CN105427674B - A kind of unmanned plane during flying state assesses early warning system and method in real time - Google Patents
A kind of unmanned plane during flying state assesses early warning system and method in real time Download PDFInfo
- Publication number
- CN105427674B CN105427674B CN201510734491.7A CN201510734491A CN105427674B CN 105427674 B CN105427674 B CN 105427674B CN 201510734491 A CN201510734491 A CN 201510734491A CN 105427674 B CN105427674 B CN 105427674B
- Authority
- CN
- China
- Prior art keywords
- unmanned plane
- early warning
- flight
- during flying
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims abstract description 53
- 238000012544 monitoring process Methods 0.000 claims abstract description 40
- 230000005540 biological transmission Effects 0.000 claims abstract description 19
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000012706 support-vector machine Methods 0.000 claims abstract description 7
- 230000000694 effects Effects 0.000 claims description 34
- 238000007689 inspection Methods 0.000 claims description 21
- 238000004891 communication Methods 0.000 claims description 17
- 238000013507 mapping Methods 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 14
- 238000005457 optimization Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 12
- 238000013523 data management Methods 0.000 claims description 10
- 238000012731 temporal analysis Methods 0.000 claims description 9
- 238000000700 time series analysis Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 5
- 230000003993 interaction Effects 0.000 claims description 5
- 238000004088 simulation Methods 0.000 claims description 5
- 239000013598 vector Substances 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims description 3
- 230000001133 acceleration Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000000714 time series forecasting Methods 0.000 claims description 3
- 238000009825 accumulation Methods 0.000 claims description 2
- 238000012417 linear regression Methods 0.000 claims description 2
- 238000007621 cluster analysis Methods 0.000 claims 1
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 230000005611 electricity Effects 0.000 claims 1
- 238000000547 structure data Methods 0.000 claims 1
- 238000012300 Sequence Analysis Methods 0.000 abstract description 3
- 241001269238 Data Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
- G08G5/0047—Navigation or guidance aids for a single aircraft
- G08G5/0069—Navigation or guidance aids for a single aircraft specially adapted for an unmanned aircraft
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of unmanned plane during flying state to assess early warning system and method in real time, including assesses early warning platform, unmanned plane and ground monitoring station, wherein：Ground monitoring station, for obtaining the Flight Condition Data of unmanned plane, pass it to and assess early warning platform；Assess early warning platform, for reading unmanned plane during flying status information and flight control data, the UAV Flight Control data accumulated by each patrol task, build unmanned plane during flying state estimation model, unmanned plane during flying state is judged, the flight directive of host computer transmission is received simultaneously, adjusts the flight of unmanned plane.Flight control data of the invention according to polling transmission line unmanned plane, the analysis method that passage time sequence analysis, clustering method and SVMs are combined, unmanned plane during flying state estimation Early-warning Model is constructed, realizes that state of flight of the unmanned plane during polling transmission line assesses early warning in real time.
Description
Technical field
The present invention relates to a kind of unmanned plane during flying state to assess early warning system and method in real time.
Background technology
Unmanned plane line data-logging plays more and more important effect in polling transmission line, and unmanned plane inspection system can
Partly to replace electrical power line inspector and have man-machine inspection system, mitigate the live load of electrical power services personnel, reduce what may be occurred
The probability of personnel hazard, the maintenance cost of power equipment is reduced, improve the safety and reliability of power network.
A large amount of flight control datas are produced in being worked for unmanned plane inspection, there is pending analysis and excavation, but at present
These data are substantially what is be scattered, are typically present in a manner of file in the computer of staff, lack effective
Collection and analysis means.This just needs to collect by unmanned plane inspection flight control data and administrative skill, establishes unmanned plane and flies
Row state estimation early warning platform, the research and application of Develop Data analysis.
Application No. " 201310480659.7 "《Unmanned plane obstruction warning system》, mainly for obstacle report in-flight
It is alert, without the assessment of state of flight of unmanned plane body itself.Application No. " 201510222453.3 "《A kind of unmanned plane management
System》, parameter and the real-time displays on map such as the current location for receiving unmanned plane, state of flight are realized, is mainly solved
Unmanned plane during flying monitors problem.Application No. " 201410160639.6 "《Unmanned plane and its state of flight auxiliary reminding method》
Unmanned plane apparatus assembly exception is judged by controller and prompted, but is not based on the forecast assessment of flying history data.
In summary, it is existing that polling transmission line unmanned plane during flying state estimation method for early warning, its effect are not managed very much
Think still there are many problems to need to solve.
How the analysis based on a large amount of UAV Flight Control data accumulated in working inspection, realize to patrol unmanned
Effective assessment of machine equipment state and state of flight problem real-time early warning, ensure that the safety of unmanned plane power transmission line polling system is steady
Fixed operation, turns into urgent problem to be solved.
The content of the invention
The present invention is in order to solve the above problems, it is proposed that a kind of unmanned plane during flying state assesses early warning system and side in real time
Method, the present invention are handled the flight control result data of unmanned plane inspection with the flight control data during inspection, made
Real-time early warning prompting can be carried out by analysis and evaluation unmanned plane equipment state by obtaining, and ensure the safety of unmanned plane polling transmission line.
To achieve these goals, the present invention adopts the following technical scheme that：
A kind of unmanned plane during flying state assesses early warning system in real time, including assesses early warning platform, unmanned plane and ground monitoring
Stand, wherein：
The ground monitoring station, for obtaining the Flight Condition Data of unmanned plane, pass it to and assess early warning platform；
The assessment early warning platform, for reading unmanned plane during flying status information and flight control data, by patrolling every time
The UAV Flight Control data of inspection task accumulation, build unmanned plane during flying state estimation model, unmanned plane during flying state are entered
Row judges, while receives the flight directive of host computer transmission, adjusts the flight of unmanned plane.
