CN115903760A - Fault diagnosis and performance evaluation method for unmanned aerial vehicle system - Google Patents
Fault diagnosis and performance evaluation method for unmanned aerial vehicle system Download PDFInfo
- Publication number
- CN115903760A CN115903760A CN202310130624.4A CN202310130624A CN115903760A CN 115903760 A CN115903760 A CN 115903760A CN 202310130624 A CN202310130624 A CN 202310130624A CN 115903760 A CN115903760 A CN 115903760A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- vehicle system
- information
- diagnosis
- 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.)
- Withdrawn
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses a method for fault diagnosis and performance evaluation of an unmanned aerial vehicle system, belongs to the field of unmanned aerial vehicles, and solves the problem of how to perform fault diagnosis and performance evaluation on the unmanned aerial vehicle system; according to the method, the unmanned aerial vehicle system is comprehensively calibrated and detected, and fault diagnosis is performed on calibration detection information of the unmanned aerial vehicle system through an integrated intelligent diagnosis model, wherein the fault diagnosis comprises case reasoning, rule-based diagnosis of an expert system, fault tree model-based diagnosis and neural network model-based diagnosis, and according to the difficulty of information acquisition and the information acquisition mode, calibration detection data are rapidly analyzed and processed, so that fault diagnosis is performed on the unmanned aerial vehicle system; if the unmanned aerial vehicle system has no fault, carrying out comprehensive performance evaluation on calibration detection information of the unmanned aerial vehicle system; thereby guarantee that unmanned aerial vehicle can normal operating work.
Description
Technical Field
The invention belongs to the field of unmanned aerial vehicles, and particularly relates to a method for fault diagnosis and performance evaluation of an unmanned aerial vehicle system.
Background
Along with the development of science and technology, unmanned aerial vehicle can replace the manpower to go to the space position that can not reach and carry out the operation work, and the type of unmanned aerial vehicle includes the multiple at present, is applied to various trade fields.
How to judge whether the unmanned aerial vehicle system has a fault and how to judge the performance of the unmanned aerial vehicle system need a certain method to determine, thereby ensuring that the unmanned aerial vehicle can normally operate. Currently there is no exact solution for the moment.
Therefore, the invention provides a method for fault diagnosis and performance evaluation of an unmanned aerial vehicle system.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a method for fault diagnosis and performance evaluation of an unmanned aerial vehicle system, which solves the problem of how to carry out fault diagnosis and performance evaluation on the unmanned aerial vehicle system.
To achieve the above object, an embodiment according to a first aspect of the present invention proposes a method for fault diagnosis and performance assessment of an unmanned aerial vehicle system, including:
carrying out comprehensive calibration detection on the unmanned aerial vehicle system;
carrying out fault diagnosis on calibration detection information of the unmanned aerial vehicle system through an integrated intelligent diagnosis model;
and if the unmanned aerial vehicle system has no fault, evaluating the comprehensive performance of the calibration detection information of the unmanned aerial vehicle system.
Further, the unmanned aerial vehicle system comprises five components of a wireless data chain, a ground main control station, flight control, airborne measurement and task cable detection.
Further, the calibration detection information includes: communication information, analog information, switching value information, power and frequency information, pressure information, vertical gyro information, temperature, angular rate information, information acquired through an AD acquisition card, and serial communication data information.
Further, carry out fault diagnosis to the calibration detection information of unmanned aerial vehicle system through integrated form intelligent diagnosis model, include:
case reasoning is carried out on the acquired calibration detection information, and if no same case exists in a case database or diagnosis fails, a next diagnosis strategy is determined according to an information acquisition mode and difficulty;
when the information is difficult to obtain, adopting a diagnosis method of an expert system based on rules; if the fault is adopted irregularly or the diagnosis fails, a diagnosis method based on a fault tree model or a neural network model is considered;
when the information is easy to obtain, a diagnosis method based on a fault tree model or a neural network model is considered;
when information is acquired in a continuous mode, a diagnosis method based on a fault tree model is adopted;
when information is acquired in a parallel mode, a diagnosis method based on a neural network model is adopted;
when all the methods fail, taking the diagnosis result as a new case;
when any fault of the unmanned aerial vehicle occurs, the fault is processed in time, and after the fault is processed, comprehensive calibration detection is continuously carried out on the unmanned aerial vehicle system.
