Electronic device and method for monitoring electrical cabinet, current distribution system and computer program

Abstract

The invention relates to an electronic device for monitoring an electrical cabinet (10), comprising an acquisition module configured to acquire values of variables representing a current and a voltage of the current, respectively, measured by a current sensor (41, 42, 43, 44) and a voltage sensor (51, 52, 53, 54), respectively; an estimation module configured to calculate an estimated state of the electrical cabinet (10) via a neural network; and a transmission module configured to transmit a message representing the estimated state in one of either visual or auditory forms. According to the invention, the acquisition module is further configured to acquire a value of the at least one additional variable, and the estimation module is configured to calculate an estimated state of the electrical cabinet (10) via the neural network as another function of the at least one additional variable.

Description

Technical Field

[0001] The present invention relates to electronic equipment and methods for assisting in monitoring an electrical cabinet, a current distribution system comprising such an equipment and an associated computer program. Background Art

[0002] In order to monitor electrical cabinets, in particular in order to detect risks of faults, such as fire in the electrical cabinet, it is known to perform on-site monitoring operations on the electrical cabinet. However, during the monitoring operations, it is not always possible to identify electrical or structural faults in the electrical cabinet. It is also known to use sensors located inside the electrical cabinet, in particular current, voltage and temperature sensors, and to send an alarm signal if the value measured by one of these sensors exceeds a predetermined threshold.

[0003] CN 115 880 848 A proposes the use of an artificial intelligence algorithm to detect electrical fires in electrical cabinets using data related to the temperature of components inside the electrical cabinet, leakage current, the intensity and voltage of the current flowing in the electrical cabinet.

[0004] However, there is a need to make detection more efficient. Summary of the invention

[0005] The object of the present invention is therefore to propose an electronic device for auxiliary monitoring allowing to resolve these drawbacks and improve detection.

[0006] To this end, the object of the present invention is to provide an electronic device for assisting monitoring of an electrical cabinet, the electrical cabinet comprising an input terminal and a plurality of output terminals, and being connectable to a power source via the input terminal and to a plurality of loads via the output terminals, and being configured to distribute current from the power source to the plurality of loads, the electrical cabinet comprising an isolating switch connected to the input terminal and a main bus connected between the isolating switch and the output terminals, the device comprising:

[0007] - an acquisition module configured to acquire values ​​of variables respectively representing the intensity and voltage of the current flowing between the input terminal and the output terminal, measured by the current sensor and the voltage sensor, respectively;

[0008] - an estimation module configured to calculate an estimated state of the electrical cabinet via a neural network, each variable acquired by the acquisition module being an input variable of the neural network, and the estimated state of the electrical cabinet being an output variable of the neural network; and

[0009] - A transmission module configured to transmit a message representing the estimated status in a visual or auditory form.

[0010] According to the invention, the acquisition module is further configured to acquire the value of at least one additional variable measured by at least one additional sensor of the gas sensor and the humidity sensor, the variable or each variable representing the amount of gas particles and the humidity inside the electrical cabinet, respectively. Furthermore, according to the invention, the estimation module is then configured to calculate, via a neural network, an estimated state of the electrical cabinet as another function of the at least one additional variable, the at least one additional variable being an additional input variable of the neural network.

[0011] Thanks to the invention, the estimation module uses at least one additional variable measured by at least one additional sensor to calculate the estimated state of the electrical cabinet. This additional variable allows more relevant variables to be input to the neural network in order to improve the reliability of the calculation of the estimated state of the electrical cabinet.

[0012] According to other advantageous aspects of the invention, the device comprises one or more of the following features, alone or in any technically possible combination:

[0013] - The acquisition module is also configured to acquire variable values ​​of additional quantities measured by the humidity sensor and by the gas sensor.

[0014] - The acquisition module is further configured to acquire a variable value of a quantity measured by the temperature sensor, the measured variable representing the temperature inside the electrical cabinet.

[0015] - The acquisition module is also configured to acquire variable values ​​measured by a plurality of temperature sensors, which represent the temperature inside the electrical cabinet, and each temperature sensor is configured to measure the following temperatures: the temperature near the input terminal, the temperature near the corresponding output terminal, the temperature of the main bus, and the temperature of the electrical protection device connected between the main bus and the corresponding output terminal.

[0016] - The acquisition module is further configured to acquire a variable value representing the vibration of the electrical cabinet measured by the vibration sensor.

[0017] The acquisition module is further configured to acquire a value representative of the noise in the electrical cabinet measured by the noise sensor.

[0018] - The estimated state of the electrical cabinet is one of the group consisting of a normal state, an abnormal state, and a critical state.

[0019] The present invention also relates to a system for distributing current between a power source and a plurality of loads, the system comprising:

[0020] - An electrical cabinet comprising:

[0021] oInput terminals, capable of connecting to power supply,

[0022] oMultiple output terminals, capable of connecting to multiple loads,

[0023] oDisconnector, connected to the input terminals, and

[0024] oMain bus, connected between the disconnector and the multiple output terminals,

[0025] The electrical cabinet is configured to distribute current from the power source toward the plurality of loads;

[0026] - a current sensor and a voltage sensor, respectively configured to measure values ​​of variables representative of a current and a voltage of the current, respectively, flowing between input terminals and output terminals of the electrical cabinet;

[0027] - Helps monitor electronic equipment in electrical cabinets.

