CN117540238B - Data security management method for industrial digital information acquisition device - Google Patents
Data security management method for industrial digital information acquisition device Download PDFInfo
- Publication number
- CN117540238B CN117540238B CN202410014473.0A CN202410014473A CN117540238B CN 117540238 B CN117540238 B CN 117540238B CN 202410014473 A CN202410014473 A CN 202410014473A CN 117540238 B CN117540238 B CN 117540238B
- Authority
- CN
- China
- Prior art keywords
- industrial data
- industrial
- data point
- points
- 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.)
- Active
Links
- 238000007726 management method Methods 0.000 title claims abstract description 33
- 238000012216 screening Methods 0.000 claims abstract description 81
- 238000001914 filtration Methods 0.000 claims abstract description 21
- 230000002159 abnormal effect Effects 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 53
- 238000009825 accumulation Methods 0.000 claims description 23
- 238000002955 isolation Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 11
- 238000010606 normalization Methods 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 abstract description 5
- 230000009467 reduction Effects 0.000 abstract description 4
- 238000004519 manufacturing process Methods 0.000 description 8
- 238000009776 industrial production Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000000739 chaotic effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007873 sieving Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Indication And Recording Devices For Special Purposes And Tariff Metering Devices (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a data security management method for an industrial digital information acquisition device, which comprises the following steps: collecting industrial information data sequences with a plurality of dimensions; obtaining a local industrial data point segment according to the industrial information data sequence; screening clusters are obtained according to the local industrial data point segments; obtaining a local screening fluctuation factor according to the screening cluster; obtaining a fluctuation constraint factor according to the local screening fluctuation factor; obtaining a fluctuation anomaly coefficient according to the distance difference between different industrial data points in the same screening cluster of the local industrial data point segments; obtaining a noise factor according to the fluctuation abnormal coefficient and the fluctuation constraint factor; obtaining a filtered data point segment according to the noise factor; and carrying out safety management on the industrial data according to the filtered data point segments. The invention ensures that the window size of the SG filtering is more intelligent, improves the credibility of the noise reduction result of the industrial data and improves the efficiency of data security management.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a data security management method for an industrial digital information acquisition device.
Background
The industrial digital information acquisition device is equipment for acquiring various industrial data such as temperature, pressure and the like in an industrial production process so as to monitor, control and analyze later; in order to ensure the safety of the industrial data, the industrial data needs to be encrypted so as to realize the safety management of the data; however, due to the influence of the industrial environment, the acquired industrial data has large noise, and the key generation and transmission process of the industrial data are greatly interfered, so that the noise reduction treatment of the industrial data is required.
The traditional method generally utilizes SG (Savitzky-Golay) filtering to denoise industrial data, but because the corresponding production environment can generate corresponding changes according to different production conditions in the industrial production process, the noise amount contained in the industrial data in the time periods with different lengths is different, but the traditional SG filtering only denoises the industrial data in the time periods with fixed lengths through a fixed window, so that the reliability of a final denoising result is reduced, the denoising efficiency of the industrial data is reduced, and the safety management efficiency of the data is reduced.
Disclosure of Invention
The invention provides a data security management method for an industrial digital information acquisition device, which aims to solve the existing problems: the traditional SG filtering can not adjust the fixed window to reduce noise of industrial data in time periods with different lengths according to different noise amounts generated by different production environments.
The invention relates to a data security management method for an industrial digital information acquisition device, which adopts the following technical scheme:
the method comprises the following steps:
collecting an industrial information data sequence of a plurality of dimensions, wherein the industrial information data sequence comprises a plurality of industrial data;
dividing an industrial information data sequence into a number of local industrial data point segments, the local industrial data point segments comprising a plurality of industrial data points; clustering the industrial data points according to the change stability condition of the industrial data points in the local industrial data point segments to obtain a plurality of screened clusters, wherein the screened clusters comprise a plurality of reference industrial data points; obtaining local screening fluctuation factors of a plurality of reference industrial data points according to the numerical fluctuation conditions of the reference industrial data points in the screening cluster; obtaining fluctuation constraint factors of each industrial data point according to trend change differences among different reference industrial data points and the local screening fluctuation factors;
obtaining a plurality of neighborhood trend distances according to the distance difference between different industrial data points in the same screening cluster of the local industrial data point segments; obtaining a fluctuation anomaly coefficient of each reference industrial data point according to the difference between different neighborhood trend distances, wherein the fluctuation anomaly coefficient is used for describing the difference between industrial data and noise data; obtaining a noise factor of each industrial data point according to the difference of fluctuation abnormal coefficients of different industrial data points on the same reference industrial data point and fluctuation constraint factors of different industrial data points, wherein the noise factor is used for describing the probability that the industrial data is interfered by noise;
Repartitioning the industrial information data sequence into a plurality of filtered data point segments according to the size of the noise factor; and carrying out safety management on the industrial data according to the filtered data point segments.
Preferably, the dividing the industrial information data sequence into a plurality of local industrial data point segments comprises the following specific methods:
the sampling time is taken as an abscissa, the industrial data is taken as an ordinate, a two-dimensional coordinate system is constructed according to the abscissa and the ordinate, for any one industrial information data sequence, the industrial information data sequence is input into the two-dimensional coordinate system, a plurality of data points are obtained, and each data point is recorded as an industrial data point;
presetting an industrial data point numberThe method comprises the steps of carrying out a first treatment on the surface of the Any one industrial data point is marked as a target industrial data point, and the target industrial data point is +.>Individual industrial data point and target industrial data point>The data point segments collectively formed by the individual industrial data points are noted as local industrial data point segments of the target industrial data point.
