Monitoring system and method for monitoring voltage network
By introducing a communication interface into the overvoltage protection device, the status value is transmitted to an external evaluation unit for evaluation, and using high computing power and artificial intelligence to predict future states, the problem of insufficient computing power of the protection device in the prior art is solved, and the correct implementation is achieved. In-depth evaluation and prediction of voltage networks and protection devices improves the stability of voltage networks and the reliability of protection devices.
Patent Information
- Application Number
- CN202380034362.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-03-04
- Filing Date
- 2023-03-01
- Publication Date
- 2024-11-26
AI Technical Summary
Existing overvoltage protection devices can only provide basic protection and status display when handling overvoltage events, cannot provide more in-depth evaluation and prediction, and due to space limitations, the computing power is insufficient to perform complex evaluations.
Design a monitoring system to transmit state values to external evaluation units for evaluation by introducing a communication interface into the protection device, and use high computing power evaluation units to perform complex evaluation and prediction, including artificial intelligence to predict future states, and through bidirectional communication The interface exchanges information with the protection device and the display device.
It realizes a deeper evaluation and prediction of the status of the voltage network and protection device, which can promptly identify potential faults and aging trends, reduce downtime, improve the stability of the voltage network and the reliability of the protection device.
Smart Images

Figure CN119032479A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to a monitoring system for monitoring a voltage network. The invention also relates to a method for monitoring a voltage network by means of the monitoring system. Background Art
[0002] Various protective devices are known from the prior art, such as surge protection devices (SPD), also called surge arresters. Such protective devices are integrated into the voltage network to be monitored and protected, such as the low-voltage network, also called the building network.
[0003] In the event of an overvoltage, for example due to a lightning event, the protective device serves to discharge the existing overvoltage in order to protect the devices present in the voltage network from the overvoltage. For this purpose, the protective device generally has at least one tripping protective component which responds in the event of an overvoltage and changes into a conductive or quasi-conductive state, thereby dissipating the overvoltage due to the associated current flow. The tripping protective component is therefore also referred to as a disconnecting device, wherein the disconnecting device is designed, for example, as a spark gap.
[0004] Such protective devices typically have a display element which displays the respective state of the protective device, for example by means of a green or red mechanically changeable display element, the respective color depending on the state of the protective device, in particular on the state of the protective component which is triggered. Such an overvoltage device is known, for example, from DE 10 2019 110 745 B3.
[0005] An overvoltage protection device is known from WO 2016 / 026522 A1, which performs evaluation or diagnosis similarly to the protection device of DE 10 2019 110 745 B3. For this purpose, the overvoltage protection device of WO 2016 / 026522 A1 has a diagnostic circuit that performs evaluation or diagnosis, so as to subsequently send the result of the diagnosis or evaluation to a controller.
[0006] However, the protection devices known in the prior art are only designed to safely and reliably reduce existing overvoltages, to avoid overloading the voltage network and to enable operation again as quickly as possible when the overvoltage event no longer exists. In addition, the current status of the protection device is displayed on site so that the user can understand the current status. However, additional knowledge cannot be obtained with such protection devices. Summary of the invention
[0007] It is therefore an object of the present invention to further improve such a protective device so that it provides more information.
[0008] According to the invention, the object is achieved by a monitoring system for monitoring a voltage network, the monitoring system having a protection device to be incorporated into the voltage network, the protection device comprising at least one protection component that triggers. The protection device has at least one communication interface, which is configured to transmit a status value of the protection device to an evaluation unit that is configured separately from the protection device. The evaluation unit is configured to perform an evaluation, so that the evaluation is outsourced from the protection device.
[0009] The basic idea of the invention is to provide an outsourced evaluation, whereby the protection device itself can be designed to save space. In contrast, the intelligence or computing power required for the evaluation can be implemented in an evaluation unit designed separately from the protection device, thereby creating an external logic that communicates with at least one protection device to be incorporated into the voltage network, for example via a computer network such as the Internet. The outsourced evaluation thus ensures that the evaluation of the status values transmitted by the protection device takes place outside the protection device. This evaluation is also referred to as diagnosis.
[0010] The status value is thus transmitted in the form of data to a separately constructed evaluation unit. For this purpose, a transmission protocol such as TCP, in particular TCP / IP, can be used.
[0011] In any case, due to the separately designed evaluation unit, the latter can have a correspondingly high computing power, whereby even complex evaluations can be performed, which are not possible with conventional protection devices. This is mainly due to the fact that only a small amount of installation space is available at the installation location (conventionally in the area of the top hat rail).
[0012] In principle, the monitoring system can include a plurality of protection devices which are integrated into the same voltage network or into different voltage networks. The plurality of protection devices can send data to the same evaluation unit, in particular communicate with the evaluation unit. As a result, the separately designed evaluation unit can obtain a plurality of status values from different protection devices, so that the evaluation unit has more data and information which can be taken into account in the evaluation.
