Warning procedure in case of failure of an energy production device and associated electronic device

Abstract

Method for alerting in case of failure of an energy production device and associated electronic device. The invention relates to an alert method implemented by a monitoring electronic device (200) connected to one or more energy production devices (100). The method comprises: determining, by a deviation cause classification model taking as input a deviation history between a value representing a prediction of the amount of energy produced by this or these energy production devices and a value representing the amount of energy actually produced by this or these energy production devices, an occurrence of a failure of at least one component of the energy production device(s); and generating an alert indicating that at least one component of the energy production device(s) is faulty. Figure for the abstract: Fig. 1A.

Description

Title of the invention: Method for alerting in case of failure of an energy production device and associated electronic device technical field

[0001] The present invention belongs to the general field of energy production systems. More particularly, the invention relates to a method for providing an alert in the event of a failure of an energy production device. It also relates to an electronic device configured to implement such a method.

[0002] It can, for example, find an application in the context of energy production systems using one or more renewable energy sources or combining renewable energy sources and so-called "conventional" energy sources, for example a fossil or nuclear energy source. Previous technique

[0003] The rise of renewable energies, among which photovoltaics and wind power occupy a prominent place, is a major economic and societal development of recent decades. However, controlling the amount of energy produced and the maintenance costs of these energy production systems proves more complex than for a conventional installation operating in a perfectly controlled environment. A conventional installation, as opposed to one that incorporates one or more renewable energy sources, relies, for example, on a fossil fuel or nuclear energy source.

[0004] The very nature of energy production systems using renewable energy sources explains this complexity. Indeed, the amount of energy produced, for example, by a wind farm or a photovoltaic solar power plant is notably dependent on environmental factors and / or the aging of the components of these systems, which are likely to occur over time.

[0005] When the energy production system under consideration consists of one or more photovoltaic panels, these aging phenomena may, for example, correspond to delamination, degradation of the anti-reflective coating of the glass or polymer covering the panel, yellowing of the ethylene-vinyl acetate encapsulant, generation of hot spots, formation of cracks within photovoltaic cells, generation of defects at the interconnection level, failure of a bypass diode, and / or potential-induced degradation (PID). These phenomena of Aging can lead to various types of failures, and may result in operation in degraded mode, particularly when part of the photovoltaic cells of a panel is in use.

[0006] To limit these failures or their impact, these energy production systems are regularly monitored using qualitative methods, including visual tests or infrared and / or electroluminescence measurements, for example, carried out by experts and / or drones. However, this operational maintenance generates significant costs (for example, €8,000 / MWp / year for a ground-mounted photovoltaic solar power plant). Furthermore, degradation and performance losses are generally detected late, and their severity is poorly estimated. As a result, these energy production systems using one or more renewable energy sources often have an actual output lower than their optimal output. Description of the invention

[0007] The present invention aims to remedy all or part of the disadvantages of the prior art, in particular those set out above, by proposing a solution which makes it possible to determine a cause of a drop in energy production, and to generate an alert when this cause is related to a failure of one or more components of the energy production device.

[0008] To this end, and according to a first aspect, the invention relates to an alert method implemented by an electronic monitoring device connected to at least one energy production device, the method comprising:

[0009] - a determination, by a cause classification model of deviations taking as input a history of deviations between a value representing a prediction of the amount of energy produced by the energy production device and a value representing the amount of energy actually produced by the energy production device, of an occurrence of a failure of at least one component of said energy production device; and

[0010] - generating an alert according to which at least one component of said device energy production is failing.

[0011] In other words, the deviation cause classification model determines that the deviations in the history are caused by a failure of one or more components of the power generation device.

[0012] By "energy production device", we mean an energy production device using one or more renewable energy sources or combining one or more renewable energy sources and one or more so-called "conventional" energy sources, for example fossil or nuclear.

[0013] By "failure of at least one component", we mean a malfunction (sudden or not) of one or more components of the energy production device, or even of the entire energy production device which then no longer produces electrical energy.

[0014] The predicted or actually produced "quantities of energy" are expressed, for example, in the form of electrical power, or voltage and / or current.

[0015] As mentioned below, the quantity of energy produced is for example predicted by an energy prediction model, and the energy prediction and deviation cause classification models correspond to machine learning models.

[0016] In general, it is considered that the steps of a process should not be interpreted as being linked to a notion of temporal succession.

[0017] In certain implementation modes, the alerting method may further include one or more of the following characteristics, taken individually or in all technically possible combinations.

[0018] In certain embodiments, the generation of an alert corresponds to the generation of an alert message intended to inform a user that at least one component of said energy production device is faulty.

[0019] In certain embodiments, this alert message is transmitted, via a communication interface, to a remote control device. Alternatively, the electronic monitoring device according to the invention includes a human-machine interface, such as a touchscreen, and the alert message is displayed on this screen. This alert message includes, for example, an identification of the faulty power generation device, and possibly the faulty component(s).