Preferably, the clustering of the industrial data points according to the variation stability of the industrial data points in the local industrial data point segments to obtain a plurality of screened clusters comprises the following specific methods:
marking standard deviations of all industrial data points in a local industrial data point section of any one industrial data point as neighborhood industrial fluctuation values of target industrial data points; obtaining neighborhood industrial fluctuation values of all industrial data points;
Presetting a cluster number intervalWill->Each positive integer contained in the cluster is taken as a cluster quantity preset value; for any preset value of the cluster number, marking any industrial data point as a first target industrial data point, and taking the preset value of the cluster number as an initial cluster number +.>According to the initial cluster number->Clustering neighborhood industrial fluctuation values of all industrial data points in a local industrial data point section of a first target industrial data point to obtain a plurality of clusters; the average value of the contour coefficients of all neighborhood industrial fluctuation values in all cluster clusters is recorded as the preset selection degree of the preset value of the cluster quantity; obtaining preset selection degrees of preset values of the number of all the clusters, marking the preset value of the number of the clusters with the largest preset selection degree as the preset value of the number of the optimal clusters, and marking each cluster corresponding to the preset value of the number of the optimal clusters as a screened cluster of the first target industrial data point.
Preferably, the local sieving fluctuation factor of a plurality of reference industrial data points is obtained according to the numerical fluctuation condition of the reference industrial data points in the sieving cluster, and the specific method comprises the following steps:
recording any one industrial data point as a second target industrial data point, recording any one industrial data point in any one screening cluster of the second target industrial data point as a reference industrial data point of the second target industrial data point, recording any one industrial data point in a local industrial data point section of the reference industrial data point as a first reference industrial data point of the reference industrial data point, and recording the first reference industrial data point as a local screening industrial data point of the reference data point if the first reference industrial data point appears in the screening cluster; all local screening industrial data points of the reference industrial data point are acquired, and standard deviations of all local screening industrial data points of the reference industrial data point are recorded as local screening fluctuation factors of the reference industrial data point.
Preferably, the fluctuation constraint factor of each industrial data point is obtained according to the trend change difference between different reference industrial data points and the local screening fluctuation factor, and the specific method comprises the following steps:
recording any one of the industrial data points as a third target industrial data point;
for any one reference industrial data point in any screening cluster of the third target industrial data point, acquiring all extreme points of all local screening industrial data points of the reference industrial data point, and recording the number of all the extreme points as the local screening extreme value quantity of the reference industrial data point; obtaining local screening extremum of all reference industrial data points in the screening cluster of the third target industrial data point;
in the method, in the process of the invention,a fluctuation constraint coefficient representing a third target industrial data point; />Representing a number of all screened clusters of the third target industrial data point; />Representing the third target industrial data point/>In the screening cluster, the variance of the local screening extremum of all the reference industrial data points; />The +.>In the screening cluster, the average value of local screening fluctuation factors of all reference industrial data points; / >An exponential function that is based on a natural constant; and acquiring fluctuation constraint coefficients of all industrial data points, carrying out linear normalization on all the fluctuation constraint coefficients, and recording each normalized fluctuation constraint coefficient as a fluctuation constraint factor.
Preferably, the method for obtaining a plurality of neighborhood trend distances according to the distance difference between different industrial data points in the same screening cluster of the local industrial data point segments comprises the following specific steps:
for any one reference industrial data point in any one screening cluster of the third target industrial data point, recording a sequence formed by all extreme points of all local screening industrial data points of the reference industrial data point as a reference industrial extreme point sequence of the reference industrial data point;
for any three adjacent extreme points in the reference industrial extreme point sequence, in the three extreme points, the Euclidean distance between the second extreme point and the first extreme point is recorded as a first distance, the Euclidean distance between the second extreme point and the third extreme point is recorded as a second distance, and the average value of the first distance and the second distance is recorded as the neighborhood trend distance of the second extreme point.
Preferably, the fluctuation anomaly coefficient of each reference industrial data point is obtained according to the difference between different neighborhood trend distances, and the specific method comprises the following steps:
In the method, in the process of the invention,a fluctuation anomaly coefficient representing any one of the reference industrial data points of any one of the industrial data points; />Representing the number of all extremum points in a reference industrial data extremum point sequence of a reference industrial data point; />Is represented in the sequence of extreme points of the reference industrial data point +.>Neighborhood trend distances of the extreme points; />Representing the average value of the neighborhood trend distances of all extreme points in a reference industrial data extreme point sequence of the reference industrial data points; />Is represented in the sequence of extreme points of the reference industrial data point +.>Industrial data of the extreme points; />An average of the industrial data representing all the locally screened industrial data points of the reference industrial data point; />The representation takes absolute value.
Preferably, the noise factor of each industrial data point is obtained according to the difference of the fluctuation abnormal coefficients of different industrial data points on the same reference industrial data point and the fluctuation constraint factors of different industrial data points, and the specific method comprises the following steps:
in the method, in the process of the invention,representing the +.f on any one industrial information data sequence>No. H of individual Industrial data points>Noise isolation factors for the individual reference industrial data points; / >Indicate->A fluctuation constraint factor for each industrial data point; />Indicating the division of the industrial information data sequence by +.>A number of all industrial data points except the individual industrial data points; />Indicate->No. H of individual Industrial data points>Fluctuation anomaly coefficients for the individual reference industrial data points; />Indicate except->No. I beyond the individual Industrial data points>No. H of individual Industrial data points>Fluctuation anomaly coefficients for the individual reference industrial data points; />Indicate except->No. I beyond the individual Industrial data points>A fluctuation constraint factor for each industrial data point;
acquisition of the firstNoise isolation factor of all reference industrial data points of the individual industrial data points, will be +.>The mean value of the noise isolation factors of all reference industrial data points of the individual industrial data points is recorded as +.>An initial noise factor for each industrial data point;
and acquiring initial noise factors of all industrial data points, carrying out linear normalization on all the initial noise isolation factors, and recording each normalized initial noise isolation factor as a noise factor.