[0013] The evaluation can therefore be carried out based on a correspondingly large database, thereby allowing correlations between different data to be determined.
[0014] For example, a connection may be identified based on a joint evaluation of different status values obtained from different protection devices.
[0015] The protective component that triggers may be a (corner) spark gap, which changes into a conducting or quasi-conducting state when an overvoltage is present.
[0016] On the one hand, it is provided that the state value of the protection device is a measured value detected by the protection device or a value representing the triggering state of a triggering protection component of the protection device. The protection device can, for example, have a measuring and / or sensor unit, by which the corresponding measured value is detected. In particular, the measured value is the value of a characteristic variable of the voltage network. Based on the characteristic variable, the state of the voltage network can be determined.
[0017] In principle, the characteristic variable can be a voltage, a current, a power, a frequency, a distortion, a harmonic, a reactive power and / or an energy value of a phase in a voltage network, in particular a multi-phase voltage network.
[0018] In particular, it is provided that the protection device has a plurality of measuring and / or sensor units. In this respect, a plurality of characteristic variables of the voltage network can be determined and transmitted to the evaluation unit in order to be able to carry out a more precise evaluation by means of the separately designed evaluation unit.
[0019] The value representing the triggering state of the protection component of the protection device that triggers can be a binary value. In this regard, "0" can represent the non-triggered state of the protection component, while "1" represents the triggered state of the protection component that triggers. Therefore, the protection device can transmit via the communication interface by means of the value representing whether the protection component that triggers has been triggered, that is, whether an overvoltage event exists.
[0020] On the other hand, it is provided that the protection device is an overvoltage protection device. In this regard, the protection device can be designed as an overvoltage protection device ("surge protection device", SPD). Therefore, the protection device is used to derive overvoltage, thereby safely and efficiently protecting devices and components integrated in the voltage network from the influence of overvoltage. Since the protection device also has a communication interface, the protection device transmits data to a separately constructed evaluation unit via the communication interface, thereby ensuring that information about the state of the protection device (i.e., the triggering state) and / or the measured values detected by the protection device are transmitted to the separately constructed evaluation unit, and the evaluation unit is configured to perform a corresponding evaluation in order to implement a more in-depth analysis.
[0021] In addition to the protection component for triggering, the protection device may further include a voltage limiting protection component. For example, the voltage limiting protection component is a metal oxide varistor. The protection element for triggering and the voltage limiting protection component may be connected in series.
[0022] According to another aspect, the system includes an evaluation unit that is constructed separately from the protection device, and the evaluation unit has at least one communication interface, which is configured to communicate with the communication interface of the protection device. Each of the communication interfaces, i.e., the communication interface of the protection device and / or the communication interface of the evaluation unit, can be constructed as a bidirectional communication interface. In this regard, the monitoring system includes, in addition to the protection device, a separately constructed evaluation unit that communicates with the protection device. The evaluation unit and / or the protection device can each have a bidirectional communication interface, so that data can not only be received but also can be sent. This results in a bidirectional communication between the protection device and the evaluation unit.
[0023] Alternatively, it can be provided that the protection device has two separate communication interfaces and / or the evaluation unit has two separate communication interfaces, whereby a unidirectional communication or data transmission respectively takes place between the corresponding communication interfaces. This can be meaningful if the data transmission in at least one direction is to have higher safety requirements than the data transmission in the respective other direction.
[0024] In principle, the evaluation unit can be a server-based evaluation unit, such as a cloud system. In this respect, the protection device can transmit at least one state value to a cloud that is in communication connection with a plurality of devices, in particular a plurality of protection devices. In particular, the evaluation unit can therefore obtain data from a large number of devices, i.e. other devices than the protection device, which data can be taken into account for the evaluation. In addition, it is possible to enable separate access to the server-based evaluation unit, so that an authorized user has access to the corresponding data, which has been transmitted from the at least one protection device to the server-based evaluation unit. In other words, the user or operator of the monitoring system can have access to the evaluation results located in the cloud. Therefore, the evaluation results determined by the evaluation unit can be present in the cloud, so that the evaluation results can be retrieved. However, it is also feasible to transmit the evaluation results from the evaluation unit to, for example, the protection device, so that the evaluation results can be directly available on site.
[0025] According to a further aspect, the evaluation unit is configured to receive input data from at least one database or measuring device. This is particularly useful if the evaluation unit is a server-based evaluation unit that communicates with a plurality of devices installed at different locations. In particular, data from a database can be taken into account in the evaluation, which data provide additional information, thereby improving the evaluation of the status value of the protective device.
