A Helicopter Transmission Shaft Abnormal Judgment Method Based on SAE and Mahalanobis Distance

A Mahalanobis distance and anomaly judgment technology, applied in geometric CAD, instrumentation, design optimization/simulation, etc., can solve problems such as difficulty in obtaining abnormal data, multiple false alarms and missed reports, etc., achieve strong versatility and scalability, and solve practical problems Effects of engineering problems, improvement of construction effect and accuracy of exception judgment

Active Publication Date: 2022-05-03
BEIHANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of method not only requires a rich background of expert knowledge, but also has many false alarms and omissions in actual engineering.
In addition, for general-purpose shaft components, many intelligent fault diagnosis methods combining signal analysis and machine learning algorithms have emerged in recent years, but such methods usually require a large amount of abnormal data, but abnormal data are often difficult to obtain in actual engineering

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Helicopter Transmission Shaft Abnormal Judgment Method Based on SAE and Mahalanobis Distance
  • A Helicopter Transmission Shaft Abnormal Judgment Method Based on SAE and Mahalanobis Distance
  • A Helicopter Transmission Shaft Abnormal Judgment Method Based on SAE and Mahalanobis Distance

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0066] A method for judging the abnormality of a helicopter transmission shaft based on SAE and Mahalanobis distance proposed by the present invention is as follows: figure 1 shown. figure 1 Flow chart of the present invention.

[0067] According to two types of typical data scenarios commonly seen in practice (including only normal data, including a large amount of normal data and a small amount of abnormal data), the present invention provides two sets of embodiments, and those skilled in the art can easily understand the present invention from the contents described in this manual other advantages and effects. Embodiments 1 and 2 are respectively as follows.

specific Embodiment 1

[0069] 1 Healthy baseline construction

[0070] 101: For common scenarios where only normal data exists in practice, only samples of parameters monitored by the helicopter transmission shaft under normal conditions are selected to form training data. In the present invention, vibration signals are used as the state representation signal of the helicopter transmission shaft. Specifically, the training data details of Embodiment 1 are shown in Table 1.

[0071] Table 1: The training data detail table of embodiment one

[0072] Composition of training data For the scene 199 normal vibration signal Only normal data exists, and abnormal data hardly exists

[0073] Select a normal sample from the above training data, the visualization result is as follows figure 2 It can be seen from the figure that the original vibration signal exhibits high-frequency characteristics, and it is difficult to directly judge the actual state of the object, so further conversi...

specific Embodiment 2

[0107] 1 Healthy baseline construction

[0108] 101: Aiming at the common scene of helicopter transmission shaft with more normal data and less abnormal data in practice, a large number of normal state helicopter transmission shaft monitoring parameter samples and a small number of abnormal state monitoring parameter samples are selected to form training data. In the present invention, vibration The signal is used as the state characterization signal of the helicopter transmission shaft. Specifically, the details of the training data in Embodiment 2 are shown in Table 6.

[0109] Table 6: The training data detail table of embodiment two

[0110] Composition of training data simulation scene 199 normal samples + 14 abnormal samples There is a lot of normal data and only a small amount of abnormal data

[0111] Select an abnormal sample from the above training data, and its visualization result is as follows Figure 11 Shown: As can be seen from the fig...

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

No PUM Login to view more

Abstract

A method for judging the abnormality of the helicopter transmission shaft based on SAE and Mahalanobis distance. This method uses the monitoring vibration data of the helicopter transmission shaft to realize the construction of the health baseline, threshold generation and abnormal judgment of the helicopter transmission shaft. First, use the helicopter transmission shaft to monitor the vibration data, obtain the input vector through FFT spectral transformation and RMS compression transformation, and use the SAE model to construct the health baseline of the transmission shaft. The health baseline includes the trained SAE model and its output health representation set. Second, based on the overall distribution mean vector and covariance matrix of the health representation set, by calculating the Mahalanobis distance between it and each health vector in the health representation set, the baseline statistical threshold of the helicopter drive shaft is generated to realize the quantitative distinction between normal and abnormal states Standard Adaptive Representation. Third, based on the health representation set and the baseline statistical threshold, the threshold abnormality judgment is performed on the real-time test data samples to realize the real-time detection of the state of the helicopter drive shaft.

Description

technical field [0001] The invention belongs to the technical field of helicopter flight control, in particular to a method for judging the abnormality of a helicopter drive shaft based on SAE and Mahalanobis distance. Background technique [0002] The transmission system is one of the three key moving parts of the helicopter, and the transmission shaft is an important component of the transmission system. Once the transmission shaft fails, it will seriously affect the helicopter and even cause fatal accidents. Therefore, it is of great significance to carry out condition monitoring on the transmission shaft of the helicopter. At present, most of the state monitoring methods of helicopter transmission shafts focus on threshold detection based on expert experience, that is, using signal analysis methods to extract fault sensitive features, and then setting expert thresholds to achieve detection. This type of method not only requires a rich background of expert knowledge, bu...

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
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/15G06F30/17G06F30/27G06F119/02
CPCY02T90/00
Inventor 程玉杰祁缨茜苏铉元宋登巍陶来发马剑吕琛
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap