scholarly journals Research on Method of Trajectory Prediction in Aircraft Flight Based on Aircraft Performance and Historical Track Data

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Shu-Yuan Jiang ◽  
Xiling Luo ◽  
Liang He
Keyword(s):  
Historical Data ◽  
Calculation Model ◽  
Performance Model ◽  
Average Error ◽  
Trajectory Prediction ◽  
Weather Information ◽  
Crossing Time ◽  
Aircraft Performance ◽  
Forecast Time ◽  
Better Than

Traditional 4D trajectory prediction based on aircraft performance models and flight procedures does not consider control handover rules. Meanwhile, method based on historical data mining cannot accurately couple with real-time conditions such as weather and also cause computational efficiency problems. This project collected a large amount of historical data to form a control experience database and mined the historical database to obtain control experience and flight intention. On the basis of the traditional aircraft performance model, this paper puts forward the aircraft maneuver mode using strategy and introduces the high-altitude wind information from the weather information into the aircraft 4D model to optimize the aircraft 4D trajectory calculation model. By comparing the flight forecast time with the real crossing time, it is found that the average error of the improved 4D forecast crossing time is less than 5% of the flight time, which is obviously better than that before optimization. It is proved that the optimized method based on historical track data is effective and reliable, and the accuracy of 4D track prediction is improved greatly.

A fuzzy neural network approach for modeling the growth kinetics of FeB and Fe2B layers during the boronizing process

2018 ◽  
Vol 106 (6) ◽  
pp. 603 ◽  
Author(s):  
Bendaoud Mebarek ◽  
Mourad Keddam
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Fuzzy Neural Network ◽  
Treatment Time ◽  
Calculation Model ◽  
Average Error ◽  
Network Approach ◽  
Neural Network Approach ◽  
Fuzzy Neural ◽  
Kinetics Of

In this paper, we develop a boronizing process simulation model based on fuzzy neural network (FNN) approach for estimating the thickness of the FeB and Fe2B layers. The model represents a synthesis of two artificial intelligence techniques; the fuzzy logic and the neural network. Characteristics of the fuzzy neural network approach for the modelling of boronizing process are presented in this study. In order to validate the results of our calculation model, we have used the learning base of experimental data of the powder-pack boronizing of Fe-15Cr alloy in the temperature range from 800 to 1050 °C and for a treatment time ranging from 0.5 to 12 h. The obtained results show that it is possible to estimate the influence of different process parameters. Comparing the results obtained by the artificial neural network to experimental data, the average error generated from the fuzzy neural network was 3% for the FeB layer and 3.5% for the Fe2B layer. The results obtained from the fuzzy neural network approach are in agreement with the experimental data. Finally, the utilization of fuzzy neural network approach is well adapted for the boronizing kinetics of Fe-15Cr alloy.

Prediksi Harga Saham Perusahaan Perbankan Menggunakan Regresi Linear Studi Kasus Bank BCA Tahun 2015-2017

2019 ◽  
Vol 11 (1) ◽  
pp. 11-15
Author(s):  
Merfin Merfin ◽  
Raymond Sunardi Oetama
Keyword(s):  
Stock Price ◽  
Historical Data ◽  
Listed Company ◽  
Market Price ◽  
Local Economy ◽  
Average Error ◽  
Stock Investment ◽  
The People ◽  
Mining Tool ◽  
A Company

Stock investment is important for financial development in a company. Moreover, the stock price displayed by the company can be known by the people and the local economy because the company has gone public on the Indonesia Economic Exchange (IDX) at www.idx.co.id. There are several fundamental factors that influence the stock market price in a listed company and as a result the number of stock investors in Indonesia is very small. This cause made it difficult for the community to predict the stock price of banking companies at inconsistent prices. The method to be used in this paper is Linear Regression using Excel tools to perform calculations and SPSS 16.0 as a data mining tool. The research data taken is historical data of banking companies for 3 periods as a whole in the form of excel that has been downloaded from the Yahoo Finance website. The final results are in the form of MAPE charts in 3 years period, and Average error chart in 3 years period.

scholarly journals LSSVR Model of G-L Mixed Noise-Characteristic with Its Applications

Entropy ◽  
2020 ◽  
Vol 22 (6) ◽  
pp. 629 ◽  
Author(s):  
Shiguang Zhang ◽  
Ting Zhou ◽  
Lin Sun ◽  
Wei Wang ◽  
Baofang Chang
Keyword(s):  
Wind Speed ◽  
Regression Models ◽  
Historical Data ◽  
Least Square ◽  
Noise Model ◽  
Noise Distribution ◽  
Short Term ◽  
Mixed Noise ◽  
Noise Models ◽  
Better Than

Due to the complexity of wind speed, it has been reported that mixed-noise models, constituted by multiple noise distributions, perform better than single-noise models. However, most existing regression models suppose that the noise distribution is single. Therefore, we study the Least square S V R of the Gaussian–Laplacian mixed homoscedastic ( G L M − L S S V R ) and heteroscedastic noise ( G L M H − L S S V R ) for complicated or unknown noise distributions. The ALM technique is used to solve model G L M − L S S V R . G L M − L S S V R is used to predict short-term wind speed with historical data. The prediction results indicate that the presented model is superior to the single-noise model, and has fine performance.