[0026] This may be weather data, climate data or generally environmental data. In particular, lightning events etc. from the database may be taken into account, thereby improving the evaluation of the status value of the protective device accordingly. Time data (weekdays, weekends, holidays, daytime and / or nighttime) or usage data of the system in this environment (e.g. for the travel plan of a train) or usage data of the charging system in this environment may also be obtained from the database.
[0027] The further measuring device may be a device that is directly incorporated into the voltage network but has no protective function for the voltage network, such as a simple current or voltage measuring device. In addition, the measuring device may be a device that measures a variable that is independent of the voltage network, such as a humidity sensor or an ambient temperature sensor or the like.
[0028] In addition to the status values transmitted by the protective devices integrated into the voltage network, the monitoring system can therefore also take into account at least one second variable in the evaluation. The second variable can be a value from a database, a measured value or a characteristic variable of the voltage network.
[0029] In this respect, the monitoring system may comprise at least one database and / or additional measuring devices.
[0030] Furthermore, the evaluation unit can have at least one processor unit, which is configured to process at least the state values acquired from the protection device. The processor unit can be configured to execute an algorithm in order to determine an evaluation result, such as an output value or a state, based on the acquired state values, in particular a state representative of the voltage network or the protection device.
[0031] This may be the (current) aging state of the protective device or the (current) state of the voltage network, ie the network state of the voltage network.
[0032] However, it is also possible to predict the corresponding states and thus the future aging state of the protection device or the future state of the voltage network, wherein at least the state values of the protection device are processed by means of the evaluation unit. This makes it possible, for example, to predict the future network quality and problems caused by aging, so that corresponding countermeasures can be introduced in good time.
[0033] In particular, the processor unit comprises an artificial intelligence which is configured to predict the state of the voltage network and / or the state of the protection device based on the state values acquired from the protection device. This may be a fault prediction of such a protection device or a state prediction of the voltage network based on previously detected data about the voltage network which have been transmitted to the evaluation unit from the at least one protection device, in particular additionally from a further device or a database.
[0034] Artificial intelligence can be used to process large amounts of data, especially different types of data, and identify the relationships (associations) between different data, thereby enabling more in-depth analysis.
[0035] In this respect, the evaluation unit, in particular the processor unit including artificial intelligence, can therefore predict future states based on historical data in order to enable the user or operator to promptly introduce appropriate countermeasures to promptly counteract a predicted poor network quality (state) of the voltage network or a predicted error of a protective device. For example, an impending failure of a protective device can be recognized early so that the protective device can be replaced in time, thereby resulting in no downtime or only minimal downtime, because a replacement device is already in stock or the protective device has been replaced before the actual failure.
[0036] Furthermore, the separately constructed evaluation unit is configured to determine an evaluation result, in particular an output value and / or a state, based on the state value of the protection device. The evaluation unit thus processes the state value transmitted by the protection device in order to obtain an evaluation result, such as an output value or a state, which is understandable to a user.
[0037] Furthermore, the separately constructed evaluation unit is provided for transmitting the determined evaluation result to the protective device or to a display device. As a result, the evaluation result (which is easily understandable to the user) can be output on the protective device itself or on a display device arranged in the installation area of the protective device. This ensures that the user at the location of the protective device is informed about the protective device, in particular its status.
[0038] On the other hand, it is provided that the protection device has at least one display, which is arranged to display the evaluation result of the evaluation unit. The display can be a digital display, for example in the form of a screen or at least one LED. There can be a plurality of LEDs, in particular multi-colored LEDs, for example red, yellow or orange and green. In particular, the display is connected to the communication interface of the protection device in a signal-transmitting manner, so that the protection device realizes the data corresponding to the evaluation result obtained via the communication interface to operate the display, i.e. the screen or one or more LEDs. Therefore, the evaluation unit transmits the evaluation result to the protection device, so that the evaluation result can be displayed at the location of the protection device.
[0039] Alternatively, the display can also be a mechanical display, such as a flap or a slider, which is mechanically moved to display the evaluation result, in particular in such a way that the red or green face is visible. The mechanical display is also (indirectly) actuated based on the data corresponding to the evaluation result received from the communication interface, because the protective device implements this accordingly, for example in order to actuate an actuator that interacts with the mechanical display.
[0040] Furthermore, the monitoring system can have a display which is constructed separately from the protection device, for example a display in a separately constructed display device. The display device can be associated with the voltage network into which the protection device is integrated. This allows for display or transmission of messages at a location which is more accessible or more frequently visited than, for example, in a technical room in which the protection device is generally installed. This ensures that the operator or operator of the monitoring system promptly and reliably obtains corresponding information, for example corresponding treatment recommendations, from the evaluation unit in order to counteract a fault in the protection device or a predicted unfavorable state of the voltage network.
[0041] In principle, it is possible for the display to provide further information, for example also treatment recommendations. These can be displayed on the display, whereby the user or operator of the monitoring system can be guided to implement corresponding measures.
