Kongu Engineering College

About: Kongu Engineering College is a based out in . It is known for research contribution in the topics: Computer science & Cluster analysis. The organization has 2001 authors who have published 1978 publications receiving 16923 citations.

Experimental study on frictional characteristics of tungsten carbide versus carbon as mechanical seals under dry and eco-friendly lubrications

Abstract: Lubrication reduces the friction between the interfaces of sliding surfaces in the mechanical seals that operate for extended period of time. Due to environmental issues caused by mineral oil-based lubricants, the use of organic based vegetable oils had increased worldwide due to the nontoxic and biodegradable characteristics. In this work an experimental study was carried out by employing a seal pair of tungsten carbide and resin impregnated carbon mechanical seals, its frictional behaviour was studied under the eco-friendly lubricant from the class of vegetable oils — soybean oil and canola oil with an eco-friendly solid lubricant i.e. boric acid powder. An experimental setup was designed and fabricated to study the frictional characteristics of the seal for varying normal load and constant speed. The friction characteristics was studied under unlubricated conditions, independent paraffin oil, soybean oil, canola oil lubricating modes and finally 1 wt.%, 3 wt.% and 5 wt.% of boric acid powder mixed individually with soybean and canola oil. After all running-in test of all lubricating conditions, 5 wt.% of boric acid powder mixed with soybean oil had contributed a hybrid tribofilm and resulted in the lowest friction coefficient value in the range of 0.06–0.07.

Multi-criteria-based approach for job scheduling in industry 4.0 in smart cities using fuzzy logic

Abstract: A flexible manufacturing system (FMS) is the model used for the system produced in the manufacturing industry, and it consists of the number of interconnected workstation. Inflexible manufacturing system scheduling of jobs has become a serious problem, even for a short breakdown of the machine and for the unexpected arrival of the product. To overcome this problem, a flexible manufacturing system using fuzzy rules is proposed. In this proposed model, four input variables are considered: (1) machine allocated processing time; (2) priority of the machine; (3) priority of the due date; and (4) priority of the setup time. The priority based on the job is the fuzzy variable, which shows the status of the job, based on which the next job will be selected for the processing in the machine. In this model, the machine will be selected first, and then, the scheduling is done based on the multi-criteria scheduling system. The obtained results are compared with the existing system and from the results. The improved scheduling strategy provides better results for the scheduling problem.

An efficient visual saliency detection model based on Ripplet transform

Abstract: Even though there have been great advancements in computer vision tasks, the development of human visual attention models is still not well investigated. In day-to-day life, one can find ample applications of saliency detection in image and video processing. This paper presents an efficient visual saliency detection model based on Ripplet transform, which aims at detecting the salient region and achieving higher Receiver Operating Characteristics (ROC). Initially the feature maps are obtained from Ripplet transform in different scales and different directions of the image. The global and local saliency maps are computed based on the global probability density distribution and feature distribution of local areas, which are combined together to get the final saliency map. Ripplet-transform-based visual saliency detection is the novel approach carried out in this paper. Experimental results indicate that the proposed method based on Ripplet transformation can give excellent performance in terms of precision, recall, F measure and Mean Absolute Error (MAE), and is compared with 10 state-of-the-art methods on five benchmark datasets.

A simulation-based analysis for improvement of productivity in sick chemical dyeing factory: a research article

Abstract: This paper provides an overview of the various processes in textile fabric industry. From the analysis of data taken during the past three years, the company has noted that it has not achieved the targeted productivity. Total productive maintenance (TPM) has been a major component of improvement strategy to enhance the organisational productivity and profitability. Identification of resources and use resources play a critical role in any industry for the improvement of quality and productivity. For example, fabric industry could not get the determined productivity since TPM was not followed. The objective of this paper is to present the result of the past three years productivity data and discussed different results obtained after implementing the procedures of TPM in the failure textile industry. A systematic methodology is presented and analysed by software for improvement productivity at the factory level. Metrics of overall equipment effectiveness (OEE) is introduced and developed a structured robust framework for improvement of quality and productivity.

A survey on the applications of Deep Neural Networks

Abstract: The real-world applications need someone who will process the data with precision and take respective actions and it has to be out there without any human intervention so basically the machines need to think and act, this is where the new era of Machine Learning, Deep Learning comes into place. Deep Learning gives the machines a way to think when trained from previous data and encounters. This paper will provide the application of Deep Learning in various fields.