The assessment early warning platform includes state of flight and assesses warning module, flight control data management module, man-machine friendship
Mutual module, communication module, wherein：
The communication module, for being communicated with ground monitoring station, unmanned plane during flying status data is received, is transmitted to winged
Row control data management module；
The flight control data management module, it is corresponding for being managed according to power transmission line unmanned machine inspection aerial mission
Flight control historical data, and obtained in real time by communication module and accumulate UAV Flight Control data；
The state of flight assesses warning module, reads what inspection aerial mission in flight control data management module accumulated
UAV Flight Control data, unmanned plane during flying status safety Early-warning Model is established, unmanned plane during flying state is judged, in advance
It is alert；
The human-computer interaction module, for obtaining and parsing external command, the external command hair after parsing is passed through into ground
Monitoring station is sent to unmanned plane and performs corresponding flight adjust instruction.
The unmanned plane includes but is not limited to the unmanned plane body of fixed-wing, rotor and more rotor forms.
The ground monitoring station, link is passed by number and is connected with unmanned plane, with unmanned plane using the logical of one-to-one connection
Letter mode；It is connected by scheming biography link with unmanned plane, reads the inspection video data of unmanned plane.
The state of flight assesses warning module, the UAV Flight Control data accumulated according to each patrol task, fortune
Unmanned plane during flying status safety Early-warning Model is established with time series analysis, clustering method and SVMs, while
When unmanned plane performs polling transmission line aerial mission, UAV Flight Control data are obtained by ground monitoring station in real time, profit
With unmanned plane during flying status safety Early-warning Model real-time judge unmanned plane during flying state, and timely early warning.
The communication module, it is one-to-many connected mode with ground monitoring station, realizes the data between ground monitoring station
Interaction, from ground monitoring station read unmanned plane GPS location, state of flight, flight control data data and inspection process
Data.
The communication module use including but not limited to current GSM, GPRS, CDMA, WCDMA, TD-SCDMA, LTE with
And WIFI communication standard wireless mobile communications.
A kind of patrol unmanned machine state of flight assesses method for early warning in real time, comprises the following steps：
(1) ground monitoring station obtains the Flight Condition Data and flight control data of unmanned plane, and it is pre- to be transmitted to assessment
Alert platform；
(2) flight control information of unmanned plane is pre-processed, built according to the effect quantity of state of flight and influence amount
Unmanned plane safe early warning object set, input of the critical data as mapping relations is extracted, determine the initial topology of mapping relations
Structure；
(3) the dynamic sample data of unmanned plane operation are combined, build the crucial operation time series variation prediction of unmanned plane
Model, the critical data of unmanned plane operation is monitored and forecast；
(4) minimized using fiducial range value as the constraints of optimization problem using training error and be used as optimization aim, structure
Build unmanned plane safe early warning model, simulation and the relation of prediction unmanned plane working condition and influence factor；
(5) Forewarn evaluation result is exported, the flight directive of unmanned plane is adjusted according to early warning judged result.
In the step (2), using cluster data analysis method, the flight control information of unmanned plane is pre-processed,
Input of the key component as mapping relations is extracted, so that it is determined that the initial primary topology of mapping relations, by formulating object
Attribute and property value describe the effect quantity of unmanned plane and influence amount information aggregate, build unmanned plane safe early warning information table, base
Data matrix is built in unmanned plane safe early warning information table, the similarity degree of each variable in expression set.
In the step (2), unmanned plane safe early warning information table S is expressed as：
S=(U, R, V, F)
R=C ∪ D
In formula, U is nonempty finite set, is the set of object, U={ x1, x2..., xn, n >=0；R=C ∪ D have in vain to be non-
Limit collection, referred to as attribute set, subset C are referred to as conditional attribute collection, that is, influence quantity set, and subset D is referred to as decision kind set, i.e. effect quantity
Collection, C={ c1, c2..., cm, m >=0；D={ d1, d2..., dk, k >=0；V=∪a∈RVaIt is the set of property value, VaRepresent category
Property a range of attributes, wherein a meets that a ∈ R, F are an information functions, and it specifies the property value of each object x in U, i.e. Va
=F (x, a), x ∈ U, a ∈ R.
In the step (2), the data matrix based on safety information table is built, object-attribute matrix is as follows：
Wherein aij(i=1 ..., n；J=1 ..., m) for i-th sample j-th of attribute property value.I-th of sample Ai
For described by the i-th row of matrix A, any two sample AKWith ALBetween similitude, pass through the line k in matrix A and L rows
Similarity degree distinguish；Any two variable aKWith aLBetween similitude, by K row with L row similarity degree come area
Point.
In the step (2), effect quantity includes motor speed, posture, speed and directional angular velocity.
In the step (2), influence amount includes temperature, state-of-charge, humidity, distance and flight time.
In the step (3), concretely comprise the following steps：Time series models are built, using Time series analysis method and variable
Analysis method, the dynamic sample data run with reference to unmanned plane, the key for establishing unmanned plane run the Time series forecasting model of variable.
The critical data includes motor speed, posture, speed and acceleration.
In the step (4), using least square method supporting vector machine algorithm, the constraint of optimization problem is used as using training error
Condition, minimized as optimization aim using fiducial range value, concluded from the safe operation primary monitoring data learning of unmanned plane
Go out UAS moving law, build unmanned plane safe early warning model, simulation and prediction unmanned plane working condition and main shadow
The relation of the factor of sound.
