitoring method and system based on big data - Google Patents
Environmental pollution assessment and monitoring method and system based on big data Download PDFInfo
- Publication number
- CN117196353B CN117196353B CN202311465602.XA CN202311465602A CN117196353B CN 117196353 B CN117196353 B CN 117196353B CN 202311465602 A CN202311465602 A CN 202311465602A CN 117196353 B CN117196353 B CN 117196353B
- Authority
- CN
- China
- Prior art keywords
- meteorological
- original data
- data point
- parameter
- parameters
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000003912 environmental pollution Methods 0.000 title claims abstract description 42
- 238000012544 monitoring process Methods 0.000 title claims abstract description 42
- 230000035772 mutation Effects 0.000 claims abstract description 66
- 238000005070 sampling Methods 0.000 claims abstract description 59
- 238000011156 evaluation Methods 0.000 claims abstract description 14
- 230000000875 corresponding effect Effects 0.000 claims description 46
- 238000012545 processing Methods 0.000 claims description 27
- 238000009499 grossing Methods 0.000 claims description 17
- 238000010606 normalization Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 8
- 230000005484 gravity Effects 0.000 claims description 8
- 238000010219 correlation analysis Methods 0.000 claims description 7
- 230000002596 correlated effect Effects 0.000 claims description 6
- 238000012935 Averaging Methods 0.000 claims description 5
- 238000011478 gradient descent method Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 238000013441 quality evaluation Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 11
- 230000000694 effects Effects 0.000 description 7
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of data supervision and management, in particular to an environmental pollution assessment and monitoring method and system based on big data. The method comprises the following steps: obtaining original data points of different meteorological parameters, obtaining mutation degree according to the distribution of the original data points in the meteorological parameters and extreme points in the meteorological parameters, obtaining distinction degree according to the mutation degree of the original data points, the distribution of the extreme points and the number of the extreme points, obtaining pearson correlation coefficients among the meteorological parameters, obtaining a time sequence range of the original data points based on sampling intervals of the meteorological parameters, further obtaining reference value of each original data point, adjusting errors generated before and after interpolation based on the reference value, obtaining an optimal interpolation curve, and evaluating and monitoring environmental pollution based on the optimal interpolation curve. The method and the device avoid the problems of over fitting with over high interpolation precision and under fitting with over low precision, and improve the accuracy of environmental pollution evaluation and monitoring.
Description
Technical Field
The invention relates to the field of data supervision and management, in particular to an environmental pollution assessment and monitoring method and system based on big data.
Background
With the rapid development of the social economy of China, the problems of environmental pollution are also more serious, and the problems of extensive attention of the society are gradually compounded. Therefore, by arranging pollution monitoring points at a plurality of local positions, collecting data of a plurality of related meteorological parameters such as gas concentration, temperature and the like in real time, and performing supervision and management on the data, environmental problems can be found and predicted as soon as possible, and because sampling intervals of sensors used for different meteorological parameters are different, spline interpolation is usually required for the meteorological parameters so as to better analyze the correlation between the different parameters, and data of the different meteorological parameters under the same time sequence can be obtained.
In the related art, a cubic interpolation algorithm is generally used for carrying out interpolation processing on data points to obtain corresponding interpolation curves, so that data of different meteorological parameters under the same time sequence is obtained, but because of differences of the change conditions of the data points in the different meteorological parameters, data points interfered by noise also exist in the meteorological parameters, the problems of over fitting with over high interpolation precision and under fitting with over low precision can be generated when spline interpolation is carried out in the prior art, and the accuracy of evaluating and monitoring the environmental pollution is reduced.
Disclosure of Invention
In order to solve the technical problems that the prior art can generate over fitting condition with over high interpolation precision and under fitting condition with over low precision when carrying out spline interpolation, thereby reducing the accuracy of environmental pollution evaluation and monitoring, the invention aims to provide an environmental pollution evaluation and monitoring method and system based on big data, and the adopted technical scheme is as follows:
the invention provides an environmental pollution evaluation and monitoring method based on big data, which comprises the following steps:
acquiring original data points of different meteorological parameters at different moments, wherein sampling intervals of the different meteorological parameters are different;
according to the distribution of the original data points in each meteorological parameter, obtaining the mutation degree of each original data point and the extreme point in the meteorological parameter; obtaining the distinguishing degree of the meteorological parameters according to the mutation degree of all original data points in each meteorological parameter, the distribution of the extreme points and the number of the extreme points;
taking any one of the meteorological parameters as the meteorological parameter to be measured, and carrying out correlation analysis on the meteorological parameter to be measured and other meteorological parameters according to the numerical value of the original data point in each meteorological parameter to obtain a correlation coefficient; acquiring a time sequence range of each original data point in the meteorological parameters to be measured according to sampling intervals of all the meteorological parameters; obtaining the reference value of each original data point in the meteorological parameters to be detected according to the distribution of the original data points of the meteorological parameters to be detected and other meteorological parameters in the time sequence range, the difference of the sampling intervals, the correlation coefficient and the distinction degree;
Performing interpolation processing on each meteorological parameter to obtain different interpolation curves; obtaining an optimal interpolation curve according to the difference between the original data point of each moment in each meteorological parameter and the data point of the interpolation curve at the corresponding moment and the reference value; and evaluating and monitoring the environmental pollution according to the optimal interpolation curves of all the meteorological parameters.
Further, the obtaining the mutation degree of each original data point and the extreme point in the meteorological parameters according to the distribution of the original data points in each meteorological parameter comprises:
acquiring two adjacent data points, which are closest to each original data point, wherein the time interval between the original data point and the corresponding adjacent data point is equal to the sampling interval, and the first original data point and the last original data point in each meteorological parameter are respectively taken as one adjacent data point of the original data point; if the original data point is larger or smaller than the two corresponding adjacent data points at the same time, taking the original data point as an extreme point;
taking the absolute value of the difference value between the original data point and each adjacent data point as an initial change value, and taking the sum value of the initial change values of the original data point and the two corresponding adjacent data points as a first mutation coefficient;
Taking the absolute value of the difference value of two adjacent data points corresponding to the original data point as a second mutation coefficient;
a degree of mutation for each raw data point is obtained, the degree of mutation being positively correlated with the first mutation coefficient, and the degree of mutation being negatively correlated with the second mutation coefficient.
