CN114707803B - Internet of things data fusion method and application thereof in intelligent power - Google Patents
Internet of things data fusion method and application thereof in intelligent power Download PDFInfo
- Publication number
- CN114707803B CN114707803B CN202210219036.3A CN202210219036A CN114707803B CN 114707803 B CN114707803 B CN 114707803B CN 202210219036 A CN202210219036 A CN 202210219036A CN 114707803 B CN114707803 B CN 114707803B
- Authority
- CN
- China
- Prior art keywords
- risk level
- monitoring
- follows
- data
- monitoring parameter
- 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
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 16
- 238000012544 monitoring process Methods 0.000 claims abstract description 98
- 238000004364 calculation method Methods 0.000 claims abstract description 40
- 230000004927 fusion Effects 0.000 claims abstract description 19
- 230000005540 biological transmission Effects 0.000 claims abstract description 11
- 238000007689 inspection Methods 0.000 claims abstract description 6
- 230000001133 acceleration Effects 0.000 claims description 13
- 238000000034 method Methods 0.000 claims description 12
- 241000854291 Dianthus carthusianorum Species 0.000 abstract description 6
- 230000000694 effects Effects 0.000 abstract description 5
- 238000005265 energy consumption Methods 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063114—Status monitoring or status determination for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Alarm Systems (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention relates to the technical field of data fusion of the Internet of things, and discloses a data fusion method of the Internet of things, which comprises the following steps: firstly, constructing a risk level of each sensor corresponding to a monitoring parameter, then calculating a membership coefficient of each monitoring parameter corresponding to each risk level, a normalized weight of each monitoring parameter, a total membership coefficient of each monitoring parameter corresponding to each risk level and a correlation coefficient of the total membership coefficient corresponding to each risk level, and finally calculating the total risk level of each monitoring parameter through the correlation coefficient; the data fusion method can be applied to a power transmission line monitoring system adopting a wireless sensor network for safety inspection, and the data fusion method has the technical effects of reducing the data redundancy and reducing the energy consumption of the nodes for transmitting data by fusion calculation on the monitoring data acquired by each sensor at the cluster head node and transmitting the fusion calculation result to the sink node.
Description
Technical Field
The invention relates to the technical field of data fusion of the Internet of things, in particular to a data fusion method of the Internet of things and application of the data fusion method of the Internet of things to intelligent power.
Background
The power transmission line is a key part for ensuring the normal operation of the whole power network, and a wireless sensor network with the advantages of all-weather online, self-organizing network, large-area coverage, adaptation to severe conditions, low cost and the like is adopted, so that the power transmission line with the distribution characteristics of long distance, wide distribution range, high maintenance difficulty, high maintenance cost and the like is subjected to inspection, and the power transmission line is an important development direction of power transmission line monitoring.
Multiple sensors may be used to monitor the same target, so that accuracy and reliability of the monitored data can be guaranteed, and the energy consumed by the sensor nodes in the wireless sensor network when data transmission is performed is far greater than the energy consumed by calculation in the nodes. Experiments show that the energy consumed by a node to transmit 1bit of data is approximately equivalent to the energy required to execute 2950 computing instructions. It is necessary to perform data fusion inside the cluster head node.
Disclosure of Invention
(One) solving the technical problems
The invention aims to provide an Internet of things data fusion method which can be applied to a power transmission line monitoring system for carrying out safety inspection by adopting a wireless sensor network.
(II) technical scheme
In order to achieve the above purpose, the present invention provides the following technical solutions:
The data fusion method of the Internet of things comprises the following steps of:
Step one, each sensor of a node in a wireless sensor network respectively collects monitoring data M corresponding to each monitoring parameter X, and feeds the monitoring data M back to the network node;
step two, the nodes in the wireless sensor network perform fusion calculation on the monitoring data M, and the process is as follows:
Step S1, constructing a risk level N (X) of the monitoring parameter X by adopting an objective scientific method, dividing the risk level N (X) into N levels according to the risk condition, and constructing a lower limit value xd and an upper limit value xu of each risk level N (X) at the same time;
step S2, calculating the membership coefficient U (X) of each monitoring parameter X corresponding to each risk level, wherein the calculation formula of the membership coefficient U (X) is as follows:
when M is less than or equal to (xd+xu)/2, U (X) =2 (M-xd)/(xu-xd);
when M > (xd+xu)/2, U (X) =2 (xu-M)/(xu xd);
And making the risk level N (X) corresponding to the membership coefficient U (X) not less than 0 be the risk level actually belonging to each monitoring parameter X;
step S3, calculating the weight Q (X) and the normalized weight W (X) of each monitoring parameter X, wherein the calculation formula is as follows:
Q(X)=[N-N(M)+1】*{1+max[U(X)】};
W(X)=Q(X)/∑Q(X);
Step S4, calculating the total membership coefficient TU (X) of each monitoring parameter X corresponding to each risk level, wherein the calculation formula of the total membership coefficient TU (X) is as follows:
TU(X)=∑W(X)*U(X);
step S5, calculating the association coefficient GU (X) of the total membership coefficient TU (X) corresponding to each risk level, the calculation formula is as follows:
GU(X)={TU(X)-min[TU(X)】}/{max[TU(X)】-min[TU(X)】};
step S6, calculating the total risk level Z (X) of each monitoring parameter X, wherein the calculation formula is as follows:
Z(X)=[N(X)*GU(X)】/∑GU(X)。
preferably, the data fusion method of the internet of things can be applied to a power transmission line monitoring system for carrying out safety inspection by adopting a wireless sensor network.
