Browsing by Author "Balli, T."

Now showing 1 - 3 of 3

Citation - Scopus: 3
Automatic Segmentation of Time Series Data With Pelt Algorithm for Predictive Maintenance in the Flat Steel Industry
(Institute of Electrical and Electronics Engineers Inc., 2024) Kaçar, S.; Balli, T.; Yetkin, E.F.
In this study, we aim to test the usability of Change Point Detection (CPD) algorithms (specifically the Pruned Exact Linear Time-PELT) to facilitate the utilization of large volumes of data within predictive mechanisms in the industry. We proposed an efficient CPD parameter selection mechanism for defect diagnosis using time-series vibration data from critical assets. We emphasized the practical algorithm PELT to ensure broad industrial applicability. Our experimental analysis, using synthetic and actual vibration data, demonstrated the practical applicability and effectiveness of PELT algorithm for automatic segmentation. The numerical results show the potential of CPD methodologies for improving predictive maintenance operations by providing an automatic segmentation mechanism. This pipeline proposes a way to increase the operational efficiency and scalability of predictive maintenance approaches, enhancing maintenance procedures and ensuring the long-term reliability of industrial systems. © 2024 IEEE.
Electricity Theft Detection Using Machine Learning Approaches: A Case Study in Turkiye
(Institute of Electrical and Electronics Engineers Inc., 2025) Cetkin, E.; Emirhan Arslan, M.; Bozbuga, B.; Furkan Kalayci, B.; Ilhan Ecevit, M.; Balli, T.; Ceylan, O.
Electricity theft, leading to financial losses and operational inefficiencies, is a significant challenge for energy utilities. In this study, advanced pre-processing, feature selection and model evaluation techniques were used to develop a machine learning model for detecting electricity theft. The dataset, which consists of over 53 million samples, was carefully preprocessed to eliminate missing values and irrelevant features. Principal component analysis (PCA) was applied to reduce dimensionality, and both undersampling and oversampling were used to avoid class imbalance. Four machine learning algorithms were evaluated: Random Forest, kNN, XGBoost and Logistic Regression. The training and evaluation of the models were performed in Jupyter Notebook using Joblib for efficient CPU-based parallel computation. The random forest with over-sampling achieved the highest performance with an accuracy of 98.23% and an F1 score of 0.90, showing the effectiveness of handling class imbalance. The results show that over-sampling the dataset leads to better results than under-sampling, emphasising the importance of this approach in detecting power theft. © 2025 Elsevier B.V., All rights reserved.
Citation - Scopus: 1
On Symbolic Prediction of Time Series for Predictive Maintenance Based on Sax-Lstm
(Institute of Electrical and Electronics Engineers Inc., 2024) Güler, A.; Balli, T.; Yetkin, E.F.
This work proposed a new forecasting approach for predictive maintenance in industrial settings, combining standard segmentation approaches like Symbolic Aggregate Approximation (SAX) and Piecewise Aggregate Approximation (PAA) with LSTM (Long-Short Time Memory). The work aims to construct a robust forecasting mechanism to estimate maintenance requirements in advance properly. We first demonstrated the results of the proposed approach for synthetically generated data and extended the results with real industrial vibration data. The algorithm's performance is assessed using real-world industry data from steel production furnaces, where timely maintenance is critical for increasing operating efficiency and reducing downtime. Experimental results show that using SAX and LSTM for forecasting industrial time series data achieves high accuracy rates (90.2 %) in a reasonable computational time. © 2024 IEEE.