[0028] According to the present invention, the system further comprises at least one additional sensor of the gas sensor and the humidity sensor, the additional sensor being configured to collect the value of at least one additional variable, the value of the at least one additional variable representing the amount of gas particles and the humidity inside the electrical cabinet, respectively. In addition, according to the present invention, the electronic device for auxiliary monitoring is according to any one of the preceding claims.

[0029] The present invention also relates to a method for auxiliary monitoring of an electrical cabinet, the electrical cabinet comprising an input terminal and a plurality of output terminals, and being connectable to a power source via the input terminal and to a plurality of loads via the output terminals, and being configured to distribute current from the power source to the plurality of loads, the electrical cabinet comprising an isolating switch connected to the input terminal and a main bus connected between the isolating switch and the output terminals, the method being implemented by an electronic device for auxiliary monitoring, the method comprising the following steps:

[0030] - acquiring the values ​​of variables measured by the current sensor and the voltage sensor respectively, the variables representing the current flowing between the input terminals and the output terminals of the electrical cabinet and the voltage of the current respectively;

[0031] - calculating an estimated state of the electrical cabinet via a neural network, each measured variable being an input variable of the neural network and the estimated state being an output variable of the neural network; and

[0032] - Transmits a message indicating the estimated status in visual or auditory form.

[0033] According to the invention, the method further comprises a step of acquiring the value of at least one additional variable measured by at least one additional sensor among a gas sensor and a humidity sensor, the variable or each variable representing respectively the amount of gas particles and the humidity inside the electrical cabinet. Furthermore, according to the invention, during the calculation step, at least one additional quantity value is an additional input variable of the neural network.

[0034] The invention also relates to a computer program comprising software instructions which, when executed by a computer, implement the method for assisting in monitoring an electrical cabinet as defined above. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The invention will become more apparent on reading the following description, given by way of non-limiting example only and with reference to the accompanying drawings, in which:

[0036] Figure 1 is a schematic diagram of a current distribution system according to the present invention;

[0037] Figure 2 is a schematic diagram of an electrical cabinet monitoring device according to the present invention;

[0038] Figure 3 is a flow chart of a method for assisting monitoring of an electrical cabinet according to the present invention. DETAILED DESCRIPTION

[0039] Figure 1 is a schematic diagram of a system 1 for distributing electric current between a power source 3 and a plurality of loads 5, to which the distribution system 1 is intended to be connected.

[0040] The power source 3 is, for example, a transformer, such as a medium voltage transformer or a medium-low voltage transformer. Alternatively, the power source is another current distribution system. The power source 3 can provide current to the distribution system 1, which is configured to distribute the current to the load 5.

[0041] The load 5 consumes the current provided by the power source 3. The load 5 is, for example, a household device, a server, a recharging station, and the like.

[0042] The distribution system 1 comprises an electrical cabinet 10. The electrical cabinet 10 is for example located inside a building and for example rests on the floor. The electrical cabinet 10 comprises a medium voltage switchboard and is advantageously configured to distribute a three-phase current with a voltage between 1000 V and 60 kV. In this case, the electrical cabinet 10 is usually constituted by such a medium voltage switchboard.

[0043] Alternatively, the electrical cabinet 10 comprises a low voltage panel and is configured to distribute three-phase current at a voltage less than or equal to 400 V. In this alternative, the electrical cabinet 10 is typically constituted by a low voltage panel.

[0044] Alternatively, the electrical cabinet 10 comprises a low voltage panel and a medium voltage panel. In this alternative, the electrical cabinet 10 is generally constituted by these medium voltage and low voltage panels.

[0045] The electrical cabinet 10 comprises a housing 11, in which most of its components are arranged. The housing 11 is, for example, in the form of a box, not shown, capable of being completely closed, and generally comprises four side walls, a rear wall mechanically integrated with the four side walls, and a front wall. The front wall generally forms a removable door, or a door that can be moved relative to the side walls between a closed configuration and an open configuration, in which the box is closed and in which the components inside the box are allowed to be accessed.

[0046] The electrical cabinet 10 is configured to distribute current from the power source 3 to a plurality of loads 5. To this end, the electrical cabinet 10 includes an input terminal 12 and several output terminals 13. When the distribution system 1 is working, the input terminal 12 is connected to the power source 3, and the output terminals 13 are connected to respective loads 5, respectively.

[0047] The electrical cabinet 10 further comprises an isolating switch 16 and a main bus 17. The isolating switch 16 is connected between the input terminal 12 and the main bus 17. The isolating switch 16 is configured to interrupt the current from the power source 3 in the electrical cabinet 10, in particular to protect the load 5 in the event of an electrical fault in the electrical cabinet 10 or upstream of the electrical cabinet 10, for example in the event of an electrical fault at the power source 3.

