MIT-World Peace University (MIT-WPU) is a top educational institute located in Pune, India. It is recognized within&nbsp;UGC under Government of Maharashtra Act No. XXXV 2017.&nbsp;

It is part of the MIT group of institutions (established in 1983) which covers 10+ campuses across India and has more than 50,000+ students enrolled across various disciplines at a given point of time. The institute houses 15 schools ranging from Engineering &amp; Technology, Design, Pharmacy, Commerce, Governance among others. It offers undergraduate, postgraduate and PhD programs among different disciplines.&nbsp;

&nbsp;

MIT World Peace University

School of Electrical Engineering

Day by day pollution in cities is increasing due to urbanization. One of the biggest challenges posed by the rapid migration of inhabitants into cities is increased air pollution. Sustainable Development Goal 11 indicates that 99 percent of the world’s urban population breathes polluted air. In such a trend of urbanization, predicting the concentrations of pollutants in advance is very important. Predictions of pollutants would help city administrations to take timely measures for ensuring Sustainable Development Goal 11. In data engineering, imputation and the removal of outliers are very important steps prior to forecasting the concentration of air pollutants. For pollution and meteorological data, missing values and outliers are critical problems that need to be addressed. This paper proposes a novel method called multiple iterative imputation using autoencoder-based long short-term memory (MIA-LSTM) which uses iterative imputation using an extra tree regressor as an estimator for the missing values in multivariate data followed by an LSTM autoencoder for the detection and removal of outliers present in the dataset. The preprocessed data were given to a multivariate LSTM for forecasting PM2.5 concentration. This paper also presents the effect of removing outliers and missing values from the dataset as well as the effect of imputing missing values in the process of forecasting the concentrations of air pollutants. The proposed method provides better results for forecasting with a root mean square error (RMSE) value of 9.8883. The obtained results were compared with the traditional gated recurrent unit (GRU), 1D convolutional neural network (CNN), and long short-term memory (LSTM) approaches for a dataset of the Aotizhonhxin area of Beijing in China. Similar results were observed for another two locations in China and one location in India. The results obtained show that imputation and outlier/anomaly removal improve the accuracy of air pollution forecasting. © 2023 by the authors.

World University root node

School of Electronics & Communication Engineering

Engineering and Technology

School of Computer Engineering & Technology

Algorithms

Novel MIA-LSTM Deep Learning Hybrid Model with Data Preprocessing for Forecasting of PM2.5

Electric Vehicles (EVs) are gaining interest because of the sky rocketing oil prices and increased pollution level in major cities across the world. Almost all EV motors need rare earth magnet which are in limited supply. In order to reduce this dependency, EVs are looking for magnet free motors. One of the alternatives gaining significant mindshare across industry is Switched Reluctance motor (SRM). SRM largely satisfies all the requirements of EV. However, its performance is mainly dependent on converter and controller topology. This paper critically analyses the various parameter of SRM during dynamic loading condition like speed, torque ripple and current, using various converter topologies. Analysis of 60 kW, 4 phase SRM for EV application has been presented with mid-point converter and asymmetric bridge converters along with the proportional plus integral (PI) hysteresis controller. Results shows that asymmetric bridge converter provides enhanced performance for EV application. © 2022

Materials Today: Proceedings

Comparative analysis of converter topologies used in switched reluctance motor for high torque electric vehicle application

In this invention a test jig for testing electric bicycle and electric motors used in electric bicycle is developed. The motors used in bicycles can be tested. The performance of the bicycles on road with slope can be tested on the developed jig. In the developed jig performance of the motors also can be tested. There is a facility of loading the motor is provided in this developed jig. Various types of electric motors can be tested on the jig. There is a facility of record speed torque temperature of motor and other parameters of motors. The facility of loading the motor is also provided. The load is applied on the motor in proportion to slope of the motor. Various sensors are fixed in the test jig. Internet of things is used to transfer the data collected. The data is received remotely on the computer. The data collected automatically stored in a computer. The data received can be accessed remotely using internet. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Lecture Notes in Networks and Systems

Electric Sports Bicycle Motor Testing in a Laboratory Jig Using Cloud Computing and Internet of Things

International Journal of Advanced Manufacturing Technology

Lie group dee learning technique to identify the precision errors by map geometry functions in smart manufacturing

