Note: Descriptions are shown in the official language in which they were submitted.
A METHOD AND SYSTEM FOR AUTOMATIC DETECTION OF
MALFUNCTIONS/INEFFICIENT HOUSEHOLD ELECTRONIC HEATING DEVICE
Field of the invention
The present invention generally relates to the field of monitoring electronic
appliances, and
particularly to the field of automatic detection of household appliance
malfunction of
inefficiency.
Background art
Summary of the present invention
The present invention provides a method for automatic detection malfunction or
inefficiency of electronic heating device, implemented by a server module and
a plurality
of household client modules, wherein each of said server module and plurality
of
household client modules comprising one or more processors, operatively
coupled to
non-transitory computer readable storage devices, on which are stored modules
of
instruction code, wherein execution of said instruction code by said one or
more processors implements the following actions:
- acquiring data related to each monitored household for generating a
training set,
including at least one of, power consumption of each electronic heating
device,
power consumption of each household, household profile parameters, and
household
residents' profile parameters;
- training an electric Heating classification model for identifying
existence of electronic
heating based on load data
- Determining the of existence of electronic heating and type of the device
based on
the Heating classification model;
- Training an insights model based on daily load pattern to identify
activation and
activation pattern of the electronic heating devices using Periodic secured
household
power consumption readings with no temperature not including summer period;
- Prediction Detection and Identification of HVAC activation, activation
pattern based
on pattern insights model using Periodic secured household power consumption
readings with no temperature of summer period; and
Date Recue/Date Received 2020-05-27
- Clustering aggregating in winter time activation pattern into Bins
based on
temperature for identifying malfunctioning or inefficiency based on HVAC
behavior
in different temp bins.
According to some embodiments of the present invention the method further
comprising
the step of determining malfunction or inefficiency based on how the
electronic heating
device/HVAC performs on different weather scenarios by identifying
exaptational
activation pattern in regular temperature.
comprising the step of training an ML model based on winter labels and the
aggregated
metrics in temp bin and Identifying deviations of the HVAC performance at each
temperature bin) for determining if the HVAC has a malfunction/ inefficient or
not.
According to some embodiments of the present invention the method further
comprising
the step of training an electric Heating classification model to identify
existence of steady
load electronic heating based on load data
According to some embodiments of the present invention the acquired data
further
include Thermostats reading data
According to some embodiments of the present invention the clarification model
is
further based on Checking Sub-hourly load patterns ¨ identifying if the load
pattern have
similar pattern to know types of load pattern which indicates HVAC activity
based
According to some embodiments of the present invention the clarification model
is
further based on Checking correlation between the load signal and the
temperature
signal.
According to some embodiments of the present invention the insights model is
using
Multi-output convolutional network.
According to some embodiments of the present invention the insights model
determine
activation pattern of HVAC including several metrics concerning the
performance of the
HVAC including at least one of: percent of time active, Count of on/off
switches,
Activations during the nighttime.
The present invention provides a system for automatic detection malfunction or
inefficiency of electronic heating device, implemented by a server module and
a plurality
2
Date Recue/Date Received 2020-05-27
of household client modules, wherein each of said server module and plurality
of
household client modules comprising one or more processors, operatively
coupled to
non-transitory computer readable storage devices, on which are stored modules
of
instruction code, wherein execution of said instruction code by said one or
more processors implements the following modules:
- acquisition module for aggregating and acquiring data related to each
monitored
household for generating a training set, including at least one of, power
consumption
of each electronic heating device, power consumption of each household,
household
profile parameters, and household residents' profile parameters;
- Electric Heating classification Module configured for training an
electric Heating
classification model for identifying existence of electronic heating based on
load data
- Prediction module for electrical heating configured to determine the of
existence of
electronic heating and type of the device based on the Heating classification
model;
- insights model module configured for training an insights model based
Daily load
pattern to identify activation and activation pattern of the electronic
heating devices
using Periodic secured household power consumption readings with no
temperature
not including summer period;
- Prediction module of HVAC activation pattern configured for prediction,
detection and Identification of HVAC activation, activation pattern based on
pattern
insights model using Periodic secured household power consumption readings
with
no temperature of summer period;
According to some embodiments of the present invention the prediction module
further comprising the step of determining malfunction or inefficiency based
on
how the electronic heating device/HVAC performs on different weather scenarios
by
identifying exaptational activation pattern in regular temperature.
