MERCon - 2020

Permanent URI for this collectionhttp://192.248.9.226/handle/123/16315

Browse

Browsing MERCon - 2020 by Author "Abeykoon, AMHS"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    item: Conference-Full-text
    A machine learning approach for nilm based on superimposed current profiles
    (IEEE, 2020-07) Abeykoon, AMHS; Perera, APS; Sanjeewika, RK; Matharage, MDNV; Abeysinghe, AP; Weeraddana, C; Edussooriya, CUS; Abeysooriya, RP
    This research focuses on identifying a new implementation of a machine learning approach for Nonintrusive load monitoring (NILM). We mathematically superimpose current profiles of individual appliances and compare against the actual combinational current profiles. This simple yet effective method is tested on combinations of 6 household devices in a typical low voltage residential installation and the high accuracy of correct identification confirms the proposed method is feasible. The proposed method eases the burden of the training phase which is considered as an inherent limitation of all supervised deep learning NILM models. We deploy the method on a Raspberry Pi 3 providing a solution to increase the scalability of NILM
  • Thumbnail Image
    item: Conference-Full-text
    Sensor-less detection of wheel alignment error for a wheeled mobile robot using the disturbance observer
    (IEEE, 2020-07) Paudel, S; Abeykoon, AMHS; Arunya, SD; Weeraddana, C; Edussooriya, CUS; Abeysooriya, RP
    Estimating the wheel camber error is a challenging task without attaching an additional sensors or mechanisms on the Electrical vehicles. Almost all the electrical automobiles are using several combinations of sensors to detect the camber errors, toe in/out errors and other wheel conditions measurements. This paper introduces a simple method to identify the camber and toe in/out error using disturbance observer(DOB) without using any additional sensors or mechanisms. Proposed concept is practically demonstrated by using a differential drive mobile robot. The Wheeled mobile robot (WMR) is commanded to run on a predefined path and torque profile is observed to identify whether wheels of the vehicles are misaligned.