Further, the obtaining the distinguishing degree of the meteorological parameters according to the mutation degree of all original data points in each meteorological parameter, the distribution of the extreme points and the number of the extreme points comprises:
dividing all original data points in each meteorological parameter based on the position of the extreme point to obtain different extreme value intervals, wherein the original data points in the extreme value intervals do not comprise the extreme point;
taking the number of original data points in an extremum interval where each original data point is located as an initial weight of each original data point, wherein the initial weight of each extremum point is 0;
normalizing the initial weight to obtain the final weight of each original data point;
according to the final weight, carrying out weighted summation on the mutation degree of the corresponding original data point in each meteorological parameter to obtain the integral mutation degree of the meteorological parameter;
Taking the ratio of the number of extreme points in each meteorological parameter to the total number of original data points in the corresponding meteorological parameter as the extreme point specific gravity of the meteorological parameter;
normalizing the product value of the integral mutation degree and the extreme point specific gravity to obtain a fluctuation characteristic value of the meteorological parameter; and carrying out negative correlation mapping on the fluctuation characteristic value to obtain the degree of distinction between each meteorological parameter and noise.
Further, the performing correlation analysis on the weather parameter to be measured and other weather parameters according to the value of the original data point in each weather parameter to obtain a correlation coefficient includes:
and acquiring a pearson correlation coefficient according to the values of all the original data points in the meteorological parameters to be measured and the values of all the original data points in other meteorological parameters, and taking the pearson correlation coefficient as a correlation coefficient between the meteorological parameters to be measured and each other meteorological parameter.
Further, the obtaining the time sequence range of each original data point in the meteorological parameters to be measured according to the sampling intervals of all the meteorological parameters includes:
taking the least common multiple of the sampling intervals of all meteorological parameters as a standard sampling duration;
taking the ratio of the standard sampling time length to the sampling interval of the meteorological parameter to be measured as the standard sampling quantity of the meteorological parameter to be measured;
Taking the standard sampling number of other original data points which are closest to the moment of each original data point in the meteorological parameter to be measured as reference data points of the original data points;
and acquiring a time sequence range of each original data point, wherein the left end point of the time sequence range is a minimum value corresponding to the moment of the reference data point, and the right end point of the time sequence range is a maximum value corresponding to the moment of the reference data point.
Further, the obtaining the reference value of each original data point in the meteorological parameter to be measured according to the distribution of the original data points of the meteorological parameter to be measured and other meteorological parameters in the time sequence range, the difference of the sampling intervals, the correlation coefficient and the distinction degree includes:
taking the absolute value of the difference value between the sampling interval of the meteorological parameter to be detected and the sampling interval of each other meteorological parameter as the sampling interval difference, and carrying out negative correlation normalization processing on the sampling interval difference to obtain a first coefficient;
taking the correlation coefficient between the meteorological parameter to be measured and each other meteorological parameter as a second coefficient;
taking the standard deviation of the original data points of each other meteorological parameter in the time sequence range as the fluctuation degree of the other meteorological parameters in the time sequence range; carrying out negative correlation normalization processing on the fluctuation degree, and multiplying the obtained product by the discrimination degree of the corresponding meteorological parameter to obtain a third coefficient;
Multiplying the first coefficient, the second coefficient and the third coefficient to obtain an adjustment coefficient of each other meteorological parameter;
performing dynamic time warping processing on the to-be-detected meteorological parameters and original data points of each other meteorological parameter in the time sequence range based on a DTW algorithm to obtain the similarity degree of the to-be-detected meteorological parameters and each other meteorological parameter in the time sequence range; taking the average value of all the similarity degrees as the overall similarity degree;
multiplying the difference value of each similarity degree and the overall similarity degree by the adjustment coefficient to obtain the similarity deviation of each other meteorological parameter;
and carrying out normalization processing after averaging the square sums of similarity deviations of all other meteorological parameters to obtain the reference value of each original data point in the meteorological parameters to be measured.
Further, the interpolating each meteorological parameter to obtain a different interpolation curve includes:
acquiring preset initial smoothing parameters, and optimizing the preset initial smoothing parameters according to a gradient descent method to acquire different adjustment smoothing parameters;
and carrying out interpolation processing on each meteorological parameter by using each adjustment smoothing parameter based on a cubic spline interpolation algorithm to obtain interpolation curves of the meteorological parameters under different adjustment smoothing parameters.
Further, the obtaining the optimal interpolation curve according to the difference between the original data point of each time in each meteorological parameter and the data point of the interpolation curve at the corresponding time and the reference value includes:
taking the difference value between the original data point of each moment in each meteorological parameter and the data point of the interpolation curve at the corresponding moment as the initial interpolation error of each original data point;
taking the product of the initial interpolation error and the reference value as an optimized interpolation error for each raw data point;
averaging the square sum of the optimized interpolation errors of all the original data points to obtain the integral interpolation error of each interpolation curve;
and taking the interpolation curve corresponding to the minimum value of the overall interpolation error as the optimal interpolation curve of each meteorological parameter.
Further, the evaluating and monitoring the environmental pollution according to the optimal interpolation curve of all the meteorological parameters comprises:
and respectively selecting data points with the same time sequence on the optimal interpolation curves of all the meteorological parameters, acquiring a data point sequence of each meteorological parameter, and inputting the data point sequence of all the meteorological parameters into an air quality evaluation algorithm for environmental pollution evaluation and monitoring.
The invention also provides an environmental pollution evaluation and monitoring system based on big data, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes any one of the steps of the environmental pollution evaluation and monitoring method based on big data when executing the computer program.
The invention has the following beneficial effects:
according to the method, the original data points in different meteorological parameters are comprehensively analyzed, and a large amount of data are subjected to supervision management, so that the existing environmental problem can be accurately predicted, the difference of the data fluctuation characteristics of the different meteorological parameters is considered, the noise interference is often represented as the characteristic of high-frequency fluctuation, the obtained extreme points can be further analyzed by reflecting the fluctuation characteristics of the original data points in the meteorological parameters according to the obtained mutation degree, the mutation degree of the original data points is combined to obtain the distinction degree, the possibility that the fluctuation part appearing in each meteorological parameter is noise interference based on the distinction degree is reflected, the correlation degree between the meteorological parameters is considered, the analysis of the original data points of the meteorological parameters to be detected and other meteorological parameters in the time sequence range is further considered through the analysis of the original data points of each meteorological parameter to be detected, the tolerance degree of the error generated after interpolation is reflected through the obtained reference value, the subsequent interpolation processing process is optimized by utilizing the reference value, the optimal interpolation curve is obtained, the fitting and the under fitting problem in the interpolation process are avoided, the optimal weather pollution to the monitoring effect can be improved, and the environmental pollution can be accurately estimated.