According to some embodiments of the present invention prediction module
further
comprising the step of training an ML model based on winter labels and the
aggregated metrics in temp bin and Identifying deviations of the HVAC
performance at each temperature bin) for determining if the HVAC has a
malfunction
or inefficient or not.
3
Date Recue/Date Received 2020-05-27
According to some embodiments of the present invention the training modules
further
comprising the step of training an electric Heating classification model to
identify
existence of steady load electronic heating based on load data
According to some embodiments of the present invention wherein the acquired
data
further include Thermostats reading data.
According to some embodiments of the present invention the clarification model
is
further based on Checking Sub-hourly load patterns ¨ identifying if the load
pattern
have similar pattern to know types of load pattern which indicates HVAC
activity.
According to some embodiments of the present invention the clarification model
is
further based on Checking correlation between the load signal and the
temperature
signal.
According to some embodiments of the present invention the insights model is
using
Multi-output convolutional network.
According to some embodiments of the present invention the insights model
determining activation pattern of HVAC including several metrics concerning
the
performance of the HVAC including at least one of: percent of time active,
Count of
on/off switches, Activations during the nighttime.
Brief description of the drawings
For a better understanding of various embodiments of the invention and to show
how the same
may be carried into effect, reference will now be made, purely by way of
example, to the
accompanying drawings in which like numerals designate corresponding elements
or sections
throughout.
With specific reference now to the drawings in detail, it is stressed that the
particulars shown are
by way of example and for purposes of illustrative discussion of the preferred
embodiments of
the present invention only, and are presented in the cause of providing what
is believed to be the
most useful and readily understood description of the principles and
conceptual aspects of the
invention. In this regard, no attempt is made to show structural details of
the invention in more
detail than is necessary for a fundamental understanding of the invention, the
description taken
4
Date Recue/Date Received 2020-05-27
with the drawings making apparent to those skilled in the art how the several
forms of the
invention may be embodied in practice. In the accompanying drawings:
Figure 1 presents a block diagram depicting an overview of an electronic
heating malfunction
system in accordance with some embodiments of the present invention.
Figure 2 present high level overviews of the models of Figure 1 in accordance
with some
embodiments of the present invention.
Figure 3 is a flow diagram, depicting the function of a data acquisition
module according to
some embodiments of the present invention.
Figure 4 is a flow diagram, depicting the function of a Electric Heating
classification model
according to some embodiments of the present invention.
Figure 5 is a flow diagram, depicting the function of Electric Heating
prediction model
according to some embodiments of the present invention.
Figure 6 is a flow diagram, depicting the function of the insights model
Training set Daily load
pattern module according to some embodiments of the present invention.
Figure 7 is a flow diagram, depicting the function of the insights model
Prediction Detection and
Identification of HVAC according to some embodiments of the present invention.
Figure 8 is a flow diagram, depicting the function of the Clustering
activation pattern into Bins
based on temperature according to some embodiments of the present invention.
Figure 9 is a flow diagram, depicting the functionality of the malfunction
training and prediction
module (ML),according to some embodiments of the present invention.
Detailed description of the drawings
Figure 1 presents a block diagram depicting an overview of a electronic
heating malfunction
systems in accordance with some embodiments of the present invention.
The electronic heating malfunction system is comprised of two sub systems :
subsystem 100A
for identifying existence of an electronic heating device, specifically the
existence of HVAC
activation and a the second subsystem 100B for identifying/prediction of
malfunctioning
HVAC.
The first subsystem A, is comprised of: Disaggregation Data acquisition module
1200 reading
periodic household power consumption readings with temperature data on
summer/winter time
Date Recue/Date Received 2020-05-27
(100) , for proving training data to Electric Heating classification model
1300A, training to
identify existence of electronic heating based on load data.
Additionally or alternatively the system comprises an Electric Heating
classification model
1300B, for training to identify existence of steady load electronic heating
based on load data
Based on one of the classification modules using the activation on load data
of current tested
house holds after the training period , is determined the existence of the of
an electronic heating
appliance.