Preferably, the monitoring the parameter X in the internet of things data fusion method applied to intelligent power includes: ambient temperature X1, ambient humidity X2, ambient wind speed X3, wire vibration acceleration X4, wire temperature X5.
(III) beneficial technical effects
Compared with the prior art, the invention has the following beneficial technical effects:
firstly, constructing a risk level of each sensor corresponding to a monitoring parameter, then calculating a membership coefficient of each monitoring parameter corresponding to each risk level, a normalized weight of each monitoring parameter, a total membership coefficient of each monitoring parameter corresponding to each risk level and a correlation coefficient of the total membership coefficient corresponding to each risk level, and finally calculating the total risk level of each monitoring parameter through the correlation coefficient, thereby realizing fusion calculation of the monitoring parameters corresponding to each sensor;
In the process of fusion calculation, the judgment of the corresponding risk level of the monitoring data of each monitoring parameter is established according to the magnitude range of the pre-constructed risk level, and the magnitude range of the risk level is determined by an objective scientific method, so that the beneficial technical effect of objectively and scientifically judging the risk level of the monitoring data can be realized;
The fusion calculation method can be applied to a power transmission line monitoring system adopting a wireless sensor network for safety inspection, and the technical effects of reducing the data redundancy and reducing the energy consumption of the nodes for transmitting data are achieved by carrying out fusion calculation on monitoring data acquired by each sensor at a cluster head node and then transmitting the fusion calculation result to a sink node.
Detailed Description
The data fusion method of the Internet of things comprises the following steps of:
Step one, each sensor of a node in a wireless sensor network respectively collects monitoring data M corresponding to each monitoring parameter X, and feeds the monitoring data M back to the network node;
Step two, the nodes in the wireless sensor network perform fusion calculation on the monitoring data M, and the specific fusion calculation process is as follows:
Step S1, constructing a risk level N (X) of the monitoring parameter X by adopting an objective scientific method, dividing the risk level N (X) into N levels according to the risk condition, and constructing a lower limit value xd and an upper limit value xu of each risk level N (X) at the same time;
step S2, calculating the membership coefficient U (X) of each monitoring parameter X corresponding to each risk level, wherein the calculation formula of the membership coefficient U (X) is as follows:
when M is less than or equal to (xd+xu)/2, U (X) =2 (M-xd)/(xu-xd);
when M > (xd+xu)/2, U (X) =2 (xu-M)/(xu xd);
And making the risk level N (X) corresponding to the membership coefficient U (X) not less than 0 be the risk level actually belonging to each monitoring parameter X;
step S3, calculating the weight Q (X) and the normalized weight W (X) of each monitoring parameter X, wherein the calculation formula is as follows:
Q(X)=[N-N(M)+1】*{1+max[U(X)】};
W(X)=Q(X)/∑Q(X);
Step S4, calculating the total membership coefficient TU (X) of each monitoring parameter X corresponding to each risk level, wherein the calculation formula of the total membership coefficient TU (X) is as follows:
TU(X)=∑W(X)*U(X);
step S5, calculating the association coefficient GU (X) of the total membership coefficient TU (X) corresponding to each risk level, the calculation formula is as follows:
