Ranjit Kumar TA

Dry spinning is a popular method of spinning dissolved polymers such as polypropylene, acrylics and modacrylics. In this process, the polymer is dissolved in the organic solvent at high temperature and is extruded through a spinneret having hundreds of holes. A stream of conditioned air is passed through the nozzle placed across the extruded fibers in the air gap to initiate the cooling of polymer/fiber. Polymer stretching in this air gap helps in achieving the desired fiber tenacity. Hence the… Show more

Dry spinning is a popular method of spinning dissolved polymers such as polypropylene, acrylics and modacrylics. In this process, the polymer is dissolved in the organic solvent at high temperature and is extruded through a spinneret having hundreds of holes. A stream of conditioned air is passed through the nozzle placed across the extruded fibers in the air gap to initiate the cooling of polymer/fiber. Polymer stretching in this air gap helps in achieving the desired fiber tenacity. Hence the air gap and the cooling air properties play crucial roles in stable spinning.
The present work focusses on understanding the energy transport phenomena between the cooling air and the fibers in the air gap. Dry spinning module in commercial CFD solver, ANSYS Fluent, is used to account for the two way coupling between the fibers and the cooling air. Due to the limitation in this module, the fiber is assumed to behave as a Newtonian fluid. The convective energy transport between the fibers and the surrounding air has been modeled using the Kase-Matsuo correlation for the cross flow conditions. The model does not account for the fiber dynamics and the mass transfer between the fiber and the air. The model predictions are validated with the experimental trials in terms of the velocity and the temperature of the air in the air gap. The model provides insights on the profiles of fiber temperature, strain rates, diameter, velocity etc. at various points along the fiber length in the air gap. These profiles are rather difficult to measure during experiments in these prevailing conditions. To gain further understanding into the air-fiber interactions, the effects of temperature & mass flow rate of the cooling air, spinneret hole density and initial fiber diameter are investigated. This developed understanding can help in achieving the stable spinning. Show less

Bearings constitute a crucial part of machinery that need to be continuously
monitored. Major breakdowns can be prevented if bearing defects are identified at the earlier
stage. Sound signals of the bearings can be used to continuously monitor bearing life. This
paper uses sound signals acquired in bearings under healthy and simulated faulty conditions for
the purpose of fault diagnosis through machine learning approach. The statistical features were
extracted from the sound… Show more

Bearings constitute a crucial part of machinery that need to be continuously
monitored. Major breakdowns can be prevented if bearing defects are identified at the earlier
stage. Sound signals of the bearings can be used to continuously monitor bearing life. This
paper uses sound signals acquired in bearings under healthy and simulated faulty conditions for
the purpose of fault diagnosis through machine learning approach. The statistical features were
extracted from the sound signals. Significantly important features were selected using J48
decision tree algorithm. Support Vector Machine (SVM) is used as a classifier. The selected
features were given as inputs for the c-SVM and ν-SVM (nu – SVM) model of SVM and their
classification accuracies were compared. Show less

Bearing is one of vital transmission elements, finding numerous applications in small, medium and large machineries. Vibration signals of a rotating machine contain the dynamic information about its operating condition. This paper uses the vibration signals acquired in bearings under healthy and simulated faulty conditions for the purpose of fault diagnosis through machine learning approach. The descriptive statistical features were extracted from vibration signals and the important attributes… Show more

Bearing is one of vital transmission elements, finding numerous applications in small, medium and large machineries. Vibration signals of a rotating machine contain the dynamic information about its operating condition. This paper uses the vibration signals acquired in bearings under healthy and simulated faulty conditions for the purpose of fault diagnosis through machine learning approach. The descriptive statistical features were extracted from vibration signals and the important attributes were selected using decision tree (dimensionality reduction).The selected features were then used for classification using J48 decision tree algorithm. The paper also discusses the effect of various parameters on classification accuracy. Show less