[0048] Alternatively, the disconnect switch 16 is a circuit breaker, for example an air circuit breaker.

[0049] The main bus 17 is connected between the isolating switch 16 and the output terminal 13. The main bus 17 is usually connected to the output terminal 13 indirectly.

[0050] In fact, if Figure 1 As shown, the electrical cabinet 10 comprises a first secondary bus 18 , a second secondary bus 19 , a first electrical protection device 22 and several second electrical protection devices 23 .

[0051] The primary bus 17 is connected to a first and a second secondary bus 18 , 19 .

[0052] The first secondary bus 18 is connected to a first protection device 22. The first protection device 22 is for example an air circuit breaker, or a miniature circuit breaker, or even a differential circuit breaker.

[0053] The second secondary bus 19 is connected to a second protection device 23. Figure 1 In the example of , four second protection devices 23 are shown. Advantageously, the second protection devices 23 are miniature circuit breakers or differential circuit breakers.

[0054] Alternatively, not shown, the electrical cabinet 10 comprises additional secondary busses, not shown, each of which is connected to at least one additional electrical protection device.

[0055] The protection devices 22, 23 are configured to interrupt the current flowing from the electrical cabinet 10 to the load 5, particularly downstream of the electrical cabinet 10, particularly in the event of an electrical fault between the output terminal 13 and the load 5, or in the event of an electrical fault in the load 5, so as to protect the distribution system 1 and the load 5.

[0056] The electrical cabinet 10 advantageously comprises a drawer 25. The second protection devices 23 are then advantageously housed in the drawer 25. The drawer 25 is usually accessible by a user, for example to manipulate the second protection devices 23, to replace or add them, or, when the second protection devices 23 are circuit breakers, to reset them after an electrical fault.

[0057] According to an alternative solution that is not shown, the electrical cabinet 10 comprises several drawers in which additional electrical protection devices are housed.

[0058] The electrical cabinet 10 comprises a plinth 27. The plinth 27 advantageously accommodates connection cables, for example between the power source 3 and the disconnector, or between the first protection device 22 and the load 5. According to a particularly advantageous arrangement not shown, the plinth accommodates all cables connected to the protection devices and the loads.

[0059] The dispensing system 1 also includes a sensor. More specifically, Figure 1 In the example shown, the dispensing system 1 comprises current sensors 41 , 42 , 43 , 44 ; voltage sensors 51 , 52 , 53 , 54 ; gas sensors 56 , 57 ; humidity sensors 58 , 59 ; temperature sensors 61 , 62 , 63 , 64 , 65 ; a vibration sensor 67 and a noise sensor 69 .

[0060] exist Figure 1 In the example shown, the number of current sensors 41, 42, 43 and 44 is four, namely a first current sensor 41, a second current sensor 42, a third current sensor 43 and a fourth current sensor 44, and is configured to measure the value of a variable representing the intensity of the current flowing in the electrical cabinet 10. More precisely, the current sensors 41 to 44 are configured here to measure the current in the input terminal 12 by the first current sensor 41, the current in the first secondary bus 18 by the second current sensor 42, the current in the main bus 17 by the third current sensor 43, and the current in the second secondary bus 19 by the fourth current sensor 44, respectively.

[0061] Advantageously, the current sensors 41 to 44 are three-phase current sensors, in other words, they are configured to measure the current intensity of each phase.

[0062] As an alternative, not shown, the distribution system 1 comprises an additional current sensor configured to measure the intensity of the current further flowing through the protection devices 22 and 23 and the output terminal 13 .

[0063] Particularly advantageously, the distribution system 1 comprises current sensors measuring the current intensity in each of the aforementioned elements and also current sensors measuring the current intensity at different locations of the main bus 17 and the first and second secondary buses 18 , 19 , at each output terminal 13 and at each protection device 23 .

[0064] exist Figure 1 In the example of FIG. 1 , the number of the voltage sensors 51, 52, 53, and 54 is four, namely, the first voltage sensor 51, the second voltage sensor 52, the third voltage sensor 53, and the fourth voltage sensor 54, and is configured to measure the value of a variable representing the voltage of the current flowing in the electrical cabinet 10. More precisely, the voltage sensors 51 to 54 measure the potential difference between the current flowing in the electrical cabinet 10 and the reference potential. Figure 1 In the example, the voltage sensors 51 to 54 are configured to measure the voltage of the current flowing in the input terminal 12 by the first voltage sensor 51, in the first secondary bus 18 by the second voltage sensor 52, in the main bus 17 by the third voltage sensor 53, and in the second secondary bus 19 by the fourth voltage sensor 54.

[0065] Advantageously, the voltage sensors 51 to 54 are three-phase voltage sensors, in other words configured to measure the voltage of each phase of the current.

[0066] As an alternative, not shown, the distribution system 1 comprises an additional voltage sensor configured to measure the voltage of the current flowing in the protection devices 22 and 23 and the output terminal 13 .