Preferably, the method for repartitioning the industrial information data sequence into a plurality of filtered data point segments according to the size of the noise factor comprises the following specific steps:
presetting a noise factor threshold Any one of the industrial information numbersStarting the first accumulation process according to the first industrial data point in the sequence as the starting point, the step length is 1, and continuously accumulating the noise factors until the value of the accumulated noise factors is greater than or equal to +.>Stopping the first accumulation process, and recording the data segment formed by the accumulated industrial data points in the first accumulation process as a first filtering data point segment; starting the second accumulation process by taking the first industrial data point after the first filtered data point segment as a starting point and the step length as 1, and continuously accumulating the noise factors until the value of the accumulated noise factors is greater than or equal to +.>Stopping the second accumulation process, and recording the data segment formed by the accumulated industrial data points in the second accumulation process as a second filtering data point segment; and the like, stopping obtaining the filtered data point segments until the noise factors of all the industrial data points are accumulated.
Preferably, the method for performing security management on industrial data according to the filtered data point segment includes the following specific steps:
and taking each filtering data point segment as a window, performing SG filtering on industrial data in the window according to the window to obtain filtered industrial data, performing RSA asymmetric encryption on the filtered industrial data to obtain encrypted industrial data, and storing the encrypted industrial data in an industrial database.
The technical scheme of the invention has the beneficial effects that: obtaining local screening fluctuation factors of reference industrial data points according to the variation stability condition of the industrial data points in an industrial information data sequence, obtaining fluctuation constraint factors of the industrial data points according to the trend variation difference between different reference industrial data points and the local screening fluctuation factors, obtaining fluctuation anomaly coefficients of the reference industrial data points according to the distance difference between different industrial data points in the same screening cluster of local industrial data point segments, obtaining noise factors of the industrial data points according to the fluctuation anomaly coefficient difference between different industrial data points on the same reference industrial data point and the fluctuation constraint factors of different industrial data points, and carrying out safety management on the industrial data according to the noise factors; the fluctuation constraint factor of the invention reflects the data fluctuation intensity of the industrial data points in the screening cluster of the industrial data points, the fluctuation anomaly coefficient reflects the fluctuation variation chaotic degree of the local screening industrial data points of the parameter industrial data points caused by noise interference, and the noise factor reflects the probability of the industrial data being interfered by noise; the window size of SG filtering is determined more intelligently, the credibility of the noise reduction result of industrial data is improved, and the efficiency of data security management is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart showing the steps of a method for data security management for an industrial digital information acquisition device according to the present invention.
Detailed Description
In order to further describe 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 for a data security management method for an industrial digital information acquisition device according to the invention in combination with the accompanying drawings and 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 following specifically describes a specific scheme of the data security management method for the industrial digital information acquisition device provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a data security management method for an industrial digital information acquisition device according to an embodiment of the invention is shown, and the method includes the following steps:
step S001: industrial information data sequences of several dimensions are collected.
It should be noted that, in the conventional method, the industrial data is usually denoised by using SG (Savitzky-Golay) filtering, but because the corresponding production environment can generate corresponding changes due to different production conditions in the industrial production process, the noise amount contained in the industrial data in the time periods with different lengths is different, the conventional SG filtering only denoises the industrial data in the time periods with fixed lengths through a fixed window, so that the reliability of the final denoising result is reduced, the denoising efficiency of the industrial data is reduced, and the data safety management efficiency is improved. Therefore, the embodiment provides a data security management method for an industrial digital information acquisition device.
Specifically, in order to implement the data security management method for the industrial digital information acquisition device provided in this embodiment, an industrial information data sequence needs to be acquired first, and the specific process is as follows: the temperature sensor, the pressure sensor and the current sensor in the industrial digital information acquisition device are used for acquiring three industrial dimension data types, namely temperature data, pressure data and current data, once every 2 seconds, and the temperature data, the pressure data and the current data acquired each time are recorded as industrial data, and the total acquisition time is 200 seconds; taking any one industrial dimension data type as an example, arranging all industrial data of the industrial dimension data type according to the sequence from small to large of sampling time, and marking the arranged sequence as an industrial information data sequence; all industrial information data sequences are acquired. In addition, in this embodiment, the sampling time is 1 second, the industrial dimension data types are temperature data, pressure data, and current data, and the total collection time is 200 seconds, which is not specifically limited, where the sampling time, the industrial dimension data types, the number, and the total collection time may be determined according to specific implementation conditions.
So far, all industrial information data sequences are obtained by the method.
Step S002: dividing an industrial information data sequence into a plurality of local industrial data point segments; clustering the industrial data points according to the change stability condition of the industrial data points in the local industrial data point segments to obtain a plurality of screened clusters; obtaining local screening fluctuation factors of a plurality of reference industrial data points according to the numerical fluctuation conditions of the reference industrial data points in the screening cluster; and obtaining the fluctuation constraint factor of each industrial data point according to the trend change difference among different reference industrial data points and the local screening fluctuation factor.
In practical situations, as the industrial environment is changed along with the industrial process, corresponding environmental interference factors are changed continuously, so that the acquired industrial data contains a certain degree of noise, the noise is randomly distributed in the industrial data, and the industrial data acquired in different time periods are fluctuated to different degrees; however, since industrial data itself fluctuates with the industrial process itself, it is not possible to determine the actual noise-affected industrial data directly from the fluctuation of the individual industrial data.
It should be further noted that, the industrial data interfered by noise usually represents a single industrial data fluctuation, while the industrial data changed by the conventional industrial process usually represents a fluctuation change within a certain time range, and the relevance of the fluctuation change within the time range is strong; therefore, the embodiment obtains the fluctuation constraint factor of the industrial data point according to the change condition of the industrial data within a certain time range so as to facilitate subsequent analysis and processing.