The second subsystem is comprised of: insights model 1500 for training daily
load pattern to
identify activation and activation pattern using training data 1600 of
periodic secured household
power consumption readings with no temperature of summer period and regardless
of time in
day and prediction module 1700 for Detection and Identification of HVAC
Activation and
activation pattern based on pattern insights model. The second subsystem
activation is based on
the identification data of the existence of HVAC appliance in the household.
The subsystem B is further comprised of Aggregation model For training
Clustered/aggregated
in winter time activation pattern into Bins based on temperature for
identifying malfunctioning
of the HVAC or inefficient working of the HVAC based on HVAC behavior in
different temp
bins. The malfunction or inefficiency determination is based on how the HVAC
performs on
different weather scenarios.(identifying exaptational activation pattern in
"regular temperature).
Additionally or alternatively the system comprise malfunction or inefficiency
training and
prediction module (ML) 1900
Figure 2 present high-level overviews of the models of Figure 1 in accordance
with some
embodiments of the present invention.
Modules 200a & 200b are configured to interface the server module 100 using
any type of wired
or wireless data communication standard (e.g. LAN, WAN, WiFi, GSM, 3GPP, LTE
etc.), and
convey to the server 100 data pertaining to a specific household. This data
includes at least one
of: the household's properties, the household's overall power consumption,
concurrent
temperature measurements, Thermostats reading data and data relating to
electronic heating
appliance installed therein.
The training set household client 200a is comprised of at least one of the
following sub modules:
6
Date Recue/Date Received 2020-05-27
= electronic heating appliance agent module 2100,
= Household power meter interface 2200a,
= Thermostats reader 2300, and
= Client alerts module 2400.
The global household client 200b is comprised of the following sub module:
= Household power meter interface 2200b
The electronic heating appliance agent module 2100, acquires data relating to
at least one of:
electronic heating appliance activation time; and
The Household power meter interface 2200a, acquires the power consumption of
the household
over time. According to some embodiments, the Household power meter interface
2200a obtains
household power consumption readings every 15/30/60 minutes from a smart
household power
meter.
The client configuration module 2300 provides an interface for introducing
household-specific
parameters. These parameters include at least one of:
= the electronic heating appliance properties (e.g. make and model);
= residents' profile parameters (e.g. number of residents, household
occupancy
throughout the day).
The server 100 is a module implemented in software or hardware or any
combination thereof,
configured to interface a plurality of household client modules 200a & 200b,
according to some
embodiments. The server 100 obtains from each of the plurality of household
client modules
200a & 200b data pertaining to each respective household, said data including
at least part of:
= electronic heating appliance activation time;
= thermostat reading;
= Frequent regular household power consumption readings;
= Indoor temperature; and
= Resident profile parameters.
7
Date Recue/Date Received 2020-05-27
According to some embodiments, the server module 100 also communicates with an
administrative client module (not shown), which provides an administrative
interface for system
configuration, real-time alerts and production of historical reports.
The server module 100 includes several sub modules for analyzing said obtained
data,
identifying electronic heating appliance as efficient or inefficient, and
alerting against suspected
conditions of inefficiency or malfunction.
In first model 1000A, the sub-modules include at least one of the following:
= The data acquisition module 1100,
= Electric Heating classification model 1300,
= Prediction module for electrical heating 1400
= insights model Training set Daily load pattern module 1500
= Prediction module for HVAC activation pattern 1700
= Aggregation model by temp bin module 1800
= malfunction inefficiency training and prediction module (ML) 1900;
The data acquisition module 1100 accumulates real-time data from multiple
private client
modules, and stores it in a database for further processing.
Figure 3 is a flow diagram, depicting the function of a data acquisition
module according to
some embodiments of the present invention. This module resides within the
server 100, and
accumulates data pertaining to specific households, both within the household
training group and
beyond it. The data accumulation module 1100 data, as detailed bellow, in a
database for further
analysis:
Acquiring periodic power consumption of each electronic heating within the
household training
set by the electronic heating agent module 1052
Acquiring periodic household-level power consumption readings 1054
8
Date Recue/Date Received 2020-05-27
Optionally acquiring household-specific residents' profile parameters (e.g.
number of
inhabitants, household occupancy throughout the day etc. 1056
Optionally acquiring the day of week and month of the year 1058;
acquiring environmental data including temperature 1060;
Figure 4 is a flow diagram, depicting the function of a Electric Heating
classification model
according to some embodiments of the present invention.