In the step (4), specific method is：Use a Nonlinear Mapping by sample from former space reflection to dimension for
In k high-dimensional feature space, linear regression is then carried out in high-dimensional feature space, it is comprehensive according to structural risk minimization principle
Close and consider function complexity and error of fitting, regression function is looked back into problem equivalent in minimum cost functional, it is bright using glug
Day and KKT optimal conditions, optimization problem is converted into the system of linear equations solved with least square method, obtains unmanned plane safety
The regression model of early warning.
In the step (5), specific method is：According to the influence amount of unmanned plane and the threshold values sample data of effect quantity, by
Time sequence analysis algorithm calculates the influence amount for trying to achieve unmanned plane and the threshold values of effect quantity, will try to achieve phase according to safe early warning model
Answer the threshold values of effect quantity and effect quantity to make the difference and seek absolute value, according to its relation with standard deviation, unmanned plane running status is carried out
Judge, if necessary to alarm, then alarm, and adjust unmanned plane during flying state, state of flight problem is uploaded into unmanned plane during flying
State estimation Warning Service device.
In the step (5), method for early warning is specially：
WhenWhen, unmanned plane during flying is normal；
WhenWhen, it is believed that unmanned plane during flying is normal, the change of observation trendless；
WhenWhen, it is believed that unmanned plane during flying is substantially abnormal, and observation has tendency change；
WhenWhen, alarmed；
When observation trendless changes, it is thus necessary to determine that whether the effect quantity and influence amount of the unmanned plane exceed its valve
Value, if exceeded, output abnormality and alarm.
Wherein s is the standard deviation of model,Respective effects amount, y are tried to achieve for safe early warning modeltFor the threshold values of effect quantity.
Beneficial effects of the present invention are：
(1) by using the method for the present invention, can in real time according to the flight control data of polling transmission line unmanned plane,
The analysis method that passage time sequence analysis, clustering method and SVMs are combined, construct unmanned plane during flying shape
State assesses Early-warning Model, realizes that state of flight of the unmanned plane during polling transmission line assesses early warning in real time；
(2) while the forecast assessment of the assessment to unmanned plane body state of flight itself and flying history data, solve
The real-time monitoring problem of unmanned plane during flying, unmanned plane during flying safety is ensured, is had broad application prospects.
Brief description of the drawings
Fig. 1 is the system structure diagram of the present invention；
Fig. 2 is the schematic flow sheet of the present invention；
Fig. 3 is the automatic estimation flow schematic diagram of state of flight of the present invention.
Embodiment：
The invention will be further described with embodiment below in conjunction with the accompanying drawings.
As shown in figure 1, the present invention is by unmanned plane during flying state estimation early warning platform, ground monitoring station and unmanned plane three parts
Composition, wherein, it is one-to-many between unmanned plane during flying state estimation early warning platform and ground monitoring station to be connected, for building nobody
Machine state of flight assessment models, and the state of flight information and flight control data data of unmanned plane are read, assessment is provided in real time
Early warning；One-to-one connection between ground monitoring station and unmanned plane, for reading unmanned plane during flying status data, and is passed to
Unmanned plane during flying state estimation early warning platform.
Unmanned plane during flying state estimation early warning platform, the UAV Flight Control data accumulated by each patrol task,
The analysis method being combined with time series analysis, clustering method and SVMs, establish unmanned plane during flying state
Safe early warning model, while when unmanned plane performs polling transmission line aerial mission, nothing is obtained by ground monitoring station in real time
Man-machine flight control data, using unmanned plane during flying status safety Early-warning Model real-time judge unmanned plane during flying state, and in time
Early warning.
Unmanned plane can use the unmanned plane body of the forms such as fixed-wing, rotor, more rotors.
Ground monitoring station, link is passed by number and is connected with unmanned plane, for reading the state of flight information of unmanned plane.Ground
Face monitoring station can be also connected by scheming biography link with unmanned plane, for reading the inspection video data of unmanned plane.Ground monitoring
Stand and be connected by way of radio communication or wire communication with flight control data processing server, by unmanned plane during flying shape
State information and flight control data data, it is sent in unmanned plane during flying state estimation Warning Service device.
Human-computer interaction module, which uses, to be included current unmanned plane controlling equipment or is set selected from remote control, keyboard, mouse, audio
Standby, display, multichannel ring curtain stereo projection system, for obtaining and parsing external command, the external command after parsing is sent out
Unmanned plane is sent to by ground monitoring station and performs corresponding flight adjust instruction.
Flight control data management module, corresponding flight is managed according to power transmission line unmanned machine inspection aerial mission respectively
Historical data is controlled, and is obtained in real time by communication module and accumulates UAV Flight Control data.
State of flight assess warning module, using in flight control data management module inspection aerial mission accumulate nobody
Machine flight control data, the analysis method being combined with time series analysis, clustering method and SVMs, establish
Unmanned plane during flying status safety Early-warning Model.Simultaneously when unmanned plane performs polling transmission line aerial mission, to obtaining in real time
UAV Flight Control data, judge unmanned plane during flying state using unmanned plane during flying status safety Early-warning Model, and it is pre- in real time
It is alert.
Communication module, interacted for realizing with data between ground monitoring station, nobody is read from ground monitoring station
The Monitoring Datas such as GPS location, state of flight, flight control data data and the inspection process data of machine, and by Monitoring Data
It is sent to unmanned plane during flying state estimation early warning platform.The communication module using including but not limited to current GSM, GPRS, CDMA,
WCDMA, TD-SCDMA, LTE and WIFI communication standard wireless mobile communications.