Specifically, the sampling time is taken as an abscissa, the industrial data is taken as an ordinate, a two-dimensional coordinate system is constructed according to the abscissa and the ordinate, any one industrial information data sequence is taken as an example, the industrial information data sequence is input into the two-dimensional coordinate system, a plurality of data points are obtained, and each data point is obtainedThe points are noted as industrial data points; presetting an industrial data point numberWherein the present embodiment is +.>To describe the example, the present embodiment is not particularly limited, wherein +.>Depending on the particular implementation; any one industrial data point is marked as a target industrial data point, and the target industrial data point is +.>Individual industrial data point and +.>The segment of data that each industrial data point collectively constitutes is noted as a segment of local industrial data points for that target industrial data point. Wherein if the number of industrial data points actually existing before the target industrial data point does not satisfy the preset value Then the industrial data point actually existing before the target industrial data point and +.>The data point segment formed by the industrial data points is recorded as a local industrial data point segment of the target industrial data point; if the number of industrial data points actually present after the target industrial data point does not satisfy the preset +.>Then the target industrial data point is preceded by +.>The industrial data points and the data point segments formed by the industrial data points actually existing after the target industrial data point are recorded as the target workerLocal industrial data point segments of industrial data points. It should be further noted that the target industrial data point is included in the local industrial data point segment of the target industrial data point.
Further, marking the standard deviation of all industrial data points in the local industrial data point section of the target industrial data point as the neighborhood industrial fluctuation value of the target industrial data point; obtaining neighborhood industrial fluctuation values of all industrial data points; presetting a cluster number intervalWherein the present embodiment is +.>To describe the example, the present embodiment is not particularly limited, wherein +.>Depending on the particular implementation; will->Each positive integer contained in the cluster is taken as a cluster quantity preset value; taking any preset value of the cluster number as an example, recording any industrial data point as a first target industrial data point, and taking the preset value of the cluster number as an initial cluster number +. >According to the initial cluster number->Clustering neighborhood industrial fluctuation values of all industrial data points in a local industrial data point section of the first target industrial data point to obtain a plurality of clusters; the average value of the contour coefficients of all neighborhood industrial fluctuation values in all cluster clusters is recorded as the preset selection degree of the preset value of the cluster quantity; acquiring preset selection degrees of preset values of the number of all the clusters, marking the preset value of the number of the clusters with the largest preset selection degree as the preset value of the number of the optimal clusters, marking each cluster corresponding to the preset value of the number of the optimal clusters as the sieve of the first target industrial data pointAnd (5) clustering. Wherein each industrial data point corresponds to a plurality of screened clusters; the obtaining of the contour coefficients is a well-known technique, and this embodiment will not be described in detail; in addition according to the initial cluster number->The clustering process is a well-known content of the K-means clustering algorithm, and this embodiment will not be described in detail.
Further, any one of the screened cluster of the first target industrial data point is marked as a reference industrial data point of the first target industrial data point, any one of the industrial data points in the local industrial data point segment of the reference industrial data point is marked as a first reference industrial data point of the reference industrial data point, and if the first reference industrial data point appears in the screened cluster, the first reference industrial data point is marked as a local screened industrial data point of the reference data point; acquiring all local screening industrial data points of the reference industrial data point, and recording standard deviations of all local screening industrial data points of the reference industrial data point as local screening fluctuation factors of the reference industrial data point; a local screening fluctuation factor of all reference industrial data points in the screening cluster of the first target industrial data point is obtained. Wherein each industrial data point corresponds to a plurality of screened clusters, each industrial data point comprises a plurality of reference industrial data points in each screened cluster, and each reference industrial data point corresponds to a local screened fluctuation factor. It should be noted that all the reference industrial data points of each industrial data point are arranged in order from the small to the large sampling time by default.
Further, taking any one reference industrial data point of the first target industrial data point in the screening cluster as an example, acquiring all extreme points of all local screening industrial data points of the reference industrial data point, and recording the number of all the extreme points as the local screening extreme value quantity of the reference industrial data point; and acquiring local screening extremum amounts of all reference industrial data points of the first target industrial data point in the screening cluster. Wherein each reference industrial data point corresponds to a local screened extremum.
Further, a fluctuation constraint coefficient of the first target industrial data point is obtained according to the local screening fluctuation factors and the local screening extremum of each reference industrial data point in all the screening clusters of the first target industrial data point. The calculation method of the fluctuation constraint coefficient of the first target industrial data point comprises the following steps:
in the method, in the process of the invention,a fluctuation constraint coefficient representing the first target industrial data point; />A number of all screened clusters representing the first target industrial data point; />Representing +.>In the screening cluster, the variance of the local screening extremum of all the reference industrial data points; / >Representing +.>In the screening cluster, the average value of local screening fluctuation factors of all reference industrial data points; />An exponential function that is based on a natural constant; example use->The functions are used for representing inverse proportion relation and normalization processing, and an implementer can realize the following conditions according to actual situationsSelecting an inverse proportion function and a normalization function; and if the fluctuation constraint coefficient of the first target industrial data point is larger, the numerical fluctuation of the industrial data point in the screening cluster of the first target industrial data point is more severe, the degree of noise interference of the first target industrial data point is higher, and the noise reduction constraint is required for the first target industrial data point. And acquiring fluctuation constraint coefficients of all industrial data points, carrying out linear normalization on all the fluctuation constraint coefficients, and recording each normalized fluctuation constraint coefficient as a fluctuation constraint factor.
So far, the fluctuation constraint factors of all industrial data points are obtained through the method.
Step S003: obtaining a plurality of neighborhood trend distances according to the distance difference between different industrial data points in the same screening cluster of the local industrial data point segments; obtaining a fluctuation anomaly coefficient of each reference industrial data point according to the difference between different neighborhood trend distances; and obtaining the noise factor of each industrial data point according to the difference of the fluctuation abnormal coefficients of different industrial data points on the same reference industrial data point and the fluctuation constraint factors of different industrial data points.