[0042] There is no direct signal transmission between the at least one triggering protection component and the display, i.e. there is no signal-transmitting, wired signal line or wireless connection. Ultimately, a measured value or a value representing the triggering state of the triggering protection component of the protection device is detected and transmitted by the protection device via the communication interface to a separately constructed evaluation unit, which communicates with the protection device in order to transmit an evaluation result that should be output via the display. In this regard, there is no direct data transmission between the triggering protection component of the protection device and the display of the protection device, but only an indirect data transmission via a separately constructed evaluation unit, which communicates with the at least one communication interface.
[0043] The protective device can have a housing in which at least the protective component that triggers and the communication interface are at least partially accommodated. In this respect, the protective device is a component that includes the corresponding components and protects them from environmental influences.
[0044] The invention further provides a method for monitoring a voltage network by means of a monitoring system, the method comprising the following steps:
[0045] detecting the state value by means of a protective device which is integrated into the voltage network to be monitored,
[0046] transmitting the detected state value to an evaluation unit which is designed separately from the protective device, and
[0047] The transmitted status values are processed by means of the evaluation unit, so that an outsourced evaluation takes place.
[0048] In this respect, it is ensured that the state values detected by the protective device can be processed by means of complex evaluation techniques in order to determine an output value or to predict a state of the protective device or of the voltage network. The evaluation result, for example the correspondingly determined output value or the predicted state, can be transmitted to the protective device or to a display device that is constructed separately from the protective device and can be associated with the voltage network in which the protective device is integrated. If the evaluation result is transmitted to the protective device, a corresponding bidirectional communication occurs between the protective device and the evaluation unit, even if this takes place via a unidirectional communication interface.
[0049] For example, the evaluation result or its data representation is displayed on the protection device itself or on a display device constructed separately from the protection device, thereby informing the user or operator of the monitoring system. The operator or operator can then initiate corresponding measures to prevent failure of the protection device or minimize downtime or to stabilize the voltage network and thus counteract the predicted poor network quality.
[0050] Furthermore, the evaluation unit can determine an evaluation result, in particular an output value and / or a state. The evaluation unit transmits the evaluation result back to the protective device or to a display device, wherein the evaluation result is output. This ensures that the evaluation result (which is easily understandable to the user) is output, for example, at the location of the protective device, for example via the protective device itself, in particular via a display of the protective device, or via a separately constructed display device, which is arranged in the region of the protective device.
[0051] In principle, it is therefore possible to estimate or predict the future network quality or the state of the protection device based on historical and / or current data, so that the network operator of the voltage network and / or the power customer / power user can recognize future disturbances early. In other words, the network operator and / or the power customer / power user can predict the moment and intensity of the upcoming network disturbance. It is thus possible to introduce corresponding measures to avoid the upcoming network disturbance, at least reduce its intensity or generally minimize the impact of the upcoming network disturbance to a specific range. It is also possible to predict the aging state (wear) of the protection device, so that the upcoming fault of the protection device can be recognized early.
[0052] Due to unstable voltage networks, for network operators and / or power customers / power users, how the voltage network behaves in the future in terms of its network quality (network state) is often more decisive than the current network state (to which it is no longer possible to react anyway). This applies in a similar way to protective devices, the operability of which should be ensured in the future. Looking ahead thus makes it possible to promptly introduce suitable measures to counteract predicted network disturbances, i.e., deteriorating states of the voltage network or failures of protective devices.
[0053] In other words, the network operator and / or the electricity customer / power user can thus design the voltage network to be more resistant to disturbances to be expected in the future or to replace protective devices.
[0054] The future state of the voltage network or protection devices can be predicted for the next hours, days or weeks, giving the network operator and / or the electricity customer / power user enough time to introduce possible countermeasures in time so that they can still resist the predicted disturbance or deterioration.
[0055] Countermeasures to be taken with regard to the voltage network may, for example, consist in avoiding further loading during predicted weak phases of the voltage network, thereby ensuring fail-safe operation of devices and / or machines, the operation of which should not be disturbed. In this respect, countermeasures may consist in disconnecting non-essential machines or devices from the network during predicted weak phases of the voltage network, or in not connecting them to the voltage network, in order to reduce or not increase the load further. With regard to predicted errors of protective devices, countermeasures may consist in timely procurement and installation of replacement devices before the protective device actually fails.
[0056] In principle, the voltage network can be a local network, also called a building network, which is associated with a private household or an industrial building. Thus, the voltage network can be a low-voltage network, for example a building network connected to a power supply network.