The process of preparing the Electric Heating classification model comprise
the followings steps:
Obtaining at least part of the following data in respect to each household
within the training set:
(step 1310)
= Total household power consumption, from the household power meter
interface
= Electric Heating power consumption, from the electronic heating agent
module
= Environmental data and Day of week and month of the year from the data
acquisition
module
= thermostat data measurement for identifying if the electric heating work
or not
applying machine learning algorithm (step 1320) in relation to all households
in the training set,
according to the said obtained data, thus creating the "Electric Heating
classification model "., to
determine exitances of electrical heating device based on at least one of the
fooling parameters :
1. Checking daily load in various temperature bins ¨ if colder days have
significantly
higher load beyond predefined threshold
2. Checking Sub-hourly load patterns ¨ identifying if the load pattern have
similar pattern to
know types of load pattern which indicates HVAC activity based
3. Checking correlation between the load signal and the temperature signal,
Figure 5 is a flow diagram, depicting the function of Electric Heating
prediction model according
to some embodiments of the present invention.
9
Date Recue/Date Received 2020-05-27
The process of predicting existence of electrical heating device using the
Electric Heating
classification model comprise the followings steps:
Obtaining at least part of the following data in respect to each household
after the training set:
(step 1410)
= Total household power consumption, from the household power meter
interface
= Electric Heating power consumption, from the electronic heating agent
module
= Environmental data and Day of week and month of the year from the data
acquisition
module
Using "Hvac classification model "., to determine exitances of electrical
heating device based on
obtained data (step 1420);
The existence of electronic heating device can be achieved in alternative
technique using the
method described in patent application no.us 20190034817, as summarized bellow
The present invention provides a method for determining the presence of an
appliance such as
electronic heating device within a surveyed household, based on periodic
surveying of the
household's electric meter.
The method comprising the steps of: pre-processing groups of households of
historical
consumption of appliances based actual measurement performed by sensors
associated with said
appliances in relation to profile of household including characteristics of
the household and/or
lifestyle of the occupant and environmental time dependent parameters, and
determining the probability of each appliance presence and specifically
electronic heating device
at the surveyed household based on identified profile parameters and actual
behavior pattern of the
analyzed household based on sampled measurement taken at predefined discrete
time periods such
15 minutes in relation to actual time dependent environmental parameters of
the relevant time
period, by processing identified statistical correlations between presence of
appliances at each
household and 1) household profiles parameters, 2) household actual periodic
consumption pattern
3) household actual periodic consumption pattern in relation to environmental
time dependent
parameters.
Date Recue/Date Received 2020-05-27
Figure 6 is a flow diagram, depicting the function of the insights model
Training set Daily load
pattern module according to some embodiments of the present invention.
The process of preparing the insights model for predicting activation and
activation pattern of an
electronic heating devices comprises the followings steps:
Obtaining at least part of the following data in respect to each household
within the training set
houses that have both smart meter and smart thermostat (step 1510)
= Total household power consumption, from the household power meter
interface
= Load patterns of the household power meter interface
= thermostat data measurement
applying training a machine learning algorithm (step 1520) in relation to all
households in the
training set using Multi-output convolutional network, according to the said
obtained data, thus
creating the "Hvac classification model daily activation pattern"., to
determine activation pattern
of HVAC including several metrics concerning the performance of the HVAC
including at least
one of :percent of time active, Count of on/off switches, Activations during
the nighttime
Figure 7 is a flow diagram, depicting the function of the insights model
Prediction Detection and
Identification of HVAC according to some embodiments of the present invention.
The process of predicting activation and activation pattern of an electronic
heating devices using
the insights model for, comprises the followings steps:
Obtaining at least part of the following data in respect to each household
from beyond the
training set: (step 1710);
= Household power consumption, from the household power meter interface
= Day of week and month of the year from the data acquisition module
= Cooling day and heating day indication from the data acquisition module.
ii
Date Recue/Date Received 2020-05-27
Using insights model Training after the training stage, to determine
activation pattern of the
HVAC ,using obtained total household power consumption and load pattern with
no temperature
of summer period and regardless of time in day (step 1720);
Figure 8 is a flow diagram, depicting the function of the Clustering
activation pattern into Bins
based on temperature according to some embodiments of the present invention.