[0067] It is particularly advantageous if the distribution system 1 comprises a voltage sensor measuring the voltage of the current flowing in each of the aforementioned elements and, in addition, a voltage sensor measuring the voltage of the current at different locations of the main bus 17 and of the first and second secondary buses 18 , 19 , at each output terminal 13 and in each protection device 23 .

[0068] exist Figure 1In the example of FIG. 1 , the number of gas sensors 56 and 57 is two, namely a first gas sensor 56 and a second gas sensor 57, and are configured to measure a variable representing the number of gas particles inside the electrical cabinet 10, in other words, inside the housing 11 of the electrical cabinet 10. More precisely, the gas sensors 56 and 57 measure the number of particles of at least one given gas. Preferably, the gas sensors 56 and 57 measure the type of gas inside the electrical cabinet, and the number of particles of each gas.

[0069] like Figure 1 As shown, the first gas sensor 56 is located in the housing 11 and is advantageously located at the top of the housing 2, in other words, at the position farthest from the ground. The second gas sensor 57 is located inside the drawer 19, on the inner wall of the drawer 19.

[0070] In an alternative not shown, the dispensing system 1 comprises an additional gas sensor configured to measure the amount of gas particles in or near the output terminals 13. In the case where the output terminals 13 are adjacent to each other, in other words, the distance of any output terminal 13 from any other output terminal 13 is less than 10 cm, then a single gas sensor 56 or 57 is advantageously sufficient to measure the amount of gas particles near all output terminals 13.

[0071] exist Figure 1 In the example of FIG. 1 , there are two humidity sensors 58 and 59 , namely a first humidity sensor 58 and a second humidity sensor 59 , which are configured to measure a variable representing humidity. In particular, the variable represents the air humidity inside the housing 11 .

[0072] In practice, humidity sensors 58 and 59 are typically also sensors representing a variable of the ambient temperature, in other words a variable representing the air temperature in the vicinity of humidity sensors 58, 59. "In the vicinity" means located at a distance of no more than a few centimeters, for example no more than ten centimeters.

[0073] like Figure 1 As shown, the first humidity sensor 58 is located near the input terminal 12 in the housing 11 and is configured to measure a variable representing the air humidity near the input terminal 12. The second humidity sensor 59 is located inside the drawer 19, on the inner wall of the drawer 19, and is configured to measure a variable representing the air humidity inside the drawer 19.

[0074] In an alternative not shown, the dispensing system 1 comprises an additional humidity sensor configured to measure the humidity in or near the output terminals 13. In case the output terminals 13 are adjacent to each other, a single humidity sensor 58 or 59 is advantageously sufficient to measure the humidity near all output terminals 13.

[0075] exist Figure 1In the example shown, there are five temperature sensors 61, 62, 63, 64, and 65, namely, a first temperature sensor 61, a second temperature sensor 62, a third temperature sensor 63, a fourth temperature sensor 64, and a fifth temperature sensor 65. The temperature sensors 61 to 65 are configured to measure a variable value representing the temperature of the electrical cabinet 10. More specifically, the temperature sensors 61 to 65 are surface temperature sensors, and are configured to measure a variable value representing the surface temperature of an element of the electrical cabinet 10.

[0076] The temperature sensors 61 to 65 are configured here to measure the temperature of the input terminal 12 through the first temperature sensor 61, the temperature of the first secondary bus 18 through the second temperature sensor 62, the temperature of the main bus 17 through the third temperature sensor 63, the temperature of the first protection device 22 through the fourth temperature sensor 64, and the temperature of one of the second protection devices 23 through the fifth temperature sensor 65.

[0077] In an alternative not shown, the distribution system 1 comprises additional temperature sensors configured to measure the temperature of five of the following elements: the main bus 17, the second secondary bus 19, the protection device 22 and the output terminal 13.

[0078] Particularly advantageously, the distribution system 1 comprises temperature sensors measuring the temperature of each of the aforementioned elements and additionally temperature sensors measuring the temperature at different locations on the main bus 17 and the first 18 and second secondary buses 19 and at each protection device 23 .

[0079] The vibration sensor 67 is configured to collect the value of a variable representing the vibration of the electrical cabinet 10. The vibration of the electrical cabinet 10 is caused, for example, by the passage of small animals such as rodents or by poor fastening of the electrical cabinet components to each other. The vibration sensor 67 is, for example, an accelerometer or a gyroscope. Figure 1 In the example of , the vibration sensor 67 is located in the base 27. Alternatively, the vibration sensor 67 is located on one of the following elements: the housing 11, the input terminal 12, the first secondary bus 18, the main bus 17, the second secondary bus 19, the electrical protection devices 22 and 23, and the output terminal 13; and is configured to measure a variable representing vibration near the corresponding element.

[0080] According to an alternative that is not shown, the dispensing system 1 comprises several vibration sensors located on all or some of the above-mentioned elements.

[0081] In particularly advantageous manner, the distribution system 1 comprises vibration sensors measuring the vibrations of each of the aforementioned elements and, moreover, vibration sensors measuring the vibrations at different locations of the primary bus 17 and of the first and second secondary buses 18 , 19 .