[0020] In certain implementation modes, the alert is generated after a certain number of failure occurrences are reached. When the alert message is transmitted to a remote control device, such an implementation mode can help limit message transmission and thus prevent congestion of the telecommunications network linking the electronic monitoring device to the remote control device.

[0021] In certain embodiments, the representative value of a prediction of a quantity of energy produced by the energy production device is determined by an energy prediction model.

[0022] These prediction and classification models correspond to machine learning models. In some implementation modes, the deviation cause classification model and / or the energy prediction model are multi-input regression models (linear or non-linear).

[0023] Each of the energy prediction and / or deviation cause classification models can be implemented on a single electronic device, or distributed across several interconnected electronic devices.

[0024] In certain implementations, the energy prediction and / or deviation cause classification models are implemented in the form of neural networks (convolution, perceptron, autoencoder, recurrent, etc.). According to one particular implementation, the neural networks considered are recurrent neural networks of the "long short-term memory" (LSTM) type.

[0025] Furthermore, it is important to note that there are no limitations on the type of training technique used to obtain the energy prediction model. Any technique implementing a machine learning algorithm and providing, as output, a prediction of the amount of energy produced given environmental data corresponding to input data, can be considered in the context of the invention (for example, support vector machine, logistic regression, etc.). In other words, the energy prediction model is independent of the training method used to train this model.

[0026] Similarly, no limitation is attached to the type of training technique used to obtain the deviation cause classification model. Any technique implementing a machine learning algorithm and providing, as output, a probability that a certain cause has generated deviations given a deviation history (corresponding to input data) can be considered in the context of the invention (for example, support vector machine, logistic regression, etc.). In other words, the deviation cause classification model is independent of the training method used to train this model.

[0027] In addition, any training criterion known to a person skilled in the art can be considered during the training phase of these machine learning models, such as the least squares method or cross-entropy minimization.

[0028] In some implementation modes, the deviation history includes only deviations greater than a first value.

[0029] In certain embodiments, the alerting process further includes a comparison of a deviation with the first value, and an addition of said deviation to the deviation history, depending on the result of said comparison.

[0030] In some embodiments, the comparison is implemented at a constant frequency.

[0031] In certain embodiments, the deviation cause classification model is configured to determine whether the deviations are caused by a change in environmental data of the energy production device, by a change in at least one sensor measuring said environmental data, by a change in at least one component of the energy production device, or by a failure of at least one component of said energy production device.

[0032] As mentioned previously, the steps of adapting the classification model and generating an alert are implemented when the determined cause of these deviations is a failure of at least one component of said energy production device.

[0033] "Environmental data" means any data relating to the environment of the energy production device that may affect the amount of energy produced by that device. As mentioned below, this includes, for example, meteorological data and / or geographical data (position, orientation, etc.).

[0034] In certain embodiments, the energy production device includes at least one photovoltaic cell and the environmental data corresponds to at least one of the following: data representing solar radiation on said cell (such as luminance and / or radiance), data representing a temperature of said cell, data representing a humidity level, data representing a wind speed, data representing an orientation of the cell, data representing a geographical position of the cell, and / or a combination of at least two of the above environmental data.

[0035] In some embodiments, the energy production device includes a photovoltaic solar panel, a photodiode and / or a phototransistor.

[0036] In certain embodiments, the deviation cause classification model is further configured to determine a type of failure and / or said at least one failing component.

[0037] In certain embodiments, the method further includes an adaptation of the deviation cause classification model, and this adaptation corresponds to a retraining of the deviation cause classification model.

[0038] In certain embodiments, an adaptation is performed after each determination of a component failure occurrence. The adaptation step is then, for example, implemented in response to this failure determination, and the model is retrained so as not to consider the photovoltaic panel as operating in degraded mode, even if one or more components of this photovoltaic panel are faulty and induce a decrease in electricity production. Alternatively, the adaptation is performed after several failures (for example when a certain number n of failures (n > 1) is reached).

[0039] In certain embodiments, the method further comprises:

[0040] - a determination, by said classification model, that new deviations are caused by a change in environmental data of the energy production device, a change in at least one sensor measuring said environmental data and / or a change in at least one component of the energy production device; and,

[0041] - a retraining of the energy prediction model.

[0042] In certain embodiments, the representative value of a prediction of a quantity of energy produced by the energy production device is determined by an energy prediction model, and the method further includes a determination of a size of the history as a function of the deviation cause classification model, for example as a function of its accuracy and / or the computing and / or storage capacities of a device on which this model is installed (at least partially).

[0043] In certain implementations, the size of the history is determined based on resources accessible by this electronic monitoring device. These resources correspond, for example, to computing / processing resources and / or storage resources.

[0044] In certain embodiments, the representative value of a prediction of a quantity of energy produced by the energy production device is determined by an energy prediction model, and the method further includes training the energy prediction model from environmental data sets of said energy production device and from representative values ​​of a quantity of energy actually produced by the energy production device considering said environmental data sets, the training of the energy prediction model being implemented when none of the components of said energy production device is faulty or considered to be faulty.