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 environmental pollution evaluation and monitoring method based on big data according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description refers to the specific implementation, structure, characteristics and effects of the environmental pollution assessment and monitoring method and system based on big data according to the present invention, which are provided by the present invention with reference to the accompanying drawings and the preferred embodiments. 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 method and a system for evaluating and monitoring environmental pollution based on big data, which are specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of an environmental pollution evaluation and monitoring method based on big data according to an embodiment of the present invention is shown, where the method includes:
step S1: raw data points of different meteorological parameters at different moments are acquired, wherein sampling intervals of the different meteorological parameters are different.
Because the current environmental pollution problem is more serious, in order to discover the existing environmental pollution problem as early as possible and to make further management on the pollution problem in time, a plurality of pollution monitoring points are generally required to be set, and the data of each pollution monitoring point is collected to be supervised and managed, so that the environmental pollution problem is monitored.
Because the most direct influence on the environment is the influence of pollutants on the air, the monitoring and evaluation of the environmental pollution are realized by carrying out supervision and management on meteorological data related to the air, the embodiment of the invention firstly collects data points of different meteorological parameters at different moments through corresponding sensors arranged in pollution monitoring points, wherein the meteorological parameters comprise but are not limited to the concentration, the speed, the temperature, the humidity and the like of various gas components, and the sampling intervals of the different meteorological parameters can be different due to the fact that the sensors used for the different meteorological parameters are different, and the fact that the sampling intervals of the sensors are intrinsic parameter values is needed to be explained; considering that there is a difference in dimension between different meteorological parameters, further normalization processing needs to be performed on the original data points in each meteorological parameter, so as to eliminate the influence of the difference in dimension between different meteorological parameters on subsequent analysis.
Because sampling intervals among different meteorological parameters are different, interpolation processing is needed to be carried out on the meteorological parameters in the follow-up process in order to better analyze the correlation among the different meteorological parameters, so that a large amount of data support can be provided for the follow-up interpolation processing by acquiring original data points of the different meteorological parameters, the follow-up accuracy of monitoring and managing the meteorological data is improved, and the pollution problem in the environment can be accurately predicted.
Step S2: according to the distribution of each original data point in each meteorological parameter, obtaining the mutation degree of each original data point and the extreme point in the meteorological parameter; and obtaining the distinguishing degree of the meteorological parameters according to the mutation degree of all original data points in each meteorological parameter, the distribution of the extreme points and the number of the extreme points.
Because of the limitations of the sensor, noise is usually interfered during the process of collecting the original data points by the sensor, the original data points often show high-frequency fluctuation characteristics due to noise interference, and the original data points in the meteorological parameters are abnormal, so that fluctuation characteristics of the original data points can be caused, therefore, the mutation degree of each original data point and extreme points in the meteorological parameters can be obtained firstly according to the distribution of each original data point in each meteorological parameter, the fluctuation condition of the original data points in the meteorological parameters is reflected through the mutation degree, and the distinguishing degree of the meteorological parameters is accurately analyzed by combining the extreme points in the meteorological parameters in the follow-up process.
Preferably, in one embodiment of the present invention, the method for acquiring the mutation degree of each original data point and the extreme point in the meteorological parameter specifically includes:
acquiring two adjacent data points, which are closest to each original data point, wherein the time interval between the original data point and the corresponding adjacent data point is equal to the sampling interval, and considering that only one adjacent data point exists between the first original data point and the last original data point in each meteorological parameter, the first original data point and the last original data point can be respectively used as the adjacent data points of the first original data point and the last original data point; if the original data point is larger or smaller than the two corresponding adjacent data points at the same time, taking the original data point as an extreme point; taking the absolute value of the difference value between the original data point and each adjacent data point as an initial change value, and taking the sum of the initial change values of the original data point and the two corresponding adjacent data points as a first mutation coefficient; taking the absolute value of the difference value of two adjacent data points corresponding to each original data point as a second mutation coefficient; the mutation degree of each original data point is obtained, wherein the mutation degree is positively correlated with the first mutation coefficient, and the mutation degree is negatively correlated with the second mutation coefficient. The expression of the degree of mutation may specifically be, for example:
Wherein,indicate->The first part of the meteorological parameters>The degree of mutation of the individual raw data points; />Indicate->The first part of the meteorological parameters>A number of raw data points; />Indicate->The first part of the meteorological parameters>One of the adjacent ones of the original data points; />Indicate->The first part of the meteorological parameters>Another adjacent data point of the plurality of original data points; />Representing the first adjustment factor, preventing denominator from being 0, in one embodiment of the invention the first adjustment factor +.>The specific value of the first adjustment factor set to 0.01 may be set by the practitioner according to the specific implementation scenario, and is not limited herein.
During the acquisition of the degree of mutation for each raw data point in each meteorological parameter,andrepresenting the absolute value of the difference between the original data point and each adjacent data point, respectively, i.e. the initial change value, which can reflect the original data point and the phaseThe change conditions between the adjacent data points are further added to obtain a first mutation coefficient, the larger the first mutation coefficient is, the larger the difference between the original data points and the adjacent data points is, the mutation degree of the original data points can not be accurately reflected by the first mutation coefficient, so that the absolute value of the difference value of all the adjacent data points corresponding to each original data point is >As the second mutation coefficient, the larger the first mutation coefficient is, the smaller the second mutation coefficient is, which means that the larger the difference between the original data point and the adjacent data point is, the mutation degree of the original data point is +.>The larger.
After the extreme points in each meteorological parameter are extracted and the mutation degree of the original data points is obtained, the high-frequency fluctuation characteristic shown by noise interference of the sensor may be similar to the fluctuation characteristic generated by abnormality of part of the meteorological parameters, so that the distinction degree of the meteorological parameters can be further obtained according to the mutation degree of all the original data points in each meteorological parameter, the distribution of the extreme points and the number of the extreme points, the noise condition in the meteorological parameters is reflected through the distinction degree, the larger the distinction degree is, the weaker the fluctuation characteristic of the original data points in the meteorological parameters is, and the relatively flatter the high-frequency fluctuation part in the meteorological parameters is more likely to be caused by noise.