[0082] The noise sensor 69 is configured to collect the value of a variable representing the noise inside the electrical cabinet 10. The noise inside the electrical cabinet 10 is caused, for example, by small animals such as rodents, poor fastening of electrical cabinet components to each other, or foreign objects such as tools forgotten during maintenance being mistakenly introduced into the electrical cabinet. For example, the noise sensor 69 is a microphone. Figure 1 In the example of the embodiment, the noise sensor 69 is located in the drawer 25 and is configured to measure a variable representing the noise in the drawer 25. Alternatively, the noise sensor 69 is located on or near one of the following elements: the housing 11, the input terminal 12, the electrical protection devices 22 and 23, the output terminal 13, and the base 27; and is configured to measure a variable representing the noise near the corresponding element.

[0083] According to an alternative that is not shown, the dispensing system 1 comprises several noise sensors located on or near all or some of the aforementioned elements and configured to measure the noise near all or some of the aforementioned elements.

[0084] The distribution system 1 also includes electronic equipment 90 for assisting in monitoring the electrical cabinet 10, also referred to as monitoring auxiliary equipment 90. Figure 1 In the example shown, the monitoring auxiliary device 90 is a separate electronic device located inside the housing 11. Alternatively, not shown, the monitoring auxiliary device 90 is included in other electronic devices, for example, in a server, preferably located outside the housing 11.

[0085] The monitoring auxiliary device 90 includes a collection module 92, an estimation module 94 and a transmission module 96. Figure 2 shown.

[0086] exist Figure 2 In the example of , the monitoring auxiliary device 90 includes an information processing unit 100 , which includes, for example, a memory 102 and a processor 104 associated with the memory 102 .

[0087] exist Figure 2 In the example of , the acquisition module 92, the estimation module 94 and the transmission module 96 are all implemented in the form of software or software blocks that can be executed by the processor 104. The memory 102 of the monitoring auxiliary device 90 can then store the acquisition software, the estimation software and the transmission software. The processor 104 can then execute each of the acquisition software, the estimation software and the transmission software.

[0088] In an alternative solution not shown, the acquisition module 92 , the estimation module 94 and the transmission module 96 are all implemented in the form of programmable logic components such as FPGA (field programmable gate array) or integrated circuits such as ASIC (application-specific integrated circuit).

[0089] When the monitoring auxiliary device 90 is implemented in the form of one or more software programs, in other words, in the form of a computer program (also referred to as a computer program product), it can also be recorded on a computer-readable medium (not shown). A computer-readable medium is, for example, a medium capable of storing electronic instructions and coupled to a bus of a computer system. For example, the readable medium is an optical disk, a magneto-optical disk, a ROM memory, a RAM memory, any type of non-volatile memory (e.g., a flash memory or NVRAM) or a magnetic card. Then, the computer program including the software instructions is stored on the readable medium.

[0090] The acquisition module 92 is configured to acquire values ​​of variables measured by each current sensor 41 to 44 , each voltage sensor 51 to 54 , each gas sensor 56 and 57 , each humidity sensor 58 and 59 , each temperature sensor 61 to 64 , the vibration sensor 67 , and the noise sensor 69 .

[0091] The estimation module 94 is configured to calculate the estimated state of the electrical cabinet 10 via an artificial neural network (ANN) (hereinafter referred to as a neural network). To this end, the estimation module 94 uses the values ​​collected by the collection module 92, so that each variable collected by the collection module 92 is an input variable of the neural network. The estimated state is the output variable of the neural network.

[0092] A neural network consists of a series of ordered layers of neurons, each of which takes input from the output of the previous layer. More precisely, each layer consists of neurons that take input from the output of neurons in the previous layer or from the input variables of the first layer.

[0093] Alternatively, more complex neural network structures can be envisioned, where a layer can be linked to layers further away than the immediately preceding layer.

[0094] Each neuron is also associated with an operation, in other words, a type of processing performed by the neuron in the corresponding processing layer.

[0095] Each layer is linked to other layers via a number of synapses. A synaptic weight is associated with each synapse, which forms a link between two neurons. This is usually a real number, with both positive and negative values. In some cases, the synaptic weight is a complex number.

[0096] Each neuron is capable of performing a weighted sum of the values ​​received from the neurons of the previous layer, then multiplying each value by the respective synaptic weight of each synapse or link between the neuron and the neurons of the previous layer, then applying an activation function (usually a nonlinear function) to the weighted sum, and delivering the value resulting from the application of the activation function at the output of the neuron, particularly to the neurons of the next layer to which it is connected. The activation function allows nonlinearity to be introduced into the processing performed by each neuron. The sigmoid function, the hyperbolic tangent function, and the Heaviside function are examples of activation functions.

[0097] As an optional addition, each neuron can also apply a multiplicative factor (also called a bias) to the output of the activation function, and the value output by the neuron is the product of the bias value and the value output by the activation function.