[0045] In certain embodiments, the method further includes training the deviation cause classification model from a plurality of deviation histories between a value representing a prediction of a quantity of energy produced by the energy production device and a value representing a quantity of energy actually produced by the energy production device, each of the histories in the plurality being associated with a label corresponding to a cause of said deviations.

[0046] In some embodiments, the energy prediction model corresponds to a recurrent neural network including so-called "lower" layers, the training of the energy prediction model being implemented in a learning environment distinct from an operating environment, and the adaptation step further includes a partial retraining of the energy prediction model in the operating environment by freezing the lower layers of the recurrent neural network.

[0047] According to a second aspect, the present application relates to an electronic monitoring device configured to implement an alert method for the present application.

[0048] Depending on the implementation methods, the device can in particular be configured to implement any one of the implementation methods of the alerting process of this application.

[0049] According to a third aspect, the present application relates to a system comprising an energy production device and the electronic monitoring device according to the second aspect.

[0050] According to a fourth aspect, the present application relates to a computer program comprising instructions for implementing an alerting method, when said program is executed by a processor.

[0051] Depending on the implementation methods, the computer program may include instructions for implementing any of the implementation methods of the alerting process of this application.

[0052] This program may use any programming language, and be in the form of source code, object code, or code intermediate between source code and object code, such as in a partially compiled form, or in any other desirable form.

[0053] According to a fifth aspect, the invention relates to a computer-readable recording medium on which a computer program according to the present application is recorded.

[0054] The information or recording medium can be any entity or device capable of storing the program. For example, the medium can include a storage means, such as a ROM, for example a CD-ROM or a microelectronic circuit ROM, or a magnetic recording means, for example a hard disk drive.

[0055] On the other hand, the information or recording medium can be a transmissible medium such as an electrical or optical signal, which can be transmitted via an electrical or optical cable, by radio, or by other means. The program according to the invention can, in particular, be downloaded onto an Internet-type network.

[0056] Alternatively, the information or recording medium may be an integrated circuit in which the program is incorporated, the circuit being adapted to execute or to be used in the execution of the process in question. Brief description of the drawings

[0057] Other features and advantages of the present invention will become apparent from the description below, with reference to the accompanying drawings, which illustrate an example of an embodiment without being limiting in any way. In the figures:

[0058] [Fig. 1 A] [Fig. 1 A] is a first example of a system in which an alert procedure in the event of failure of an energy production device can be implemented;

[0059] [Fig.1B] [Fig.1B] is a second example of a system in which an alert method in case of failure of an energy production device can be implemented;

[0060] [Fig.2] [Fig.2] represents modules embedded in an electronic device supervision according to an example of implementation of the invention;

[0061] [Fig.3] [Fig.3] schematically represents an example of hardware architecture of an electronic monitoring device;

[0062] [Fig.4] [Fig.4] represents, in the form of a flowchart, a particular mode of implementation of an alert procedure in the event of a failure of an energy production device, for example executed by the electronic monitoring device of [Fig.2]; and

[0063] [Fig. 5] [Fig. 5] represents, in the form of a flowchart, a particular mode of Implementation of an alert procedure in case of failure of an energy production device, for example executed by the electronic device of [Fig. 2]. [Fig. 5] is a detailed version of the alert procedure illustrated with reference to [Fig. 4].

[0064] [Fig.6] [Fig.6] illustrates an example of training data for the model of classification of the cause of deviation.

[0065] Description of implementation methods

[0066] The [Fig. 1 A] is a first example of a system in which an alert procedure in the event of failure of an energy production device can be implemented.

[0067] As illustrated in [Fig. 1A], the energy production system 1000-1 comprises a photovoltaic panel 100. This photovoltaic panel 100 is, for example, mounted on a stand, placed on a roof, or integrated into a building. This photovoltaic panel 100 can also be integrated into a vehicle, such as an airplane, boat, or train. The electricity produced by a photovoltaic panel is generally in the form of direct current, and this electricity is, for example, used directly to power certain industrial machines, recharge Batteries, including electric vehicle batteries, or various other uses. The electricity produced by the 100 photovoltaic panel can also be converted into alternating current, which can then be either fed into the local or national power grid or used locally.

[0068] The photovoltaic panel 100 comprises one or more photovoltaic modules 10, each photovoltaic module 10 itself comprising one or a plurality of photovoltaic cells. In the present embodiment, the photovoltaic panel 100 is considered to have three photovoltaic modules 10. It should be noted, however, that there is no limitation on the number of photovoltaic modules 10. The following developments can indeed be easily generalized by those skilled in the art to cases where a higher or lower number of photovoltaic modules 10 is considered.