GU(X)={TU(X)-min[TU(X)】}/{max[TU(X)]-min[TU(X)】};
step S6, calculating the total risk level Z (X) of each monitoring parameter X, wherein the calculation formula is as follows:
Z(X)=[N(X)*GU(X)】/∑GU(X);
an internet of things data fusion method applied to intelligent power comprises the following steps:
Step one, each sensor of a cluster head node in a wireless sensor network respectively collects monitoring data M corresponding to each monitoring parameter X in a power transmission line and the surrounding environment, and feeds the monitoring data M back to the cluster head node;
Wherein the monitoring parameter X comprises: ambient temperature X1, ambient humidity X2, ambient wind speed X3, wire vibration acceleration X4, wire temperature X5;
Secondly, the cluster head node performs fusion calculation on the monitoring data M;
taking the following group of sample data as an example, the fusion calculation process is specifically described;
Monitored data m1=26.6 ℃ for ambient temperature X1;
monitored data m2=30% of ambient humidity X2;
monitoring data m3=0.5M/s for the ambient wind speed X3;
Monitor data m4=0.83M/s 2 of wire vibration acceleration X4;
Monitored data m5=80 ℃ for wire temperature X5;
Step S1, constructing a risk level N (X) of the monitoring parameter X by adopting an objective scientific method, wherein the risk level N (X) can be classified into N levels according to the risk condition;
and (3) making: n=3;
n (X) 1 represents a risk level of 1, i.e., N (X) 1=1;
n (X) 2 represents a risk level of 2, i.e., N (X) 2=2;
N (X) 3 represents a risk level of 3, i.e., N (X) 3=3;
the danger levels are respectively low, normal and high, the corresponding numbers 1, 2 and 3 are used for representing, and the larger the number is, the higher the danger level is;
then: the magnitude ranges of the risk level 1 corresponding to the monitoring parameters X are respectively as follows:
The value range of the ambient temperature X1 is [ X1d1, X1u1 ];
The value range of the ambient humidity X2 is [ X2d1, X2u1 ];
the value range of the ambient wind speed X3 is [ X3d1, X3u1 ];
The value range of the wire vibration acceleration X4 is [ X4d1, X4u1 ];
The value range of the wire temperature X5 is [ X5d1, X5u1 ];
The magnitude ranges of the risk level 2 corresponding to the monitoring parameters X are respectively as follows:
The value range of the ambient temperature X1 is (X1 d2, X1u 2);
The value range of the ambient humidity X2 is (X2 d2, X2u 2);
The value range of the ambient wind speed X3 is (X3 d2, X3u 2);
The value range of the wire vibration acceleration X4 is (X4 d2, X4u 2);
the value range of the wire temperature X5 is (X5 d2, X5u 2);
The magnitude ranges of the risk level 3 corresponding to the monitoring parameters X are respectively as follows:
the value range of the ambient temperature X1 is [ X1d3, X1u3 ];
The value range of the ambient humidity X2 is [ X2d3, X2u3 ];
the value range of the ambient wind speed X3 is [ X3d3, X3u3 ];
The value range of the wire vibration acceleration X4 is [ X4d3, X4u3 ];
the value range of the wire temperature X5 is [ X5d3, X5u3 ];
and carrying out assignment processing on the endpoint values of the value range, wherein the specific assignment is as follows:
And (3) making: x1d1=0, x1u1=20=x1d2, x1u2=40=x1d3, x1u3=60;
Then: the environmental temperature X1 has a value range of [0, 20 ] at the risk level 1, a value range of (20, 40) at the risk level 2, and a value range of [40, 60] at the risk level 3;
And (3) making: x2d1=0, x2u1=50=x2d2, x2u2=70=x2d3, x2u3=100;
then: the environmental humidity X2 has a value range of [0, 50 ] at the risk level 1, a value range of (50, 70) at the risk level 2, and a value range of [70, 100] at the risk level 3;
