Ensemble Machine Learning Methods for better Dynamic Assessment of Transformer Status

نویسندگان

چکیده

Analyzing dissolved gases in the transformer's mineral oil helps to detect and classify systemic faults electric power transformers. Formerly, empirical methods such as Rogers ratio, Duval triangles 1–4–5, pentagons 1–2 were used for transformer fault classification. Loose fit every type is one of most prominent disadvantages conventional methods. Formulating robust machine learning algorithms, decision trees, can significantly overcome loose issue. This paper focuses on implementing four different tree including a regular classifier, bagging boosting stacking classifier six types distinctly. Further, this study shows that efficacy accuracy mentioned classifiers could be far exceeded when combined using wisdom crowd approach. The approach essentially merges predicted classes from individual decides final prediction via hard-voting routine. computational evaluation revealed given voting improve transformers' online diagnostic up 91%, thus aiding early forecast preventive maintenance.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

diagnostic and developmental potentials of dynamic assessment for writing skill

این پایان نامه بدنبال بررسی کاربرد ارزیابی مستمر در یک محیط یادگیری زبان دوم از طریق طرح چهار سوال تحقیق زیر بود: (1) درک توانایی های فراگیران زمانیکه که از طریق برآورد عملکرد مستقل آنها امکان پذیر نباشد اما در طول جلسات ارزیابی مستمر مشخص شوند; (2) امکان تقویت توانایی های فراگیران از طریق ارزیابی مستمر; (3) سودمندی ارزیابی مستمر در هدایت آموزش فردی به سمتی که به منطقه ی تقریبی رشد افراد حساس ا...

15 صفحه اول

Ensemble Methods in Machine Learning

Ensemble methods are learning algorithms that construct a set of classi ers and then classify new data points by taking a weighted vote of their predictions The original ensemble method is Bayesian aver aging but more recent algorithms include error correcting output coding Bagging and boosting This paper reviews these methods and explains why ensembles can often perform better than any single ...

متن کامل

Fault Detection of Anti-friction Bearing using Ensemble Machine Learning Methods

Anti-Friction Bearing (AFB) is a very important machine component and its unscheduled failure leads to cause of malfunction in wide range of rotating machinery which results in unexpected downtime and economic loss. In this paper, ensemble machine learning techniques are demonstrated for the detection of different AFB faults. Initially, statistical features were extracted from temporal vibratio...

متن کامل

Ensemble Methods – Classifier Combination in Machine Learning

The last ten years have seen a research explosion in machine learning. The rapid growing is largely driven by the following two forces. First, separate research communities in symbolic machine learning, computational learning theory, neural network, statistics and pattern recognition have discovered one another and begun to work together. Second, machine learning technologies are being applied ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Journal of institution of engineers (India) series B

سال: 2021

ISSN: ['2250-2106', '2250-2114']

DOI: https://doi.org/10.1007/s40031-021-00599-1