Sökning: "Fault detection"

Visar resultat 1 - 5 av 133 uppsatser innehållade orden Fault detection.

  1. 1. Metodik för utveckling av Proof of Concept inom Internet of Things : XPD (eXtreme PoC Development) en ny projektmetodik som säkrar affärsnyttan i utvecklingen av IoT-lösningar

    Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS); KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Fridtjof Aleström; Emil Almgren; [2019]
    Nyckelord :Internet of Things; IoT; Proof-of-Concept; PoC; Projektmetodik; XPD;

    Sammanfattning :  Internet of Things (IoT) is a phenomenon that involves providing things or objects with sensors and internet connection. The field of IoT is growing rapidly and there are strong incentives for companies to follow the trend to develop and create an IoT. LÄS MER

  2. 2. Vibration analysis for predictive maintenance of a rotary pump. : Optimal accelerometer configuration based on vibration analysis for cavitation detection of a bi-winged positive displacement pump.

    Master-uppsats, KTH/Skolan för industriell teknik och management (ITM)

    Författare :Gustav Osswald; [2019]
    Nyckelord :;

    Sammanfattning : Predictive maintenance based on condition monitoring uses sensor and system data to prevent damage, in advance to a failure occurring, allowing for a service to be performed at an optimal position in time. Condition based predictive maintenance estimates time of system failure based on a priori information, which has shown to be much more cost effective than traditional maintenance methods. LÄS MER

  3. 3. Methods to identify broken neutral fault in LV distribution grids by using existing smart meters infrastructure

    Master-uppsats, KTH/Skolan för industriell teknik och management (ITM)

    Författare :Christoforos Menos-Aikateriniadis; [2019]
    Nyckelord :;

    Sammanfattning : The vast majority of Swedish utility network customers for nearly a decade has been supported by Advanced Metering Management (AMM) systems, including smart meters. Vattenfall´s modern smart meters enable a new level of monitoring for LV networks and improved MV network supervision. LÄS MER

  4. 4. Functional Testing of the Electrical Power System of the MIST Satellite

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Stefano Barra; [2019]
    Nyckelord :;

    Sammanfattning : The Electrical Power System is the key subsystem for the survival of the satellite.It not only supplies power to the satellite by keeping the battery adequatelycharged, but it also provides crucial fault detection and recovery functions. LÄS MER

  5. 5. Evaluation of machine learning methods for anomaly detection in combined heat and power plant

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Fredrik Carls; [2019]
    Nyckelord :Machine Learning; Anomaly detection; Fault detection; Health condition monitoring; Sensor surveillance; PHM; CHP Plant Boilers; k-Nearest Neighbor; One-Class Support Vector Machine; Auto-encoder; Maskininlärning; Anomalidetektion; Feldetektering; Tillståndsbevakning; Sensorövervakning; PHM; Kraftvärmeverkpannor; k-Nearest Neighbor; One-Class Support Vector Ma- chine; Auto-encoder;

    Sammanfattning : In the hope to increase the detection rate of faults in combined heat and power plant boilers thus lowering unplanned maintenance three machine learning models are constructed and evaluated. The algorithms; k-Nearest Neighbor, One-Class Support Vector Machine, and Auto-encoder have a proven track record in research for anomaly detection, but are relatively unexplored for industrial applications such as this one due to the difficulty in collecting non-artificial labeled data in the field. LÄS MER