Tezislər / Theses



Yüklə 17,55 Mb.
Pdf görüntüsü
səhifə98/493
tarix02.10.2023
ölçüsü17,55 Mb.
#151572
1   ...   94   95   96   97   98   99   100   101   ...   493
BHOS Tezisler 2022 17x24sm

THE 3
rd
 INTERNATIONAL SCIENTIFIC CONFERENCES OF STUDENTS AND YOUNG RESEARCHERS 
dedicated to the 99
th
anniversary of the National Leader of Azerbaijan Heydar Aliyev
107
DETECTION OF EMERGENCY CASES AT POWER PLANT 
EQUIPMENT BASED ON MACHINE LEARNING 
Bakshiyev Mardan 
Baku Higher Oil School 
Baku, Azerbaijan 
Mardan.bakshiyev.std@bhos.edu.az
Supervisor: Ph.D Associate Professor Leyla Muradkhanli 
Keywords
: predictive analysis, regression model, learning algorithm, data analysis
During the period of actively using process equipment events or 
accidents that may adversely affect it or cause its failure inevitably occur. A 
model able to predict the future emergency would make it possible to timely 
take measures for eliminating it, thus helping to achieve more efficient use 
of process equipment. Development and investigation of such models is the 
subject of predictive analytics. The modern trends in predictive analytics 
combine the methods of statistical and intellectual analysis of data with the 
use of learned algorithms. They are inherent in all of the presently available 
predictive analytics methods applied in thermal power engineering and imply 
preliminary “teaching” of the model on the basis of available input data. Such 
input data include “historical” values of measured parameters characterizing 
the operation of particular process equipment; these data are taken from the 
archives stored in the power unit process control system’s set of 
computerized automation tools for a long time of power unit operation 
(usually 1–3 years). In addition, data about the defects (malfunctions) 
revealed for this period of time, which can lead to an accident unless having 
been removed, are also used.



Yüklə 17,55 Mb.

Dostları ilə paylaş:
1   ...   94   95   96   97   98   99   100   101   ...   493




Verilənlər bazası müəlliflik hüququ ilə müdafiə olunur ©azkurs.org 2024
rəhbərliyinə müraciət

gir | qeydiyyatdan keç
    Ana səhifə


yükləyin