Research of Flash Automatic Marking Based on Logical Formal

2012 ◽  
Vol 468-471 ◽  
pp. 2849-2853
Author(s):  
Wei Zheng ◽  
Ya Ping Wu ◽  
Yao Fei Chen
Keyword(s):  
Formal Method ◽  
Formal System ◽  
Average Error ◽  
Formal Description ◽  
Whole Process ◽  
Better Than

The author proposes a scheme of flash automatic marking based on animation effects. Describe the question's marking information by using the logical formal method. Achieve automatic marking by building the logical formal system. Focuses on two components of the scheme: logical formal description and SWF to XML. Describes the whole process of logical formal marking with example. Analysis of manual and automatic marking shows that: logical Formal automatic marking error is better than the manual average error.

High-accuracy four-dimensional trajectory prediction for civil aircraft

2012 ◽  
Vol 116 (1175) ◽  
pp. 45-66 ◽  
Author(s):  
W. Schuster ◽  
M. Porretta ◽  
W. Ochieng
Keyword(s):  
Flight Control ◽  
Three Dimensional ◽  
High Accuracy ◽  
Trajectory Prediction ◽  
Entire Duration ◽  
Civil Aircraft ◽  
Model Aircraft ◽  
Simplifying Assumptions ◽  
Definition Of ◽  
Better Than

AbstractCurrent state-of-the-art trajectory prediction tools typically model aircraft as three-dimensional point-masses, and make a number of simplifying assumptions about the actual and anticipated dynamics states of the aircraft. They are typically based on predefined settings obtained from existing databases such as Eurocontrol’s Bada rather than real-time information, including on the environment, available onboard the aircraft. This significantly limits trajectory prediction performance. This paper proposes a high-accuracy four-dimensional trajectory prediction model for use onboard civil aircraft, as well as by ground-based systems, which addresses these limitations. It is designed for strategic traffic capacity optimisation and conflict-detection and resolution over time-horizons covering the entire duration of a flight. The model incorporates a number of features including a novel flight-control-system and an enhanced flight-script that incorporates new taxonomy and content thereby enabling better definition of aircraft intent. The accuracy of the model is characterised using operational data acquired during a real flight trial. Results show that the performance of the proposed model is significantly better than the current models. Its accuracy is better than the required navigation performance for departure, en route and Non-Precision-Approach phases of flight.

scholarly journals A CLOUD BASED SECURITY FOR ADVANCED MINIMIZING ENERGY BASED DATA SHARING IN MULTI-CLOUDS

2020 ◽  
pp. 16-22
Keyword(s):  
Cloud Services ◽  
Document Management ◽  
Weather Information ◽  
Cloudy Weather ◽  
Client Data ◽  
Data Files ◽  
Cloud Servers ◽  
First Time ◽  
District Administration ◽  
Better Than

Protect Cloud is better than protecting your account calculate with internal consumption characteristics assets. In terms of cloud computing, it provides cloud services give an endless storage and file information and creates an abstracts information uploading the data of various clients. It can help customers reduce economic costs of document management by moving with the district administration utility and policies to use on cloud servers. Offer safe statistics The security key can be confiscated Distribute and share information for dynamic groups. Within this task, the existing scheme is able to help Dynamic organizations work effectively when there are new users in case of joining the organization or termination of the user from the organization, the private keys of the opposite party customers do not need to be reimbursed now and do not need to do so date. In addition, the scheme can achieve comfort customer cancellation cannot be a blocked client data files can be retrieved for the first time although they conspired with unbelievers of clouds. To avoid these threats, conspiracies against information are a how to remove a copy of a statistical copy, the cloud has been widely used in garages to reduce storage space, throughput and deployment in cloudy weather information is saved. Recommended compiler The encryption model has been widely followed Convenient anti-conspiracy, correct and reliable control a variety of compiler keys.

Application of the Nelson model to four timelag fuel classes using Oklahoma field observations: model evaluation and comparison with National Fire Danger Rating System algorithms

2007 ◽  
Vol 16 (2) ◽  
pp. 204 ◽  
Author(s):  
J. D. Carlson ◽  
Larry S. Bradshaw ◽  
Ralph M. Nelson ◽  
Randall R. Bensch ◽  
Rafal Jabrzemski
Keyword(s):  
Fire Danger ◽  
Rating System ◽  
Field Observations ◽  
Fuel Moisture ◽  
Next Generation ◽  
Nelson Model ◽  
Weather Information ◽  
Weather Observations ◽  
Fire Danger Rating System ◽  
Better Than

The application of a next-generation dead-fuel moisture model, the ‘Nelson model’, to four timelag fuel classes using an extensive 21-month dataset of dead-fuel moisture observations is described. Developed by Ralph Nelson in the 1990s, the Nelson model is a dead-fuel moisture model designed to take advantage of frequent automated weather observations. Originally developed for 10-h fuels, the model is adaptable to other fuel size classes through modification of the model’s fuel stick parameters. The algorithms for dead-fuel moisture in the National Fire Danger Rating System (NFDRS), on the other hand, were originally developed in the 1970s, utilise once-a-day weather information, and were designed to estimate dead-fuel moisture for mid-afternoon conditions. Including all field observations over the 21-month period, the Nelson model showed improvement over NFDRS for each size fuel size class, with r2 values ranging from 0.51 (1000-h fuels) to 0.79 (10-h fuels). However, for observed fuel moisture at or below 30%, the NFDRS performed better than the Nelson model for 1-h fuels and was about the same accuracy as the Nelson for 10-h fuels. The Nelson model is targeted for inclusion in the next-generation NFDRS.

Sign in / Sign up

Export Citation Format

Share Document