scholarly journals Modeling Simulation and Fault Analysis of Aircraft Air Conditioning System Based on Grasshopper Algorithm Improved Support Vector Machine

2021 ◽  
Author(s):  
Huiyong Wu ◽  
shuchun jin ◽  
zhu jin
Keyword(s):  
Support Vector Machine ◽  
Simulated Annealing ◽  
Fault Injection ◽  
Optimal Parameter ◽  
Fault Analysis ◽  
Operating Conditions ◽  
Support Vector ◽  
Circulation System ◽  
Aircraft Component ◽  
Air Circulation

Abstract To effectively analyze the working state of the air circulation system when the aircraft flies at high altitude, it is necessary to simulate and analyze on the ground. A simulated annealing-grasshopper algorithm is proposed to optimize the support vector machine ( SAGOA-SVM ). The overall simulation model of the aircraft air circulation system is established, and the fault injection analysis is carried out. The support vector machine is introduced to classify the system results. The grasshopper algorithm simulated annealing and position offset are used to optimize the support vector machine, and the optimal parameter values are obtained. The results show that the simulation system can effectively simulate the temperature changes of the aircraft under various operating conditions. The optimized support vector machine can effectively distinguish the fault types of the aircraft component outlet, and the system convergence speed is accelerated to avoid the problem of falling into the local optimal value.

Stock Index Prediction and Analysis Based on GASA-SVM

2013 ◽  
Vol 798-799 ◽  
pp. 842-845
Author(s):  
Li Zhe Ma
Keyword(s):  
Support Vector Machine ◽  
Simulated Annealing ◽  
Prediction Model ◽  
Simulated Annealing Algorithm ◽  
Optimal Parameter ◽  
Stock Index ◽  
Gaussian Kernel ◽  
Support Vector ◽  
Kernel Parameter ◽  
Annealing Algorithm

In order to improve the prediction accuracy of stock index, eliminate of the blindness of parameters selection for support vector machine, a stock index prediction method combined the genetic simulated annealing algorithm (GASA) which integrated the parallel search of genetic algorithm with the probabilistic sudden jumping characteristics of simulated annealing algorithm, with support vector machine (SVM) is proposed. Using daily data of Shanghai stock index opening quotation which is normalization processed, the stock index prediction model based on GASA-SVM is established. Optimal parameter error penalty parameter c=1 and Gaussian kernel parameter g=1.625 are obtained. Compared the result with GA-SVM prediction model, the comparative analysis shows that GASA-SVM(MSE= 0.000191111) model prediction capabilities are superior to GA-SVM(MSE=0.000018825) prediction model. It can provide valuable references for the investors.

Optimal Training of Artificial Neural Networks to Forecast Power System State Variables

2014 ◽  
Vol 3 (1) ◽  
pp. 65-82 ◽  
Author(s):  
Victor Kurbatsky ◽  
Denis Sidorov ◽  
Nikita Tomin ◽  
Vadim Spiryaev
Keyword(s):  
Genetic Algorithm ◽  
Support Vector Machine ◽  
Simulated Annealing ◽  
Power System ◽  
Simulated Annealing Algorithm ◽  
Active Power ◽  
Support Vector ◽  
State Variables ◽  
Annealing Algorithm ◽  
Artificial Neural

The problem of forecasting state variables of electric power system is studied. The paper suggests data-driven adaptive approach based on hybrid-genetic algorithm which combines the advantages of genetic algorithm and simulated annealing algorithm. The proposed method has two stages. At the first stage the input signal is decomposed into orthogonal basis functions based on the Hilbert-Huang transform. The genetic algorithm and simulated annealing algorithm are applied to optimal training of the artificial neural network and support vector machine at the second stage. The results of applying the developed approach for the short-term forecasts of active power flows in the electric networks are presented. The best efficiency of proposed approach is demonstrated on real retrospective data of active power flow forecast using the hybrid-genetic support vector machine algorithm.

A New Method for Fault Detection of Rotating Machines in Motion Control Applications Using PROFIdrive Information and Support Vector Machine Classifier

2020 ◽  
Vol 143 (4) ◽  
Author(s):  
Andre Luis Dias ◽  
Afonso Celso Turcato ◽  
Guilherme Serpa Sestito ◽  
Murilo Silveira Rocha ◽  
Dennis Brandão ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Motion Control ◽  
Diagnostic System ◽  
Operating Conditions ◽  
Support Vector ◽  
Electric Motors ◽  
Rotating Machines ◽  
Worst Case ◽  
Control Applications ◽  
Mechanical Faults

Abstract Electric motors are widely used in the industry. Several studies have proposed methods to detect anomalies in their operation, but always using sensors dedicated to this purpose. In this sense, this work aims to fill gaps in related works presenting a method for the detection of faults in rotating machines driven by electric motors in motion control applications using PROFINET network and PROFIdrive profile. The proposed method does not require any additional or dedicated sensors to provide data to the diagnostic system. Instead, the proposed methodology is based on the analysis of data transmitted in the communication network, which already exists for control purposes. Support vector machine (SVM) is used as a classifier of five different mechanical faults. The results provide that the methodology is feasible and efficient under different machine operating conditions, achieving, in the worst case, 97.78% efficiency.

Modeling of Flexible Structures by Means of Least Square Support Vector Machine

2015 ◽  
Author(s):  
Hammam Tamimi ◽  
Dirk Söffker
Keyword(s):  
Support Vector Machine ◽  
Least Squares ◽  
Flexible Structures ◽  
Operating Conditions ◽  
Least Square ◽  
Support Vector ◽  
Suitable Model ◽  
Support Vector Machine Algorithm ◽  
Training Time ◽  
Svm Algorithm

This paper investigates modeling of flexible structures by means of the least squares support vector machine (LS-SVM) algorithm. Modeling is the first step to obtain a suitable model-based controller for any given system. Accurate modeling of a flexible structure based on experimental data using LS-SVM algorithm requires less knowledge about the physical system. Least squares support vector machine algorithm can achieve global and unique solution when compared with other soft computing algorithms. Also, LS-SVM algorithm requires less training time. In this paper, the successful use of support vector machine algorithm to model the flexible cantilever is demonstrated. The acquired model is able to provide accurate prediction of the system output under different operating conditions. Experimental results demonstrate the efficiency and high precision of the proposed approach.

Sign in / Sign up

Export Citation Format

Share Document