Search results for: Sai Harshini Irigineni

Authors: Sai Harshini Irigineni, Suresh Kumar Reddy Narala

Abstract:

The industrial applicability of aluminium metal matrix composites (AMMCs) has been rapidly growing due to their exceptional materials traits such as low weight, high strength, excellent thermal performance, and corrosion resistance. The increasing demand for AMMCs in automobile, aviation, aerospace and defence ventures has opened up windows of opportunity for the development of processing methods that facilitate low-cost production of AMMCs with superior properties. In the present work, owing to its economy, efficiency, and suitability, powder metallurgy (P/M) technique was employed to develop AMMCs with pure aluminium as matrix material and titanium diboride (TiB₂) as reinforcement. AMMC samples with different weight compositions (Al-0.1%TiB₂, Al-5%TiB₂, Al-10%TiB₂, and Al-15% TiB₂) were prepared through hot press compacting followed by traditional sintering. The developed AMMC was subjected to metallographic studies and mechanical characterization. Experimental evidences show significant improvement in mechanical properties such as tensile strength, hardness with increasing reinforcement content. The current study demonstrates the superiority of AMMCs over conventional metals and alloys and the results obtained may be of immense in material selection for different structural applications.

Keywords: AMMCs, mechanical characterization, powder metallurgy, TiB₂

Procedia PDF Downloads 129

Authors: Kaarthik K., Harshini S., Karthika M., Kripanandhini T.

Abstract:

Water is an essential part of living organisms. Major water pollution is caused due to contamination of industrial wastewater in the river. The most important step in bringing wastewater contaminants down to levels that are safe for nature is wastewater treatment. The contamination of river water harms both humans who consume it and the aquatic life that lives there. We introduce a new cloud-based industrial IoT paradigm in this work for real-time control and monitoring of wastewater. The proposed system prevents prohibited entry of industrial wastewater into the plant by monitoring temperature, hydrogen power (pH), CO₂ and turbidity factors from the wastewater input that the wastewater treatment facility will process. Real-time sensor values are collected and uploaded to the cloud by the system using an IoT Wi-Fi Module. By doing so, we can prevent the contamination of industrial wastewater entering the river earlier, and the necessary actions will be taken by the users. The proposed system's results are 90% efficient, preventing water pollution due to industry and protecting human lives.

Keywords: sensors, pH, CO₂, temperature, turbidity

Procedia PDF Downloads 109

Authors: Samhita Mummadi, Sree Divya Nagalli, Harshini Vemuri, Saketh Charan Nakka, Sumesh K. J.

Abstract:

One of the most significant challenges faced by people in today’s digital era is an alarming increase in fraudulent activities on online platforms. The fascination with online shopping to avoid long queues in shopping malls, the availability of a variety of products, and home delivery of goods have paved the way for a rapid increase in vast online shopping platforms. This has had a major impact on increasing fraudulent activities as well. This loop of online shopping and transactions has paved the way for fraudulent users to commit fraud. For instance, consider a store that orders thousands of products all at once, but what’s fishy about this is the massive number of items purchased and their transactions turning out to be fraud, leading to a huge loss for the seller. Considering scenarios like these underscores the urgent need to introduce machine learning approaches to combat fraud in online shopping. By leveraging robust algorithms, namely KNN, Decision Trees, and Random Forest, which are highly effective in generating accurate results, this research endeavors to discern patterns indicative of fraudulent behavior within transactional data. Introducing a comprehensive solution to this problem in order to empower e-commerce administrators in timely fraud detection and prevention is the primary motive and the main focus. In addition to that, sentiment analysis is harnessed in the model so that the e-commerce admin can tailor to the customer’s and consumer’s concerns, feedback, and comments, allowing the admin to improve the user’s experience. The ultimate objective of this study is to ramp up online shopping platforms against fraud and ensure a safer shopping experience. This paper underscores a model accuracy of 84%. All the findings and observations that were noted during our work lay the groundwork for future advancements in the development of more resilient and adaptive fraud detection systems, which will become crucial as technologies continue to evolve.

Keywords: behavior analysis, feature selection, Fraudulent pattern recognition, imbalanced classification, transactional anomalies

Procedia PDF Downloads 24