As shown in Fig. 2 the unmanned plane during flying state for polling transmission line assesses method for early warning in real time, comprise the following steps：
1. obtaining flight control data, unmanned plane during flying state estimation early warning platform obtains nothing in real time by ground monitoring station
Man-machine flight control data.
2. unmanned plane during flying state is assessed automatically, appraisal procedure is as shown in figure 3, including step as follows：
1) flight control data imports.
2) data prediction, using cluster data analysis method, the flight control information of unmanned plane is pre-processed, taken out
Input of the key component as mapping relations is taken, so that it is determined that the initial primary topology of mapping relations.
It is (temperature, state-of-charge, wet by effect quantity (motor speed, posture, speed, directional angular velocity etc.) and influence amount
Degree, distance, flight time etc.) composition unmanned plane safe early warning information represent research object set.The knowledge of these objects
Be by specify object attribute (unmanned plane effect quantity and influence amount) and their property value (Monitoring Data) come what is described.
One unmanned plane safe early warning information table, represent when meeting some conditions (influence amount), unmanned plane effect quantity
Situation.One unmanned plane safe early warning information table S can be expressed as：
S=(U, R, V, F) formula (1)
R=C ∪ D formulas (2)
In formula, U is nonempty finite set, is the set of object, U={ x1, x2..., xn, n >=0；R=C ∪ D have in vain to be non-
Limit collection, referred to as attribute set, subset C are referred to as conditional attribute collection (influence quantity set), and subset D is referred to as decision kind set (effect quantity
Collection), C={ c1, c2..., cm, m >=0；D={ d1, d2..., dk, k >=0；V=∪a∈RVaIt is the set of property value, VaRepresent
Attribute a range of attributes, wherein a meet a ∈ R.F：It is an information function, it specifies the property value of each object x in U,
That is Va=F (x, a), x ∈ U, a ∈ R.
Table 1 is the unmanned plane safe early warning information table defined by formula (1), one in its every a line representation theory domain
Sample, each row represent attribute and property value.
The unmanned plane safe early warning information table of form 1
Thus we can build the data matrix based on safety information table, and object-attribute matrix is as follows：
Formula (3)
Wherein aij(i=1 ..., n；J=1 ..., m) for i-th sample j-th of attribute property value.I-th of sample Ai
For described by the i-th row of matrix A, so the similitude between any two sample AK and AL, can pass through the K in matrix A
Go with the similarity degree of L rows to distinguish；Any two variable aKWith aLBetween similitude, can pass through K row with L arrange
Similarity degree distinguish.
3) time series models are built, using Time series analysis method and variable analysis method, are run with reference to unmanned plane
Dynamic sample data, establish crucial operation variable (motor speed, posture, speed, acceleration etc.) time series forecasting of unmanned plane
Model.
4) SVM model constructions, using least square method supporting vector machine algorithm, the constraint of optimization problem is used as using training error
Condition, minimized as optimization aim using fiducial range value, concluded from the safe operation primary monitoring data learning of unmanned plane
Go out UAS moving law, so as to realize the structure to unmanned plane safe early warning model, realize effective simulation and prediction
The relation of unmanned plane working condition and major influence factors.
Assuming that training sample is { (x1, y2) ..., (xi, yi), wherein xi∈X∈Rm, X is referred to as the input space, xiIt is i-th
The input value of individual learning sample, and be m dimensional vectors, yi∈Y∈RmFor corresponding aim parameter.Using a Nonlinear Mapping θ
(c) in the high-dimensional feature space F for being k from former space reflection to dimension by sample, then carried out in high-dimensional feature space linear
Return.If regression function is：
F (x)=(ω, θ (x))+b formulas (4)
In formula, ω is weight vector, ω ∈ Rk, for the item of described function f (x) complexities；(ω, θ (x)) represents ω and θ (x)
Inner product；θ is RmNonlinear Mapping of the space to F spaces；B is constant, b ∈ R.
According to structural risk minimization principle, function complexity and error of fitting are considered, above-mentioned function looks back problem
It is equivalent to minimize cost functional：
Formula (5)
ε=yi-ωT·θ(xi)-b, i=1,2 ..., 1 formula (6)
Wherein, ε is slack variable, ε >=0；C is punishment parameter, and C ＞ 0, its effect is complicated in empiric risk and model
Compromise is taken between degree.
Formula (9) uses the core concept of Statistical Learning Theory, and both controlled training error, there is Controlling model complexity, purpose
It is to obtain a small expected risk.The generalization ability of model can so be improved.
In order to solve above-mentioned optimization problem, Lagrangian is established：
Formula (7)
In formula, αiFor Lagrange multiplier.
According to KKT (Karush-Kuhn-Tucker) optimal conditions：
Formula (8)
Formula (9)
Formula (10)
Formula (11)
After eliminating ε and ω, following system of linear equations is obtained：
Formula (12)
In formula, e=[1,1 ..., 1]T；I is unit matrix；α=[α1, α2..., αl]T；Qij=(xi)T；θ(xi)=K (xi,
xj) it is kernel function, i, j=1,2 ..., l.
It can be obtained by formula 12, optimization problem is converted into the linear side solved with least square method by above-mentioned algorithm of support vector machine
Journey group.Following regression model can finally be obtained：
Formula (13)
5) calculate and export Forewarn evaluation result.