[0098] Alternatively, the neural network is a convolutional neural network. A convolutional neural network is also sometimes referred to as a convolutional neural network or CNN.

[0099] In a convolutional neural network, each neuron in the same layer has exactly the same connection pattern as its neighboring neurons, but at different input locations. The connection pattern is called a convolution kernel.

[0100] A fully connected neuron layer is a layer in which each neuron of the layer is connected to all neurons of the previous layer.

[0101] This type of layer is often called a "fully connected" layer, or sometimes a "dense layer".

[0102] The estimated state of the electrical cabinet 10 is advantageously a state from the group consisting of a normal state, an abnormal state and a critical state. The normal state is associated with the normal operation of the electrical cabinet 10, in other words, the neural network estimates that there are no electrical, mechanical or thermal faults in the electrical cabinet 10. The abnormal state is associated with the abnormal operation of the electrical cabinet 10, in other words, the neural network estimates that there are electrical, mechanical or thermal faults, but they do not cause problems that require immediate action on the part of the user. An abnormal state is, for example, the detection of noise in the electrical cabinet 10 without any changes in other variables measured by the sensor. The critical state is associated with a critical fault in the electrical cabinet 10, in other words, the neural network believes that there is an electrical, mechanical or thermal fault and it poses a significant risk to the operation of the electrical cabinet, requiring, for example, urgent maintenance operations and / or cutting off the current flowing in the electrical cabinet 10, in other words, shutting down the electrical cabinet 10.

[0103] In other words, the normal state, the abnormal state and the critical state correspond to three consecutive critical levels, the normal state is associated with a first level, the abnormal state is associated with a second level higher than the first level, and finally the critical state is associated with a third level higher than the second level. These states allow the user to estimate whether it is necessary to intervene in the electrical cabinet 10 for maintenance operations, and the urgency of the maintenance operations.

[0104] The neural network is trained during a preliminary training phase so that it can correctly predict the estimated state during an inference phase following this preliminary training phase. The training is performed using training data corresponding to the input variables and output variables of the neural network. The training data are, for example, examples of sensor measurements, and the estimated state of the electrical cabinet associated with these measurements. An error calculation is performed between the predicted output variable (by the neural network according to the input training data) and the corresponding output training data, and then an adjustment of the synaptic weights of the neural network is performed as a function of the calculated error, for example via a gradient back-propagation algorithm and the repetition described above, in order to minimize the error, in other words, to gradually reduce the error until a predetermined minimum threshold is reached.

[0105] The training phase is complete when the error has been reduced to this threshold. The synaptic weights and any biases used for neural network inference are obtained at the end of this training phase, in other words, corresponding to the minimum error between the predicted output variables and the corresponding output training data.

[0106] The transmission module 96 is configured to transmit a message representing the estimated state in one of two forms: visual or auditory. The transmission module 96 is, for example, a human-machine interface, or is connected to a human-machine interface, for displaying a message representing the estimated state of the electrical cabinet 10. The message is, for example, a color code, a color associated with the estimated state, or an auditory message, in particular an alarm if the estimation module 94 calculates that the estimated state is a critical state. Those skilled in the art will understand that each estimated state is associated with a corresponding visual or auditory output, and is different from one estimated state to another, so that the user can more easily and quickly perceive which state of the electrical cabinet 10 the monitoring auxiliary device 90 has estimated. In other words, each estimated state is associated with a corresponding color and / or sound message.

[0107] Optionally, the transmission module 96 is configured to transmit additional information related to the sensor, such as the value of a variable measured by the sensor.

[0108] Particularly advantageously, the estimation module 94 is configured to estimate the state of the electrical cabinet 10 for several different risks associated with the electrical cabinet 10. A first risk is, for example, a fault in the electrical cabinet 10, whether electrical, mechanical or thermal; a second risk is, for example, the risk of an arc discharge in the electrical cabinet 10. Advantageously, other risks are estimated by the estimation module 94, such as the risk of the presence of small animals or rodents inside the electrical cabinet 10, the risk of the presence of water inside the electrical cabinet 10, etc.

[0109] In the case where the estimation module 94 is configured to estimate the state of the electrical cabinet 10 for several risks, the estimation module 94 calculates the estimated state for each risk. In this case, the output variable of the neural network is the estimated state of the electrical cabinet 10 for each risk, and the transmission module 96 is then configured to transmit a message representing the estimated state of each risk.

[0110] Advantageously, the estimation module 94 is configured to generate a resulting estimation state that is equal to the estimation state of the maximum risk when the estimation is performed. For example, the maximum risk is the risk with the highest probability of occurrence. Alternatively or additionally, the maximum risk is the risk with the highest criticality according to a predefined criticality order between risks, while having a probability of occurrence greater than a predefined minimum threshold. The transmission module 96 is then configured to transmit a message representing the resulting estimation state, or even to transmit additional information related to the maximum risk when the estimation is performed.

[0111] Alternatively, the estimation module 94 calculates the estimated state of the electrical cabinet 10 only for the greatest risk. In this case, the output variable of the neural network is the estimated state of the electrical cabinet 10 for the greatest risk, and the transmission module 96 is then configured to transmit a message representing the estimated state for said risk.