[0057] For the prediction, the state value can be detected multiple times, i.e. at least at two different times, and transmitted to the evaluation unit, wherein the values detected at different times can be fed into a processor unit of the evaluation unit for evaluation. Thus, the future time course can be predicted from the time course of the state values detected in the past, which can extend up to the present. The future time course can here relate to the detected state value itself, so that the future time course of the state value is predicted, which time course corresponds to the predicted future state of the voltage network or the protective device.
[0058] When evaluating the data attached to the state value, there may be a data fusion of two different parameters, which enables the future of the corresponding state to be understood. In other words, when processing the two different parameters together, using the correlation of these parameters to each other, it is possible to draw conclusions about future behavior.
[0059] The artificial intelligence can take in state values detected at at least two different times as input variables and output a future state as an output variable. Thus, the artificial intelligence can be trained to recognize corresponding associations between values of state values detected at different times and learn corresponding technical relationships, thereby enabling reliable or very accurate predictions of future states of the voltage network or protective device.
[0060] In particular, a method for training artificial intelligence to predict the future state of a voltage network or a protection device is therefore also provided. The method for training comprises the following steps:
[0061] - providing a training data set for the artificial intelligence, the training data set comprising at least a state value at a first moment, a state value at a second moment and an actual state of the voltage network or the protection device at a third moment, the third moment being later than the first moment and the second moment,
[0062] - feeding the state value at the first moment and the state value at the second moment into a processor unit having an artificial intelligence to be trained, the processor unit having the artificial intelligence jointly processing the state values detected at different moments and outputting a predicted future state of the voltage network or the protection device at a third moment,
[0063] - comparing the predicted future state of the voltage network or the protection device at a third time instant with the actual state of the voltage network or the protection device at the third time instant, the actual state of the voltage network or the protection device at the third time instant being part of the training data set, determining a deviation between the predicted future state of the voltage network or the protection device at the third time instant and the actual state of the voltage network or the protection device at the third time instant, and
[0064] - Feedback the deviation between the predicted future state of the voltage network or the protection device at the third moment and the actual state of the voltage network or the protection device at the third moment, so as to adjust the weight factor of the artificial intelligence to be trained if the deviation is outside the tolerance range.
[0065] Thus, the artificial intelligence can be trained accordingly via at least one training data set, which includes not only the state values at the first time but also the state values at the second time, in particular the corresponding time series or time sequence of the state values, and the actual future state of the voltage network or the protective device existing at a third time, which is located after the time of determining or detecting the state value. In particular, the first time and the second time do not coincide, so that the state values are recorded at two different times.
[0066] In principle, when training artificial intelligence, it can also be stipulated that the artificial intelligence does not output the state of the voltage network or the protection device at discrete moments, but outputs the state in an interval including a third moment, that is, predicts the future state of the voltage network or the protection device for a future time period.
[0067] The respective tolerance range for the deviation can be predefined and / or can be determined by the user, for example as a percentage or a variance.
[0068] In principle, an artificial intelligence trained with the aid of the above-described method can be used to predict future states of a voltage network or a protective device, ie for evaluating state values that have already been transmitted to an evaluation unit.
[0069] In other words, the processor unit comprises a trained artificial intelligence, in particular an artificial intelligence trained according to the method described above.
[0070] On the one hand, it is provided that the artificial intelligence has at least one artificial neural network, for example an artificial recurrent neural network (RNN) or an artificial convolutional neural network (CNN). The artificial intelligence can have a long short-term memory (LSTM) network or a gated recurrent unit (GRU). Such a neural network allows the prediction of states in the future based on a time series or a time sequence. The artificial intelligence thus learns from past data (historical data), wherein the artificial intelligence predicts the future state of the voltage network or the protective device. BRIEF DESCRIPTION OF THE DRAWINGS
[0071] Further advantages and features of the present invention are derived from the following description and the accompanying drawings with reference to them. In the drawings:
[0072] Figure 1 A schematic diagram showing a monitoring system according to the present invention; and
[0073] Figure 2 The method according to the invention for monitoring a voltage network is shown. DETAILED DESCRIPTION
[0074] Figure 1 1 shows a monitoring system 10 which is provided for monitoring a voltage network 12 , which is a building network or a low-voltage network which is connected to a power supply network 14 .
[0075] In the embodiment shown, the voltage network 12 is shown as a multi-phase building network or low-voltage network.
[0076] The monitoring system 10 comprises a protective device 16 which is integrated into the voltage network 12. The protective device 16 is designed as a surge protection device (“surge protection device”, SPD), which is also called a surge arrester.
[0077] In this respect, the protection device 16 comprises a triggering protection component 18, which in the case of a triggering changes into a conductive or quasi-conductive state in order to conduct the overvoltage that occurs in an overvoltage event such as a lightning strike, wherein a corresponding current can flow away, thereby correspondingly protecting the devices integrated into the voltage network 12. After the overvoltage event has ended, the protection device 16 or the triggering protection component 18 returns to its initial state again. The triggering protection component 18 can be designed as a (corner) spark gap or a gas discharge conductor ("GDT").