If a certain moment t, according to the influence amount of unmanned plane and the threshold values sample data of effect quantity, calculated by time series analysis
Method calculates the influence amount threshold values such as the motor temperature for trying to achieve unmanned plane, state-of-charge, humidity, air route, distance, speed, flight time
xtWith the threshold values y of the effect quantity such as temperature rise, specific energy consumption, motor speedt.Respective effects amount is tried to achieve by safe early warning modelWill
With the threshold values y of effect quantitytIt is compared, obtainsAccording to Probability Statistics Theory,Fall into the probability of [0,2S]
For 95.5%, the probability for falling into [0,3S] is 99.7%, and wherein S is the standard deviation of model.Accordingly, can be by following several situations pair
Unmanned plane running status carries out early warning.
Normally：
It is normal：Observation trendless changes；
It is abnormal：Observation has tendency change；
Alarm：
When the 3rd kind and the 4th kind of situation occurs, it is necessary to analyze unmanned plane service data, the unmanned plane is determined
Whether effect quantity and influence amount exceed its threshold values and output abnormality and alarm.
3. judging whether problem, enter 4 if there is problem, there is no problem, and flow terminates.
4. unmanned plane during flying state issues early warning, the problem of unmanned plane there may be, carries out early warning.
5. judge whether to need problem adjustment, it is necessary to be adjusted into 6, it is not necessary to be adjusted into 7；
6. state of flight adjust instruction issues, carried out by ground monitoring station real time down flight control instruction to unmanned plane
State of flight adjusts.
State of flight problem uploads to unmanned plane during flying state estimation Warning Service device, and it is real-time to terminate unmanned plane during flying state
Assess early warning flow.
Although above-mentioned the embodiment of the present invention is described with reference to accompanying drawing, model not is protected to the present invention
The limitation enclosed, one of ordinary skill in the art should be understood that on the basis of technical scheme those skilled in the art are not
Need to pay various modifications or deformation that creative work can make still within protection scope of the present invention.
Claims (16)
1. a kind of unmanned plane during flying state assesses early warning system in real time, it is characterized in that：Including assessing early warning platform, unmanned plane and ground
Face monitoring station, wherein：
The ground monitoring station, for obtaining the Flight Condition Data of unmanned plane, pass it to and assess early warning platform；
The assessment early warning platform, for reading unmanned plane during flying status information and flight control data, is appointed by each inspection
The UAV Flight Control data of business accumulation, build unmanned plane during flying state estimation model, unmanned plane during flying state are sentenced
It is disconnected, while the flight directive of host computer transmission is received, adjust the flight of unmanned plane；
The assessment early warning platform includes state of flight and assesses warning module, flight control data management module, man-machine interaction mould
Block, communication module, wherein：
The communication module, for being communicated with ground monitoring station, unmanned plane during flying status data is received, is transmitted to flight control
Data management module processed；
The flight control data management module, for managing corresponding flight according to power transmission line unmanned machine inspection aerial mission
Historical data is controlled, and is obtained in real time by communication module and accumulates UAV Flight Control data；
The state of flight assesses warning module, reads inspection aerial mission in flight control data management module accumulates nobody
Machine flight control data, unmanned plane during flying status safety Early-warning Model is established, unmanned plane during flying state is judged, early warning；
The human-computer interaction module, for obtaining and parsing external command, the external command hair after parsing is passed through into ground monitoring
Station is sent to unmanned plane and performs corresponding flight adjust instruction.
2. a kind of unmanned plane during flying state as claimed in claim 1 assesses early warning system in real time, it is characterized in that：The ground prison
Control station, link is passed by number and is connected with unmanned plane, the communication mode of one-to-one connection is used with unmanned plane；By scheming to pass link
It is connected with unmanned plane, reads the inspection video data of unmanned plane.
3. a kind of unmanned plane during flying state as claimed in claim 1 assesses early warning system in real time, it is characterized in that：The flight shape
State assesses warning module, the UAV Flight Control data accumulated according to each patrol task, with time series analysis, cluster
Analysis method and SVMs establish unmanned plane during flying status safety Early-warning Model, while perform transmission line of electricity in unmanned plane and patrol
When examining aerial mission, UAV Flight Control data are obtained by ground monitoring station in real time, utilize unmanned plane during flying status safety
Early-warning Model real-time judge unmanned plane during flying state, and timely early warning.
4. a kind of unmanned plane during flying state as claimed in claim 1 assesses early warning system in real time, it is characterized in that：The communication mould
Block, it is one-to-many connected mode with ground monitoring station, realization interacts with the data between ground monitoring station, from ground monitoring station
Middle GPS location, state of flight, flight control data data and the inspection process data for reading unmanned plane.
5. a kind of patrol unmanned machine state of flight assesses method for early warning in real time, it is characterized in that：Comprise the following steps：
(1) ground monitoring station obtains the Flight Condition Data and flight control data of unmanned plane, is transmitted to assessment early warning and puts down
Platform；
(2) flight control information of unmanned plane is pre-processed, nobody is built according to the effect quantity of state of flight and influence amount
Machine safe early warning object set, input of the critical data as mapping relations is extracted, determine the initial primary topology of mapping relations；
(3) the dynamic sample data of unmanned plane operation are combined, build the crucial operation time series variation forecast model of unmanned plane,
The critical data of unmanned plane operation is monitored and forecast；
(4) minimized using fiducial range value as optimization aim as the constraints of optimization problem using training error, build nothing
Man-machine safety Early-warning Model, simulation and the relation of prediction unmanned plane working condition and influence factor；
(5) Forewarn evaluation result is exported, the flight directive of unmanned plane is adjusted according to early warning judged result.
