Browsing by Author "Karjalainen, Joonas"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Implementation of Automated Software Testing Tools for Machine Automation
    (2017-12-11) Haapamäki, Tomi; Karjalainen, Joonas; Sähkötekniikan korkeakoulu; Visala, Arto
    Automation software is an increasingly important and complex component of industrial systems and machines. Efficient testing of the software has therefore become a major concern, and automated testing is viewed as an effective solution for the issue. A software development method known as continuous integration particularly takes advantage of automated testing by performing tests frequently in order to reveal defects early. However, in the field of automation systems the role of automated testing has been limited by the challenging properties of the software, such as the involvement of physical hardware. This master's thesis studies the feasibility of automated testing of programmable logic controller software in the context of a continuous integration process. In addition, the suitability of hardware-in-the-loop simulation and OPC Unified Architecture in this type of application is considered. The literary review of the thesis examines the literature related to automated software testing and continuous integration. The practical section presents the design and implementation of an automated testing system for industrial automation software. The system was designed particularly for industrial cranes. The results of this thesis suggest that automated testing in the context of continuous integration can be applied in industrial automation software development. However, there may be considerable challenges involved. Hardware-in-the-loop simulation proved to be a generally suitable testing environment, but the quality of the simulation can limit the portion of automatable test cases. In addition, OPC Unified Architecture was recognized as an effective interoperability solution between the testing system and the logic controller.
  • Thumbnail Image
    Item
    Predicting Electricity Outages Caused by Convective Storms
    (2018-08-17) Tervo, Roope; Karjalainen, Joonas; Jung, Alexander; Finnish Meteorological Institute; Department of Computer Science
    We consider the problem of predicting power outages in an electrical power grid due to hazards produced by convective storms. These storms produce extreme weather phenomena such as intense wind, tornadoes and lightning over a small area. In this paper, we discuss the application of state-of-the-art machine learning techniques, such as random forest classifiers and deep neural networks, to predict the amount of damage caused by storms. We cast this application as a classification problem where the goal is to classify storm cells into a finite number of classes, each corresponding to a certain amount of expected damage. The classification method use as input features estimates for storm cell location and movement which has to be extracted from the raw data. A main challenge of this application is that the training data is heavily imbalanced as the occurrence of extreme weather events is rare. In order to address this issue, we applied SMOTE technique.