Further, case reasoning is to match the acquired fault information with historical fault information in a case database, and to diagnose by querying the same or similar fault phenomena occurring in the case database before.
Further, the method for evaluating the comprehensive performance of the unmanned aerial vehicle system comprises the following steps:
let the unmanned aerial vehicle system have m physical quantities d = (d) 1 ,d 2 ,d 3 ,…,d m ) The performance number p = (p) 1 ,p 2 ,p 3 ,…,p m ) Corresponding value of the utility function μ = (μ) 1 ,μ 2 ,μ 3 ,…,μ m ) Weight of physical quantity w = (w) 1 ,w 2 ,w 3 ,…,w m ) Maximum point d of performance index max ＝(r max1 ,r max2 ,r max3 ,…,r maxm ) Minimum value point d of performance index min ＝(r min1 ,r min2 ,r min3 ,…,r minm ) Then, there are:
the first situation is as follows: if the physical quantity p k The larger the requirement, the better, where k =1,2 \ 8230m; the utility function is then:
μ k ＝d k /r maxk ，d k ∈[r mink ,r maxk ]
case two: if the physical quantity p k The smaller the requirement, the better, the utility function is:
μ k ＝1+(r mink -d k )/r maxm ，d k ∈[r mink ,r maxk ]
case three: if the physical quantity p k Is required to be in 1 ,r 2 ]With a good range, the utility function is:
the performance evaluation indexes of all components of the unmanned aerial vehicle system can be calculated by applying a linear weighting method, namely:
wherein i represents a component of the unmanned aerial vehicle system, i =1,2,3 \ 8230n; n is the number of the components of the unmanned aerial vehicle system; e.g. of the type i An index of performance rating for the ith component;
the calculation formula of the comprehensive performance evaluation index of the unmanned aerial vehicle system is as follows:
wherein q is i Is the weight of the ith component.
Compared with the prior art, the invention has the beneficial effects that:
according to the method, the unmanned aerial vehicle system is comprehensively calibrated and detected, and fault diagnosis is performed on calibration detection information of the unmanned aerial vehicle system through an integrated intelligent diagnosis model, wherein the fault diagnosis comprises case reasoning, rule-based diagnosis of an expert system, fault tree model-based diagnosis and neural network model-based diagnosis, and according to the difficulty of information acquisition and the information acquisition mode, calibration detection data are rapidly analyzed and processed, so that fault diagnosis is performed on the unmanned aerial vehicle system; if the unmanned aerial vehicle system has no fault, carrying out comprehensive performance evaluation on calibration detection information of the unmanned aerial vehicle system; the problem of how to carry out failure diagnosis and performance assessment to unmanned aerial vehicle system is solved to guarantee that unmanned aerial vehicle can normal operating work.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
Detailed Description
The technical solutions of the present invention will be described below clearly and completely in conjunction with the embodiments, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the system for integrated calibration and detection of a drone includes the following steps:
the method comprises the following steps: carrying out comprehensive calibration detection on the unmanned aerial vehicle system;
in the embodiment of the invention, the unmanned aerial vehicle system comprises five components of a wireless data link, a ground main control station, flight control, airborne measurement and task cable detection, and covers the main technical state of the unmanned aerial vehicle system;
the method comprises the steps that comprehensive calibration detection is carried out on five components of an unmanned aerial vehicle system, and calibration information and/or detection information of each component of the unmanned aerial vehicle system are obtained;
it should be noted that, it is prior art to perform comprehensive calibration and detection on five components of the unmanned aerial vehicle system, and specific details are not described herein in detail;
step two: carrying out fault diagnosis on calibration detection information of the unmanned aerial vehicle system through an integrated intelligent diagnosis model;
in the embodiment of the invention, during the comprehensive calibration and detection process of the unmanned aerial vehicle system, the electronic device receives and outputs various information, such as alternating current information, analog information, switching value information, power and frequency information, pressure information, vertical gyro information, temperature and angular rate information, information acquired by an AD acquisition card, serial communication data information and the like;
analyzing and processing different types of information, and diagnosing whether a current unmanned aerial vehicle system has a fault, wherein a fault diagnosis method based on artificial intelligence is generally adopted, and an expert system and a neural network system are two most active fault diagnosis modes in the current fault diagnosis field; however, the expert system has the bottleneck problem of knowledge acquisition and the combined explosion problem of logical reasoning, and although the neural network solves the problem, the neural network has the problems of low learning efficiency, low training speed, weak comprehension capability, easy falling into local minimum points and the like;