Preferably, in one embodiment of the present invention, the method for acquiring the distinguishing degree of the meteorological parameters specifically includes:
dividing all original data points in each meteorological parameter based on the position of the extreme point to obtain different extreme value intervals, wherein the original data points in the extreme value intervals do not comprise the extreme point; taking the number of the original data points in the extremum interval of each original data point as the initial weight of each original data point, wherein the initial weight of the extremum point is 0 because the extremum point does not belong to the extremum interval; normalizing the initial weight to obtain the final weight of each original data point; according to the final weight, carrying out weighted summation on the mutation degree of the corresponding original data point in each meteorological parameter to obtain the integral mutation degree of the meteorological parameter; taking the ratio of the number of extreme points in each meteorological parameter to the total number of original data points in the corresponding meteorological parameter as the extreme point specific gravity of the meteorological parameter; normalizing the product value of the integral mutation degree and the extreme point specific gravity to obtain a fluctuation characteristic value of the meteorological parameter; and carrying out negative correlation mapping on the fluctuation characteristic values to obtain the degree of distinction between each meteorological parameter and noise. The expression of the discrimination may specifically be, for example:
Wherein,indicate->Distinguishing the individual meteorological parameters; />Indicate->The first part of the meteorological parameters>The degree of mutation of the individual raw data points; />Indicate->Total number of raw data points in the individual meteorological parameters; />Indicate->Individual gasThe number of extreme points in the image parameters; />Indicate->The first part of the meteorological parameters>The number of raw data points in the extremum interval where the raw data points lie, i.e. +.>The first part of the meteorological parameters>Initial weights of the raw data points; />Representing a normalization function for normalization processing; />Representing natural constants; />Representing a second regulatory factor, in one embodiment of the invention the second regulatory factor +.>The specific value of the second adjustment factor is set to 0.2, which may be set by the practitioner according to the specific implementation scenario, and is not limited herein.
During the acquisition of the differential of each meteorological parameter,representing the final weight of each raw data point in the meteorological parameter, wherein +.>Representing the number of original data points in the extremum interval in which the original data point is located, the larger the value, the description of the original data point in the extremum intervalThe more the number of data points, the lower the probability that the original data point in the extremum interval is interfered by noise, the higher the final weight obtained by the original data point in the extremum interval is, and the extremum point does not belong to the extremum interval, so the final weight of the extremum point is the minimum value 0, and the second adjusting factor- >Setting to 0.2, when the number of the original data points in the extremum interval exceeds 10, the subsequent difference is extremely small, and the change is relatively quick when the number of the original data points in the extremum interval is 1 to 10, so that the interference of noise on the calculation distinction degree is avoided as much as possible, and the overall mutation degree of the meteorological parameters is obtained by carrying out weighted summation on the mutation degree through the final weight; />Representing the duty ratio of the extreme point in each meteorological parameter in the original data point, namely the specific gravity of the extreme point, wherein the higher the specific gravity of the extreme point is, the higher the condition that the original data point in the meteorological parameter continuously tends to change is, and the method is used for restraining the overall mutation degree, so that the fluctuation characteristic value is further obtained, and the negative correlation mapping is carried out to obtain the distinction degree->The greater the degree of discrimination, the weaker the fluctuation feature of the weather parameter is, and the more stable the weather parameter tends to be, and the greater the likelihood that the fluctuation part of the weather parameter is considered to be noise when the fluctuation feature of the weather parameter is analyzed in the subsequent step.
Step S3: taking any one of the meteorological parameters as the meteorological parameter to be measured, and carrying out correlation analysis on the meteorological parameter to be measured and other meteorological parameters according to the numerical value of the original data point in each meteorological parameter to obtain a correlation coefficient; acquiring a time sequence range of each original data point in the meteorological parameters to be measured according to sampling intervals of all the meteorological parameters; and obtaining the reference value of each original data point in the meteorological parameters to be measured according to the distribution of the original data points, the difference of sampling intervals, the correlation coefficient and the distinction degree of the meteorological parameters to be measured and other meteorological parameters in the time sequence range.
According to the embodiment of the invention, the reference value of each original data point in the meteorological parameters is required to be analyzed, so that the final interpolation effect can be guaranteed to be optimal, in order to analyze each meteorological parameter more truly and specifically, comprehensive analysis is required to be carried out by combining other meteorological parameters, therefore, any one meteorological parameter can be used as the meteorological parameter to be tested, all the meteorological parameters except the meteorological parameter to be tested are other meteorological parameters, certain correlation among different meteorological parameters is considered, and therefore, the correlation analysis can be carried out on the meteorological parameter to be tested and the other meteorological parameters according to the numerical value of the original data point in each meteorological parameter, so that the correlation coefficient is obtained, and the correlation degree between the meteorological parameter to be tested and each other meteorological parameter is reflected by the correlation coefficient.
Preferably, in one embodiment of the present invention, the pearson correlation coefficient is obtained according to the values of all the original data points in the weather parameter to be measured and the values of all the original data points in each other weather parameter, and the pearson correlation coefficient is used as the correlation coefficient between the weather parameter to be measured and each other weather parameter, where it is to be noted that the method for obtaining the pearson correlation coefficient is a technical means known to those skilled in the art, and will not be described in detail herein, in the subsequent steps Representing the weather parameter to be measured and +.>The larger the correlation coefficient between the other meteorological parameters, the higher the correlation degree between the meteorological parameters to be measured and certain other meteorological parameters.
Further, the time sequence range of each original data point in the meteorological parameters to be detected can be obtained, and in the follow-up process, the original data points of the meteorological parameters to be detected and a plurality of other parameters to be detected in the time sequence range are comprehensively analyzed, so that the accurate reference value of each original data point is obtained.