It should be noted that, the fluctuation constraint factor of the industrial data point is obtained based on the whole industrial information data sequence, and the condition of the whole sequence can be represented; but there are also large errors in the local industrial data; therefore, the fluctuation abnormal coefficients of the industrial data points are obtained by analyzing the fluctuation conditions of the industrial data in the similar time range among different industrial data points, so that the noise factors of the industrial data points are obtained by comprehensively analyzing the fluctuation constraint factors and the fluctuation abnormal coefficients, and the subsequent denoising encryption processing is facilitated.
Specifically, any one industrial data point on the industrial information data sequence is recorded as a second target industrial data point, and any one reference industrial data point in any one screening cluster of the second target industrial data point is taken as an example; and (3) recording a sequence formed by all the extreme points of all the local screened industrial data points of the reference industrial data point as a reference industrial extreme point sequence of the reference industrial data point, taking any three adjacent extreme points in the reference industrial extreme point sequence as examples, recording Euclidean distances between a second extreme point and a first extreme point as a first distance, recording Euclidean distances between the second extreme point and a third extreme point as a second distance, recording the average value of the first distance and the second distance as the neighborhood trend distance of the second extreme point, and acquiring the neighborhood trend distance of all the extreme points in the reference industrial data extreme point sequence. The obtaining of the euclidean distance is a well-known technique, and this embodiment will not be described in detail. In addition, for the first extreme point in the reference industrial extreme point sequence, the euclidean distance between the second extreme point and the first extreme point is recorded as the neighborhood trend distance of the first extreme point; and for the last extreme point in the reference industrial extreme point sequence, marking the Euclidean distance between the last second extreme point and the last first extreme point as the neighborhood trend distance of the last extreme point.
Further, the fluctuation anomaly coefficient of the reference industrial data point is obtained according to the neighborhood trend distance of all extreme points in the reference industrial data extreme point sequence of the reference industrial data point. The calculation method of the fluctuation anomaly coefficient of the reference industrial data point comprises the following steps:
in the method, in the process of the invention,a fluctuation anomaly coefficient representing the reference industrial data point; />Representing the number of all extremum points in a sequence of extremum points of the reference industrial data point; />Is represented in the sequence of extreme points of the reference industrial data point +.>Neighborhood trend distances of the extreme points; />Representing the average value of the neighborhood trend distances of all extreme points in the reference industrial data extreme point sequence of the reference industrial data point; />Is represented in the sequence of extreme points of the reference industrial data point +.>Industrial data of the extreme points; />A mean of the industrial data representing all the locally screened industrial data points of the reference industrial data point; />The representation takes absolute value; />A degree weight representing the superposition of noise by the reference industrial data point; and if the fluctuation anomaly coefficient of the reference industrial data point is larger, which indicates that the fluctuation variation of the local screened industrial data point of the reference industrial data point caused by noise interference is more chaotic. Acquiring fluctuation anomaly coefficients of all reference industrial data points of the second target industrial data point; a fluctuation anomaly coefficient is obtained for all reference industrial data points for all industrial data points on the industrial information data sequence.
Further, according to the first of the industrial information data sequencesNo. H of individual Industrial data points>No. of the reference Industrial data Point and other Industrial data points>Fluctuation anomaly coefficient of the reference industrial data point +.>The fluctuation constraint factor of each industrial data point and other industrial data points is obtained by +.>No. H of individual Industrial data points>Noise isolation factors for the individual reference industrial data points. Wherein->No. H of individual Industrial data points>The method for calculating the noise isolation factors of the reference industrial data points comprises the following steps:
in the method, in the process of the invention,indicate->No. H of individual Industrial data points>Noise isolation factors for the individual reference industrial data points; />Indicate->A fluctuation constraint factor for each industrial data point; />Indicating the division of the industrial information data sequence by +.>A number of all industrial data points except the individual industrial data points; />Indicate->No. H of individual Industrial data points>Fluctuation anomaly coefficients for the individual reference industrial data points; />Indicate except->No. I beyond the individual Industrial data points>No. H of individual Industrial data points>Fluctuation anomaly coefficients for the individual reference industrial data points; />Indicate except->No. I beyond the individual Industrial data points>Fluctuation constraint factors for individual industrial data points. Wherein if%>No. H of individual Industrial data points >The greater the noise isolation factor of the reference industrial data point, the description +.>The more likely that anomalies around the individual industrial data points are caused by noise, reflecting +.>The more likely that individual industrial data points belong to noise points.
Further, obtain the firstNoise isolation factor of all reference industrial data points of the individual industrial data points, will be +.>The mean value of the noise isolation factors of all reference industrial data points of the individual industrial data points is recorded as +.>Initial noise factor for each industrial data point. And acquiring initial noise factors of all industrial data points, carrying out linear normalization on all the initial noise isolation factors, and recording each normalized initial noise isolation factor as a noise factor. Noise factors are obtained for all industrial data points.
So far, the noise factors of all noise points are obtained through the method.
Step S004: repartitioning the industrial information data sequence into a plurality of filtered data point segments according to the size of the noise factor; and carrying out safety management on the industrial data according to the filtered data point segments.
Specifically, a noise factor threshold is presetWherein the present embodiment is +.>To describe the example, the present embodiment is not particularly limited, wherein +. >Depending on the particular implementation; starting the first industrial data point in the industrial information data sequence as a starting point, and starting the first accumulation process with a step length of 1, and continuously accumulating the noise factors until the value of the accumulated noise factors is greater than or equal to +.>Stopping the first accumulation process, and recording the data segment formed by the accumulated industrial data points in the first accumulation process as a first filtering data point segment; starting the second accumulation process by taking the first industrial data point after the first filtered data point segment as a starting point and the step length as 1, and continuously accumulating the noise factors until the value of the accumulated noise factors is greater than or equal to +.>Stopping the second accumulation process, and recording the data segment formed by the accumulated industrial data points in the second accumulation process as a second filtering data point segment; starting the third accumulation process by taking the first industrial data point after the second filtered data point segment as a starting point and the step length as 1, and continuously accumulating the noise factors until the value of the accumulated noise factors is greater than or equal to +.>Stopping the third accumulation process, and recording the data segment formed by the accumulated industrial data points in the third accumulation process as a third filtering data point segment; and the like, stopping obtaining the filtered data point segments until the noise factors of all the industrial data points are accumulated; all filtered data point segments are acquired. Wherein if the noise factor value accumulated in the last accumulation is smaller than +. >The segment of the industrial data points that have been accumulated in the last accumulation process is then noted as the last filtered data point segment.
