Browsing by Author "Viswanath, S."

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Analysis of piezoelectric composite beams and plates with multiple delaminations
    (2006) Raja, S.; Prathima Adya, H.P.; Viswanath, S.
    In the present work, the effect of delamination or debonding on the static and dynamic characteristics of laminated piezoelectric beams and plates is studied. A four-noded quadrilateral shear flexible plate element is developed to model the damages in composite substrate and in piezoelectric layers. The elastic stiffness and electro-elastic stiffness degradations are introduced at the elemental level through coupled constitutive relations. The undamaged structure is modeled as a single laminate while the delaminated region is modeled as sublaminates whose interface contains the desired delamination or debonding. The continuity of displacement is maintained across the delaminated edge by imposing the strain-based multipoint constraints. Numerical studies are conducted on composite specimens with surface bonded active layers. The results are presented to evaluate the performance of these smart structures in the presence of delamination. For actuators, the performance is measured in terms of the achievable deflection control and in sensors as a measurable output voltage. It is observed that actuator and sensor debonding degrade the capabilities of active materials significantly. Therefore, the study concludes that a damage tolerant approach is essential for the design of smart structural systems to account for damage-induced uncertainty in the functional properties of smart actuators and sensors. Copyright © 2006 SAGE Publications.
  • No Thumbnail Available
    Item
    Deep Learning Based LSTM and SeqToSeq Models to Detect Monsoon Spells of India
    (2019) Viswanath, S.; Saha, M.; Mitra, P.; Nanjundiah, R.S.
    Monsoon spells are important climatic phenomenon modulating the quality and quantity of monsoon over a year. India being an agricultural country, identification of monsoon spells is extremely important to plan agricultural policies following the phases of monsoon to attain maximum productivity. Monsoon spells� detection involve analyzing and predicting monsoon at daily levels which make it more challenging as daily-variability is higher as compared to monsoon over a month or an year. In this article, deep-learning based long short-term memory and sequence-to-sequence models are utilized to classify monsoon days, which are finally assembled to detect the spells. Dry and wet days are classified with precision of 0.95 and 0.87, respectively. Break spells are observed to be forecast with higher accuracy than the active spells. Additionally, sequence-to-sequence model is noted to perform superior to that of long-short term memory model. The proposed models also outperform traditional classification models for monsoon spell detection. � Springer Nature Switzerland AG 2019.