Prediction of Flight Status of Logistics UAVs Based on an Information Entropy Radial Basis Function Neural Network
Aiming at addressing the problems of short battery life, low payload and unmeasured load ratio of logistics Unmanned Aerial Vehicles (UAVs), the Radial Basis Function (RBF) neural network was trained with the flight data of logistics UAV from the Internet of Things to predict the flight status of lo...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-05-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/11/3651 |
_version_ | 1797532845052264448 |
---|---|
author | Qin Yang Zhaofa Ye Xuzheng Li Daozhu Wei Shunhua Chen Zhirui Li |
author_facet | Qin Yang Zhaofa Ye Xuzheng Li Daozhu Wei Shunhua Chen Zhirui Li |
author_sort | Qin Yang |
collection | DOAJ |
description | Aiming at addressing the problems of short battery life, low payload and unmeasured load ratio of logistics Unmanned Aerial Vehicles (UAVs), the Radial Basis Function (RBF) neural network was trained with the flight data of logistics UAV from the Internet of Things to predict the flight status of logistics UAVs. Under the condition that there are few available input samples and the convergence of RBF neural network is not accurate, a dynamic adjustment method of RBF neural network structure based on information entropy is proposed. This method calculates the information entropy of hidden layer neurons and output layer neurons, and quantifies the output information of hidden layer neurons and the interaction information between hidden layer neurons and output layer neurons. The structural design and optimization of RBF neural network were solved by increasing the hidden layer neurons or disconnecting unnecessary connections, according to the connection strength between neurons. The steepest descent learning algorithm was used to correct the parameters of the network structure to ensure the convergence accuracy of the RBF neural network. By predicting the regression values of the flight status of logistics UAVs, it is demonstrated that the information entropy-based RBF neural network proposed in this paper has good approximation ability for the prediction of nonlinear systems. |
first_indexed | 2024-03-10T11:06:09Z |
format | Article |
id | doaj.art-283bb9e0d1524999b3e9eeb4b28508b9 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T11:06:09Z |
publishDate | 2021-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-283bb9e0d1524999b3e9eeb4b28508b92023-11-21T21:09:05ZengMDPI AGSensors1424-82202021-05-012111365110.3390/s21113651Prediction of Flight Status of Logistics UAVs Based on an Information Entropy Radial Basis Function Neural NetworkQin Yang0Zhaofa Ye1Xuzheng Li2Daozhu Wei3Shunhua Chen4Zhirui Li5School of Mechanical Engineering, Hefei University of Technology, Hefei 230009, ChinaSchool of Mechanical Engineering, Hefei University of Technology, Hefei 230009, ChinaSchool of Mechanical Engineering, Hefei University of Technology, Hefei 230009, ChinaSchool of Mechanical Engineering, Hefei University of Technology, Hefei 230009, ChinaSchool of Mechanical Engineering, Hefei University of Technology, Hefei 230009, ChinaSchool of Mechanical Engineering, Hefei University of Technology, Hefei 230009, ChinaAiming at addressing the problems of short battery life, low payload and unmeasured load ratio of logistics Unmanned Aerial Vehicles (UAVs), the Radial Basis Function (RBF) neural network was trained with the flight data of logistics UAV from the Internet of Things to predict the flight status of logistics UAVs. Under the condition that there are few available input samples and the convergence of RBF neural network is not accurate, a dynamic adjustment method of RBF neural network structure based on information entropy is proposed. This method calculates the information entropy of hidden layer neurons and output layer neurons, and quantifies the output information of hidden layer neurons and the interaction information between hidden layer neurons and output layer neurons. The structural design and optimization of RBF neural network were solved by increasing the hidden layer neurons or disconnecting unnecessary connections, according to the connection strength between neurons. The steepest descent learning algorithm was used to correct the parameters of the network structure to ensure the convergence accuracy of the RBF neural network. By predicting the regression values of the flight status of logistics UAVs, it is demonstrated that the information entropy-based RBF neural network proposed in this paper has good approximation ability for the prediction of nonlinear systems.https://www.mdpi.com/1424-8220/21/11/3651internet of thingslogistics dronesRBF neural networkinformation entropynonlinear system |
spellingShingle | Qin Yang Zhaofa Ye Xuzheng Li Daozhu Wei Shunhua Chen Zhirui Li Prediction of Flight Status of Logistics UAVs Based on an Information Entropy Radial Basis Function Neural Network Sensors internet of things logistics drones RBF neural network information entropy nonlinear system |
title | Prediction of Flight Status of Logistics UAVs Based on an Information Entropy Radial Basis Function Neural Network |
title_full | Prediction of Flight Status of Logistics UAVs Based on an Information Entropy Radial Basis Function Neural Network |
title_fullStr | Prediction of Flight Status of Logistics UAVs Based on an Information Entropy Radial Basis Function Neural Network |
title_full_unstemmed | Prediction of Flight Status of Logistics UAVs Based on an Information Entropy Radial Basis Function Neural Network |
title_short | Prediction of Flight Status of Logistics UAVs Based on an Information Entropy Radial Basis Function Neural Network |
title_sort | prediction of flight status of logistics uavs based on an information entropy radial basis function neural network |
topic | internet of things logistics drones RBF neural network information entropy nonlinear system |
url | https://www.mdpi.com/1424-8220/21/11/3651 |
work_keys_str_mv | AT qinyang predictionofflightstatusoflogisticsuavsbasedonaninformationentropyradialbasisfunctionneuralnetwork AT zhaofaye predictionofflightstatusoflogisticsuavsbasedonaninformationentropyradialbasisfunctionneuralnetwork AT xuzhengli predictionofflightstatusoflogisticsuavsbasedonaninformationentropyradialbasisfunctionneuralnetwork AT daozhuwei predictionofflightstatusoflogisticsuavsbasedonaninformationentropyradialbasisfunctionneuralnetwork AT shunhuachen predictionofflightstatusoflogisticsuavsbasedonaninformationentropyradialbasisfunctionneuralnetwork AT zhiruili predictionofflightstatusoflogisticsuavsbasedonaninformationentropyradialbasisfunctionneuralnetwork |