[0069] As illustrated by [Fig. 1A], the photovoltaic panel 100 is equipped with environmental data measurement sensors:

[0070] - a light sensor 20 configured to measure a quantity of light and / or solar radiation reaching this sensor. According to a particular implementation mode, the light sensor 20 performs measurements in the ultraviolet, visible and infrared ranges, and covers, for example, a range from 280 to 950 nanometers (nm). Alternatively, the light sensor 20 performs measurements only in the visible range, and covers, for example, a range from 400 to 700 nm;

[0071] - a temperature sensor 30 configured to measure the temperature reached by the photovoltaic panel 100 and / or the temperature in the vicinity of said photovoltaic panel 100 (for example, less than 10 meters from this panel);

[0072] - an anemometer 40 installed on or near (for example, within 10 meters) of the photovoltaic panel 100, and which measures the speed and / or pressure of the wind; this anemometer 20 can also be coupled to a wind vane (not shown) which determines the origin of this wind;

[0073] - an inertial measurement unit 50 which integrates, for example, a compass as well as a gyroscope. This inertial unit 50 can also integrate an accelerometer. In a particular implementation mode, the compass, gyroscope and accelerometer can be "3-axis" instruments, which notably allow the detection of hail impacts on the photovoltaic panel 100;

[0074] - a magnetometer; and / or

[0075] - an inclinometer.

[0076] These various sensors are, of course, only illustrative examples, and the photovoltaic panel 100 may be equipped with only some of them or include sensors other than those mentioned above. The photovoltaic panel 100 can also include several sensors of the same type (for example several temperature sensors), positioned at different locations on the photovoltaic panel.

[0077] This solar panel and the sensors that equip it are connected, directly or through a telecommunications network 300, to an electronic monitoring device 200 whose functionalities are described in more detail below.

[0078] Figure 1B is a second example of a 1000-2 system in which an alert method for failure of an energy production device can be implemented. This second example differs mainly from the first example in Figure 1A by the number of photovoltaic panels that make up the system.

[0079] As illustrated by Figure IB, the energy production system 1000-2 comprises a photovoltaic solar power plant, also called a "solar farm", including a plurality of photovoltaic panels 100,=1„ connected together in series and / or in parallel, and which can be connected to an electrical network by inverters.

[0080] A photovoltaic solar power plant typically covers an area ranging from one hectare to more than twenty square kilometers, and includes a large number of solar panels, typically from several thousand or tens of thousands to more than one million.

[0081] The 100!=1H photovoltaic panels are also equipped with sensor(s) similar to those described with reference to Figure IA. Alternatively, only some of the 10(¾.^) photovoltaic panels are equipped with sensors.

[0082] As illustrated in Figure IB, these solar panels and the sensors that equip them are connected, either directly or via a telecommunications network 300, to an electronic monitoring device 200 whose functionalities are described in more detail below. Thus, as illustrated in Figure IB, the architecture of system 1000-2 is centralized, since in this example each of the solar panels 100j=ijI is connected to the electronic monitoring device 200. Alternatively, the architecture of system 1000-2 is distributed, and system 1000-2 comprises a plurality of electronic monitoring devices 200 that can be connected to one or more solar panels.

[0083] According to one embodiment, the 100!=1H photovoltaic panels can be grouped into set(s) of panels, at least one panel (for example, each panel) of at least one set of panels (for example, of each set of panels) being connected on the one hand to a first electronic monitoring device, denoted A, responsible for monitoring only that photovoltaic panel, and on the other hand to a second electronic monitoring device, denoted B, responsible for monitoring several photovoltaic panels of that set. In some implementations, these sets can form a partition (in terms of panels) of the system (and therefore be disjoint).

[0084] In certain implementations, these sets of panels may have certain panels in common. For example, a first division may be carried out into first sets of panels of the same size (for example sets of 10 panels), each first set being supervised by a different supervision device, coupled with a second division into second sets of panels supervised by other supervision devices (for example sets based on the physical implementation of the panels, for example grouping the panels by row, and / or by column, and / or by orientation of their sensors with respect to the sun, etc.).

[0085] Each first electronic monitoring device A (unit monitoring of a single panel) is then, for example, configured to collect measurements from a first set of sensors of the single photovoltaic panel it monitors. The second electronic monitoring device B (processing, for example, information relating to several panels) can either collect, among other things, measurements from a second set of sensors of this photovoltaic panel (different from the first set of sensors, but which may have sensors in common with this first set of sensors), or retrieve information from at least two (for example, each) unit electronic monitoring devices A in order to derive other charts (e.g., average production of a subset of photovoltaic panels 100i=l..n).This configuration offers the advantage of helping to obtain statistics on individual failures (i.e., detected on a specific photovoltaic panel) and to assess the impact of individual failures on all panels measured by B (for example, when these failures are correlated). For example, a monitoring device A can identify a faulty panel, while a monitoring device B can estimate the impact of this failure on the park's production (and thus assess the urgency of replacing or repairing the faulty panel).