Preferably, in one embodiment of the present invention, the method for acquiring the time sequence range of each raw data point specifically includes:
the sampling intervals of all the meteorological parameters are different, so that the least common multiple of the sampling intervals of all the meteorological parameters can be used as a standard sampling time length; taking the ratio of the standard sampling time length to the sampling interval of the meteorological parameter to be measured as the standard sampling quantity of the meteorological parameter to be measured; taking the standard sampling number of other original data points which are closest to the moment of each original data point in the meteorological parameter to be measured as reference data points of the original data points; and acquiring a time sequence range of each original data point, wherein the left end point of the time sequence range is the minimum value of the moment of the corresponding reference data point, and the right end point of the time sequence range is the maximum value of the moment of the corresponding reference data point.
After the time sequence range of each original data point in the meteorological parameters to be detected is acquired, the original data points of the meteorological parameters to be detected and other meteorological parameters in the time sequence range can be combined, the reference value of each original data point in the meteorological parameters to be detected is analyzed, the tolerance of the original data point to errors generated by interpolation in the subsequent interpolation process is evaluated through the reference value, and the larger the reference value, the smaller the tolerance of the original data point to the errors is.
Preferably, in one embodiment of the present invention, the method for obtaining the reference value of each raw data point in the meteorological parameter to be measured specifically includes:
taking the absolute value of the difference value between the sampling interval of the meteorological parameter to be detected and the sampling interval of each other meteorological parameter as the sampling interval difference, and carrying out negative correlation normalization processing on the sampling interval difference to obtain a first coefficient; taking the correlation coefficient between the meteorological parameter to be measured and each other meteorological parameter as a second coefficient; taking the standard deviation of the original data points of each other meteorological parameter in the time sequence range as the fluctuation degree of the other meteorological parameters in the time sequence range; carrying out negative correlation normalization processing on the fluctuation degree, and multiplying the obtained product by the distinguishing degree of the corresponding meteorological parameters to obtain a third coefficient; multiplying the first coefficient, the second coefficient and the third coefficient to obtain an adjustment coefficient of each other meteorological parameter; based on a dynamic time warping algorithm (Dynamic Time Warping, DTW), carrying out dynamic time warping processing on original data points of the to-be-detected meteorological parameters and each other meteorological parameter in a time sequence range, and obtaining the similarity degree of the to-be-detected meteorological parameters and each other meteorological parameter in the time sequence range; taking the average value of all the similarity degrees as the overall similarity degree; multiplying the difference value of each similarity degree and the overall similarity with an adjustment coefficient to obtain the similarity deviation of each other meteorological parameter; the square sum of similarity deviation of all other meteorological parameters is averaged and then normalized to obtain the reference value of each original data point in the meteorological parameters to be measured, and it should be noted that dynamic time warping is a technical means well known to those skilled in the art, and will not be described herein. The expression of the reference value may specifically be, for example:
Wherein,representing the%>Reference value of the individual raw data points; />Indicate->Adjusting coefficients of other meteorological parameters; />Representing the total number of meteorological parameters, since the embodiment of the invention performs data acquisition on a plurality of different meteorological parameters, the method is +.>；/>Indicating +.>Within the time sequence range of the original data points, the meteorological parameters to be measured and the +.>The degree of similarity between the raw data points of the other meteorological parameters; />Indicating +.>In the time sequence range of the original data points, the average value of the similarity degree between the meteorological parameter to be detected and the original data points of all other meteorological parameters, namely the overall similarity degree; />Representing the sampling interval of the meteorological parameters to be measured; />Indicate->Sampling intervals of other meteorological parameters; />Representing the weather parameter to be measured and +.>Correlation coefficients between the other meteorological parameters; />Indicate->Distinguishing the other meteorological parameters; />Indicating +.>Within the time sequence range of the original data points +.>Standard deviation of raw data points of other meteorological parameters; />Representing a normalization function for normalization processing; />Representing natural constants.
In the process of acquiring the reference value of the original data point in the meteorological parameter to be measured, the embodiment of the invention comprises the following steps ofBased on the reference value of the original data point in the meteorological parameter to be measured, the similarity degree between the meteorological parameter to be measured and other meteorological parameters is reduced by taking the difference of sampling intervals into consideration, so the method is +.>As a first coefficient, for adjusting the degree of similarity; since the degree of correlation between the weather parameter to be measured and each other weather parameter is different, the degree of similarity between the weather parameter to be measured and each other weather parameter is reduced, the correlation coefficient is increased>As a second coefficient; the embodiment of the invention uses standard deviation->Representing the fluctuation degree of original data points of other meteorological parameters in a time sequence range, wherein the larger the standard deviation is, the larger the fluctuation degree caused by noise is, and the reference price of the original data points in the meteorological parameters to be measured isThe smaller the value, the further the normalization processing of the negative correlation is carried out on the standard deviation, and the differentiation degree is combined>For->Constraint is carried out to obtain a third coefficient, and the product of the first coefficient, the second coefficient and the third coefficient is used as the adjustment coefficient of each other meteorological parameter +.>Based on adjustment coefficient->For->Adjusting to obtain the reference value of each data point in the meteorological parameters to be measured >。
Based on the above process, the reference value of the original data point in each meteorological parameter can be obtained, and in the subsequent process of interpolating the meteorological parameters, the error before and after the interpolation of the original data point can be adjusted by utilizing the reference value, so that the optimal interpolation effect can be ensured.
Step S4: performing interpolation processing on each meteorological parameter to obtain different interpolation curves; obtaining an optimal interpolation curve according to the difference and the reference value of the original data point of each time in each meteorological parameter and the data point of the interpolation curve at the corresponding time; and evaluating and monitoring the environmental pollution according to the optimal interpolation curves of all the meteorological parameters.
Because the sampling intervals of the sensors of different meteorological parameters are different, interpolation processing is needed to be carried out on the meteorological parameters in order to more accurately monitor and manage the collected meteorological data, data points with the same time sequence are selected from the obtained interpolation curves, multiple interpolation can be carried out on each meteorological parameter to obtain the best interpolation effect, a plurality of different interpolation curves are obtained, and the best interpolation curve is selected from the different interpolation curves.
Preferably, in one embodiment of the present invention, the method for obtaining the different interpolation curves specifically includes:
The preset initial smoothing parameters are obtained, in one embodiment of the present invention, the preset initial smoothing parameters are set to 1, and specific values thereof can be set by an implementer according to specific implementation scenarios, which are not limited herein, but the range of the preset initial smoothing parameters is ensured to beOptimizing preset initial smoothing parameters according to a gradient descent method to obtain different adjustment smoothing parameters; based on a cubic spline interpolation algorithm, each weather parameter is interpolated by using each adjustment smoothing parameter to obtain an interpolation curve of the weather parameter under different adjustment smoothing parameters, and it should be noted that a gradient descent method and the cubic spline interpolation algorithm are technical means well known to those skilled in the art, and are not described herein.