The process of clustering activation pattern comprises at least one of
following steps:
Each of the metrics of the insights model are aggregated by different
temperature bins
(step 1810);
removed from the data Days that are extremely hot or cold are sufficient load,
and of predicted
on percent from the daily model (step 1820);
Checking the HVAC performs on different weather scenarios.at each bin
(step 1830);
Determining malfunction or inefficiency based on how the HVAC performs on
different
weather scenarios.(identifying exaptational activation pattern in "regular
temperature" (step
1840);
Identifying deviations of the HVAC performance at each day/period in
comparison to
behavior of other HVAC in the same weather scenarios (step 1850);
Identifying deviations of the HVAC performance at each temperature bin vs
behavior of other
HVAC in the same temperature bins and the performance of this HVAC in
different temperature
bins to establish if this HVAC is malfunction/ inefficienc or not. (step
1860);
12
Date Recue/Date Received 2020-05-27
Figure 9 is a flow diagram, depicting the functionality of the malfunction
inefficiency training
and prediction module (ML), according to some embodiments of the present
invention.
The process of predicting the malfunction or inefficiency of electrical
heating device using
prediction ML model comprise the followings steps:
Obtaining at least part of the following data in respect to each household
from beyond for
training set: (step 1910);
= Household power consumption, from the household power meter interface
= Day of week and month of the year from the data acquisition module
= Environmental data including temperature
= metrics of the insights model aggregated by different temperature bins
Training an ML model based on winter labels and the aggregated metrics in temp
bin and
Identifying deviations of the HVAC performance at each temperature bin) for
determining if the
HVAC has a malfunction/ inefficient or not, (step 1920);
Obtaining at least part of the following data in respect to each household
from beyond the
training set: (step 1930);
Household power consumption, from the household power meter interface
= Day of week and month of the year from the data acquisition module
= Environmental data including temperature
= of the insights model aggregated by different temperature bins
= Identified deviations of the HVAC performance at each temperature bin
removed from the data Days that are extremely hot or cold are sufficient load,
and of predicted
on% from the daily model, (step 1940);
Determining malfunction or inefficiency of HVAC using the ML model using on
the metrics of
the previous model are aggregated by different temperature bins, For this
aggregation we only
consider days that have clear signs of HVAC activity (sufficient load, and
predicted on% from
13
Date Recue/Date Received 2020-05-27
the daily model) ¨ this is mainly because HVAC is not turned on every day
during the winter,
and some houses may have two different HVACs (primary HVAC system is gas run,
and only
secondary is electric), step 1950)
These features are later used to train a classifier. The classifier can be
implemented for example
using a gradient boosted tree-based algorithm described in
The system of the present invention may include, according to certain
embodiments of
the invention, machine readable memory containing or otherwise storing a
program of
instructions which, when executed by the machine, implements some or all of
the apparatus,
methods, features and functionalities of the invention shown and described
herein. Alternatively
or in addition, the apparatus of the present invention may include, according
to certain
embodiments of the invention, a program as above which may be written in any
conventional
programming language, and optionally a machine for executing the program such
as but not
limited to a general purpose computer which may optionally be configured or
activated in
accordance with the teachings of the present invention. Any of the teachings
incorporated herein
may wherever suitable operate on signals representative of physical objects or
substances.
Unless specifically stated otherwise, as apparent from the following
discussions, it is
appreciated that throughout the specification discussions, utilizing terms
such as, "processing",
"computing", "estimating", "selecting", "ranking", "grading", "calculating",
"determining",
"generating", "reassessing", "classifying", "generating", "producing", "stereo-
matching",
"registering", "detecting", "associating", "superimposing", "obtaining" or the
like, refer to the
action and/or processes of a computer or computing system, or processor or
similar electronic
computing device, that manipulate and/or transform data represented as
physical, such as
electronic, quantities within the computing system's registers and/or
memories, into other data
similarly represented as physical quantities within the computing system's
memories, registers or
other such information storage, transmission or display devices. The term
"computer" should be
broadly construed to cover any kind of electronic device with data processing
capabilities,
including, by way of non-limiting example, personal computers, servers,
computing system,
communication devices, processors (e.g. digital signal processor (DSP),
microcontrollers, field
programmable gate array (FPGA), application specific integrated circuit
(ASIC), etc.) and other
electronic computing devices.