[0086] Depending on the implementation, the exchange of information between "unit" monitoring devices and monitoring devices processing information relating to several panels can be done either by wired communication or by wireless communication (Wifi for example).

[0087] It is noted that the system may include, in certain implementations, a multi-level hierarchical structure (for example three or more) between supervisory devices.

[0088] Fig. 2 represents modules embedded in an electronic supervisory device 200 according to an example of implementation of the invention.

[0089] As illustrated in [Fig. 2], the electronic monitoring device 200 includes, in particular:

[0090] - a MOD_DET determination module including a classification model of cause of deviations taking as input a history of deviations between a value representing a prediction of the amount of energy produced by the energy production device (100, 100;) and a value representing the amount of energy actually produced by the energy production device (100, 100;), and providing as output a cause of these deviations; and

[0091] - a M0D_WAR module for generating an alert that at least one component of the power generation device is faulty, this module being activated when the cause is a failure of at least one component of the power generation device.

[0092] Their functionalities are described in more detail below with reference to different modes of implementation.

[0093] Fig. 3 schematically represents an example of the hardware architecture of an electronic monitoring device 200.

[0094] As illustrated in [Fig. 3], the electronic monitoring device 200 has the hardware architecture of a computer. Thus, the electronic monitoring device 200 includes, in particular, a processor 1, random access memory 2, read-only memory 3 and non-volatile memory 4. It also has communication means 5.

[0095] The read-only memory 3 of the electronic monitoring device 200 constitutes a storage medium according to the invention, readable by the processor 1, on which a computer program PROG according to the invention is stored, comprising instructions for executing steps of the alerting process according to the invention. The PROG program defines functional modules of the electronic monitoring device 200, which rely on or control the hardware elements 1 to 5 of the electronic monitoring device 200 mentioned above. These functional modules are illustrated in [Fig. 2] by way of no limitation, and are described in more detail below with reference to different implementation methods.

[0096] In certain embodiments, the communication means 5 enable the electronic monitoring device 200 to obtain representative values ​​of the quantities of energy actually produced by the energy production device(s) 100, as well as representative values ​​of environmental data from the energy production device. To this end, the communication means 5 include a wired or wireless communication interface capable of implementing any suitable communication protocol.

[0097] Figure 4 represents, in the form of a flowchart, a particular method of implementing an alert procedure in the event of a failure of a production device. energy, for example executed by the electronic monitoring device of the [Fig.2],

[0098] In the present embodiment, the alerting method includes a first step S410 in which the cause of deviations between a value representing a prediction of the amount of energy produced by the energy production device 100, 100; and a value representing the amount of energy actually produced by the energy production device 100, 100z is determined. This step is implemented, for example, by the M0D_DET module of the electronic monitoring device 200. An example of the implementation of this step S410 is described in more detail with reference to step S570 of [Fig. 5].

[0099] The alerting method further includes a step S415 in which it is determined whether these deviations are caused by a failure of at least one component of said energy production device 100, 100,-. An example of the implementation of this step S415 is described in more detail with reference to step S575 of [Fig. 5].

[0100] If this is the case (choice "Y"), an S420 step is implemented in which the deviation cause classification model is adapted so that the photovoltaic panel is no longer considered to be operating in degraded mode, even if one or more components of this photovoltaic panel are faulty and induce a decrease in electricity production (i.e., the current operation, due to at least one a priori faulty component, becomes the reference operation (against which a deviation must be detected) for the classification model). In this way, if new deviations are detected during a subsequent iteration, their cause can be determined independently. This S420 step is implemented, for example, by the MOD_RET module of the 200 electronic monitoring device. An example of the implementation of this S420 step is described in more detail with reference to step S550 in [Fig. 5].

[0101] The method further includes a step S430 in which an alert is generated to warn that at least one component of said energy production device 100, 100z is faulty. This step S430 is implemented, for example, by the M0D_WAR module of the electronic monitoring device 200. An example of the implementation of this step S430 is described in more detail with reference to step S585 in [Fig. 5].

[0102] Figure 5 represents, in flowchart form, a particular method of implementation implementation of an alert procedure in case of failure of an energy production device, for example executed by the electronic device 200 of [Fig.2]. [Fig.5] is a detailed version of the alert procedure illustrated with reference to [Fig.4].

[0103] The alerting process first comprises a first PI phase, called the "training phase", during which the prediction and classification models The models used in this alerting process are trained in a learning environment. This first PI phase includes steps S510 and S520 and can be implemented either by the 200 electronic supervisory device or by a separate electronic device. The process further includes a P2 phase, which includes step S530, during which the models previously trained in the learning environment are transferred to an environment called the "operational environment." Finally, the alerting process includes a third phase, P3, called the operational phase, which includes steps S540 to S590, described below.

[0104] As illustrated in Figure 5, the alerting method includes a first step S510 in which an energy prediction model is trained. This energy prediction model is intended to predict the amount of energy produced by an energy-producing device, such as devices 100, 100; in Figures IA and IB. According to a particular implementation, this prediction model is implemented using an artificial neural network, such as a recurrent neural network. This recurrent neural network corresponds, for example, to an LSTM-type network.