carry out fault diagnosis through integrated form intelligent diagnosis model to unmanned aerial vehicle system's calibration detection information in this application, specifically be:
case reasoning is carried out on the acquired calibration detection information, and if no same case exists in a case database or diagnosis fails, a next diagnosis strategy is determined according to an information acquisition mode and difficulty; the case reasoning is to match the acquired fault information with historical fault information in a case database and diagnose by inquiring the same or similar fault phenomena occurring in the case database;
when the information is difficult to obtain but the symptom description is relatively easy, a diagnosis method based on a rule expert system is adopted; if the rule is available or the diagnosis fails, considering a diagnosis method based on a fault tree model or a neural network model;
the diagnosis method of the rule-based expert system adopts an artificial intelligence technology, simulates the thinking process of human expert decision according to the knowledge and reasoning ability provided by the expert, and solves the problem which needs to be solved by the expert originally;
the diagnosis method based on the fault tree model is an analysis method which analyzes various factors (including hardware, software, environment, human factors and the like) which possibly cause the faults of the unmanned aerial vehicle system from whole to part in a tree shape by step in a detailed mode, draws a logic block diagram (namely a fault tree), further determines the fault combination mode of the causes of the faults of the unmanned aerial vehicle system, the influence of the causes on the unmanned aerial vehicle system and the probability of the faults to occur, calculates the fault probability of the unmanned aerial vehicle system, and adopts corresponding corrective measures, thereby improving the reliability of the system;
the diagnosis method based on the neural network model is characterized in that expert knowledge and diagnosis examples are distributed in the network in a weight value and threshold value mode through learning of experience samples, and uncertainty reasoning is completed by utilizing information retentivity of the neural network;
when the information is easy to obtain, a diagnosis method based on a fault tree model or a neural network model is considered for diagnosis;
when information is acquired in a continuous mode, a diagnosis method based on a fault tree model is adopted;
when information is acquired in a parallel mode, a diagnosis method based on a neural network model is adopted;
when all the methods fail, taking the diagnosis result as a new case;
when any fault of the unmanned aerial vehicle occurs, timely processing is carried out, and after the processing is finished, comprehensive calibration detection is continuously carried out on the unmanned aerial vehicle system;
step three: if the unmanned aerial vehicle system has no fault, carrying out comprehensive detection evaluation on calibration detection information of the unmanned aerial vehicle system;
in the embodiment of the invention, only the important indexes which play a decisive role in the system performance of the unmanned aerial vehicle system are usually selected as physical quantities;
because the unmanned aerial vehicle system has various physical quantities, some requirements are larger and better, some requirements are smaller and better, other requirements are in a certain range, and the dimensions are different, in order to unify the dimensions of all the physical quantities, a method for calculating a utility function is adopted here, a proper utility function is established for each physical quantity, and then utility function values of different physical quantities are calculated, so that the physical quantities with dimensions are converted into dimensionless values;
let the unmanned aerial vehicle system have m physical quantities d = (d) 1 ,d 2 ,d 3 ,…,d m ) The performance number p = (p) 1 ,p 2 ,p 3 ,…,p m ) Corresponding utility function value μ = (μ) 1 ,μ 2 ,μ 3 ,…,μ m ) Weight of physical quantity w = (w) 1 ,w 2 ,w 3 ,…,w m ) Maximum value point d of performance index max ＝(r max1 ,r max2 ,r max3 ,…,r maxm ) Minimum value point d of performance index min ＝(r min1 ,r min2 ,r min3 ,…,r minm ) Then, there are:
the first situation is as follows: if the physical quantity p k The larger the requirement the better, with k =1,2 \ 8230m; the utility function is then:
μ k ＝d k /r maxk ，d k ∈[r mink ,r maxk ]
the second situation: if the physical quantity p k The smaller the requirement, the better, the utility function is:
μ k ＝1+(r mink -d k )/r maxm ，d k ∈[r mink ,r maxk ]
case three: if the physical quantity p k Is required to be in 1 ,r 2 ]With a good range, the utility function is:
the performance evaluation indexes of all components of the unmanned aerial vehicle system can be calculated by applying a linear weighting method, namely:
wherein i represents a component of the unmanned aerial vehicle system, i =1,2,3 \8230n; n is the number of the components of the unmanned aerial vehicle system;
in summary, the calculation formula of the comprehensive performance evaluation index of the unmanned aerial vehicle system is as follows:
wherein n is the number of the divided unmanned aerial vehicle components, and is 5 here; e.g. of the type i (ii) a performance rating index for the ith component; q. q.s i Is the weight of the ith component.