and (3) making: x3d1=0, x3u1=20=x3d2, x3u2=40=x3d3, x3u3=60;
then: the value range of the ambient wind speed X3 at the dangerous level 1 is [0, 20 ], the value range at the dangerous level 2 is (20, 40), and the value range at the dangerous level 3 is [40, 60];
And (3) making: x4d1=0, x4u1=10=x4d2, x4u2=20=x4d3, x4u3=30;
Then: the value range of the vibration acceleration X4 of the lead is [0, 10 ] at the dangerous level 1, the value range of the vibration acceleration X4 of the lead is (10, 20) at the dangerous level 2, and the value range of the vibration acceleration X4 of the lead is [20, 30 ] at the dangerous level 3;
And (3) making: x5d1=40, x5u1=80=x5d2, x5u2=100=x5d3, x5u3=120;
Then: the value range of the wire temperature X5 at the dangerous level 1 is [40, 80 ], the value range at the dangerous level 2 is (80, 100), and the value range at the dangerous level 3 is [100, 120 ];
step S2, calculating the membership coefficient U (X) of each monitoring parameter X corresponding to each risk level, wherein the calculation formula of the membership coefficient U (X) is as follows:
when M is less than or equal to (xd+xu)/2, U (X) =2 (M-xd)/(xu-xd);
when M > (xd+xu)/2, U (X) =2 (xu-M)/(xu xd);
And making the risk level N (X) corresponding to the membership coefficient U (X) not less than 0 be the risk level actually belonging to each monitoring parameter X;
The specific calculation results of the membership coefficient U (X1) of the monitoring data M1 of the ambient temperature X1 corresponding to each risk level are as follows:
as a result of: (x1d1+x1u1)/2= (0+20)/2=10, m1=26.6;
so that: m1 > (x1d1+x1u1)/2;
Thus: the membership coefficient U (X1) 1 of the monitoring data M1 corresponding to the risk level 1 is calculated as follows:
U(X1)1=2(x1u1-M1)/(x1u1-x1d1)=2(20-26.6)/(20-0)=-0.660;
as a result of: (x1d2+x1u2)/2= (20+40)/2=30, m1=26.6;
So that: m1 < (x1d2+x1u2)/2;
thus: the membership coefficient U (X1) 2 of the monitoring data M1 corresponding to the risk level 2 is calculated as follows:
U(X1)2==2(M1-x1d2)/(x1u2-x1d2)=2(26.6-20)/(40-20)=0.660;
as a result of: (x1d3+x1u3)/2= (40+60)/2=50, m1=26.6;
So that: m1 < (x1d3+x1u3)/2;
thus: the membership coefficient U (X1) 3 of the monitoring data M1 corresponding to the risk level 3 is calculated as follows:
U(X1)3==2(M1-x1d3)/(x1u3-x1d3)=2(26.6-40)/(60-40)=-1.340;
in summary, the monitoring data M1 belongs to the risk level 2, i.e., N (M1) =2;
The specific calculation results of the membership coefficient U (X2) of the monitoring data M2 of the ambient humidity X2 corresponding to each risk level are as follows:
as a result of: (x2d1+x2u1)/2= (0+50)/2=25, m2=30;
So that: m2 > (x2d1+x2u1)/2;
thus: the membership coefficient U (X2) 1 of the monitoring data M2 corresponding to the risk level 1 is calculated as follows:
U(X2)1=2(x2u1-M2)/(x2u1-x2d1)=2(50-30)/(50-0)=0.800;
As a result of: (x2d2+x2u2)/2= (50+70)/2=60, m2=30;
So that: m2 < (x2d2+x2u2)/2;
thus: the membership coefficient U (X2) 2 of the monitoring data M2 corresponding to the risk level 2 is calculated as follows:
U(X2)2==2(M2-x2d2)/(x2u2-x2d2)=2(30-50)/(70-50)=-2.000;
as a result of: (x2d3+x2u3)/2= (70+100)/2=85, m2=30;
so that: m2 < (x2d3+x2u3)/2;
Thus: the membership coefficient U (X2) 3 of the monitoring data M2 corresponding to the risk level 3 is calculated as follows:
U(X2)3==2(M2-x2d3)/(x2u3-x2d3)=2(30-70)/(100-70)=-2.667;
in summary, the monitoring data M2 belongs to the risk level 1, i.e., N (M2) =1;
the specific calculation results of the membership coefficient U (X3) of the monitoring data M3 of the ambient wind speed X3 corresponding to each risk level are as follows:
As a result of: (x3d1+x3u1)/2= (0+20)/2=10, m3=0.5;
so that: m3 < (x3d1+x3u1)/2;