[0105] This energy prediction model is trained with training data comprising environmental data sets, each set being associated with a quantity of energy produced. In other words, the quantity of energy produced refers to the quantity of energy actually produced by the energy production device 100, 100; in a particular context defined by the associated environmental data.

[0106] The energy production device 100, 100; previously mentioned corresponds for example to a photovoltaic panel, and these environmental data correspond for example to a data representative of solar radiation on this panel, of a temperature of this panel, of an ambient humidity level, of a wind speed, of an orientation of this panel and / or of a geographical position of this panel.

[0107] It is important to note that in certain embodiments, the S510 training of the energy prediction model is performed when none of the components of said energy production device 100, 100; is faulty or considered to be so. In this way, the training focuses on correlating only environmental data with quantities of energy produced, and the risk of introducing bias is thus reduced.

[0108] The alerting method further includes a step S520 in which a deviation cause classification model is trained. According to a particular implementation, this classification model is implemented using an artificial neural network, such as a recurrent neural network. This recurrent neural network corresponds, for example, to an LSTM type network. In a mode Specifically, this deviation cause classification model is designed to determine whether deviations between a predicted energy quantity and an energy quantity actually produced by the energy production device 100, 100 are caused by:

[0109] - either by a failure of one or more components of the production device energy 100, 100;

[0110] - either through a change in the environmental data of the production device energy (100, 100;), by changing at least one sensor measuring said environmental data, and / or by changing at least one component of the energy production device 100, 100(-,

[0111] "Changing at least one sensor" corresponds, for example, to replacing one or more sensors, and / or to a change in the measurement capabilities of one or more sensors resulting in drift (for example, due to aging). "Changing at least one component" of the energy production device corresponds, for example, to replacing one or more components of the energy production device, and / or to a change in the capabilities of one or more components of the energy production device. For example, photovoltaic cells experience a reduction in capacity when they are covered with dust, dead leaves, or bird droppings.

[0112] To achieve this, the classification model is trained with training data consisting of sets of deviation histories associated with deviation causes. More precisely, a deviation history designates a temporal sequence of deviations between a value representing a prediction of a quantity of energy produced by the energy production device (100, 100;) and a value representing a quantity of energy actually produced by the energy production device (100, 100;), and each history is associated with a "cause" that generated the deviations in this sequence.

[0113] According to a particular implementation, the cause relating to the failure of one or more components of the energy production device is represented by the label and other causes (for example, changes in environmental data, changes in at least one measuring sensor or changes in components) are represented by the label "LDD".

[0114] Figure 6 illustrates an example of training data for the deviation cause classification model.

[0115] As illustrated in Figure 6, this training data includes deviation histories 600-1, ..., 600-i, 600-j, ..., 600-n, each associated with an LDD cause that generated these deviations. The deviation history 600-1 consists of a temporal sequence of deviations d^ ..., d^ and is associated with the label " Lj^”, the 600-i deviation history consists of a time sequence of deviations d^ ..., and is associated with the label "Epp", the 600-j deviation history consists of a time sequence of deviations d...,dj^, and is associated with the label "LCd", and the 600-n deviation history consists of a time sequence of deviations d^ ..., dn_6 and is associated with the label "^cn"-

[0116] To acquire this training data, changes in environmental data and failures of one or more components are simulated, for example. For each of these situations, the (now trained) energy prediction model predicts, at different times 6..., a quantity of energy produced by the energy production device. Then, the difference between the predicted quantity of energy and the quantity of energy actually produced by the device is recorded in a data structure, with a label (for example, LCD, LDD) representing the cause that generated these differences. This data structure corresponds, for example, to an ordered list.

[0117] As illustrated in [Fig. 6], each history comprises six deviations associated with six different time points. It should be noted, however, that there is no limitation on the size of these histories. The following developments can indeed be easily generalized by those skilled in the art if a different size is considered. Furthermore, in a particular implementation method, an optimal history size is determined prior to the previously mentioned step S520.

[0118] To do this, a range of sizes is determined, for example, based on the resources of the electronic device (200) or resources accessible by this electronic device (200). By "resource," we mean hardware resources (for example, memory) and / or processing resources (for example, in terms of capacity and / or processing time). Then, different history sizes within this range are considered, and their accuracy is determined.

[0119] More precisely, the deviation cause classification model is applied several times, considering different historical data sizes. Then the combination {size; accuracy obtained with this size] is recorded. According to a particular implementation, a range of sizes to be tested is determined, for example, based on previously obtained historical data. The bounds of this range are defined, for example, based on the minimum and maximum duration of deviations in this historical data related to changes in environmental data. Alternatively, or in combination, the maximum bound is determined based on available resources. These resources may correspond to accessible computing power or the computing power inherent to the electronic monitoring device (a large size can result in a very long response time) and / or the memory capacity of this electronic device.

