Player is loading...
Intelligent feed-back on user comfort in low energy buildings
Rui Oliveira, University of Aveiro, PT
Tuesday, May 7, 2019 · 10:09 a.m. · 09m 40s
Embed
Transcriptions
Note: this content has been automatically generated.
00:00:00
so when morning uh everyone uh my name is really via
00:00:05
uh i'm a p. h. d. student from a portable a diversity of operating a my
00:00:12
work is is provided by john camp remove the same trickle maybe and and long period
00:00:20
and uh my work is about to the the
00:00:23
intelligence feedback on user comfort in low energy buildings
00:00:34
yeah
00:00:36
ah ha ha ha ha ah okay
00:00:44
so we know that the the buildings are the um have a significant uh
00:00:49
a part or the energy demand and the consequently a d. c. o. two emissions
00:00:55
that's a a lot of incentives and the directives uh um
00:01:00
and being that a lot but to motivate the energy building renovation
00:01:05
so at the incision a tower the implementation
00:01:08
of smart buildings concept um could be a challenge
00:01:13
so for these we believe that artificial intelligence uh could be the solution
00:01:21
regarding the oddities of my disease uh the smart
00:01:25
buildings have a uh a lot of smart sensors
00:01:29
and they uh produce a lot of data a lot of information uh about the the the buildings
00:01:36
so the compiler everything that i can map data mining and
00:01:40
artificial intelligence uh will be need do you need it and the
00:01:46
several researches are doing the a lot of studies uh about the energy efficient but
00:01:53
uh also we need a um studies complying
00:01:58
energy efficient thermal comfort and indoor air quality um
00:02:06
and then uh taught demise the these requirements um are something
00:02:11
dark to to apply so and we stick approach is needed
00:02:16
where the concerns such as well uh l. c. l. c. buildings
00:02:21
well being quality of life and in our environment quality quality is needed
00:02:28
so in the past the research uh work um
00:02:33
i made a lot of work with the uh uh measuring the buildings a timber to
00:02:39
room e. d. d. eh i made a lot of air tight pants with a border test
00:02:44
uh to measure the they appear permeability all the
00:02:47
buildings and also uh them all and the energy simulation
00:02:52
uh using in this case uh the energy plus a software um
00:02:59
and also in finally a building organisation such as the organisational
00:03:04
thermal insulation windows in systems for cooling and for for eating
00:03:12
moving on uh to use uh the uh uh uh we stick approach
00:03:17
we want to develop a machine learning a base it on competitive smart algorithm taking account
00:03:23
uh the real time input data in the buildings from a lot of sensors
00:03:30
um that we can coupling that sort
00:03:35
we can capping the the energy in our environment quite tedious
00:03:40
weather forecasting and of course uh the monitoring data to
00:03:44
um produce or um that give us the energy efficient
00:03:51
efficiency either demo environment and also in the final the shaping of the user be able
00:03:59
so about that and the uh um focus
00:04:02
on the quality of a indoor air um
00:04:08
the the goal the all these framework uh that you try
00:04:12
to build we'll the we need the feedback to the users
00:04:17
uh uh in the eye perspective a way of the air
00:04:21
quality of the air quality range um as you know as
00:04:25
you can see in the table so in a smart man
00:04:29
or we want to warning words like advisable should masts um
00:04:36
for the um for the users so uh
00:04:42
in that short term like uh these actions you need to
00:04:47
to um to make to make now or in along the um
00:04:53
we no longer a ten actions that we we can do a um during the time
00:05:01
so the
00:05:04
to get these actions and the disease our pair barely mean our tasks
00:05:09
uh the trying to construct a the zero to model in the in the the the softer
00:05:15
so we need the test cells in either the tools for example like a city scene that are we trying
00:05:21
to to use and to make the simulations of c. e. o.'s english uh not show two in the inside
00:05:28
in this case we we trying to seem like these for one's own
00:05:33
for now and then we'll we'll uh produce for a a more zones
00:05:38
more sources of zero to so this is a typical sell best with
00:05:43
a volume cheaper for with a two point seven uh meters of the eight
00:05:50
there is a a there is a um is a traditional massive construction okay