thus: the membership coefficient U (X3) 1 of the monitoring data M3 corresponding to the risk level 1 is calculated as follows:
U(X3)1=2(M3-x3d1)/(x3u1-x3d1)=2(0.5-0)/(20-0)=0.050;
as a result of: (x3d2+x3u2)/2= (20+40)/2=30, m3=0.5;
So that: m3 < (x3d2+x3u2)/2;
thus: the membership coefficient U (X3) 2 of the monitoring data M3 corresponding to the risk level 2 is calculated as follows:
U(X3)2=2(M3-x3d2)/(x3u2-x3d2)=2(0.5-20)/(40-20)=-1.950;
as a result of: (x3d3+x3u3)/2= (40+60)/2=50, m3=0.5;
so that: m3 < (x3d3+x3u3)/2;
thus: the membership coefficient U (X3) 3 of the monitoring data M3 corresponding to the risk level 3 is calculated as follows:
U(X3)3=2(M3-x3d3)/(x3u3-x3d3)=2(0.5-40)/(60-40)=-3.950;
in summary, the monitoring data M3 belongs to the risk level 1, i.e., N (M3) =1;
The specific calculation result of the monitoring data M4 of the wire vibration acceleration X4 corresponding to the membership coefficient U (X4) of each risk level is as follows:
as a result of: (x4d1+x4u1)/2= (0+10)/2=5, m4=0.83;
so that: m4 < (x4d1+x4u1)/2;
Thus: the membership coefficient U (X4) 1 of the monitoring data M4 corresponding to the risk level 1 is calculated as follows:
U(X4)1=2(M4-x4d1)/(x4u1-x4d1)=2(0.83-0)/(10-0)=0.166;
as a result of: (x4d2+x4u2)/2= (10+20)/2=15, m4=0.83;
So that: m4 < (x4d2+x4u2)/2;
thus: the membership coefficient U (X4) 2 of the monitoring data M4 corresponding to the risk level 2 is calculated as follows:
U(X4)2=2(M4-x4d2)/(x4u2-x4d2)=2(0.83-10)/(20-10)=-1.834;
as a result of: (x4d3+x4u3)/2= (20+30)/2=25, m4=0.83;
so that: m4 < (x4d3+x4u3)/2;
thus: the membership coefficient U (X4) 3 of the monitoring data M4 corresponding to the risk level 3 is calculated as follows:
U(X4)3=2(M4-x4d3)/(x4u3-x4d3)=2(0.83-20)/(30-20)=-3.834;
in summary, the monitoring data M4 belongs to the risk level 1, i.e., N (M4) =1;
The specific calculation results of the membership coefficient U (X5) of the monitoring data M5 of the wire temperature X5 corresponding to each risk level are as follows:
As a result of: (x5d1+x5u1)/2= (40+80)/2=60, m5=80;
So that: m5 > (x5d1+x5u1)/2;
thus: the membership coefficient U (X5) 1 of the monitoring data M5 corresponding to the risk level 1 is calculated as follows:
U(X5)1=2(x5u1-M5)/(x5u1-x5d1)=2(80-80)/(80-40)=0;
As a result of: (x5d2+x5u2)/2= (80+100)/2=90, m5=80;
so that: m5 < (x5d2+x5u2)/2;
thus: the membership coefficient U (X5) 2 of the monitoring data M5 corresponding to the risk level 2 is calculated as follows:
U(X5)2=2(M5-x5d2)/(x5u2-x5d2)=2(80-80)/(100-80)=0;
As a result of: (x5d3+x5u3)/2= (100+120)/2=110, m5=80;
So that: m5 < (x5d3+x5u3)/2;
Thus: the membership coefficient U (X5) 3 of the monitoring data M5 corresponding to the risk level 3 is calculated as follows:
U(X5)3=2(M5-x5d3)/(x5u3-x5d3)=2(80-100)/(120-100)=-2.000;
in summary, since the wire temperature X5 has a value range of [40, 80 ] at the risk level 1 and a value range of (80, 100) at the risk level 2, the monitoring data M5 belongs to the risk level 1, i.e., N (M5) =1;
step S3, calculating the weight Q (X) and the normalized weight W (X) of each monitoring parameter X, wherein the calculation formula is as follows:
Q(X)=[N-N(M)+1】*{1+max[U(X)1,(U(X)2,(U(X)3】};
W(X)=Q(X)/∑Q(X);
the weight Q (X1) of the ambient temperature X1 is calculated as follows:
Q(X1)=[N-N(M1)+1】*{1+max[U(X1)1,(U(X1)2,(U(X1)3】}=[3-2+1】*{1+0.660}=3.32;
the weight Q (X2) of the ambient humidity X2 is calculated as follows:
Q(X2)=[N-N(M2)+1】*{1+max[U(X2)1,(U(X2)2,(U(X2)3】}=[3-1+1】*{1+0.800}=5.4;
the weight Q (X3) of the ambient wind speed X3 is calculated as follows:
Q(X3)=[N-N(M3)+1】*{1+max[U(X3)1,(U(X3)2,(U(X3)3】}=[3-1+1】*{1+0.050}=3.15;
the weight Q (X4) of the wire vibration acceleration X4 is calculated as follows:
