National Institute of Technology, Karnataka

About: National Institute of Technology, Karnataka is a education organization based out in Mangalore, Karnataka, India. It is known for research contribution in the topics: Corrosion & Cloud computing. The organization has 5017 authors who have published 7057 publications receiving 70367 citations.

Application and Evaluation of Random Forest Classifier Technique for Fault Detection in Bioreactor Operation

Abstract: Bioreactors and associated bioprocesses are quite complex and nonlinear in nature. A small change in initial condition can greatly alter the output product quality. It is pretty difficult at times to model the system mathematically. In this work, the fault detection problem is studied in the context of bioreactors, mainly, a reactor from the penicillin production process. It is very important to identify the faults in a live process to avoid product quality deterioration. We have focused on the process history-based methods to identify the faults in a bioreactor. We want to introduce random forest (RF), a powerful machine learning algorithm, to identify several types of faults in a bioreactor. The algorithm is simple, easy to use, shows very good generalization ability without compromising much on the classification accuracies, and also has an ability to give variable importance as a part of the algorithm output. We compared its performance with two popular methods, namely support vector machines (SVM) an...

Industrial Automation Using Internet of Things

Abstract: This chapter presents a comprehensive view of Industrial Automation using internet of things (IIoT). Advanced Industries are ushering in a new age of physical production backed by the information-based economy. The term Industrie 4.0 refers to the 4th paradigm shift in production, in which intelligent manufacturing technology is interconnected with physical machines. IIoT is basically a convergence of industrial systems with advanced, near-real-time computing and analytics, powered by low cost and low power sensing devices leveraging global internet connectivity. The key benefits of Industrial IoT systems are a) improved operational efficiency and productivity b) reduced maintenance costs c) improved asset utilization, monitoring and maintenance d) development of new business models e) product innovation and f) enhanced safety. Key parameters that impact Industrial Automation are a) Security b) Data Integrity c) Interoperability d) Latency e) Scalability, Reliability, and Availability f) Fault tolerance and Safety, and g) Maintainability, Serviceability, and Programmability. Industrial Automation Using Internet of Things

Characteristic mode-based compact circularly polarized metasurface antenna for in-band RCS reduction

Abstract: This paper presents a novel design of a low profile circularly polarized (CP) metasurface (MTS) antenna with in-band radar cross-section (RCS) reduction property. The MTS is loaded as a superstrate on slot antenna and it can be viewed as a polarization-dependent MTS (PDMTS). The rectangular patch-based PDMTS is analyzed using characteristic mode analysis to find two orthogonal degenerate modes, which produces CP waves. Linearly polarized slot antenna is used to excite the PDMTS. The performance of PDMTS loaded slot antenna is analyzed numerically using full-wave analysis method. The PDMTS CP antenna is fabricated and its performance is tested experimentally. The proposed antenna has a compact structure and it has an overall size of at the resonant frequency of 5.86 GHz. The simulated results are in well agreement with the measured results and it is well suited for C-band Radar and Satellite communication.

Noniterative Method for Combined Acoustic-Electrical Partial Discharge Source Localization

Abstract: The combined acoustic-electrical system is used in the factory or plant environment for the partial discharge (PD) source localization in power transformers. A noniterative method for this combined acoustic-electrical PD-locator-system is devised and presented in this paper for the first time. It employs three acoustic emission (AE) sensors. The proposed method is compared with the existing noniterative method used in the all-acoustic system, which employs four AE sensors. The comparative study shows that the proposed method can locate the PD source irrespective of its position within the tank, whereas the prevailing noniterative method for the all-acoustic system fails to locate the PD source at certain positions within the tank. The effect of the sensor positioning on the performance of the method is studied, and some guidelines for the sensor placement on the transformers tank wall in a factory or plant environment are suggested. The proposed method is also applied to the data taken from the published literature. The localization results are compared with those of an existing iterative method (Newton's method) to prove its superiority in terms of computational time.