14
Date Recue/Date Received 2020-05-27
The present invention may be described, merely for clarity, in terms of
terminology
specific to particular programming languages, operating systems, browsers,
system versions,
individual products, and the like. It will be appreciated that this
terminology is intended to
convey general principles of operation clearly and briefly, by way of example,
and is not
intended to limit the scope of the invention to any particular programming
language, operating
system, browser, system version, or individual product.
It is appreciated that software components of the present invention including
programs
and data may, if desired, be implemented in ROM (read only memory) form
including CD-
ROMs, EPROMs and EEPROMs, or may be stored in any other suitable typically non-
transitory
computer-readable medium such as but not limited to disks of various kinds,
cards of various
kinds and RAMs. Components described herein as software may, alternatively, be
implemented
wholly or partly in hardware, if desired, using conventional techniques.
Conversely, components
described herein as hardware may, alternatively, be implemented wholly or
partly in software, if
desired, using conventional techniques.
Included in the scope of the present invention, inter alia, are
electromagnetic signals
carrying computer-readable instructions for performing any or all of the steps
of any of the
methods shown and described herein, in any suitable order; machine-readable
instructions for
performing any or all of the steps of any of the methods shown and described
herein, in any
suitable order; program storage devices readable by machine, tangibly
embodying a program of
instructions executable by the machine to perform any or all of the steps of
any of the methods
shown and described herein, in any suitable order; a computer program product
comprising a
computer useable medium having computer readable program code, such as
executable code,
having embodied therein, and/or including computer readable program code for
performing, any
or all of the steps of any of the methods shown and described herein, in any
suitable order; any
technical effects brought about by any or all of the steps of any of the
methods shown and
described herein, when performed in any suitable order; any suitable apparatus
or device or
combination of such, programmed to perform, alone or in combination, any or
all of the steps of
any of the methods shown and described herein, in any suitable order;
electronic devices each
including a process or/and a cooperating input device and/or output device and
operative to
perform in software any steps shown and described herein; information storage
devices or
physical records, such as disks or hard drives, causing a computer or other
device to be
Date Recue/Date Received 2020-05-27
configured so as to carry out any or all of the steps of any of the methods
shown and described
herein, in any suitable order; a program pre-stored e.g. in memory or on an
information network
such as the Internet, before or after being downloaded, which embodies any or
all of the steps of
any of the methods shown and described herein, in any suitable order, and the
method of
uploading or downloading such, and a system including server/s and/or client/s
for using such;
and hardware which performs any or all of the steps of any of the methods
shown and described
herein, in any suitable order, either alone or in conjunction with software.
Any computer-
readable or machine-readable media described herein is intended to include non-
transitory
computer- or machine-readable media.
Any computations or other forms of analysis described herein may be performed
by a
suitable computerized method. Any step described herein may be computer-
implemented. The
invention shown and described herein may include (a) using a computerized
method to identify a
solution to any of the problems or for any of the objectives described herein,
the solution
optionally include at least one of a decision, an action, a product, a service
or any other
information described herein that impacts, in a positive manner, a problem or
objectives
described herein; and (b) outputting the solution.
The scope of the present invention is not limited to structures and functions
specifically
described herein and is also intended to include devices which have the
capacity to yield a
structure, or perform a function, described herein, such that even though
users of the device may
not use the capacity, they are, if they so desire, able to modify the device
to obtain the structure
or function.
Features of the present invention which are described in the context of
separate
embodiments may also be provided in combination in a single embodiment.
For example, a system embodiment is intended to include a corresponding
process
embodiment. Also, each system embodiment is intended to include a server-
centered "view" or
client centered "view", or "view" from any other node of the system, of the
entire functionality of
the system, computer-readable medium, apparatus, including only those
functionalities
performed at that server or client or node.
16
Date Recue/Date Received 2020-05-27