Q(X4)=[N-N(M4)+1】*{1+max[U(X4)1,(U(X4)2,(U(X4)3】}=[3-1+1】*{1+0.166}=3.498;
The weight Q (X5) of the wire temperature X5 is calculated as follows:
Q(X5)=[N-N(M5)+1】*{1+max[U(X5)1,(U(X5)2,(U(X5)3】}=[3-1+1】*{1+0}=3;
the normalized weight W (X1) of the ambient temperature X1 is calculated as follows: w (X1) =q (X1)/[ Q (X1) +q (X2) +q (X3) +q (X4) +q (X5) ] =3.32/[ 3.32+5.4+3.15+3.498+3 ] = 0.1807;
The normalized weight W (X2) of the ambient humidity X2 is calculated as follows: w (X2) =q (X2)/[ Q (X1) +q (X2) +q (X3) +q (X4) +q (X5) ] = 5.4/[3.32+5.4+3.15+3.498+3 ] = 0.2940;
The normalized weight W (X3) of the ambient wind speed X3 is calculated as follows: w (X3) =q (X3)/[ Q (X1) +q (X2) +q (X3) +q (X4) +q (X5) ] =3.15/[ 3.32+5.4+3.15+3.498+3 ] =0.1715;
normalized weight W (X4) of wire vibration acceleration X4 is calculated as follows:
W(X4)=Q(X4)/[Q(X1)+Q(X2)+Q(X3)+Q(X4)+Q(X5)】=3.498/[3.32+5.4+3.15+3.498+3】=0.1904;
the normalized weight W (X5) of the wire temperature X5 is calculated as follows:
W(X5)=Q(X5)/[Q(X1)+Q(X2)+Q(X3)+Q(X4)+Q(X5)】=3/[3.32+5.4+3.15+3.498+3】=0.1633;
Step S4, calculating the total membership coefficient TU (X) of each monitoring parameter X corresponding to each risk level, wherein the calculation formula of the total membership coefficient TU (X) is as follows:
TU(X)=W(X1)*U(X1)+W(X2)*U(X2)+W(X3)*U(X3)+W(X4)*U(X4)+W(X5)*U(X5);
the total membership coefficient TU (X) 1 of each monitoring parameter X corresponding to the risk level 1 is calculated as follows:
TU(X)1=W(X1)*U(X1)1+W(X2)*U(X2)1+W(X3)*U(X3)1+W(X4)*U(X4)1+W(X5)*U(X5)1
=0.1807*(-0.660)+0.2940*0.800+0.1715*0.050+0.1904*0.166+0.1633*0=0.1561;
the total membership coefficient TU (X) 2 of each monitoring parameter X corresponding to the risk level 2 is calculated as follows:
TU(X)2=W(X1)*U(X1)2+W(X2)*U(X2)2+W(X3)*U(X3)2+W(X4)*U(X4)2+W(X5)*U(X5)2
=0.1807*0.660+0.2940*(-2.000)+0.1715*(-1.950)+0.1904*(-1.834)+0.1633*0=-1.1524;
the total membership coefficient TU (X) 3 of each monitoring parameter X corresponding to the risk level 3 is calculated as follows:
TU(X)3=W(X1)*U(X1)3+W(X2)*U(X2)3+W(X3)*U(X3)3+W(X4)*U(X4)3+W(X5)*U(X5)3
=0.1807*(-1.340)+0.2940*(-2.667)+0.1715*(-3.950)+0.1904*(-3.834)+0.1633*(-2.000)=-2.7605;
step S5, calculating the association coefficient GU (X) of the total membership coefficient TU (X) corresponding to each risk level, the calculation formula is as follows:
GU(X)={TU(X)-min[TU(X)1,TU(X)2,TU(X)3】}/{max[TU(X)1,TU(X)2,TU(X)3]-min[TU(X)1,TU(X)2,TU(X)3】};
The association coefficient GU (X) 1 of the total membership coefficient TU (X) 1 corresponding to the risk level 1 is calculated as follows:
GU(X)1={TU(X)1-min[TU(X)1,TU(X)2,TU(X)3】}/{max[TU(X)1,TU(X)2,TU(X)3]-min[TU(X)1,TU(X)2,TU(X)3】}
={0.1561-(-2.7606)}/{0.1561-(-2.7606)}
=1;
the association coefficient GU (X) 2 of the total membership coefficient TU (X) 2 corresponding to the risk level 2 is calculated as follows:
GU(X)2={TU(X)2-min[TU(X)1,TU(X)2,TU(X)3】}/{max[TU(X)1,TU(X)2,TU(X)3]-min[TU(X)1,TU(X)2,TU(X)3】}
={(-1.1524)-(-2.7606)}/{0.1561-(-2.7606)}
=0.551;
the association coefficient GU (X) 3 of the total membership coefficient TU (X) 3 corresponding to the risk level 3 is calculated as follows:
GU(X)3={TU(X)3-min[TU(X)1,TU(X)2,TU(X)3】}/{max[TU(X)1,TU(X)2,TU(X)3]-min[TU(X)1,TU(X)2,TU(X)3】}
={(-2.7606)-(-2.7606)}/{0.1561-(-2.7606)}
=0;
step S6, calculating the total risk level Z (X) of each monitoring parameter X, wherein the calculation formula is as follows:
Z(X)=[N(X)*GU(X)】/∑GU(X)
=[N(X)1*GU(X)1+N(X)2*GU(X)2+N(X)3*GU(X)3】/[GU(X)1+GU(X)2+GU(X)3】
=[1*1+2*0.551+3*0】/[1+0.551+0】
=1.355;
in summary, Z (X) is greater than N (X) 1 and less than N (X) 2, and the fusion calculation result shows that the overall risk level Z (X) of each monitoring parameter X is 1.
