Datum
do 17 maart 2022 | 15:00
Dit evenement heeft reeds plaatsgevonden.
Bekijk de agenda voor aankomende evenementen en trainingen.
Organisator
DGBC
De sector Verwarming, Ventilatie en Airconditioning (HVAC) is verantwoordelijk voor een groot deel van het totale wereldwijde energieverbruik. Een aanzienlijk deel wordt veroorzaakt door onjuiste bediening van besturingen en onjuist onderhoud. HVAC-systemen worden steeds complexer, vooral als gevolg van multi-commodity energiebronnen, en als gevolg daarvan zal de kans op storingen in systemen en controles toenemen. Tijdens dit webinar zal Arie Taal hier verder op ingaan.
The Heating, Ventilation and Air Conditioning (HVAC) sector is responsible for a large part of the total global energy consumption, a significant part of which is caused by incorrect operation of controls and incorrect maintenance.
HVAC systems are becoming increasingly complex, especially due to multi-commodity energy sources, and as a result, the potential for failures in systems and controls will increase. That is why energy performance diagnostic systems are paramount. However, despite much research on Fault Detection and Diagnosis (FDD) methods for HVAC systems, they are rarely applied. An important reason is that the proposed methods differ from the design approaches of HVAC designers who use process and instrumentation diagrams (P&IDs).
The so-called 4S3F method made a step forward towards a systematic and automated multi-system and multi-level fault and energy performance diagnosis by developing an energy performance FDD architecture based on information embedded in P&IDs. This new approach combines systems theory with data analysis. In the 4S3F method, the symptoms and faults are classified into 4 types of symptoms (balances, operating conditions (OS) and energy performances (EP) anomalies and additional information) and 3 types of faults (component, control and model faults). The detection (of symptoms) and diagnosis (identification of faults) phases are separated. The results of the symptom detection are imported in a DBN (Diagnostic Bayesian Network) method in which faults and symptom are linked in a network. The DBN software estimates the probabilities of the presence of faults.
Speaker: Arie Taal (Haagse Hogeschool)
Arie Taal has been training Mechanical Engineering students at The Hague University of Applied Sciences for over 30 years. He is an active researcher within the Energy in Transition research group at HHS and is part of the Mission Zero knowledge centre.