[0078] Furthermore, in the embodiment shown, in addition to the triggered protection component 18, the protection device 16 comprises a voltage-limiting protection component 20 connected in series with the triggered protection component 18. For example, the voltage-limiting protection component 20 is designed in the form of a metal oxide varistor.
[0079] Furthermore, it is provided that the protective device 16 has an integrated measuring and / or sensor unit 22, which is arranged in the protective device 16. This means that not only the triggering protective component 18, the optionally provided pressure-limiting protective component 20, but also the optionally provided measuring and / or sensor unit 22 are surrounded by a housing 24 of the protective device 16. In other words, the housing 24 surrounds the mentioned components 18 to 22, thereby protecting them from the environment.
[0080] Furthermore, the protective device 16 comprises a communication interface 26, with which the protective device 16 establishes a communication connection 28 with a separately designed evaluation unit 30, which also has a corresponding communication interface 32. The communication interface 26 of the protective device 16 is at least partially accommodated in the housing 24, whereby it is also protected from the environment.
[0081] The separately designed evaluation unit 30 is part of the monitoring system 10 , wherein the separately designed evaluation unit 30 does not have to be arranged at the same location as the protective device 16 , but is arranged, for example, in another room or another building.
[0082] In particular, the evaluation unit 30 can be designed as a server-based evaluation unit, ie, in the cloud. In this respect, the communication connection 28 between the protection device 16 and the evaluation unit 30 is established via an Internet connection.
[0083] If a separately designed evaluation unit 30 is provided at the location of the protective device 16 , the corresponding communication connection 28 can be designed via a Bluetooth connection or the like, in particular via a wireless communication connection with a short range.
[0084] In principle, the communication connection 28 between the protective device 16 and the separately designed evaluation unit 30 can be realized in a wired manner, for example via an Ethernet cable, or wirelessly, for example via WLAN.
[0085] The communication interfaces 26 , 32 of the protective device 16 and the evaluation unit 30 can each be designed as a bidirectional communication interface, so that bidirectional communication between the protective device 16 and the evaluation unit 30 is possible.
[0086] Alternatively, both the protective device 16 and the evaluation unit 30 can each have two communication interfaces which allow only a unidirectional communication connection, so that two unidirectional communication connections 28 are present between the protective device 16 and the evaluation unit 30. Overall, this again results in a bidirectional communication between the protective device 16 and the evaluation unit 30. Such an embodiment with separate communication interfaces is particularly useful if the data transmission in one direction has a different protocol or a different security level than the data transmission in the respective other direction.
[0087] However, it can also be provided that the protective device 16 has only one unidirectional interface as a communication interface, via which the protective device 16 can only transmit data to the evaluation unit 30. In other words, the protective device 16 is not designed to receive data from the evaluation unit 30. The communication connection 28 is then between the one unidirectional interface and the at least one communication interface 32 of the evaluation unit 30.
[0088] In principle, the protection device 16 can transmit the state values via the communication connection 28 to a separately designed evaluation unit 30 , so that the evaluation unit 30 with the processor unit 34 is provided to process the corresponding state values to obtain an evaluation result, for example to predict an output value or a state, as will be explained in more detail below.
[0089] The evaluation unit 30 can then transmit the evaluation result back to the protective device 16 via the communication connection 28, provided that the evaluation unit is designed to receive data, such as according to Figure 1 As shown in the implementation method of .
[0090] The protection device 16 may have a display 36, which is connected to the communication interface 26 in a signal-transmitting manner, so that the evaluation result transmitted from the evaluation unit 30 can be displayed via the display 36 of the protection device 16. The display 36 may be a screen. The evaluation result itself, that is, the output value or the predicted state, or its data representation can be displayed accordingly.
[0091] Alternatively, provision can be made for the evaluation unit 30 to transmit the evaluation result not directly to the protective device 16, but to a separately designed display device 38, which has a corresponding communication interface 40, with which the display device 38 communicates with the evaluation unit 30, in particular with the communication interface 32 of the evaluation unit 30. This is the case in particular if the protective device 16 itself is not designed for data reception, since it has, for example, only a unidirectional communication interface which is used only for data transmission, i.e., for transmitting the status value to the evaluation unit 30.
[0092] The display device 38 also has a display 42, via which the corresponding evaluation results, in particular their data representation, can be displayed in order to inform the user or operator of the monitoring system 10 accordingly. The display 43 of the display device 38 can also be designed as a screen.
[0093] In principle, the data representation may also include a course of action recommendation or the like, instructing a user or operator to carry out a specific course of action, which should for example counteract the predicted state of the voltage network 12 and / or the protective device 16 .
