Anomaly detection method and device for distributed UAV swarm network log analysis
An anomaly detection and distributed technology, applied in error detection/correction, instrumentation, computing, etc., can solve problems such as poor results and difficulty in abnormal detection of drone swarms, so as to solve the problem of untimely system, realize real-time monitoring, and improve safety. sexual effect
Active Publication Date: 2022-06-17
XIDIAN UNIV
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to provide an anomaly detection method and equipment for network log analysis of distributed UAV swarms to solve the problem of difficulty and poor effect of abnormal detection of UAV swarms in the above-mentioned prior art, which can realize massive log analysis. Analysis, automated anomaly detection, and real-time monitoring significantly improve the efficiency and effectiveness of UAV swarm anomaly detection
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0036] The present invention will be further described in detail below in conjunction with the accompanying drawings.
[0037] see figure 1 , An anomaly detection method oriented to network log analysis of distributed UAV swarms proposed by the present invention mainly includes the following steps: first, analyze the UAV work log, and then construct a specific model through the analyzed UAV log file, Simplify state abstraction and generate abstract model. Finally, it is looped to check whether it satisfies all the time invariants excavated, and the model is improved until the communication abstract model that satisfies all the invariants is finally generated and returned.
[0038] details as follows:
[0039] Step 1, log parsing:
[0040] (1a) The drone provides an input log, a set of defined regular expressions, and a set of channel definitions. The regular expression determines which log lines are parsed (and which are ignored), which part of a line corresponds to a vect...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
An anomaly detection method and equipment for network log analysis of distributed UAV swarms. The anomaly detection method includes the following steps: analyzing the UAV work log, mining the sequence of events in the operation process, that is, the time invariant; Build a concrete model based on machine log files, and then generate an abstract model after state abstraction and simplification; cyclically check whether the abstract model satisfies all the time invariants mined, and improve the model accordingly until finally generating and returning a model that satisfies all time invariants. Real-time monitoring of information transmission in the process of task execution is carried out by this model. The present invention also provides an anomaly detection system, a terminal device and a computer-readable storage medium for network log analysis of a distributed unmanned aerial vehicle group. The invention can realize the analysis of massive logs, automatic abnormality detection and real-time monitoring, the visualization of the abnormality detection process, and significantly improve the efficiency and effectiveness of the abnormality detection of the unmanned aerial vehicle group.
Description
technical field [0001] The invention belongs to the field of anomaly detection of unmanned aerial vehicles, and in particular relates to an anomaly detection method and equipment for network log analysis of distributed unmanned aerial vehicles. Background technique [0002] The idea of "drone swarms" comes from the concept of bee colonies in biology. Researchers hope that drone swarms can fly in groups like bees without colliding, and can coordinate with each other to complete tasks. This is quite different from investing in the development of expensive and technically complex multitasking system strategies. For different types of work objectives, UAV swarms can use the heterogeneous advantages of mixing and matching to complete work at low cost and high efficiency. In recent years, UAV-related technologies have developed rapidly. UAVs are unmanned aircraft controlled by radio remote control equipment and self-provided program control devices, or operated completely or in...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F11/34
CPCG06F11/3476
Inventor 李腾刘鸣宇蒋心烛张胜凯温子祺谢凡王申奥马建峰
Owner XIDIAN UNIV