Further, each filtering data point segment is used as a window, industrial data in the window is filtered according to the window to obtain filtered industrial data, RSA asymmetric encryption is carried out on the filtered industrial data to obtain encrypted industrial data, and the encrypted industrial data is stored in an industrial database. The RSA asymmetric encryption algorithm is a known technology, and the filtering process of the data according to the window is a known content of SG filtering, which is not described in detail in this embodiment. The encrypted industrial data is stored in the industrial database, so that the safety management of the industrial digital data is finished.
This embodiment is completed.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (8)
1. The data security management method for the industrial digital information acquisition device is characterized by comprising the following steps of:
Collecting an industrial information data sequence of a plurality of dimensions, wherein the industrial information data sequence comprises a plurality of industrial data;
dividing an industrial information data sequence into a number of local industrial data point segments, the local industrial data point segments comprising a plurality of industrial data points; clustering the industrial data points according to the change stability condition of the industrial data points in the local industrial data point segments to obtain a plurality of screened clusters, wherein the screened clusters comprise a plurality of reference industrial data points; obtaining local screening fluctuation factors of a plurality of reference industrial data points according to the numerical fluctuation conditions of the reference industrial data points in the screening cluster; obtaining fluctuation constraint factors of each industrial data point according to trend change differences among different reference industrial data points and the local screening fluctuation factors;
obtaining a plurality of neighborhood trend distances according to the distance difference between different industrial data points in the same screening cluster of the local industrial data point segments; obtaining a fluctuation anomaly coefficient of each reference industrial data point according to the difference between different neighborhood trend distances, wherein the fluctuation anomaly coefficient is used for describing the difference between industrial data and noise data; obtaining a noise factor of each industrial data point according to the difference of fluctuation abnormal coefficients of different industrial data points on the same reference industrial data point and fluctuation constraint factors of different industrial data points, wherein the noise factor is used for describing the probability that the industrial data is interfered by noise;
Repartitioning the industrial information data sequence into a plurality of filtered data point segments according to the size of the noise factor; carrying out safety management on industrial data according to the filtered data point segments;
the fluctuation constraint factor of each industrial data point is obtained according to the trend change difference among different reference industrial data points and the local screening fluctuation factor, and the method comprises the following specific steps:
recording any one of the industrial data points as a third target industrial data point;
for any one reference industrial data point in any screening cluster of the third target industrial data point, acquiring all extreme points of all local screening industrial data points of the reference industrial data point, and recording the number of all the extreme points as the local screening extreme value quantity of the reference industrial data point; obtaining local screening extremum of all reference industrial data points in the screening cluster of the third target industrial data point;
in the method, in the process of the invention,a fluctuation constraint coefficient representing a third target industrial data point; />Representing a number of all screened clusters of the third target industrial data point; />The +.>In the screening cluster, the variance of the local screening extremum of all the reference industrial data points; / >The +.>In the screening cluster, the average value of local screening fluctuation factors of all reference industrial data points; />An exponential function that is based on a natural constant; obtaining fluctuation constraint coefficients of all industrial data points, carrying out linear normalization on all the fluctuation constraint coefficients, and recording each normalized fluctuation constraint coefficient as a fluctuation constraint factor;
the noise factor of each industrial data point is obtained according to the difference of fluctuation abnormal coefficients of different industrial data points on the same reference industrial data point and the fluctuation constraint factors of different industrial data points, and the specific method comprises the following steps:
in the method, in the process of the invention,representing the +.f on any one industrial information data sequence>No. H of individual Industrial data points>Noise isolation factors for the individual reference industrial data points; />Indicate->A fluctuation constraint factor for each industrial data point; />Indicating the division of the industrial information data sequence by +.>A number of all industrial data points except the individual industrial data points; />Indicate->No. H of individual Industrial data points>Fluctuation anomaly coefficients for the individual reference industrial data points; />Indicate except->No. I beyond the individual Industrial data points>No. H of individual Industrial data points >Fluctuation anomaly coefficients for the individual reference industrial data points; />Indicate except->No. I beyond the individual Industrial data points>A fluctuation constraint factor for each industrial data point;
acquisition of the firstNoise isolation factor of all reference industrial data points of the individual industrial data points, will be +.>The mean value of the noise isolation factors of all reference industrial data points of the individual industrial data points is recorded as +.>An initial noise factor for each industrial data point;
and acquiring initial noise factors of all industrial data points, carrying out linear normalization on all the initial noise isolation factors, and recording each normalized initial noise isolation factor as a noise factor.
2. The method for data security management for an industrial digitized information acquisition device according to claim 1, wherein the dividing the industrial information data sequence into a plurality of local industrial data point segments comprises the following specific steps:
the sampling time is taken as an abscissa, the industrial data is taken as an ordinate, a two-dimensional coordinate system is constructed according to the abscissa and the ordinate, for any one industrial information data sequence, the industrial information data sequence is input into the two-dimensional coordinate system, a plurality of data points are obtained, and each data point is recorded as an industrial data point;
Presetting an industrial data point numberThe method comprises the steps of carrying out a first treatment on the surface of the Any one of the industrial data points is noted as a target industrial data point,before the target industrial data point->Individual industrial data point and target industrial data point>The data point segments collectively formed by the individual industrial data points are noted as local industrial data point segments of the target industrial data point.