[0094] The state value transmitted from the protective device 16 may be a measured value detected by the protective device 16 or a value representing a triggering state of a triggering protective component 18 of the protective device 16 .
[0095] The corresponding measured values may be measured values which have been detected by the measuring and / or sensor unit 22. In particular, the measured values are then values of characteristic variables of the voltage network 12. Characteristic variables of the voltage network 12 may be voltage, current, power, frequency, distortion (“Total Harmonic Distortion”, THD), harmonics (up to the 50th harmonic), reactive power and / or energy values.
[0096] The value representing the triggering state of the protection component 18 that is triggered may be binary, that is, "0" represents a non-triggering state, or "1" represents a triggering state.
[0097] The protective device 16 thus transmits corresponding information and data to the evaluation unit 30 , which can be used by the evaluation unit 30 to determine the overall aging state of the protective device 16 or the state of the voltage network 12 , in particular to predict the respective future state of the protective device 16 or of the voltage network 12 .
[0098] In principle, the evaluation unit 30 can also communicate with at least one other device, the other device communicating with, for example, a database 44, a measuring device 46, which is arranged separately from the voltage network 12, that is, does not record data or information of the voltage network 12; the other device communicating with, for example, a measuring device 48, which is constructed separately from the protection device 16 but detects information or data of the voltage network 12, and / or the other device is, for example, another protection device 16 equipped with another voltage network.
[0099] Evaluation unit 30 therefore receives further input data which can also be taken into account for the evaluation of the state value of protection device 16 , so that a joint evaluation of the different data takes place, whereby, for example, connections between the different data can be identified.
[0100] In particular, the evaluation unit 30 , ie the processor unit 34 , has an artificial intelligence 50 which is provided for predicting a (future) state of the voltage network 12 and / or a (future) state of the protective device 16 at least based on the state values acquired from the protective device 16 .
[0101] Failure predictions of the protective device 16 or the voltage network 12 are thus possible. Aging states of the protective device 16 and / or other events in the voltage network 12 , such as the future network quality of the voltage network 12 , can also be predicted. This is done based on input data processed by the artificial intelligence 50 .
[0102] With the aid of artificial intelligence 50 , large amounts of data, in particular data of different types and / or origins, can be processed together and correlations (associations) between the different data can be identified, thereby enabling more in-depth analyses that cannot be performed easily on site due to the required computing power.
[0103] In principle, the processor unit 34 of the evaluation unit 30 can be configured to execute a computer program having program code sections in order to monitor the voltage network 12 .
[0104] The computer program can be installed on the processor unit 34 from a computer-readable data medium storing the computer program, so that the monitoring system 10 , in particular the evaluation unit 30 having the processor unit 34 , can execute a corresponding method for monitoring the voltage network 12 .
[0105] The evaluation unit 30 therefore has a corresponding interface via which the data carrier can be coupled to the evaluation unit 30 in order to install the computer program.
[0106] The computer program can also be transmitted via a data transmission device, which is designed, for example, as a communication interface, for example for wireless communication. It can also be a LAN interface via which communication can take place.
[0107] The following uses Figure 2 A method implemented by a computer program is described.
[0108] In a first step S1, at least one state value is detected at a first time by means of the protective device 16. This can be done via the triggering protective component 18, the pressure limiting protective component 20 and / or the measuring and / or sensor unit 22. In any case, it is ensured that the protective device 16 detects the state value.
[0109] In an optional second step S2 , the protection device 16 detects a state value at a second time that is different from the first time.
[0110] In principle, the state value can be detected at multiple times. Therefore, the state value is detected multiple times in succession in time, in particular periodically, so that there is a time series / time sequence of the state values.
[0111] In a third step S3 , the state value detected at least once by the protective device 16 is transmitted to the evaluation unit 30 , in particular the processor unit 34 , so that the state value can be evaluated.
[0112] In addition, it can be provided that at least one second variable, for example a characteristic variable of the voltage network 12, a value from a database 44, a value of a measuring device 46, 48 or a state value of another protective device 16 is detected. The second variable is different from the state value. Therefore, the second variable can be detected independently of the voltage network 12, for example, read from a database 44 accessible to the evaluation unit 30, in particular via a communication interface 32. The second variable can be read from a database 44 (in particular by means of a communication interface 32), to which the evaluation unit 30 can access the database. From the database 44, data that are calculated together for the analysis, such as environmental data (such as weather data), time data (weekdays, weekends, holidays, daytime and / or nighttime) or use data of the system in this environment (for example, a travel plan for a train) or use data of the charging system in this environment can be obtained. Additional information can thus be obtained, which explains possible differences between the state values at different times.
[0113] The second variable obtained from the database 44 is transmitted to the processor unit 34 of the evaluation unit 30 , so that the processor unit 34 detects the second variable of the voltage network 12 .
