PSG College of Technology

About: PSG College of Technology is a based out in . It is known for research contribution in the topics: Machining & Thin film. The organization has 3174 authors who have published 3575 publications receiving 40690 citations.

Study on three-body abrasive wear behavior of functionally graded Al/TiB2 composite using response surface methodology

Abstract: Functionally graded LM13 Al/10 wt% TiB2 metal matrix composite has successfully produced under centrifugal casting. Hollow cylindrical composite with dimensions 150 × 150 × 15 mm was produced under rotating centrifugal speed of 1100 rpm. Microstructural characteristics were studied on the composite surfaces at distance of 1, 5.5, and 10 mm from outer periphery of the casting, and the results revealed that surface at distance of 1 mm has presence of more reinforcement particles. An objective of this study was to characterize abrasion wear behavior at the composite surfaces using dry abrasion tester. Mathematical models were developed using response surface methodology to study the relationship of parameters such as load, speed, and distance from outer periphery with abrasion wear rate. Face centered Central Composite Design with 20 experiments was preferred for dry abrasion test. Adequacy of model was predicted through analysis of variance, and the significance test result shows that load has major...

A Literature Review on the Progression of Agile Manufacturing Paradigm and Its Scope of Application in Pump Industry.

Abstract: During the recent years, the manufacturing world has been witnessing the application of agile manufacturing paradigm. The literature review reported in this paper was carried out to study this progression. This literature review was carried out in two phases. In the first phase, the literature was reviewed to trace the origin of agile manufacturing paradigm and identify its enablers. Further, during this phase, the applications of agile manufacturing reported in literature arena were reviewed. It was also discernable that certain research works have been initiated to apply agile manufacturing paradigm in pump industry. During the second phase, the researches reported on applying agile manufacturing in pump industry were reviewed. At the end of this review, it was found that so far the implementation of agile manufacturing in pump industry has been examined by the researchers by considering only certain components of pumps. In fact, the holistic implementation of agile manufacturing in the pump industry is yet to be examined by the researchers. In the context of drawing this inference, this paper has been concluded by stating that high scope exists in examining the infusing of agility characteristics in designing and manufacturing of pumps.

Intelligent Modeling Combining Adaptive Neuro Fuzzy Inference System and Genetic Algorithm for Optimizing Welding Process Parameters

Abstract: Modified 9Cr-1Mo ferritic steel is used as a structural material for steam generator components of power plants. Generally, tungsten inert gas (TIG) welding is preferred for welding of these steels in which the depth of penetration achievable during autogenous welding is limited. Therefore, activated flux TIG (A-TIG) welding, a novel welding technique, has been developed in-house to increase the depth of penetration. In modified 9Cr-1Mo steel joints produced by the A-TIG welding process, weld bead width, depth of penetration, and heat-affected zone (HAZ) width play an important role in determining the mechanical properties as well as the performance of the weld joints during service. To obtain the desired weld bead geometry and HAZ width, it becomes important to set the welding process parameters. In this work, adaptative neuro fuzzy inference system is used to develop independent models correlating the welding process parameters like current, voltage, and torch speed with weld bead shape parameters like depth of penetration, bead width, and HAZ width. Then a genetic algorithm is employed to determine the optimum A-TIG welding process parameters to obtain the desired weld bead shape parameters and HAZ width.

Comparative Analysis of COVID-19 X-ray Images Classification Using Convolutional Neural Network, Transfer Learning, and Machine Learning Classifiers Using Deep Features

Abstract: A new type of coronavirus called (SARS-CoV-2) causes the COVID-19 coronavirus disease. The World Health Organization (WHO) declared this COVID-19 disease as pandemic because the disease got spread over several countries. At present situation, there is no medicine available for prevention or cure of the infectious disease. Samples taken from persons with COVID-19 symptoms are commonly tested using Reverse Transcription–Polymerase Chain Reaction (RT-PCR) process which is costlier and also take a minimum of 24 h to get the test result as either negative or positive. The proposed work suggests the possibility of using X-ray images of persons having COVID-19 symptoms to be classified as 1) healthy, 2) COVID-19 affected, or 3) Pneumonia affected. Experimentation is carried out with data samples from each category and classification done using Convolutional Neural Network (CNN), transfer learning using VGG Net, and machine learning techniques such as Support Vector Machine (SVM) and XGBoost which utilizes features extracted with the help of Convolutional Neural Network. Out of the models compared, the SVM with CNN extracted features was able to produce a highest precision, recall, F1-score and accuracy of 95.27, 94.52, 94.94, and 95.81%, respectively in identifying healthy, Pneumonia, and COVID-19 affected persons while experimented with 5-fold cross validation.

Ant Colony Optimization based approach for efficient packet filtering in firewall

Abstract: A firewall is a security guard placed at the point of entry between a private network and the outside network. The function of a firewall is to accept or discard the incoming packets passing through it based on the rules in a ruleset. Approaches employing Neural networks for packet filtering in firewall and packet classification using 2D filters have been proposed in the literature. These approaches suffer from the drawbacks of acceptance of packets from the IP address or ports not specified in the firewall rule set and a restricted search in the face of multiple occurrences of the same IP address or ports respectively. In this paper we propose an Ant Colony Optimization (ACO) based approach for packet filtering in the firewall rule set. Termed Ant Colony Optimization Packet Filtering algorithm (ACO-PF), the scheme unlike its predecessors, considers all multiple occurrences of the same IP address or ports in the firewall rule set during its search process. The other parameters of the rule matching with the compared IP address or ports in the firewall ruleset are retrieved and the firewall decides whether the packet has to be accepted or rejected. Also this scheme has a search space lesser than that of binary search in a worst case scenario. It also strictly filters the packets according to the filter rules in the firewall rule set. It is shown that ACO-PF performs well when compared to other existing packet filtering methods. Experimental results comparing the performance of the ACO-PF scheme with the binary search scheme, sequential search scheme and neural network based approaches are presented.