[0120] Finally, a history size is selected which corresponds, for example, to the one offering the best accuracy.

[0121] This determination and use of the history size can be advantageous since it results from a compromise between the resources in terms of processing and / or memory own or accessible by the electronic monitoring device, and the accuracy of the model.

[0122] Returning to [Fig.5], the alerting process further includes a step S530 in which the evaluation and classification models previously trained in the learning environment are transferred to an operating environment separate from the learning environment.

[0123] If the training of these two models had not been previously implemented by the electronic supervisory device 200, they are then received by this electronic supervisory device 200, for example through the means of communication 5.

[0124] In a particular embodiment, step S530 includes a partial retraining of the energy prediction model, so as to adapt to the environment in which the energy production device under consideration is installed.

[0125] As mentioned previously, this energy prediction model corresponds, for example, to a neural network and includes so-called "lower" layers encoding generic features, such as generic relationships between the amount of electricity generated by a photovoltaic panel and the solar radiation reaching that panel. In some implementations, retraining can be "partial" in the sense that these "lower" layers are fixed, and gradient calculation and backpropagation are then disabled for these layers. This feature is advantageous because it helps reduce the risk of overfitting the prediction model. Furthermore, the retraining phase of the prediction model is lighter and less resource-intensive (storage and / or processing).

[0126] The alerting process includes a third phase P3, known as the operational phase, which includes steps S540 to S590. This phase aims to determine the causes related to a decrease in energy production, and to adapt, where necessary, the learning models following this determination.

[0127] During step S540, the electronic monitoring device 200 receives environmental data and the amount of energy actually produced over a time interval (defined, for example, by parameter setting) from the energy production device it manages, taking this environmental data into account. This data is received, for example, using the communication means 5 mentioned previously.

[0128] The alerting method further includes a step S550 in which a quantity of energy likely to have been produced by this energy production device during the same time interval as that mentioned in reference to step S540, and this considering the environmental data obtained in step S540, is predicted by the energy prediction model.

[0129] Then, in step S560, it is determined whether the deviation corresponding to the difference between the amount of energy actually produced and the amount of energy is less than a THR value, referred to as the "first value". If this is the case—e.g., if the deviation is less than the THR value—this means that the deviation is not significant enough to reflect either a failure of the energy production device, a change in environmental data, a sensor change, or a component change. Consequently, the alerting process loops back to step S540 (choice "Y").

[0130] If, however, the deviation is greater than or equal to the THR value, an S565 step is implemented during which the deviation is added to a deviation history. According to a particular implementation method, this history is implemented as an ordered list.

[0131] In a particular embodiment, steps S540, S550 and S560 are carried out at a constant frequency.

[0132] When a stopping condition is reached, for example when this history reaches a certain size (defined, for example, by parameter settings), an S570 step is implemented during which the cause of the deviations is determined. This S570 step is implemented, for example, by the M0D_DET module of the 200 electronic supervisory device, which includes, in particular, a deviation cause classification model.

[0133] In a particular embodiment, this deviation cause classification model is configured to determine whether deviations between a predicted quantity of energy and a quantity of energy actually produced by the energy production device 100, 100,- are caused by:

[0134] - either by a failure of one or more components of the production device energy 100, 100(-,

[0135] - either through a change in the environmental data of the production device energy (100, 100*), by changing at least one sensor measuring said environmental data, and / or by changing at least one component of the energy production device 100, 100,-.

[0136] If it is determined in step S570 that the deviations are caused by a failure of one or more components of the power generation device 100, 100f (step S575, choice "COMP"), steps S58O and S85 are implemented by the electronic supervisory device 200.

[0137] During step S580, the classification model is adapted to avoid repetitive alerts for the same cause, but also to enable the electronic monitoring device 200 to identify new deviations and causes of deviations. This step S580 is implemented, for example, by the MOD_RET module of the electronic monitoring device 200. In a particular implementation mode, this adaptation step corresponds to a retraining of this deviation cause classification model.

[0138] In the implementation illustrated in [Fig. 5], adaptation is performed after each determination of a component failure occurrence. The adaptation step is then implemented in response to this failure determination, and the model is retrained so as not to consider the photovoltaic panel as operating in degraded mode, even if one or more components of this photovoltaic panel are faulty and induce a decrease in electricity production.

[0139] In a variant (not represented by this figure 5), the adaptation is carried out only after a certain number of failures are reached (e.g., after steps S540 to S575 (choice "COMP") are repeated n times (with n> 1).

[0140] Then, step S585 is implemented, during which an alert is generated indicating that at least one component of said energy production device 100 is faulty. In a particular embodiment, this alert message is transmitted, via a communication interface, to a remote control device. Alternatively, the electronic supervisory device 200 includes a human-machine interface, such as a touchscreen, and the alert message is displayed on this screen. This alert message includes, for example, an identification of the faulty energy production device and possibly the faulty component(s). Finally, after step S585, the process loops back to step S540.