MoO3-PVA films hybridized with silver and copper nano-particles mediated by microwave heating were studied for energy applications. The composites films were characterized by Infra-red (FTIR), Thermogravimetric analysis (TGA), differential scanning calorimetry (DSC), UV–Visible spectroscopy and X-ray diffraction (XRD). The crystallite size from XRD peak width was estimated to be about 60–65 nm in the nanocomposite. The electromagnetic interference (EMI) shielding efficiency of so generated composites showed that metal containing composites have higher efficiency in X-band. The EMI study showed promising scope for application in low shielding requirement areas. The so-generated silver containing hybrid system resulted in visible light tunable band-gap (2.34–2.81 eV). Ag-MoO3-PVA (Sample PV-C) showed more than 90 % photocatalytic degradation of methylene blue dye. © 2023 Elsevier B.V.

Materials Science and Engineering: B

Microwave processed metal nanoparticles/MoO3-PVA photoactive nano-composites for energy applications

Observations and Analysis of Power Quality Indices Using Custom Power Devices in Power Distribution Network

Simultaneous localization and mapping (SLAM) is central to the foundation of robotic exploration. Over the decades, numerous advancements have been made in the field of SLAM. Currently, most of the applications based on SLAM are implemented using a single robot. In practical applications like search and rescue operations, there is a need to implement SLAM at a multi-robot level. This paper conducts a review on SLAM at a multi-robot level. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Lecture Notes in Mechanical Engineering

Multi-robot SLAM: Challenges and Solutions

The torque ripple in five-phase induction motor (FP-IM) is reduced in the proposed direct torque control (DTC) drive scheme. The three-level five-phase inverter (TL-FPI) is utilized to feed the five-phase machine due to provision of availability of more switching states as compared to two-level five-phase inverter. The implemented 81 switching states among 243 available are distributed in 20 sectors each having 18° width. The 20-sector distribution gives more fine torque ripple slopes as compared to the 10-sector distribution by increasing the switchover frequency of the switching states. The main and intermediate switching states are alternately employed which maintain the torque slope (ripple) lower. An increase in changeover frequency of voltage vectors (VVs) decreases the sharpness of torque ripple, which keeps the magnitude of torque ripple lower. While reducing the torque ripple, the common-mode voltage (CMV) is controlled. Additionally, the phase current and stator flux are improved. The several results are provided with this paper to showcase the torque ripple reduction. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

Electrical Engineering

Torque ripple reduction in three-level five-phase inverter-fed five-phase induction motor

In this paper, power quality problems that occur in an AC part of the microgrid system are detected and classified with artificial neural network. The model for generating power quality problems is developed in MATLAB simulink The simulink model consists of a solar energy source, full bridge dc-ac converter, LC filters and load. The full bridge converter is used to convert the DC solar output to single phase AC. The LC filter is used to eliminate the harmonics present in the AC output of the converter. A series RLC load is used in the proposed system. The power quality detection system is based on the pattern recognition neural network. The neural network is trained with samples of sag, swell and interruption. These power quality problems are created with the help of a circuit breaker. The duration of these problems/distortions are changed for producing the datasets for training the neural network. The dataset for training and testing is generated with the help of simulation model converter circuit. © 2021 IEEE.

Proceedings of the 2021 2nd International Conference on Communication, Computing and Industry 4.0, C2I4 2021

Power Quality Analysis in Microgrid System with Bayesian Regularized Neural Network

An electromagnetic field and artificial intelligence-based transmission line protection system for smart grid is proposed in this paper. Bayesian regularization neural network is used as an intelligence technique. Instead of conventional current transformers, the use of magnetic field sensors for monitoring the current in transmission lines is proposed. A mathematical model of the magnetic field due to the current in transmission line is developed by considering two positions of the magnetic field sensors. The developed model is simulated for extensive scenarios. Line to ground, line to line, double line to ground and three-phase faults are created. The fault current values are transformed into magnetic field values and given to the dyadic analysis filter bank for feature extraction process. The extracted features are given as an input to the neural network for the training. The Bayesian regularization algorithm is used as a training algorithm. The performance of the proposed system is compared with other algorithms. It shows that the proposed system with Bayesian regularization have 96.11% of accuracy with the combination of different faults. The results obtained show that the proposed system outperforms the existing approaches. © 2021 Taylor & Francis Group, LLC.