Claims (3)
1. The data fusion method of the Internet of things is characterized by comprising the following steps of:
Step one, each sensor of a node in a wireless sensor network respectively collects monitoring data M corresponding to each monitoring parameter X, and feeds the monitoring data M back to the network node;
step two, the nodes in the wireless sensor network perform fusion calculation on the monitoring data M, and the process is as follows:
Step S1, constructing a risk level N (X) of the monitoring parameter X by adopting an objective scientific method, dividing the risk level N (X) into N levels according to the risk condition, and constructing a lower limit value xd and an upper limit value xu of each risk level N (X) at the same time;
step S2, calculating the membership coefficient U (X) of each monitoring parameter X corresponding to each risk level, wherein the calculation formula of the membership coefficient U (X) is as follows:
when M is less than or equal to (xd+xu)/2, U (X) =2 (M-xd)/(xu-xd);
when M > (xd+xu)/2, U (X) =2 (xu-M)/(xu xd);
And making the risk level N (X) corresponding to the membership coefficient U (X) not less than 0 be the risk level actually belonging to each monitoring parameter X;
step S3, calculating the weight Q (X) and the normalized weight W (X) of each monitoring parameter X, wherein the calculation formula is as follows:
Q(X)=[N-N(M)+1]*{1+max[U(X)]};
W(X)=Q(X)/ΣQ(X);
Step S4, calculating the total membership coefficient TU (X) of each monitoring parameter X corresponding to each risk level, wherein the calculation formula of the total membership coefficient TU (X) is as follows:
TU(X)=ΣW(X)*U(X);
step S5, calculating the association coefficient GU (X) of the total membership coefficient TU (X) corresponding to each risk level, the calculation formula is as follows:
GU(X)={TU(X)-min[TU(X)]}/{max[TU(X)]-min[TU(X)]};
step S6, calculating the total risk level Z (X) of each monitoring parameter X, wherein the calculation formula is as follows:
Z(X)=[N(X)*GU(X)]/ΣGU(X)。
2. the internet of things data fusion method according to claim 1, wherein the internet of things data fusion method is applied to a power transmission line monitoring system for safety inspection by adopting a wireless sensor network.
