Proceedings on Engineering Sciences

6

Authors: Soumya A. K., Ritu Shree, Anu Sharma

The fracture behaviour of particle composites made of polymers under impact loading is predicted in this research using a hybrid machine learning approach dubbed Hybrid Artificial Neural Networks and Random Forest (HANN-RF), with a focus on mode-I fracture. The goal of the study is to create a model for prediction that accurately links input variables to histories of crack initiation, fracture toughness, and the intensity of the stress factor (SIF). A full dataset is created, with inputs for the composites' compositional properties and impact loading scenarios. The HANN-RF model combines a Random Forest (RF) method and an ANN (Artificial Neural Network) in order to improve robustness and accuracy in forecasting. Metrics like MAE, MAPE for short, and accuracy are used in model evaluation. The outcomes show that the HANN-RF technique successfully predicts and forecasts mode-I fracture behaviour, offering insightful information for evaluating the effect on resilience and longevity of particle polymer composites in a variety of applications.

8

Authors: Umesh Kumar Singh, Ramachandran T., Mohit Kumar Sharma

For power systems to operate reliably and effectively, state estimate is essential. For monitoring and control applications, it offers real-time estimates of the system's state indicators, including voltage levels and orientations. In this paper, a novel catagonfly optimization (CFO) technique that aims to improve state estimation effectiveness in electrical systems is presented. The suggested strategy combines optimization techniques from cat swarm and dragonfly. The suggested strategy is evaluated using the IEEE-118 test environment under various simulated scenarios, and the findings are contrasted with those of other methods already in use. The optimization results and statistical error assessment demonstrate the suggested CFO technique's efficiency to the alternatives. The results of this study also have the potential to improve the incorporation of sustainable energy sources, microgrids, and additional emerging innovations into existing power grids.

8

Authors: Pramod Kumar Faujdar, Ashish Simalti, Kannagi Anbazhagan

The issues in Vehicle Routing with Time Windows (VR-TW) are addressed in this study using a novel hybrid swarm-intelligent frog jumping optimisation (HSIFJO) algorithm. The method employs a diversity management strategy for developing memeplexes, which assists in preserving diversity and prevents the premature termination of the search. To increase population diversity and improve solution quality, an enhanced clone selection (CS) process is employed. To maximise the algorithm's potential, an enhanced and extended extremal optimisation (EO) strategy is used, coupled with different move operators. A proposed adaptive soft time windows (ASTW) surcharge approach acknowledges the possibility of impractical solutions during the evolution process. When compared to existing state-of-the-art heuristics, the suggested approach performs exceptionally well in performance evaluation.

8

Authors: R. Kamalraj, Vikas Verma, Manish Joshi

Effective maintenance coordination has become essential to ensuring a reliable electricity supply in power systems primarily powered by renewable sources. On the other hand, the computational complexity of the operational security standards presents difficulties for the existing planning tools. To solve this problem, a research paper suggests applying the machine learning (ML) method known as lightning search optimised random forest (LSORF) to anticipate the results of contingency analyses rapidly and effectively. The entire regional transmission system of Belgium (BE), which includes voltage ranges of 200 kV to 50 kV, is the subject of the study. Results show that LSORF regularly outperforms other benchmarks. The results demonstrate that LSORF consistently outperforms other benchmark methods. Furthermore, the study highlights the impact of projected growth in renewable energy on maintenance feasibility. This strategy provides useful insights for improving maintenance planning in renewable energy systems.

8

Authors: Kishore Kumar P, Alka Kumari, Pradeep Kumar Verma, Mohit Kumar Sharma, Vinod M, Lokesh Varshney

Non-orthogonal signal-based systems are a type of communication system that uses signals that are not mutually perpendicular (i.e., not orthogonal) to transmit information. These types of systems can increase the spectral efficiency of communication systems by allowing for more data to be transmitted in the same bandwidth. Groups of signals with non-orthogonal waveforms can increase spectral efficiency, but they also increase the potential for interference. Spectrally efficient frequency division multiplexing (SEFDM) is a well-studied waveform that was originally proposed for use in wireless systems but has since found application in millimeter wave communications at 60 GHz, optical access network architecture, and long-distance optical fiber transmission. However, non-orthogonal signal-based systems are also more susceptible to interference from other sources, which can degrade the quality of the transmitted signal. To address this problem, this paper suggests using fuzzy learning techniques to cancel out interference and improve the signal-to-noise ratio. Fuzzy learning is a type of machine learning that uses fuzzy logic (FL) to handle uncertainty and imprecision in data. By using FL techniques to cancel out interference, the non-orthogonal signal-based optical communication (OC) system could potentially achieve better performance in noisy environments. Overall, this research topic has the potential to contribute to the development of more efficient and reliable OC systems that can operate in challenging environments.

8

Authors: Ranjan Kumar, Parvesh Belwal, Harsh Shrivastava, Jisha LK, Pankaj Kumar Goswami, Gitanjali Mehta

The fact that they are unpredictable and unreliable, renewable energy sources (RES) are increasingly crucial to the electrical power grid's ability to maintain energy continuity. The challenge of energy sustainability can only be solved by energy storage technology. Regarding a Hybrid Energy Storage System (HESS) powered by a 4-wire, 3-phase grid connected solar Photovoltaic (PV) power system, a novel Smart Energy Control Technique (SECT) with a Whale optimization algorithm is presented in this work. The sustainability of energy via solar PV power generating systems is achieved by using HESS, which consists of batteries and ultra-capacitor storage devices for energy. The suggested SECT has been used for the analysis and experimental testing of several HESS operating scenarios. During experimental testing, the load status of a single sunny day and the PV power outline were constructed and dynamically assessed by utilizing SECT; some test findings in eight distinct operating modes are included in this paper. The system uses 1320W of electricity to charge the battery group, and in one of its modes of operation, the leftover energy is sent to the grid using 5% present harmonics. And because of the system's high power density, quick reaction, and great efficiency, the HESS is a highly efficient energy storage method. Simulation findings and laboratory testing have validated the suggested system.