The above formulas are all calculated by removing dimensions and taking numerical values thereof, the formula is a formula which is obtained by acquiring a large amount of data and performing software simulation to obtain the closest real situation, and the preset parameters and the preset threshold value in the formula are set by the technical personnel in the field according to the actual situation or obtained by simulating a large amount of data.
Although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the spirit and scope of the present invention.
Claims (6)
1. A method of fault diagnosis and performance assessment of an unmanned aerial vehicle system, comprising:
carrying out comprehensive calibration detection on the unmanned aerial vehicle system;
carrying out fault diagnosis on calibration detection information of the unmanned aerial vehicle system through an integrated intelligent diagnosis model;
and if the unmanned aerial vehicle system has no fault, carrying out comprehensive performance evaluation on the calibration detection information of the unmanned aerial vehicle system.
2. The method of claim 1, wherein the drone system includes five components including a wireless data link, a ground master control station, flight control, airborne measurements, and mission cable detection.
3. The method of fault diagnosis and performance assessment of unmanned aerial vehicle system of claim 1, wherein calibrating the detection information comprises: communication information, analog information, switching value information, power and frequency information, pressure information, vertical gyro information, temperature, angular rate information, information acquired through an AD acquisition card, and serial communication data information.
4. The method for fault diagnosis and performance assessment of the unmanned aerial vehicle system according to claim 1, wherein the fault diagnosis of the calibration detection information of the unmanned aerial vehicle system by the integrated intelligent diagnosis model comprises:
case reasoning is carried out on the acquired calibration detection information, and if no same case exists in a case database or diagnosis fails, a next diagnosis strategy is determined according to an information acquisition mode and difficulty;
when the information is difficult to obtain, adopting a diagnosis method of an expert system based on rules; if the fault is adopted irregularly or the diagnosis fails, a diagnosis method based on a fault tree model or a neural network model is considered;
when the information is easy to obtain, a diagnosis method based on a fault tree model or a neural network model is considered;
when information is acquired in a continuous mode, a diagnosis method based on a fault tree model is adopted;
when information is acquired in a parallel mode, a diagnosis method based on a neural network model is adopted;
when all the methods fail, taking the diagnosis result as a new case;
when any fault of the unmanned aerial vehicle occurs, the fault is processed in time, and after the fault is processed, comprehensive calibration detection is continuously carried out on the unmanned aerial vehicle system.
5. The method for fault diagnosis and performance assessment of unmanned aerial vehicle systems of claim 4, wherein case reasoning is to match acquired fault information with historical fault information in a case database, and to diagnose by querying the case database for the same or similar fault phenomena that occurred previously.