After the interpolation curves with different meteorological parameters are obtained, each interpolation curve can be evaluated, so that the optimal interpolation curve is selected, the interpolation curve is generally evaluated according to the difference between the original data point of each moment in each meteorological parameter and the data point of the interpolation curve at the corresponding moment, and the different original data points have different reference values, and the tolerance of the original data point with the larger reference value to errors is smaller, so that the optimal interpolation curve can be further selected by combining the reference values.
Preferably, in one embodiment of the present invention, the method for obtaining the optimal interpolation curve specifically includes:
taking the difference value between the original data point of each moment in each meteorological parameter and the data point of the interpolation curve at the corresponding moment as the initial interpolation error of each original data point; taking the product of the initial interpolation error and the reference value as an optimized interpolation error of each original data point; averaging the square sum of the optimized interpolation errors of all the original data points to obtain the integral interpolation error of each interpolation curve; and taking the interpolation curve corresponding to the minimum value of the overall interpolation error as the optimal interpolation curve of each meteorological parameter. The expression of the overall interpolation error may specifically be, for example:
wherein,indicate->The first part of the meteorological parameters>Overall interpolation error of the interpolation curves; />Indicate->The first part of the meteorological parameters>A number of raw data points; />Is indicated at +.>On the interpolation curve and +.>No. H of Meteorological parameters>Data points corresponding to the original data points; />First->The first part of the meteorological parameters>Reference value of the individual raw data points; />Represent the firstTotal number of raw data points in each meteorological parameter.
During the acquisition of the overall interpolation error for each interpolation curve, Representing the initial interpolation error, i.e. the error value of the original data point before and after interpolation, due to the reference value +.>The larger the original data point is, the smaller the tolerance of the error is, so the original interpolation error is adjusted by using the reference value, the original interpolation error of the original data point with larger reference value is amplified, thereby the optimized interpolation error of each original data point is obtained, the square sum of the optimized interpolation errors of all the original data points is further averaged, and the interpolation error generated by the interpolation curve on the whole, namely the whole interpolation error->The smaller the overall interpolation error after adjustment, the better the effect of the interpolation curve is, so the interpolation curve corresponding to the minimum value of the overall interpolation error is used as the optimal interpolation curve of the meteorological parameter.
After the optimal interpolation curve of each meteorological parameter is obtained, the optimal interpolation curve is a continuous curve, so that in order to solve the problem that original data points of different meteorological parameters cannot keep the same time sequence due to different sampling intervals of a sensor, the environmental pollution can be estimated and monitored according to the optimal interpolation curve of each meteorological parameter, and the accuracy of estimating and monitoring the environmental pollution is improved.
Preferably, the method for evaluating and monitoring the environmental pollution in one embodiment of the invention specifically comprises the following steps:
and respectively selecting data points with the same time sequence on the optimal interpolation curves of all the meteorological parameters, acquiring a data point sequence of each meteorological parameter, and inputting the data point sequence of all the meteorological parameters into an air quality evaluation algorithm for environmental pollution evaluation and monitoring. It should be noted that the air quality evaluation algorithm is a technical means well known to those skilled in the art, and will not be described herein.
One embodiment of the invention provides an environmental pollution evaluation and monitoring system based on big data, which comprises a memory, a processor and a computer program, wherein the memory is used for storing the corresponding computer program, the processor is used for running the corresponding computer program, and the computer program can realize the method described in the steps S1-S4 when running in the processor.
In summary, the embodiment of the invention firstly obtains the original data points of different meteorological parameters, and obtains the mutation degree of each original data point and the extreme point in the meteorological parameters according to the distribution of the original data points in each meteorological parameter; then, based on the mutation degree of each original data point in the meteorological parameters, the distribution of extreme points and the number of the extreme points, the distinguishing degree of the meteorological parameters is obtained; further taking any one of the weather parameters as a weather parameter to be measured, respectively carrying out correlation analysis on the weather parameter to be measured and each other weather parameter, and taking the pearson correlation coefficient as a correlation coefficient between the weather parameter to be measured and each other weather parameter; acquiring a time sequence range of each original data point in the meteorological parameters to be measured based on sampling intervals of all the meteorological parameters, and acquiring a reference value of each original data point in the meteorological parameters to be measured according to distribution, difference of sampling intervals, correlation coefficient and distinction of the original data points in the time sequence range of the meteorological parameters to be measured and other meteorological parameters; and then, carrying out interpolation processing on the meteorological parameters to obtain different interpolation curves, combining the reference value of the original data points and errors generated by the original data points before and after interpolation to obtain the optimal interpolation curve of each meteorological parameter, and carrying out evaluation and monitoring on environmental pollution based on the optimal interpolation curve of each meteorological parameter.