6. a kind of patrol unmanned machine state of flight as claimed in claim 5 assesses method for early warning in real time, it is characterized in that：The step
Suddenly in (2), using cluster data analysis method, the flight control information of unmanned plane is pre-processed, key component is extracted and makees
For the input of mapping relations, so that it is determined that the initial primary topology of mapping relations, by formulate attribute and the property value of object come
The effect quantity and influence amount information aggregate of unmanned plane are described, builds unmanned plane safe early warning information table, it is pre- safely based on unmanned plane
Alert information table structure data matrix, the similarity degree of each variable in expression set.
7. a kind of patrol unmanned machine state of flight as claimed in claim 5 assesses method for early warning in real time, it is characterized in that：The step
Suddenly in (2), unmanned plane safe early warning information table S is expressed as：
S=(U, R, V, F)
R=C ∪ D
In formula, U is nonempty finite set, is the set of object, U={ x1,x2,…,xn},n≥0；R=C ∪ D are nonempty finite set,
Referred to as attribute set, subset C are referred to as conditional attribute collection, that is, influence quantity set, and subset D is referred to as decision kind set, i.e. effect quantity set, C
={ c1,c2,…,cm},m≥0；D={ d1,d2,…,dk},k≥0；V=∪a∈RVaIt is the set of property value, VaRepresent attribute a
Range of attributes, wherein a meets that a ∈ R, F are an information functions, and it specifies the property value of each object x in U, i.e. Va=F
(x,a),x∈U,a∈R。
8. a kind of patrol unmanned machine state of flight as claimed in claim 5 assesses method for early warning in real time, it is characterized in that：The step
Suddenly in (2), the data matrix based on safety information table is built, object-attribute matrix is as follows：
Wherein aij(i=1 ..., n；J=1 ..., m) for i-th sample j-th of attribute property value, i-th of sample AiFor square
Described by battle array A the i-th row, any two sample AKWith ALBetween similitude, pass through the line k and the phase of L rows in matrix A
Distinguished like degree；Any two variable aKWith aLBetween similitude, distinguished by K row and the L similarity degrees arranged.
9. a kind of patrol unmanned machine state of flight as claimed in claim 5 assesses method for early warning in real time, it is characterized in that：The step
Suddenly in (2), effect quantity includes motor speed, posture, speed and directional angular velocity.
10. a kind of patrol unmanned machine state of flight as claimed in claim 5 assesses method for early warning in real time, it is characterized in that：It is described
In step (2), influence amount includes temperature, state-of-charge, humidity, distance and flight time.
11. a kind of patrol unmanned machine state of flight as claimed in claim 5 assesses method for early warning in real time, it is characterized in that：It is described
In step (3), concretely comprise the following steps：Time series models are built, using Time series analysis method and variable analysis method, with reference to
The dynamic sample data of unmanned plane operation, establish the Time series forecasting model of the crucial operation variable of unmanned plane.
12. a kind of patrol unmanned machine state of flight as claimed in claim 5 assesses method for early warning in real time, it is characterized in that：It is described
Critical data includes motor speed, posture, speed and acceleration.
13. a kind of patrol unmanned machine state of flight as claimed in claim 5 assesses method for early warning in real time, it is characterized in that：It is described
In step (4), using least square method supporting vector machine algorithm, using training error as the constraints of optimization problem, with confidence
Value range is minimized and is used as optimization aim, and UAS is summarized from the safe operation primary monitoring data learning of unmanned plane
Moving law, build unmanned plane safe early warning model, simulation and the relation of prediction unmanned plane working condition and major influence factors.
14. a kind of patrol unmanned machine state of flight as claimed in claim 5 assesses method for early warning in real time, it is characterized in that：It is described
In step (4), specific method is：Use a Nonlinear Mapping by sample from former space reflection to dimension for k high dimensional feature
In space, linear regression is then carried out in high-dimensional feature space, according to structural risk minimization principle, function is considered and answers
Miscellaneous degree and error of fitting, regression function is looked back into problem equivalent in minimizing cost functional, optimized using Lagrange and KKT
Condition, optimization problem is converted into the system of linear equations solved with least square method, obtains the recurrence mould of unmanned plane safe early warning
Type.
15. a kind of patrol unmanned machine state of flight as claimed in claim 5 assesses method for early warning in real time, it is characterized in that：It is described
In step (5), specific method is：According to the influence amount of unmanned plane and the threshold values sample data of effect quantity, by time series analysis
Algorithm calculates the influence amount for trying to achieve unmanned plane and the threshold values of effect quantity, and respective effects amount and effect will be tried to achieve according to safe early warning model
The threshold values that should be measured, which makes the difference, seeks absolute value, according to its relation with standard deviation, unmanned plane running status is judged, if desired
Alarm, then alarmed, and adjusts unmanned plane during flying state, and state of flight problem is uploaded into the pre- police uniform of unmanned plane during flying state estimation
Business device.