6. The method of fault diagnosis and performance assessment of unmanned aerial vehicle system of claim 1, wherein the method of comprehensive performance assessment of unmanned aerial vehicle system comprises:
let the unmanned aerial vehicle system have m physical quantities d = (d) 1 ,d 2 ,d 3 ,…,d m ) The performance number p = (p) 1 ,p 2 ,p 3 ,…,p m ) Corresponding utility function value μ = (μ) 1 ,μ 2 ,μ 3 ,…,μ m ) Weight of physical quantity w = (w) 1 ,w 2 ,w 3 ,…,w m ) Maximum point d of performance index max ＝(r max1 ,r max2 ,r max3 ,…,r maxm ) Minimum value point d of performance index min ＝(r min1 ,r min2 ,r min3 ,…,r minm ) Then, there are:
the first situation is as follows: if the physical quantity p k The larger the requirement the better, with k =1,2 \ 8230m; the utility function is then:
μ k ＝d k /r maxk ，d k ∈[r mink ,r maxk ]
case two: if the physical quantity p k The utility function is as follows, the smaller the requirement the better:
μ k ＝1+(r mink -d k )/r maxm ，d k ∈[r mink ,r maxk ]
a third situation: if the physical quantity p k Is required to be in 1 ,r 2 ]With a good range, the utility function is:
the performance evaluation indexes of all components of the unmanned aerial vehicle system can be calculated by applying a linear weighting method, namely:
wherein i represents a component of the unmanned aerial vehicle system, i =1,2,3 \ 8230n; n is the number of the components of the unmanned aerial vehicle system; e.g. of the type i An index of performance rating for the ith component;
the calculation formula of the comprehensive performance evaluation index of the unmanned aerial vehicle system is as follows:
wherein q is i Is the weight of the ith component.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310130624.4A CN115903760A (en) | 2023-02-17 | 2023-02-17 | Fault diagnosis and performance evaluation method for unmanned aerial vehicle system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310130624.4A CN115903760A (en) | 2023-02-17 | 2023-02-17 | Fault diagnosis and performance evaluation method for unmanned aerial vehicle system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115903760A true CN115903760A (en) | 2023-04-04 |
Family
ID=86489944
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310130624.4A Withdrawn CN115903760A (en) | 2023-02-17 | 2023-02-17 | Fault diagnosis and performance evaluation method for unmanned aerial vehicle system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115903760A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117176199A (en) * | 2023-11-02 | 2023-12-05 | 国网山东省电力公司兰陵县供电公司 | HPLC communication unit fault diagnosis method and device |
-
2023
- 2023-02-17 CN CN202310130624.4A patent/CN115903760A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117176199A (en) * | 2023-11-02 | 2023-12-05 | 国网山东省电力公司兰陵县供电公司 | HPLC communication unit fault diagnosis method and device |
| CN117176199B (en) * | 2023-11-02 | 2024-01-30 | 国网山东省电力公司兰陵县供电公司 | HPLC communication unit fault diagnosis method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5625751A (en) | Neural network for contingency ranking dynamic security indices for use under fault conditions in a power distribution system | |
| CN111539515B (en) | Complex equipment maintenance decision method based on fault prediction | |
| CN111274737A (en) | Method and system for predicting remaining service life of mechanical equipment | |
| CN109872003A (en) | Obj State prediction technique, system, computer equipment and storage medium | |
| CN114969990B (en) | Multi-model fused avionic product health assessment method | |
| CN105974273A (en) | Power distribution network fault positioning system | |
| CN110163075A (en) | A kind of multi-information fusion method for diagnosing faults based on Weight Training | |
| CN111680875A (en) | Unmanned aerial vehicle state risk fuzzy comprehensive evaluation method based on probability baseline model | |
| US11396825B2 (en) | Turbine diagnostic feature selection system | |
| CN113033011B (en) | Ship mechanical health state assessment method and system | |
| CN115903760A (en) | Fault diagnosis and performance evaluation method for unmanned aerial vehicle system | |
| CN112541430B (en) | Fault diagnosis method for fusion of temperature signal and noise signal | |
| CN112116160A (en) | Important power transmission channel disaster monitoring method based on optimized neural network improved cellular automaton | |
| CN116205265A (en) | Power grid fault diagnosis method and device based on deep neural network | |
| CN114611372A (en) | Industrial equipment health prediction method based on Internet of things edge calculation | |
| CN113135480B (en) | Elevator fault early warning method based on local and overall characteristics | |
| CN113869749A (en) | Flight training quality evaluation system and method for simulated aircraft | |
| CN115864644A (en) | Relay protection device state evaluation method, system, equipment and medium | |
| CN113033845B (en) | Construction method and device for power transmission resource co-construction and sharing | |
| CN114266370A (en) | Method and system for generating fault handling plan of power grid equipment in typhoon meteorological environment on line and storage medium | |
| CN114137915A (en) | Fault diagnosis method for industrial equipment | |
| CN114400776A (en) | Substation automation equipment state diagnosis method and system based on digital mirror image | |
| Xue et al. | Autonomous evaluation method of unmanned equipment based on OODA-I framework | |
| Liqing et al. | A frame design of helicopter health monitoring and diagnosis system based on testability | |
| CN113419140B (en) | Distribution network line fault diagnosis method and device considering human-computer-object cooperation |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230404 |