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 (7)
1. An environmental pollution assessment and monitoring method based on big data, characterized in that the method comprises the following steps:
acquiring original data points of different meteorological parameters at different moments, wherein sampling intervals of the different meteorological parameters are different;
according to the distribution of the original data points in each meteorological parameter, obtaining the mutation degree of each original data point and the extreme point in the meteorological parameter; obtaining the distinguishing degree of the meteorological parameters according to the mutation degree of all original data points in each meteorological parameter, the distribution of the extreme points and the number of the extreme points;
Taking any one of the meteorological parameters as the meteorological parameter to be measured, and carrying out correlation analysis on the meteorological parameter to be measured and other meteorological parameters according to the numerical value of the original data point in each meteorological parameter to obtain a correlation coefficient; acquiring a time sequence range of each original data point in the meteorological parameters to be measured according to sampling intervals of all the meteorological parameters; obtaining the reference value of each original data point in the meteorological parameters to be detected according to the distribution of the original data points of the meteorological parameters to be detected and other meteorological parameters in the time sequence range, the difference of the sampling intervals, the correlation coefficient and the distinction degree;
performing interpolation processing on each meteorological parameter to obtain different interpolation curves; obtaining an optimal interpolation curve according to the difference between the original data point of each moment in each meteorological parameter and the data point of the interpolation curve at the corresponding moment and the reference value; evaluating and monitoring the environmental pollution according to the optimal interpolation curves of all meteorological parameters;
the obtaining the distinguishing degree of the meteorological parameters according to the mutation degree of all original data points in each meteorological parameter, the distribution of the extreme points and the number of the extreme points comprises the following steps:
Dividing all original data points in each meteorological parameter based on the position of the extreme point to obtain different extreme value intervals, wherein the original data points in the extreme value intervals do not comprise the extreme point;
taking the number of original data points in an extremum interval where each original data point is located as an initial weight of each original data point, wherein the initial weight of each extremum point is 0;
normalizing the initial weight to obtain the final weight of each original data point;
according to the final weight, carrying out weighted summation on the mutation degree of the corresponding original data point in each meteorological parameter to obtain the integral mutation degree of the meteorological parameter;
taking the ratio of the number of extreme points in each meteorological parameter to the total number of original data points in the corresponding meteorological parameter as the extreme point specific gravity of the meteorological parameter;
normalizing the product value of the integral mutation degree and the extreme point specific gravity to obtain a fluctuation characteristic value of the meteorological parameter; carrying out negative correlation mapping on the fluctuation characteristic values to obtain the degree of distinction between each meteorological parameter and noise;
the obtaining the reference value of each original data point in the meteorological parameters to be measured according to the distribution of the original data points of the meteorological parameters to be measured and other meteorological parameters in the time sequence range, the difference of the sampling intervals, the correlation coefficient and the distinction degree comprises the following steps:
Taking the absolute value of the difference value between the sampling interval of the meteorological parameter to be detected and the sampling interval of each other meteorological parameter as the sampling interval difference, and carrying out negative correlation normalization processing on the sampling interval difference to obtain a first coefficient;
taking the correlation coefficient between the meteorological parameter to be measured and each other meteorological parameter as a second coefficient;
taking the standard deviation of the original data points of each other meteorological parameter in the time sequence range as the fluctuation degree of the other meteorological parameters in the time sequence range; carrying out negative correlation normalization processing on the fluctuation degree, and multiplying the obtained product by the discrimination degree of the corresponding meteorological parameter to obtain a third coefficient;
multiplying the first coefficient, the second coefficient and the third coefficient to obtain an adjustment coefficient of each other meteorological parameter;
performing dynamic time warping processing on the to-be-detected meteorological parameters and original data points of each other meteorological parameter in the time sequence range based on a DTW algorithm to obtain the similarity degree of the to-be-detected meteorological parameters and each other meteorological parameter in the time sequence range; taking the average value of all the similarity degrees as the overall similarity degree;
multiplying the difference value of each similarity degree and the overall similarity degree by the adjustment coefficient to obtain the similarity deviation of each other meteorological parameter;
Averaging the square sums of similarity deviations of all other meteorological parameters, and then carrying out normalization processing to obtain the reference value of each original data point in the meteorological parameters to be detected;
the obtaining the optimal interpolation curve according to the difference between the original data point of each time in each meteorological parameter and the data point of the interpolation curve at the corresponding time and the reference value comprises the following steps:
taking the difference value between the original data point of each moment in each meteorological parameter and the data point of the interpolation curve at the corresponding moment as the initial interpolation error of each original data point;
taking the product of the initial interpolation error and the reference value as an optimized interpolation error for each raw data point;
averaging the square sum of the optimized interpolation errors of all the original data points to obtain the integral interpolation error of each interpolation curve;
and taking the interpolation curve corresponding to the minimum value of the overall interpolation error as the optimal interpolation curve of each meteorological parameter.
2. The method for evaluating and monitoring environmental pollution based on big data according to claim 1, wherein the obtaining the mutation degree of each original data point and the extreme point in the meteorological parameters according to the distribution of the original data points in each meteorological parameter comprises:
Acquiring two adjacent data points, which are closest to each original data point, wherein the time interval between the original data point and the corresponding adjacent data point is equal to the sampling interval, and the first original data point and the last original data point in each meteorological parameter are respectively taken as one adjacent data point of the original data point; if the original data point is larger or smaller than the two corresponding adjacent data points at the same time, taking the original data point as an extreme point;
taking the absolute value of the difference value between the original data point and each adjacent data point as an initial change value, and taking the sum value of the initial change values of the original data point and the two corresponding adjacent data points as a first mutation coefficient;
taking the absolute value of the difference value of two adjacent data points corresponding to the original data point as a second mutation coefficient;
a degree of mutation for each raw data point is obtained, the degree of mutation being positively correlated with the first mutation coefficient, and the degree of mutation being negatively correlated with the second mutation coefficient.
3. The method for evaluating and monitoring environmental pollution based on big data according to claim 1, wherein the step of performing correlation analysis on the weather parameter to be tested and other weather parameters according to the values of the original data points in each weather parameter to obtain the correlation coefficient comprises:
And acquiring a pearson correlation coefficient according to the values of all the original data points in the meteorological parameters to be measured and the values of all the original data points in other meteorological parameters, and taking the pearson correlation coefficient as a correlation coefficient between the meteorological parameters to be measured and each other meteorological parameter.
4. The method for evaluating and monitoring environmental pollution based on big data according to claim 1, wherein the obtaining the time sequence range of each original data point in the meteorological parameters to be measured according to the sampling intervals of all the meteorological parameters comprises:
taking the least common multiple of the sampling intervals of all meteorological parameters as a standard sampling duration;
taking the ratio of the standard sampling time length to the sampling interval of the meteorological parameter to be measured as the standard sampling quantity of the meteorological parameter to be measured;
taking the standard sampling number of other original data points which are closest to the moment of each original data point in the meteorological parameter to be measured as reference data points of the original data points;
and acquiring a time sequence range of each original data point, wherein the left end point of the time sequence range is a minimum value corresponding to the moment of the reference data point, and the right end point of the time sequence range is a maximum value corresponding to the moment of the reference data point.
5. The method for evaluating and monitoring environmental pollution based on big data according to claim 1, wherein the interpolating each meteorological parameter to obtain a different interpolation curve comprises:
acquiring preset initial smoothing parameters, and optimizing the preset initial smoothing parameters according to a gradient descent method to acquire different adjustment smoothing parameters;
and carrying out interpolation processing on each meteorological parameter by using each adjustment smoothing parameter based on a cubic spline interpolation algorithm to obtain interpolation curves of the meteorological parameters under different adjustment smoothing parameters.