00:05:57
and we use these sensors
00:06:01
this is a prototype from the single company and that
00:06:06
they provide us this year who uh in the inside
00:06:10
the presence of the people inside also the temperature and immediately so
00:06:16
a lot of parameters in one and a little uh a smart sensor
00:06:23
is not sufficient he finished okay but is a
00:06:26
prototype that we trying to test that's you the um
00:06:34
but to try to do with trying to the best uh these sensors so
00:06:39
firstly uh we need to know uh um they have changed the right or
00:06:44
the the the test to use in our uh in zero to uh equation
00:06:50
so for that we used the matter that all the big a the the decay metal to uh to know
00:06:56
the air change rate and we that's the the slope of
00:07:00
the line equation we can get these uh eh change right
00:07:05
so
00:07:07
um
00:07:09
we made a lot of uh um monotony and the the is the study
00:07:18
for example uh we can leave the instructions to the companies because they need
00:07:23
uh where is the place the or the the best position of the sensor to catch the
00:07:28
presence in a presence in the also the other parameters with that trust will uh uh um
00:07:36
uh that's all a recording so uh we found that uh yeah we we we
00:07:42
tested in different places and the in different positions of the in a vertical um
00:07:49
like like in the close to the roof a close to the the thing the pavement
00:07:54
uh in the aisle for the the height of the the
00:07:58
room and also close to the ceiling so and the um
00:08:03
we it's possible to group concluded that this year to
00:08:06
consideration is not a influenced by the since a position so
00:08:11
we can put the sensor where we want far away from the kids
00:08:15
far away from the pets and the of course we that trust will recording
00:08:25
as a feature to uh works uh we
00:08:29
will try to uh um apply the framework
00:08:33
the bayes on relative in using artificial intelligence into
00:08:37
case studies one case study in speech one in button
00:08:42
button um that we present a high quality of construction and then in portugal
00:08:49
uh i second the a case study that represent a low quality or construction pieces
00:08:57
our silence so how to get the building smarts smarter
00:09:02
we can get in to see does that to the scene does that uh i think
00:09:09
this is i think in a microscopic way uh does work with and to contribute for the
00:09:15
uh the some uh what we would for a
00:09:19
smart building with a smart algorithm using artificial intelligence
00:09:24
giving feedback to the user's supporting novel energy control systems
00:09:29
and and it finally assuring demo comfort and indoor air quality
Conference Program
Intelligent feed-back on user comfort in low energy buildings
Rui Oliveira, University of Aveiro, PT
May 7, 2019 · 10:09 a.m.
169 views
Urban morphology and building PV energy production
Kin Ho Poon, National University of Singapore, SG
May 7, 2019 · 10:30 a.m.
220 views
Urban morphology, energy needs and artificial intelligence
Roberto Boghetti, University of Pisa, IT
May 7, 2019 · 10:51 a.m.
121 views
Distributed simulation applied to multi-networks urban energy systems design
Pablo Puerto, CREM / Mines d’Albi, F
May 7, 2019 · 11:13 a.m.
113 views
Les défis du domaine Energy Informatics
Jérôme Kämpf, Idiap Research Institute
May 7, 2019 · 11:32 a.m.
528 views
The Ark Energy
Laura Schwery, Fondation The Ark
May 7, 2019 · 1:38 p.m.
228 views
Industrie du futur
Richard Pasquier, HEIA-FR et Benedikt Ramsauer, Swiss-SDI
May 7, 2019 · 1:46 p.m.
281 views
Naïade : gestion optimisée d’un réseau d’eau
Benoît Golay, Institut Icare
May 7, 2019 · 2:07 p.m.
Open data des villes
Duccio Piovani, Research Lead - Data Science, nam.R
May 7, 2019 · 2:27 p.m.
IA, L’entreprise augmentée
Dominique Genoud, HES-SO Valais-Wallis
May 7, 2019 · 2:52 p.m.
Planifier le quartier de demain avec l’IA
Diane von Gunten, CREM
May 7, 2019 · 3:14 p.m.
Recommended talks
Pr. Dominique Genoud & Jérôme Treboux - Integrating machine learning and AI in practical energy applications : a review of these last 10 years activities at the Institute of Information Systems
Pr. Dominique Genoud & Jérôme Treboux, HES-SO Valais-Wallis
Nov. 15, 2021 · 10:46 a.m.
Vers une réforme du design du marché de l’électricité Suisse: Pratiques et leçons tirées des expériences internationales
Fabien Roques, Senior Vice Président Compass Lexecon / Associate Prof. Paris Dauphine
Oct. 5, 2016 · 10:46 a.m.
268 views