10

Authors: Moiz Mohammed, Mohammed Ahmed Hussain

The pre-engineered steel framed structure (PEB) introduced in 1960’s includes a structural frame, roofing system and wall supports; for the construction of industrial structure like ware houses, car showrooms, workshops, function halls, stadiums, aircraft hangars etc. is found to be economical, light weight and fast erection process. The PEB’s are built to perform some important functions, provide enough space for storing goods; aircrafts etc.. and protecting the storage items against natural disasters, wind forces, and rain. In this research work a hangar for airbus A-380 has been designed considering its dimensions; for maximum span of 120M and width of 115M and a height of 30M as a pre-engineered framed structure. For designing the structural members staad pro (V8i) software is used. This structural design is in accordance with the specification of the general construction in steel confirming to IS:800-2007 (limit state design) and wind application as per latest code confirming to IS:875-2015 ( part-III) and earthquake analysis has been done as per IS-1893-2016 (part-IV). For the first time a hangar for A-380 has been designed for using above IS Codes, structural design details, connection details have been produced and found that the total steel is 3502.43 Metric Tons.

10

Authors: Bhuvana J., Jitendra Kumar Katariya, Shambhu Bhardwaj

Mass customization is becoming the more and more of emphasis on the production optimization. In many manufacturing and service organizations, production planning and scheduling are characterized as the daily decision-making procedures. The significance of the choices made is therefore to shown in the areas of work orders, manufacturing, transportation, and distribution of the finished goods. Production scheduling is the process of regulating, determining, and maximizing the restricted resources of the production system. In this study, a novel Hybrid Dynamic Genetic-Adaptive Improved Gravitational Optimization Algorithm (HDG-AIGOA) approach is introduced to optimize the production schedule. In this case, the AIGOA classification effectiveness is increased by using the HDG method. The small and benchmark iMOPSE dataset has been used to assess the success of suggested approach. The noisy data from raw data samples are removed using the Adaptive Median Filter (AMF) filter. To extract the properties from the segmented data, a Kernel Principal Component Analysis (KPCA) is performed. The results of the research show that the recommended methodology beats earlier approaches in terms of the accuracy, Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Square Error (MSE). Our proposed method might consider to improve the production scheduling in an dynamic environment.

10

Authors: Preeti Verma, Sashilal Singh M., Ravi Angadi V., Garima Goswami, Gnana Jeba Das, Kanika Jindal

The reduction of carbon emissions in the transportation sector will be aided by the electrification of transportation in RES-based energy systems. However, the inactive addition of electric vehicles is expected to hinder sustainability efforts owing to the rise in power consumption and the significant peak impacts of charging. The three main charging methods for Electric Vehicles (EVs) in Europe are: Smart Charging (SC), Power Charging (PC), and Vehicle-To-Grid (V2G) that give varying degrees of flexibility are examined in this research. This flexibility is compared to the flexibility provided by interconnections. We depict immediate action and future planning in the power organization using the Balmorel optimization tool, and we advance the state of the art by creating new approaches to stand for battery deterioration & at-home charging. Our results show that, up to the year 2050, any rise in charging flexibility reduces system costs, modifies the energy mix, affects spot prices, and reduces CO2emissions.We quantify the reciprocal benefits of flexible charging and variable generation, which limits the economics of permanently installed batteries and causes solar energy to take the place of wind energy in passive charging. The framework that includes and lacks connection development highlights the interplay between European countries in terms of the power price framework of electric mobility. The condition of the nations with the cheapest and most decarbonizes power mix is harmed beneath the most bendable situation at the EU level, even if the best result is achieved. This necessitates an adjusted coordinating strategy at the EU level.

12

Authors: Nisha Sahal, Preethi D., Dushyant Singh,

The term deep learning-based framework for smart mobility refers to a concept or research article that suggests a framework for traffic pattern prediction using deep learning methods in the context of smart mobility. To improve traffic prediction skills and create more intelligent and effective transportation systems, the Autonomous traffic prediction: A deep learning-based framework for smart mobility idea proposes to make use of the potential of deep learning algorithms. In this study, a new Improved Spider Monkey Swarm Optimized Generative Adversarial Network (ISMSO-GAN) approach is introduced to forecast autonomous traffic for smart mobility. In this case, the GAN's classification effectiveness is increased by using the ISMSO method. The Regional Transportation Management Center's traffic dataset for Twin Cities' metro freeways is used to assess the success of the suggested approach. The noisy data from raw data samples are removed using the Adaptive Median Filter (AMF) filter. To extract the properties from the segmented data, a Kernel Principal Component Analysis (KPCA) is performed. The results of the research show that recommended methodology beats earlier approaches in terms of accuracy, Mean Square Error (MSE), Mean Absolute Error (MAE), and Prediction Rate. Our proposed method might considerably enhance traffic management and maximize resource allocation.