6. The method for evaluating and monitoring environmental pollution based on big data according to claim 1, wherein the evaluating and monitoring environmental pollution based on the optimal interpolation curve of all meteorological parameters comprises:
and respectively selecting data points with the same time sequence on the optimal interpolation curves of all the meteorological parameters, acquiring a data point sequence of each meteorological parameter, and inputting the data point sequence of all the meteorological parameters into an air quality evaluation algorithm for environmental pollution evaluation and monitoring.
7. An environmental pollution assessment and monitoring system based on big data, the system comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1-6 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311465602.XA CN117196353B (en) | 2023-11-07 | 2023-11-07 | Environmental pollution assessment and monitoring method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311465602.XA CN117196353B (en) | 2023-11-07 | 2023-11-07 | Environmental pollution assessment and monitoring method and system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117196353A CN117196353A (en) | 2023-12-08 |
| CN117196353B true CN117196353B (en) | 2024-02-27 |
Family
ID=88998335
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311465602.XA Active CN117196353B (en) | 2023-11-07 | 2023-11-07 | Environmental pollution assessment and monitoring method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117196353B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117390591B (en) * | 2023-12-11 | 2024-03-26 | 华洋通信科技股份有限公司 | Operation monitoring method and system for coal conveying belt sampling machine based on electric parameter analysis |
| CN117786584B (en) * | 2024-02-27 | 2024-04-30 | 西安中创博远网络科技有限公司 | Big data analysis-based method and system for monitoring and early warning of water source pollution in animal husbandry |
| CN117931094A (en) * | 2024-03-21 | 2024-04-26 | 山东奥斯瑞特检验检测有限公司 | Block chain-based reliable storage method for ambient air monitoring data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106228296A (en) * | 2016-07-18 | 2016-12-14 | 华南理工大学 | Screening preprocess method for the meteorological big data of overhead transmission line load evaluation |
| CN110895526A (en) * | 2019-11-29 | 2020-03-20 | 南京信息工程大学 | Method for correcting data abnormity in atmosphere monitoring system |
| CN111027686A (en) * | 2019-12-26 | 2020-04-17 | 杭州鲁尔物联科技有限公司 | Landslide displacement prediction method, device and equipment |
| CN116383754A (en) * | 2023-06-05 | 2023-07-04 | 丹纳威奥贯通道系统（青岛）有限公司 | On-line monitoring system and method for production of locomotive accessories |
| CN116773186A (en) * | 2023-08-22 | 2023-09-19 | 浙江恒齿传动股份有限公司 | Speed reducer operation detection method and system based on multi-mode data |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| PL3343249T3 (en) * | 2017-01-03 | 2020-05-18 | UBIMET GmbH | Method for increasing the spatial resolution of a weather prediction |
-
2023
- 2023-11-07 CN CN202311465602.XA patent/CN117196353B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106228296A (en) * | 2016-07-18 | 2016-12-14 | 华南理工大学 | Screening preprocess method for the meteorological big data of overhead transmission line load evaluation |
| CN110895526A (en) * | 2019-11-29 | 2020-03-20 | 南京信息工程大学 | Method for correcting data abnormity in atmosphere monitoring system |
| CN111027686A (en) * | 2019-12-26 | 2020-04-17 | 杭州鲁尔物联科技有限公司 | Landslide displacement prediction method, device and equipment |
| CN116383754A (en) * | 2023-06-05 | 2023-07-04 | 丹纳威奥贯通道系统（青岛）有限公司 | On-line monitoring system and method for production of locomotive accessories |
| CN116773186A (en) * | 2023-08-22 | 2023-09-19 | 浙江恒齿传动股份有限公司 | Speed reducer operation detection method and system based on multi-mode data |
Non-Patent Citations (1)
| Title |
|---|
| 建筑能耗用室外气象资料的研究历史与现状;万蓉;刘加平;;工业建筑(第S1期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117196353A (en) | 2023-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117196353B (en) | Environmental pollution assessment and monitoring method and system based on big data | |
| CN109542740B (en) | Abnormality detection method and apparatus | |
| CN110070282B (en) | Low-voltage transformer area line loss influence factor analysis method based on comprehensive relevance | |
| CN115876258B (en) | Livestock and poultry breeding environment abnormity monitoring and alarming system based on multi-source data | |
| CN115824993B (en) | Method and device for determining water body chemical oxygen demand, computer equipment and medium | |
| CN116066343A (en) | Intelligent early warning method and system for fault model of oil delivery pump unit | |
| CN110852906B (en) | Method and system for identifying electricity stealing suspicion based on high-dimensional random matrix | |
| CN110298765B (en) | Power distribution network power consumption abnormality detection method based on objective correlation factors | |
| CN117313020B (en) | Data processing method of bearing type tension sensor | |
| CN117540325B (en) | Business database anomaly detection method and system based on data variation capture | |
| CN110956331A (en) | Method, system and device for predicting operation state of digital factory | |
| CN117556366A (en) | Data abnormality detection system and method based on data screening | |
| CN112949735A (en) | Liquid hazardous chemical substance volatile concentration abnormity discovery method based on outlier data mining | |
| CN116842722A (en) | Method, system and electronic equipment for determining confidence coefficient of simulation model of gas turbine | |
| CN114487284B (en) | Method and system for measuring concentration of heavy metal in air | |
| CN107506824B (en) | Method and device for detecting bad observation data of power distribution network | |
| CN113139673A (en) | Method, device, terminal and storage medium for predicting air quality | |
| CN107506779B (en) | Estimation method and system for water content of plant stems | |
| CN117216489B (en) | Waterproof coating quality inspection analysis method and system based on Internet | |
| CN117992894B (en) | Agricultural greenhouse environment abnormal data monitoring method based on Internet of things | |
| CN114593960B (en) | Pure steam sampling method and system under multiple factors | |
| CN116661522B (en) | Intelligent temperature regulation and control method for temperature change test box based on data processing | |
| CN117798744B (en) | Method for monitoring running state of numerical control machine tool | |
| CN117786445B (en) | Intelligent processing method for operation data of automatic yarn reeling machine | |
| CN113093845B (en) | Exhibition hall exhibition environment analysis regulation and control central control system based on cloud computing and Internet of things |
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 |