3 September 2021 in IEEE Access
In this paper water cycle algorithm-based fractional order PI controller (FOPI) is proposed for virtual flux-oriented control of a three-phase grid-connected PWM rectifier. FOPI controller makes the PWM rectifier control more robust due to the fractional behavior. Fractional-order controllers have an additional degree of freedom, so a wider range of parameters is available to provide better control and robustness in the plant. The optimization and design of the FOPI controller are done using the water cycle algorithm (WCA). WCA is an optimization method inspired by monitoring the water cycle operation and flow of water bodies like streams and rivers toward the sea. The performance of the FOPI controller is compared with the classical integer order PI controller. The parameters of PI and FOPI controllers are optimized and designed using the WCA technique, leading to WCA-PI and WCA-FOPI controllers. The system is tested using MATLAB/Simulink. The simulation results verify the better performance of WCA-FOPI in terms of settling time, rise time, peak overshoot, and Total Harmonic Distortion (THD) of grid current. A robustness measurement with line filter parametric variations and non-ideal supply voltage (unbalance and distorted supply voltage) is carried out. The WCA-FOPI demonstrates more robustness as compared to WCA-PI. Simulation findings validate the WCA-FOPI controller outcomes as compared to WCA-PI in terms of control effect and robustness.
6 January 2022 in Multimedia Tools and Applications
2 November 2020 in Computers and Electrical Engineering
17 May 2022 in IEEE Internet of Things Journal
The combustible and noxious gases are among the prominent issues affecting the life and the mining operations of underground coal mines (UCM). Commonly adopted hazard monitoring methodologies in UCM are fuzzy, rule-based systems, statistical methods and other expert systems, but these models are not reliable for highly complex and non-linear systems. The neural-network’s ability to learn and create non-linear relationships is beneficial to making hazard prediction models. Especially, Convolutional Neural Networks (CNN) auto feature extraction capabilities make it more suitable for the task. But, UCM’s harsh and crucial environment may result in sensor malfunctioning and faults, giving rise to data uncertainty. Like other data-driven models, data uncertainty significantly affects CNN’s performance. This study involves designing an effective and reliable gas hazard monitoring system using a hybrid of Dempster Shafer evidence theory (DSET)-based filter and one-dimensional CNN (1DCNN) classifier. The novelty of this study is the integration of DSET and 1DCNN to predict the UCM hazard more reliably, even in malfunctioning node scenarios. Inherent usage limitations on traditional communication techniques restricts the application of cloud-based machine learning (ML) methods and this study use novel edge-implementation of the filter and the classifier using edge machine learning (EML) technology. The proposed model’s hazard classification accuracy is 99.6%, even in the faulty node scenarios, where the traditional approaches fail.
10 May 2018 in Wireless Personal Communications