3. The method for data security management for an industrial digital information acquisition device according to claim 1, wherein the clustering of the industrial data points according to the variation stability of the industrial data points in the local industrial data point segments to obtain a plurality of screened clusters comprises the following specific steps:
marking standard deviations of all industrial data points in a local industrial data point section of any one industrial data point as neighborhood industrial fluctuation values of target industrial data points; obtaining neighborhood industrial fluctuation values of all industrial data points;
presetting a cluster number intervalWill->Each positive integer contained in the cluster is taken as a cluster quantity preset value; for any preset value of the cluster number, marking any industrial data point as a first target industrial data point, and taking the preset value of the cluster number as an initial cluster number +.>According to the initial cluster number- >Clustering neighborhood industrial fluctuation values of all industrial data points in a local industrial data point section of a first target industrial data point to obtain a plurality of clusters; all are gatheredThe average value of the contour coefficients of all neighborhood industrial fluctuation values in the class clusters is recorded as the preset selection degree of the preset value of the number of the class clusters; obtaining preset selection degrees of preset values of the number of all the clusters, marking the preset value of the number of the clusters with the largest preset selection degree as the preset value of the number of the optimal clusters, and marking each cluster corresponding to the preset value of the number of the optimal clusters as a screened cluster of the first target industrial data point.
4. The method for data security management for an industrial digital information acquisition device according to claim 1, wherein the obtaining the local screening fluctuation factor of a plurality of reference industrial data points according to the numerical fluctuation condition of the reference industrial data points in the screening cluster comprises the following specific steps:
recording any one industrial data point as a second target industrial data point, recording any one industrial data point in any one screening cluster of the second target industrial data point as a reference industrial data point of the second target industrial data point, recording any one industrial data point in a local industrial data point section of the reference industrial data point as a first reference industrial data point of the reference industrial data point, and recording the first reference industrial data point as a local screening industrial data point of the reference data point if the first reference industrial data point appears in the screening cluster; all local screening industrial data points of the reference industrial data point are acquired, and standard deviations of all local screening industrial data points of the reference industrial data point are recorded as local screening fluctuation factors of the reference industrial data point.
5. The method for data security management for an industrial digital information acquisition device according to claim 1, wherein the method for obtaining a plurality of neighborhood trend distances according to the distance difference between different industrial data points in the same screening cluster of local industrial data point segments comprises the following specific steps:
for any one reference industrial data point in any one screening cluster of the third target industrial data point, recording a sequence formed by all extreme points of all local screening industrial data points of the reference industrial data point as a reference industrial extreme point sequence of the reference industrial data point;
for any three adjacent extreme points in the reference industrial extreme point sequence, in the three extreme points, the Euclidean distance between the second extreme point and the first extreme point is recorded as a first distance, the Euclidean distance between the second extreme point and the third extreme point is recorded as a second distance, and the average value of the first distance and the second distance is recorded as the neighborhood trend distance of the second extreme point.
6. The method for data security management for an industrial digital information acquisition device according to claim 5, wherein the obtaining the fluctuation anomaly coefficient of each reference industrial data point according to the difference between different neighborhood trend distances comprises the following specific steps:
In the method, in the process of the invention,a fluctuation anomaly coefficient representing any one of the reference industrial data points of any one of the industrial data points; />Representing the number of all extremum points in a reference industrial data extremum point sequence of a reference industrial data point; />Is represented in the sequence of extreme points of the reference industrial data point +.>Neighborhood trend distances of the extreme points; />Representing extreme points of reference industrial data at reference industrial data pointsIn the sequence, the average value of the neighborhood trend distances of all extreme points; />Is represented in the sequence of extreme points of the reference industrial data point +.>Industrial data of the extreme points; />An average of the industrial data representing all the locally screened industrial data points of the reference industrial data point; />The representation takes absolute value.
7. The method for data security management for an industrial digitized information acquisition device according to claim 1, wherein the repartitioning the industrial information data sequence into a plurality of filtered data point segments according to the size of the noise factor comprises the following specific steps:
presetting a noise factor thresholdStarting the first industrial data point in any one industrial information data sequence as a starting point, and starting the first accumulation process with a step length of 1, and continuously accumulating the noise factors until the value of the accumulated noise factors is greater than or equal to +. >Stopping the first accumulation process, and recording the data segment formed by the accumulated industrial data points in the first accumulation process as a first filtering data point segment; starting the second accumulation process by taking the first industrial data point after the first filtered data point segment as a starting point and the step length as 1, and continuously accumulating the noise factors until the value of the accumulated noise factors is greater than or equal to +.>Stopping the second accumulation process, and recording the data segment formed by the accumulated industrial data points in the second accumulation process as a second filtering data point segment; and the like, stopping obtaining the filtered data point segments until the noise factors of all the industrial data points are accumulated.