[0141] Returning to step S575, if it is determined that the deviations are caused by a change in the environmental data of the energy production device 100, 100z, by a change in at least one sensor measuring said environmental data, or by a change in at least one component of the energy production device 100, 100,- (option "ENV"), step S590 is implemented by the electronic monitoring device 200. During this step S590, the energy prediction model is retrained on new environmental data in order to readjust to the new environmental conditions. Finally, after step S590, the process loops back to step S540.

[0142] The invention has been described so far in the case where the deviation cause model is configured to distinguish two types of deviation causes, but the invention is in fact generalizable without difficulty by a person skilled in the art in the case where more than two types of causes are considered.

[0143] Thus, in a particular embodiment, the deviation cause model is configured to distinguish either a failure of one or more components of the energy production device 100, 100; or a change in the environmental data of the energy production device 100, 100f; or a change in at least one sensor measuring said environmental data; or a change in at least one component of the energy production device 100, 100,-.

[0144] In a particular embodiment, the deviation cause model is further configured to determine a type of failure and / or the failing component(s).

[0145] Thus, the deviation cause model is for example trained and configured to identify delamination, degradation of the anti-reflective layer of the glass or polymer covering the panel, yellowing of the ethylene-vinyl acetate encapsulant, generation of hot spots, formation of cracks within photovoltaic cells, generation of defects at the level of interconnections, failure of a bypass diode or potential-induced degradation ("Potential Induced Degradation", PID, according to Anglo-Saxon terminology.

[0146] The invention has also been described so far in the case where the energy production device is a photovoltaic panel, but the invention remains applicable in the case where the energy production device is a photodiode, a phototransistor, or a wind turbine.

Claims

Demands

1. An alerting method implemented by an electronic monitoring device (200) connected to at least one energy production device (100, 100,), the method comprising: • a determination (S410, S570), by a deviation cause classification model taking as input a deviation history between a value representative of a prediction of a quantity of energy produced by the energy production device (100, 100;) and a value representative of a quantity of energy actually produced by the energy production device (100, 100;), of an occurrence of a failure of at least one component of said energy production device (100, 100;); and • a generation (S430, S585) of an alert that at least one component of said energy production device (100, 100,) is faulty.

2. An alerting method according to claim 1, the representative value of a prediction of an amount of energy produced by the energy production device (100, 100;) being determined by an energy prediction model.

3. Alerting method according to claim 1 or 2, the deviation history comprising only deviations greater than a first value.

4. A warning method according to any one of claims 1 to 3, the deviation cause classification model being configured to determine whether the deviations are caused by a change in environmental data of the energy production device (100, 100f), by a change in at least one sensor measuring said environmental data, by a change in at least one component of the energy production device (100, 100f), or by a failure of at least one component of said energy production device (100, 100f).

5. An alerting method according to any one of claims 1 to 4, the deviation cause classification model being further configured to determine a type of failure and / or said at least one failing component.

6. Alerting method according to any one of claims 1 to 5, further comprising an adaptation (S420, S580) of the deviation cause classification model, the adaptation corresponding to a retraining of the deviation cause classification model.

7. An alert method according to any one of claims 2 to 6 in combination with claim 2, further comprising: • a determination (S570), by said classification model, that new deviations are caused by a change in environmental data of the energy production device (100, 100f), a change in at least one sensor measuring said environmental data and / or a change in at least one component of the energy production device (100, 100f); and, • a retraining (S590) of the energy prediction model.

8. An alerting method according to any one of claims 1 to 7, the representative value of a prediction of an amount of energy produced by the energy production device (100, 100,) being determined by an energy prediction model, the method further comprising a determination of a history size based on the deviation cause classification model.

9. An alert method according to any one of claims 1 to 8, the representative value of a prediction of an amount of energy produced by the energy production device (100, 100,-) being determined by an energy prediction model, the method further comprising training (S510) the energy prediction model from environmental data sets of said energy production device (100, 100,) and from representative values ​​of an amount of energy actually produced by the energy production device (100, 100,) considering said environmental data sets, the training (S510) of the energy prediction model being implemented when none of the components of said energy production device (100, 100,) is faulty or considered to be faulty.

10. An alerting method according to any one of claims 1 to 9, further comprising a drive (S520) of the model classification of cause of deviations from a plurality of deviation histories between a value representative of a prediction of a quantity of energy produced by the energy production device (100, 100,) and a value representative of a quantity of energy actually produced by the energy production device (100, 100;), each of the histories of the plurality being associated with a label corresponding to a cause of said deviations.

11. Electronic monitoring device (200) configured to implement an alerting method according to any one of claims 1 to 10.

12. Computer program (PROG) comprising instructions for implementing an alerting method according to any one of claims 1 to 10, when said program is executed by a processor.

13. Computer-readable recording medium on which a computer program according to claim 12 is recorded.

Images