Neuro-Fuzzy Logic Controller for Switching Capacitor Banks in Power Factor Correction within the Manufacturing Industry
Journal Title: Journal of Intelligent Systems and Control - Year 2024, Vol 3, Issue 2
Abstract
Regulatory bodies in electrical engineering mandate the installation of power factor (PF) improvement systems to elevate PF values to between 0.9 and 0.96. Compliance is enforced by regional or local utility companies through penal rates and incentives for PF values nearing unity. Traditional power factor correction (PFC) systems often utilize microprocessor-based controllers for switching capacitor banks, which can result in under- or over-compensation of reactive power. This study developed an adaptive neuro-fuzzy inference system (ANFIS) utilizing a Sugeno-Takagi inference model based on the sub-clustering method to address the limitations of sensitivity and response time observed in existing microcontroller-based PFC systems. The proposed neuro-fuzzy (NF) controller comprises a five-layered model with two inputs, i.e., kilowatt (KW) and kilovolt-ampere reactive (KVAR), and one output (PF). A 25-rule set performance of the developed program was achieved, with significant improvements observed after 50 epochs, culminating in an error rate of 0.050691 recorded post the second epoch. The results demonstrated that the developed controller exhibits higher sensitivity and faster response time compared to existing PF controllers. Consequently, the implementation of the proposed controller is recommended for optimizing the switching of capacitor banks, thereby enhancing PF in manufacturing industries characterized by variable load conditions.
Authors and Affiliations
Olamide Omolara Olusanya, Gbenga Mufutau Adebajo, Ibrahim Giwa, Kennedy Okokpujie, Samuel Adebayo Daramola, Adenugba Vincent Akingunsoye5
Keywords
Related Articles
- EP ID EP752424
- DOI https://doi.org/10.56578/jisc030203
- Views 40
- Downloads 1
System Identification and Control of Automatic Car Pedal Pressing System
This paper mainly explores the system identification and control of an automatic car pedal pressing system. Specifically, the system identification was achieved using an artificial neural network, with the help of MATLAB...
Performance Evaluation of a Sliding Mode Control-Kalman Filter-Based Mathematical Model for Altitude and Attitude Control in Quadcopters
This study presents an evaluation of a mathematical model designed for altitude and attitude control in quadcopters, employing Sliding Mode Control (SMC) in conjunction with the Kalman Filter algorithm. The developed mat...
Design and Implementation of FPGA for Digital Channelization Processing
To address the rate mismatch between high-bandwidth, high-sampling-rate analog-to-digital converters (ADCs) and low-bandwidth, low-sampling-rate baseband processors, digital signal processing techniques were employed to...
Integration of IoT for Smart Energy Management: Advancing Home Automation and Power Efficiency
The growing demand for energy, driven by urbanization and environmental concerns, has highlighted the need for innovative solutions in power management, particularly within residential and small business settings. This s...
Adaptive Road Crack Detection and Segmentation Using Einstein Operators and ANFIS for Real-Time Applications
A novel approach for road crack detection and segmentation was proposed, incorporating Einstein operators within an Adaptive Neuro-Fuzzy Inference System (ANFIS). This methodology leverages advanced fuzzy aggregation tec...