8. The method for data security management for an industrial digital information acquisition device according to claim 1, wherein the method for security management of industrial data according to the filtered data point segment comprises the following specific steps:
and taking each filtering data point segment as a window, performing SG filtering on industrial data in the window according to the window to obtain filtered industrial data, performing RSA asymmetric encryption on the filtered industrial data to obtain encrypted industrial data, and storing the encrypted industrial data in an industrial database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410014473.0A CN117540238B (en) | 2024-01-05 | 2024-01-05 | Data security management method for industrial digital information acquisition device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410014473.0A CN117540238B (en) | 2024-01-05 | 2024-01-05 | Data security management method for industrial digital information acquisition device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117540238A CN117540238A (en) | 2024-02-09 |
| CN117540238B true CN117540238B (en) | 2024-03-22 |
Family
ID=89796160
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410014473.0A Active CN117540238B (en) | 2024-01-05 | 2024-01-05 | Data security management method for industrial digital information acquisition device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117540238B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117764290B (en) * | 2024-02-22 | 2024-06-07 | 深圳市智德森水务科技有限公司 | BIM model data management method for hydraulic engineering construction |
| CN117851815B (en) * | 2024-03-07 | 2024-05-10 | 哈能(浙江)电力科技有限公司 | Real-time early warning method and system for safety state of switch cabinet |
| CN117879769B (en) * | 2024-03-11 | 2024-05-28 | 陕西惠延机械有限公司 | Data pushing and transmitting method for tunnel lining trolley cloud platform system |
| CN118010939B (en) * | 2024-04-10 | 2024-06-18 | 山东华检检测有限公司 | Intelligent formaldehyde detection method |
| CN118395311A (en) * | 2024-07-01 | 2024-07-26 | 惠州盛世达科技有限公司 | Intelligent analysis method and system for production data of electronic components |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020155755A1 (en) * | 2019-01-28 | 2020-08-06 | 平安科技（深圳）有限公司 | Spectral clustering-based optimization method for anomaly point ratio, device, and computer apparatus |
| US11487273B1 (en) * | 2021-04-30 | 2022-11-01 | Dalian University Of Technology | Distributed industrial energy operation optimization platform automatically constructing intelligent models and algorithms |
| CN116186634A (en) * | 2023-04-26 | 2023-05-30 | 青岛新航农高科产业发展有限公司 | Intelligent management system for construction data of building engineering |
| CN116702082A (en) * | 2023-08-09 | 2023-09-05 | 深圳市泽信智能装备有限公司 | Dust monitoring method of micron-sized powder dust-free charging system |
| CN116821833A (en) * | 2023-08-29 | 2023-09-29 | 好林(威海)新材料有限公司 | Data anomaly detection method for machine filter cloth adhesion |
| CN116910593A (en) * | 2023-09-14 | 2023-10-20 | 北京豪迈生物工程股份有限公司 | Signal noise suppression method and system for chemiluminescent instrument |
| CN117078048A (en) * | 2023-10-17 | 2023-11-17 | 深圳市福山自动化科技有限公司 | Digital twinning-based intelligent city resource management method and system |
| CN117313016A (en) * | 2023-11-28 | 2023-12-29 | 北京易能中网技术有限公司 | New energy power transaction spot electricity price difference data processing method |
-
2024
- 2024-01-05 CN CN202410014473.0A patent/CN117540238B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020155755A1 (en) * | 2019-01-28 | 2020-08-06 | 平安科技（深圳）有限公司 | Spectral clustering-based optimization method for anomaly point ratio, device, and computer apparatus |
| US11487273B1 (en) * | 2021-04-30 | 2022-11-01 | Dalian University Of Technology | Distributed industrial energy operation optimization platform automatically constructing intelligent models and algorithms |
| CN116186634A (en) * | 2023-04-26 | 2023-05-30 | 青岛新航农高科产业发展有限公司 | Intelligent management system for construction data of building engineering |
| CN116702082A (en) * | 2023-08-09 | 2023-09-05 | 深圳市泽信智能装备有限公司 | Dust monitoring method of micron-sized powder dust-free charging system |
| CN116821833A (en) * | 2023-08-29 | 2023-09-29 | 好林(威海)新材料有限公司 | Data anomaly detection method for machine filter cloth adhesion |
| CN116910593A (en) * | 2023-09-14 | 2023-10-20 | 北京豪迈生物工程股份有限公司 | Signal noise suppression method and system for chemiluminescent instrument |
| CN117078048A (en) * | 2023-10-17 | 2023-11-17 | 深圳市福山自动化科技有限公司 | Digital twinning-based intelligent city resource management method and system |
| CN117313016A (en) * | 2023-11-28 | 2023-12-29 | 北京易能中网技术有限公司 | New energy power transaction spot electricity price difference data processing method |
Non-Patent Citations (2)
| Title |
|---|
| 「数据分析」十六种常用的数据分析方法分享;袋鼠云;《https://www.dtstack.com/news/7370》;20210107;论文第1-5页 * |
| Abnormal Pre-detection Algorithm Based on Time Series;Yang Hao等;《2019 IEEE Fifth International Conference on Big Data Computing Service and Applications (BigDataService)》;20191231;论文第262-265页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117540238A (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117540238B (en) | Data security management method for industrial digital information acquisition device | |
| CN115329910B (en) | Intelligent processing method for enterprise production emission data | |
| CN117473351B (en) | Power supply information remote transmission system based on Internet of things | |
| CN108801437B (en) | Distributed optical fiber vibration sensing positioning method and device based on disturbance signal feature extraction | |
| CN113670616B (en) | Bearing performance degradation state detection method and system | |
| CN116760908B (en) | Agricultural information optimization management method and system based on digital twin | |
| CN118134539B (en) | User behavior prediction method based on intelligent kitchen multi-source data fusion | |
| CN117951630B (en) | Abnormal breathing pattern recognition method for patient with severe respiratory disease | |
| CN117574305B (en) | Real-time monitoring method and system for running state of equipment | |
| CN116975503B (en) | Soil erosion information management method and system | |
| CN117727313B (en) | Intelligent noise reduction method for wild bird sound data | |
| CN116308963B (en) | Government affair data analysis method and system | |
| CN111414354A (en) | Wind power plant data processing method and device and computer readable storage medium | |
| CN117291843B (en) | Efficient management method for image database | |
| CN113780354A (en) | Telemetry data anomaly identification method and device for dispatching automation master station system | |
| CN115099291B (en) | Building energy-saving monitoring method | |
| CN118503634B (en) | Intelligent acquisition method, system and equipment for coal mine general protection data | |
| CN118393290B (en) | Power grid fault detection method based on 5G4G short sharing wireless communication | |
| CN118248169B (en) | Gas leakage identification method based on audio data and related device | |
| CN118195641B (en) | Block chain-based intelligent manufacturing field production whole-flow traceability method | |
| CN117992808B (en) | Big data-based computer network management method and system | |
| CN118467935B (en) | Motor data denoising method and system | |
| CN118277732B (en) | Training method and system for large-scale data learning machine model | |
| CN114997978B (en) | High-quality taxpayer identification method based on taxpayer operation characteristics | |
| CN118245762B (en) | Signal empirical mode decomposition method and system |
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 |