[0112] In order to best estimate the various risks, some sensors are advantageously added, or possibly removed. In particular, in the case of estimating the risk of an electric arc, the vibration sensor 67 and the noise sensor 69 are particularly advantageous in order to obtain the most precise and accurate prediction possible, whereas in the case of estimating the risk of an electrical, mechanical or thermal failure in an electrical cabinet, the vibration sensor 67 and the noise sensor 69 can be omitted without this having a significant impact on the accuracy of the calculations performed by the estimation module 94.

[0113] The risks taken into account by the estimation module 94 for calculating the estimated status are advantageously selected by the user, with sensors being added according to the risks the user wishes the estimation module 94 to assess. Alternatively, the sensors required for calculating the estimated status for the various risks are present in the electrical cabinet 10, and the sensors are then activated by the monitoring aid 90 according to the risks selected by the user.

[0114] A method for assisting in monitoring the electrical cabinet 10 implemented by the monitoring assistance device 90 will now be described.

[0115] The electrical cabinet 10 is in operation, so current flows from the power source 3 to the load 5 through the electrical cabinet 10. The current sensors 41 to 44, the voltage sensors 51 to 54, the gas sensors 56 and 57, the humidity sensors 58 and 59, the temperature sensors 61 to 64, the vibration sensor 67, and the noise sensor 69 are in operation and can perform measurement according to the risk of the estimated state to be calculated.

[0116] During step 201 , the monitoring auxiliary device 90 , more specifically the acquisition module 92 , acquires the values ​​of the variables measured by the current sensors 41 to 44 , the voltage sensors 51 to 54 , the gas sensors 56 and 57 , the humidity sensors 58 and 59 , the temperature sensors 61 to 64 , the vibration sensor 67 and the noise sensor 69 .

[0117] These values ​​are transmitted to the estimation module 94, which calculates the estimated state of the electrical cabinet 10 by means of a neural network in a subsequent step 202. As previously described, each variable measured by the current sensors 41 to 44, the voltage sensors 51 to 54, the gas sensors 56 and 57, the humidity sensors 58 and 59, the temperature sensors 61 to 64, the vibration sensor 67, and the noise sensor 69 is an input variable of the neural network, and the output variable of the neural network is the estimated state.

[0118] During step 203, after calculating the state 202, the transmission module 96 transmits visually, audibly or visually and audibly a message representative of the state estimated in the calculation step 202. Optionally, the transmission module 96 also transmits additional data, such as values ​​measured by sensors.

[0119] Alternatively, during step 202, the estimation module 94 calculates an estimated state for each risk. In this case, during step 203, the transmission module 96 transmits a message representative of the estimated state for each risk.

[0120] According to another alternative, if the estimation module 94 is configured to estimate several risks associated with the electrical cabinet, during step 202, the estimation module 94 generates, in addition to calculating the estimated state in step 202, a resulting estimated state equal to the estimated state of the greatest risk when the estimation is performed. In this case, at step 203, the transmission module 96 transmits a message representing the resulting estimated state and possibly also additional information related to the type of risk that was greatest when the estimation was performed.

[0121] According to an alternative (not shown), when the estimated state is equal to the critical state, the estimation module 94 is advantageously further configured to control the disconnector 16 to the open position, corresponding to the absence of current flow in the electrical cabinet 10 .

[0122] Thus, the monitoring aid 90 aids in monitoring the electrical cabinet 10. The possibility of evaluating certain specific risks (such as arc risk) by adding specific sensors allows the monitoring of the electrical cabinet 10 to be customized according to the user's preferences. The emission of messages representing the estimated status facilitates the user's decision making. Based on the messages sent by the transmission module 96, the user decides on the action to be taken, such as a maintenance operation and the date on which it is to be performed, and / or the cutting off of the current flowing in the electrical cabinet 10.

[0123] To the extent technically feasible, any feature described above with respect to one embodiment or alternative may be implemented with respect to other embodiments and alternatives described above.

Claims

1. An electronic device (90) for assisting monitoring of an electrical cabinet (10), the electrical cabinet (10) comprising an input terminal (12) and several output terminals (13), and being connectable to a power source (3) via the input terminal (12) and to a plurality of loads (5) via the output terminals (13), and being configured to distribute current from the power source (3) to the plurality of loads (5), the electrical cabinet (10) comprising an isolating switch (16) connected to the input terminal (12) and a main bus (17) connected between the isolating switch (16) and the output terminals (13), the electronic device (90) comprising: - an acquisition module (92) configured to acquire values ​​of variables respectively representing the current flowing between the input terminal (12) and the output terminal (13) and the voltage of the current, measured by the current sensor (41, 42, 43, 44) and the voltage sensor (51, 52, 53, 54); - an estimation module (94) configured to calculate an estimated state of the electrical cabinet (10) via a neural network, each variable collected by the collection module (92) being an input variable of the neural network, and the estimated state of the electrical cabinet (10) being an output variable of the neural network; and - a transmission module (96) configured to transmit a message representing the estimated status in one of a visual form and an auditory form; The acquisition module is also configured to acquire the value of at least one additional variable measured by at least one additional sensor among a gas sensor (56, 57) and a humidity sensor (58, 59), the variable or each variable representing the amount of gas particles and the humidity inside the electrical cabinet (10), respectively. It is characterized in that The acquisition module (92) is also configured to acquire the value of a variable representing the noise in the electrical cabinet (10) measured by the noise sensor (69), and the estimation module (94) is then configured to calculate the estimated state of the electrical cabinet (10) via the neural network as another function of at least one additional variable, the at least one additional variable including a variable representing the noise, the at least one additional variable being an additional input variable of the neural network.