3. The method for data fusion of the internet of things according to claim 2, wherein the monitoring of the parameter X in the method for data fusion of the internet of things applied to intelligent power comprises: ambient temperature X1, ambient humidity X2, ambient wind speed X3, wire vibration acceleration X4, wire temperature X5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210219036.3A CN114707803B (en) | 2022-03-08 | 2022-03-08 | Internet of things data fusion method and application thereof in intelligent power |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210219036.3A CN114707803B (en) | 2022-03-08 | 2022-03-08 | Internet of things data fusion method and application thereof in intelligent power |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114707803A CN114707803A (en) | 2022-07-05 |
CN114707803B true CN114707803B (en) | 2024-05-31 |
Family
ID=82168816
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210219036.3A Active CN114707803B (en) | 2022-03-08 | 2022-03-08 | Internet of things data fusion method and application thereof in intelligent power |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114707803B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108512901A (en) * | 2018-02-10 | 2018-09-07 | 深圳智达机械技术有限公司 | The structural safety monitoring system that builds a bridge based on wireless sensor network |
CN109389256A (en) * | 2017-08-02 | 2019-02-26 | 南京理工大学 | Utilize the method for polynary dust explosion parametric synthesis assessment combustible dust explosion danger grade |
CN109993344A (en) * | 2019-01-09 | 2019-07-09 | 淮阴工学院 | Harmful influence tank car operating status prediction technique and system based on multisource data fusion |
WO2019161593A1 (en) * | 2018-02-26 | 2019-08-29 | 北京科技大学 | Monitoring and early warning method for electromagnetic radiation and underground sound of coal and rock dynamic disaster hazard |
CN110209055A (en) * | 2019-06-12 | 2019-09-06 | 洛阳师范学院 | Second-order system controller and control method based on reference model and disturbance observation |
RU2735163C1 (en) * | 2020-06-01 | 2020-10-28 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Государственный морской университет имени адмирала Ф.Ф. Ушакова" | Method of preliminary ship routing generation |
-
2022
- 2022-03-08 CN CN202210219036.3A patent/CN114707803B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109389256A (en) * | 2017-08-02 | 2019-02-26 | 南京理工大学 | Utilize the method for polynary dust explosion parametric synthesis assessment combustible dust explosion danger grade |
CN108512901A (en) * | 2018-02-10 | 2018-09-07 | 深圳智达机械技术有限公司 | The structural safety monitoring system that builds a bridge based on wireless sensor network |
WO2019161593A1 (en) * | 2018-02-26 | 2019-08-29 | 北京科技大学 | Monitoring and early warning method for electromagnetic radiation and underground sound of coal and rock dynamic disaster hazard |
CN109993344A (en) * | 2019-01-09 | 2019-07-09 | 淮阴工学院 | Harmful influence tank car operating status prediction technique and system based on multisource data fusion |
CN110209055A (en) * | 2019-06-12 | 2019-09-06 | 洛阳师范学院 | Second-order system controller and control method based on reference model and disturbance observation |
RU2735163C1 (en) * | 2020-06-01 | 2020-10-28 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Государственный морской университет имени адмирала Ф.Ф. Ушакова" | Method of preliminary ship routing generation |
Non-Patent Citations (2)
Title |
---|
基于多源异构信息融合的煤矿冒顶事故预报技术;梁亚婷;杨振宏;屈利伟;;西安科技大学学报;20130131(第01期);全文 * |
基于高斯隶属度的融合算法在改进Leach中的应用;陈伟琦;胡斌杰;;传感器与微***;20110220(第02期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN114707803A (en) | 2022-07-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116300652B (en) | Power control cabinet on-line monitoring system based on data analysis | |
CN106875105B (en) | Power distribution network differentiation planning method considering composite fault risk | |
CN107895947A (en) | A kind of power distribution network vulnerable line discrimination method | |
CN114707803B (en) | Internet of things data fusion method and application thereof in intelligent power | |
CN107316129B (en) | Comprehensive assessment method for natural disaster flashover risk of power transmission line | |
CN112228290B (en) | Intelligent early warning method for faults of variable pitch system of wind turbine | |
CN116961240B (en) | Intelligent frequency converter monitoring system based on data analysis | |
CN109857177B (en) | Building electrical energy-saving monitoring method | |
CN115979349A (en) | Power station space environment monitoring method and system | |
CN111148117A (en) | LEACH protocol cluster head selection method based on position and energy correlation | |
CN116317104A (en) | Power transmission line dynamic capacity-increasing prediction system and method based on data center station | |
Kelli et al. | Risk analysis of DNP3 attacks | |
CN116540941A (en) | Data storage safety control system based on cloud computing | |
CN117544998B (en) | Wireless network speed intelligent evaluation system based on artificial intelligence | |
Behdadnia et al. | Leveraging deep learning to increase the success rate of DOS attacks in PMU-based automatic generation control systems | |
CN113055891A (en) | Wireless sensor network secure routing protocol based on self-adaptive trust mechanism | |
CN104661250B (en) | The route of Wind turbines wireless senser condition monitoring system substitutes self-healing method | |
CN114577457A (en) | Energy efficiency testing system and method for condensation heat exchanger | |
CN113701690B (en) | Equivalent icing thickness measuring method and system for straight line tower of equal-span power transmission and distribution line | |
CN115839776A (en) | Heat radiation error correction method for bolt and nut gasket structure | |
CN112510704B (en) | Online coal consumption curve real-time generation method and system | |
CN107490454A (en) | Pressure transmitter temperature-compensating output intent | |
CN111207484B (en) | Central air-conditioning system fault diagnosis method based on object-oriented Bayesian network | |
CN210606715U (en) | Novel super corrosion-resistant overhead transmission conductor | |
Bergström et al. | Dynamic capacity rating for wind cooled overhead lines |
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 |