Internet of things based metaheuristic reliability centered maintenance of distribution transformers

Abstract

The transformer is a vital component of the power system. Continuous stress on the transformer due to overload, transient and faults will lead to physical damages. The isolation of the transformer causes significant revenue loss and inconvenience to the consumers at the distribution level. This invites the need to achieve a reliable power supply to the consumers and to perform maintenance activity appropriately. Optimized and predictive maintenance strategies are evolved to improve power availability for consumers. The model considers dispersive generation at the customer end, namely solar photovoltaics standalone system, diesel generation, and vehicle to load capabilities. Incipient or critical status of transformers’ functional parameters are observed through the transformer terminal unit and sent to the internet of things platform. The remote processing unit acquires the information from all the distribution transformer and generates the optimized and reliability-centered maintenance schedule. In the proposed work, new reliability indices concerning the consumer dispersive generation are defined. The maximization of the reliability problem is solved using the coconut tree optimization technique. The highest reliability of power supply to the consumer and maintenance schedule are obtained. Economic facet of the estimated maintenance schedule exhibit benefit for both utility and consumer as it encapsulate time of use tariff. The heuristic dataset is used to synthesize the trained model by the machine learning algorithm and future maintenance schedule is predicted. The comparative study is made for the outcome of time-based optimized and predicted maintenance schedules against reliability.

Predictive Maintenance for Distribution System Operators in Increasing Transformers’ Reliability

“…As the amount of data available for learning rises, they adaptively improve at performing their tasks. Optimized and predictive maintenance strategies are evolved to improve power availability for consumers [48]. Although SVM and k-means clustering are well-known techniques, their efficiency varies depending on the dataset and situation at hand.…”

Strategi Waktu Penggantian Filter Mesin Grain Cooling Pellet di PT. Indofood Sukses Makmur Tbk. Divisi Bogasari Flour Mills Surabaya

“…Jika terjadi perbedaan cukup besar maka model teoritis yang diasumsikan akan ditolak. Pada proses uji K-S, data tersebut tidak perlu dikelompokkan (semua informasi tetap utuh, tidak ada yang hilang) dan berlaku terhadap berbagai besaran sampel (n) [13]- [16], [23]- [27].…”

Data mining in predictive maintenance systems: A taxonomy and systematic review

“…In this line, there are many works that collect vibration signals from different experimental rotors (Cakir et al, 2021; Li et al, 2019; Liang et al, 2020; Liao et al, 2016; Pang et al, 2020; Qian et al, 2019; Satishkumar & Sugumaran, 2017; Song et al, 2021; Una et al, 2017; Wang et al, 2018; Wang, Zhang, et al, 2020; Yang, Lei, et al, 2019; Zhang, Li, Wang, et al, 2019), fans (Sampaio et al, 2019; Xu et al, 2021; Zenisek, Holzinger, & Affenzeller, 2019), centrifugal pumps (Hu et al, 2020), air compressors (Cupek et al, 2018) or industrial robots (Panicucci et al, 2020). Some works (Venkataswamy et al, 2020; Zenisek, Holzinger, & Affenzeller, 2019; Zenisek, Kronberger, et al, 2019) generate synthetic data from a mathematical approach that models the behavior of their problem, using for that specialized software in simulation.…”

“…Thus, linear SVM has been used in binary classification (Cakir et al, 2021; Gohel et al, 2020; Khodabakhsh et al, 2018; Lasisi & Attoh‐Okine, 2018; Pałasz & Przysowa, 2019; Proto et al, 2020; Shamayleh et al, 2020; Susto et al, 2015) to classify the events according to their proximity to the failure threshold. In multiclass scenarios, linear SVM has been studied together with other methods in both prediction of multiple degradation states (Chen, Hsu, et al, 2021; Cheng et al, 2020; Quatrini et al, 2020; Shafi et al, 2018; Venkataswamy et al, 2020), and several failure modes detection (Una et al, 2017; Xu et al, 2021). Specifically, in Cheng et al (2020) and Shafi et al (2018), SVM achieves the best performance.…”

“…. (2018),Quatrini et al (2020),Hu et al (2020),Panicucci et al (2020),Chen, Hsu, et al (2021) Support Vector MachinesLeahy et al (2018),Quatrini et al (2020),Venkataswamy et al (2020), Cheng et al (2020), Hu et al (2020), Chen, Hsu, et al (2021), Aqueveque et al (2021) Bayesian models Hu et al (2020), Ruiz-Sarmiento et al (2020), Aqueveque et al (2021) Artificial Neural Networks Ullah et al (2017), Srivastava et al (2018), Quatrini et al (2020), Cheng et al (2020), Hu et al (2020) DL-Deep Neural Networks Chen, Hsu, et al (2021) DL-Recurrent Neural Networks Zhang, Zhang, and Li (2019), Fernandes et al (2020), Bampoula et al (2021), Chen, Zhu, et al (2021), Usuga-Cadavid et al , et al (2020), Pezze et al (2021) K-nearest neighbors The principle behind distance-based methods is to find a predefined number of training samples closest to the new point, and predict the label from these. K-Nearest Neighbors (kNN) is a type of instance-based learning based on the k nearest neighbors of each query point, where k is a parameter that indicates the amount of neighbors to consider.…”