2. The device (90) according to claim 1, wherein the acquisition module (92) is further configured to acquire the values ​​of additional variables measured by the humidity sensor (56, 57) and by the gas sensor (58, 59).

3. The device (90) according to any one of claims 1 to 2, wherein the acquisition module (92) is also configured to acquire the value of a variable measured by a temperature sensor (61, 62, 63, 64, 65), the measured variable representing the temperature inside the electrical cabinet (10).

4. The device (90) according to any one of claims 1 to 2, wherein the acquisition module (92) is further configured to acquire the value of a variable measured by a plurality of temperature sensors (61, 62, 63, 64, 65), wherein the variable represents the temperature inside the electrical cabinet (10), and each temperature sensor (61, 62, 63, 64, 65) is configured to measure the following temperatures: the temperature near the input terminal (12), the temperature near the corresponding output terminal (13), the temperature of the main bus (17), and the temperature of the electrical protection device (22, 23) connected between the main bus (17) and the corresponding output terminal (13).

5. The device (90) according to any one of claims 1 to 2, wherein the acquisition module (92) is further configured to acquire the value of a variable representative of the vibration of the electrical cabinet (10) measured by a vibration sensor (67).

6. The apparatus (90) according to any one of claims 1 to 2, wherein the estimated state of the electrical cabinet (10) is one of the group consisting of a normal state, an abnormal state, and a critical state.

7. A system (1) for distributing current between a power source (3) and a plurality of loads (5), the system (1) comprising: - an electrical cabinet (10), comprising: oInput terminals (12), which can be connected to a power source (3), oSeveral output terminals (13), capable of connecting to multiple loads (5), oisolating switch (16), connected to the input terminals (12), and o a main bus (17) connected between the isolating switch (16) and the plurality of output terminals (13), The electrical cabinet (10) is configured to distribute current from the power source (3) to the plurality of loads (5); - current sensors (41, 42, 43, 44) and corresponding voltage sensors (51, 52, 53, 54) configured to measure values ​​of variables representative of the current and the voltage of the current, respectively, flowing between the input terminals (12) and the output terminals (13) of the electrical cabinet (10); - electronic monitoring auxiliary equipment (90) for an electrical cabinet (10), The system (1) further comprises at least one additional sensor from the gas sensors (56, 57) and the humidity sensors (58, 59), the at least one additional sensor being configured to collect the value of at least one additional variable, the at least one additional variable representing the amount of gas particles and the humidity inside the electrical cabinet (10), respectively, characterized in that: The system further comprises a noise sensor (69), and the electronic monitoring aid (90) is according to any one of claims 1 to 2.

8. A method for assisting monitoring of an electrical cabinet (10), the electrical cabinet (10) comprising an input terminal (12) and a plurality of output terminals (13), and being connectable to a power source (3) via the input terminal (12) and to a plurality of loads (5) via the output terminals (13), and being configured to distribute current from the power source (3) to the plurality of loads (5), the electrical cabinet (10) comprising an isolating switch (16) connected to the input terminal (12) and a main bus (17) connected between the isolating switch (16) and the output terminals (13), the method being implemented by an electronic monitoring auxiliary device (90), the method comprising the following steps: - collecting (201) the values ​​of variables measured by current sensors (41, 42, 43, 44) and voltage sensors (51, 52, 53, 54), respectively, these variables representing the current flowing between the input terminal (12) and the output terminal (13) of the electrical cabinet and the voltage of the current; - calculating (202) an estimated state of the electrical cabinet (10) via a neural network, each measured variable being an input variable of the neural network and the estimated state being an output variable of the neural network; and - transmitting (203) a message representing the estimated status in one of a visual form or an audio form, The method further comprises a step of acquiring (201) the value of at least one additional variable measured by at least one additional sensor among the gas sensors (56, 57) and the humidity sensors (58, 59), the variable or each variable representing the humidity and the amount of gas particles in the electrical cabinet (10), respectively, characterized in that The method further comprises a step (201) for acquiring the value of a variable representative of the noise in the electrical cabinet measured by a noise sensor (69), and that during the calculation step (202), the at least one additional variable comprises a variable representative of the noise and the at least one additional variable is an additional input variable of the neural network.

9. A computer program comprising software instructions which, when executed by a computer, implement the method according to claim 8.

Images