Fault identification method, device, computer readable storage medium and electronic equipment

Abstract

The present disclosure relates to a fault identification method, device, computer-readable storage medium and electronic equipment. The method includes: acquiring a first index data set of a target UAV within a time period to be evaluated, wherein the first index data set includes an index sequence composed of a plurality of index values ​​arranged in chronological order; for the first index Perform data preprocessing on the data set to obtain a second index data set; for each index sequence in the second index data set, perform secondary data processing on the index sequence according to the index characteristics of the index sequence to obtain the second index sequence Three index data sets; according to the third index data set, perform fault identification on the target UAV. Thus, the value of each index in the processed index sequence can reflect the quality of the corresponding index. Afterwards, based on the index data set processed by the above data, fault identification is performed on the target UAV, thereby improving the efficiency and accuracy of UAV fault identification.

Description

technical field [0001] The present disclosure relates to the field of unmanned aerial vehicles, and in particular, to a fault identification method, device, computer-readable storage medium, and electronic equipment. Background technique [0002] With the development of the UAV industry, users have higher and higher requirements for UAV products. Being able to accurately identify the flight failure of UAVs has positive guiding significance for the subsequent maintenance of UAVs. [0003] At present, the following two methods are mainly used to identify UAV faults: (1) through the actual observation of the flight status of the unmanned aircraft by experienced personnel or by checking the flight data of the UAV to determine whether there is a fault in the UAV; (2) through Build a control system simulation model to determine the flight failure of the UAV by simulating the flight process of the UAV, but the accuracy of the control system simulation model cannot be guaranteed, an...

AI Technical Summary

Problems solved by technology

Among them, ordinary normalization is to map the index data to the [0,1] interval, and ensure that the data size and interval ratio remain unchanged, but this method is not applicable to some indicators of drones, for example, accelerometer vibration indicators , because the accelerometer itself carries a lot of vibration and noise, its value is too large or too small may be faulty data, after ordinary normalization, the quality of the data is not reflected in the data size at the data processing level

The support vector machine algorithm has a good effect on the processing of binary classification problems, but it has certain difficulties in processing overly complex classification problems, and the neural network needs a large amount of sample data as training support to achieve a better result.

In the case of poor data preprocessing and limited sample data, it is difficult to achieve the desired effect by applying the above method to evaluate the flight quality and fault identification of UAVs.

Images