16. a kind of patrol unmanned machine state of flight as claimed in claim 5 assesses method for early warning in real time, it is characterized in that：It is described
In step (5), method for early warning is specially：
WhenWhen, unmanned plane during flying is normal；
WhenWhen, it is believed that unmanned plane during flying is normal, the change of observation trendless；
WhenWhen, it is believed that unmanned plane during flying is substantially abnormal, and observation has tendency change；
WhenWhen, alarmed；
When observation trendless changes, it is thus necessary to determine that whether the effect quantity and influence amount of the unmanned plane exceed its threshold values, such as
Fruit exceeds, output abnormality and alarm；
Wherein s is the standard deviation of model,Respective effects amount, y are tried to achieve for safe early warning modeltFor the threshold values of effect quantity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510734491.7A CN105427674B (en) | 2015-11-02 | 2015-11-02 | A kind of unmanned plane during flying state assesses early warning system and method in real time |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510734491.7A CN105427674B (en) | 2015-11-02 | 2015-11-02 | A kind of unmanned plane during flying state assesses early warning system and method in real time |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105427674A CN105427674A (en) | 2016-03-23 |
| CN105427674B true CN105427674B (en) | 2017-12-12 |
Family
ID=55505847
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510734491.7A Active CN105427674B (en) | 2015-11-02 | 2015-11-02 | A kind of unmanned plane during flying state assesses early warning system and method in real time |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105427674B (en) |
Families Citing this family (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105788394A (en) * | 2016-04-16 | 2016-07-20 | 吉林医药学院 | Maintenance detection simulated training system for unmanned plane |
| CN105825718A (en) * | 2016-04-26 | 2016-08-03 | 广东容祺智能科技有限公司 | Unmanned aerial vehicle comprehensive management platform system |
| FR3052273B1 (en) * | 2016-06-02 | 2018-07-06 | Airbus | PREDICTION OF TROUBLES IN AN AIRCRAFT |
| CN106096207B (en) * | 2016-06-29 | 2019-06-07 | 武汉中观自动化科技有限公司 | A kind of rotor wing unmanned aerial vehicle wind resistance appraisal procedure and system based on multi-vision visual |
| CN106444572A (en) * | 2016-07-21 | 2017-02-22 | 中交信通（天津）科技有限公司 | Unmanned aerial vehicle safety monitoring and warning device based on Beidou system |
| CN106769089B (en) * | 2016-12-19 | 2019-04-23 | 中国航空工业集团公司沈阳飞机设计研究所 | Unmanned plane during flying performance evaluation method for real-time monitoring integrated with flight quality assessment |
| CN106774411B (en) * | 2016-12-31 | 2020-03-03 | 清华大学深圳研究生院 | Unmanned aerial vehicle middleware system based on PHM |
| CN106971432A (en) * | 2017-04-11 | 2017-07-21 | 中国人民解放军海军航空工程学院青岛校区 | A kind of airplane data management record system and data presentation technique |
| CN107229234A (en) * | 2017-05-23 | 2017-10-03 | 深圳大学 | The distributed libray system and method for Aviation electronic data |
| CN107590878A (en) * | 2017-09-13 | 2018-01-16 | 中国人民解放军火箭军工程大学 | A kind of unmanned plane during flying safe prediction apparatus for evaluating and method |
| CN107516451A (en) * | 2017-10-08 | 2017-12-26 | 景遥（上海）信息技术有限公司 | Fixed-wing UAV Intelligent flight training system |
| CN108259223B (en) * | 2017-12-07 | 2021-03-26 | 中国航空工业集团公司西安航空计算技术研究所 | Unmanned aerial vehicle network system security situation perception evaluation method for preventing GPS deception |
| CN110568855A (en) * | 2018-06-06 | 2019-12-13 | 上海资誉电子科技有限公司 | Unmanned aerial vehicle visual flight management system and method based on big data calculation engine |
| CN110222375B (en) * | 2019-05-13 | 2021-07-13 | 北京航空航天大学 | Safety monitoring method for carrier aircraft landing process |
| CN110321951B (en) * | 2019-07-01 | 2021-03-16 | 青岛海科虚拟现实研究院 | VR simulated aircraft training evaluation method |
| CN113449238B (en) * | 2020-03-24 | 2023-04-25 | 丰翼科技(深圳)有限公司 | Unmanned aerial vehicle safe operation method and device, electronic equipment and storage medium |
| CN111554286A (en) * | 2020-04-26 | 2020-08-18 | 云知声智能科技股份有限公司 | Method and equipment for controlling unmanned aerial vehicle based on voice |
| CN111582740B (en) * | 2020-05-13 | 2023-05-23 | 电子科技大学 | Multi-rotor unmanned aerial vehicle risk assessment system |
| CN111935811A (en) * | 2020-06-28 | 2020-11-13 | 北京遥测技术研究所 | Airborne swarm terminal adaptive power control method based on temperature sensor |
| CN111862550B (en) * | 2020-08-13 | 2021-11-30 | 深圳市高巨创新科技开发有限公司 | Formation unmanned aerial vehicle group departure alarm method and system |
| CN113759968B (en) * | 2021-09-01 | 2022-07-01 | 中国南方电网有限责任公司超高压输电公司贵阳局 | Unmanned aerial vehicle-based power grid line patrol planning method and system |
| CN114373238A (en) * | 2021-12-06 | 2022-04-19 | 特金智能科技(上海)有限公司 | Attendance checking method and device for unmanned aerial vehicle inspection flight, electronic equipment and storage medium |
| CN114201925B (en) * | 2022-02-17 | 2022-06-17 | 佛山科学技术学院 | Unmanned aerial vehicle cluster cooperative task planning method, electronic equipment and readable storage medium |
| CN115164884B (en) * | 2022-07-19 | 2024-05-03 | 中国民航大学 | Unmanned aerial vehicle flight state on-line monitoring system |
| CN116384695B (en) * | 2023-04-11 | 2024-01-26 | 中国人民解放军陆军工程大学 | Unmanned aerial vehicle operation monitoring method and system based on independent overruling and combined overruling |
| CN116523384B (en) * | 2023-04-11 | 2024-05-14 | 中国人民解放军陆军工程大学 | Unmanned aerial vehicle efficiency determining method and system based on independent overruling and combined overruling |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103824340A (en) * | 2014-03-07 | 2014-05-28 | 山东鲁能智能技术有限公司 | Intelligent inspection system and inspection method for electric transmission line by unmanned aerial vehicle |
| CN104597907A (en) * | 2014-11-27 | 2015-05-06 | 国家电网公司 | Method for accurately evaluating flight of UAV (unmanned aerial vehicle) inspection system of overhead transmission line |
| CN104765968A (en) * | 2015-04-21 | 2015-07-08 | 合肥工业大学 | Unmanned aerial vehicle system health status evaluation device |
| CN104820428A (en) * | 2015-04-20 | 2015-08-05 | 余江 | Memory type track reproduction method of unmanned aerial vehicle and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7818127B1 (en) * | 2004-06-18 | 2010-10-19 | Geneva Aerospace, Inc. | Collision avoidance for vehicle control systems |
| KR102282901B1 (en) * | 2009-02-02 | 2021-07-29 | 에어로바이론먼트, 인크. | Multimode unmanned aerial vehicle |
-
2015
- 2015-11-02 CN CN201510734491.7A patent/CN105427674B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103824340A (en) * | 2014-03-07 | 2014-05-28 | 山东鲁能智能技术有限公司 | Intelligent inspection system and inspection method for electric transmission line by unmanned aerial vehicle |
| CN104597907A (en) * | 2014-11-27 | 2015-05-06 | 国家电网公司 | Method for accurately evaluating flight of UAV (unmanned aerial vehicle) inspection system of overhead transmission line |
| CN104820428A (en) * | 2015-04-20 | 2015-08-05 | 余江 | Memory type track reproduction method of unmanned aerial vehicle and device |
| CN104765968A (en) * | 2015-04-21 | 2015-07-08 | 合肥工业大学 | Unmanned aerial vehicle system health status evaluation device |
Non-Patent Citations (1)
| Title |
|---|
| 跟踪地面目标小型无人机地面显控平台的设计与实现;王洋 等;《遥测遥控》;20091130;第30卷(第6期);第31-35页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105427674A (en) | 2016-03-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105427674B (en) | A kind of unmanned plane during flying state assesses early warning system and method in real time | |
| CN108011948B (en) | Industrial equipment integration monitored control system based on edge calculation | |
| CN107276816A (en) | A kind of long-range monitoring and fault diagnosis system and method for diagnosing faults based on cloud service | |
| CN106529764A (en) | 3D visualized smart water affairs operation system | |
| CN107358388A (en) | A kind of WMS based on Internet of Things and the storage quality risk appraisal procedure based on the system | |
| US11982409B2 (en) | Safety monitoring methods and Internet of Things systems of pipe network reliability degree based on intelligent gas | |
| CN110189070B (en) | Intelligent logistics Internet of things system | |
| CN102801767A (en) | Prognostics and health management (PHM) system for single-level aircraft structure and implementation method | |
| CN109490713A (en) | A kind of method and system moving inspection and interactive diagnosis for cable run | |
| CN111275948B (en) | Electric fire fighting early warning system | |
| CN113592128A (en) | Big data electric wire netting operation monitoring system | |
| CN103560590B (en) | Electric network intelligent scheduling framework and its implementation | |
| CN204515507U (en) | Based on the electromechanical equipment operation remote monitoring management system of Internet of Things | |
| CN108225439A (en) | A kind of electronic communication environment monitoring system | |
| CN105898898A (en) | Information monitoring system based on wireless sensor network | |
| KR20150026230A (en) | Self running building energy management system using bim data | |
| CN106681244A (en) | Intelligent distributed distribution room remote monitoring system | |
| CN103914058B (en) | The fault diagnosis and alarm method and system of a kind of oil-gas pipeline industrial control equipment remote monitoring system | |
| CN110443411A (en) | Method based on the ADS-B data prediction flight landing time | |
| CN103473363A (en) | Base station high-altitude inspection system based on aircraft and inspection method of base station high-altitude inspection system | |
| CN104392591A (en) | Transmission pole fault monitoring expert system | |
| CN104270830A (en) | Workshop following type environmental parameter monitoring system based on wireless sensor networks | |
| CN110262313A (en) | Power Material key point remote supervision system based on technology of Internet of things | |
| CN203135932U (en) | IoT monitoring management system | |
| CN112821456B (en) | Distributed source-storage-load matching method and device based on transfer learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Wang Yue Central Road Ji'nan City, Shandong province 250002 City No. 2000 Co-patentee after: National Network Intelligent Technology Co., Ltd. Patentee after: Electric Power Research Institute of State Grid Shandong Electric Power Company Co-patentee after: State Grid Corporation of China Address before: Wang Yue Central Road Ji'nan City, Shandong province 250002 City No. 2000 Co-patentee before: Shandong Luneng Intelligent Technology Co., Ltd. Patentee before: Electric Power Research Institute of State Grid Shandong Electric Power Company Co-patentee before: State Grid Corporation of China |
|
| CP01 | Change in the name or title of a patent holder | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201029 Address after: 250101 Electric Power Intelligent Robot Production Project 101 in Jinan City, Shandong Province, South of Feiyue Avenue and East of No. 26 Road (ICT Industrial Park) Patentee after: National Network Intelligent Technology Co.,Ltd. Address before: Wang Yue Central Road Ji'nan City, Shandong province 250002 City No. 2000 Patentee before: ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER Co. Patentee before: National Network Intelligent Technology Co.,Ltd. Patentee before: STATE GRID CORPORATION OF CHINA |
|
| TR01 | Transfer of patent right |