[0114] However, the second variable may also be a characteristic variable of the voltage network 12 which is detected by one of the measuring devices 46 , 48 or the further protective device 16 and which is transmitted to the processor unit 34 of the evaluation unit 30 so that the processor unit 30 detects the characteristic variable of the voltage network 12 .
[0115] If the state value of protective device 16 is also a characteristic variable, two characteristic variables that differ from one another can therefore be determined.
[0116] In principle, corresponding characteristic variables of the voltage network 12 can be voltage, current, power, frequency, distortion, harmonics, reactive power and / or energy values of the voltage network 12 , in particular phases of the multiphase voltage network 12 .
[0117] As already mentioned above, a time series / time sequence of state values can be detected. This can also apply to the second variable which is detected optionally, thus detected multiple times, in particular periodically.
[0118] For example, when the state value is detected, the second variable is always also detected, so that the state value and the second variable are detected in parallel, in particular simultaneously.
[0119] This means, in particular, that when the state values are detected at different points in time, a corresponding data record is also read from the database 44 in each case, which data record represents a second variable, for example weather data present at the respective point in time.
[0120] In a fourth step S4 , at least the state variable is fed to the processor unit 34 , ie, to the artificial intelligence 50 .
[0121] In particular, the state parameter detected at the first moment, the state parameter detected at the second moment and the second parameter are fed as input parameters to the artificial intelligence 50, which processes the input parameters together, thereby predicting the (future) state of the voltage network 12 and / or the (future) state of the protective device 16 based on the state values detected at the at least two different moments by the processor unit 34, in particular the artificial intelligence 50.
[0122] For the prediction, the processor unit 34 has an artificial intelligence 50 which receives at least the state value, in particular the state value detected at the at least two different times, and the second variable as input variables and outputs the future state of the voltage network 12 or of the protective device 16 as output variables. The output variable thus corresponds to the evaluation result of the evaluation unit 30.
[0123] The artificial intelligence 50 may include at least one artificial neural network, for example a convolutional neural network (CNN) or an artificial recurrent neural network (RNN), such as a long short-term memory (LSTM) network or a gated recurrent unit (GRU).
[0124] The artificial intelligence 50 is thus able to predict the future state of the voltage network 12 and / or the protective device 16 at least based on the acquired time series, i.e. the time sequence of the state values. For this purpose, the artificial intelligence 50 processes at least the state values, which have been detected at different times in particular, and optionally a second variable, for example a value from the database 44, a measured value of the measuring device 46, 48 and / or a value of the further protective device 16.
[0125] The artificial intelligence 50 may have been previously trained by means of a method in which the artificial intelligence 50 is trained to predict the (future) state of the voltage network 12 and / or the protective device 16 based on the state values, which are detected in particular at at least two different times. The artificial intelligence 50 is therefore a trained artificial intelligence 50.
[0126] In a first training step, a training data set is provided to the artificial intelligence 50, which training data set includes at least a state value at a first time, a state value at a second time, and an actual state of the voltage network 12 or the protective device 16 at a third time. The third time is later than the first time and the second time, so that the third time is a future time to be predicted starting from the first time and the second time.
[0127] Additionally, the training data set may include a second variable different from the state value, so that the training data set includes at least two different variables. The second variable may be a characteristic variable of the voltage network 12, which is different from the state value. The second variable may also correspond to a measured value of the measuring device 46, 48 or a value from the database 44.
[0128] In particular, the training data set may include a time series or a time sequence of state values, such that the state values are measured or detected at different moments in time.
[0129] The optionally specified second variable can also be included in the training data set as a time series or time sequence. Thus, the training data set can include data of at least two different variables for a specific time period and information about the state of the voltage network 12 or the protective device 16, which is obtained at a time later than the specific time period.
[0130] However, it is also possible that the training data set can also include corresponding information on more than just two different variables, so that more information or data are provided overall, whereby the training is more extensive and the predictive power of the correspondingly trained artificial intelligence 50 is higher.
[0131] In a second training step, at least the state value detected at the first moment and the state value detected at the second moment, in particular the time series or time sequence of the state values, are fed to a processor unit 34, which has a trained artificial intelligence 50. The processor unit 34 with the artificial intelligence 50 processes the state values detected at different moments (in particular the time series or time sequence) together and outputs a predicted future state of the voltage network 12 or the protection device 16 at a third moment, for which the training data set includes the actual state of the voltage network 12 or the protection device 16.
[0132] Accordingly, during the training process, the artificial intelligence 50 learns the corresponding relationship between the state value detected at the first moment and the state value detected at the second moment, as well as the impact on the subsequent state of the voltage network 12 or the protection device 16, so that the artificial intelligence 50 is trained to predict the future state of the voltage network 12 or the protection device 16 based on past or current data.
[0133] Furthermore, a second variable can optionally be included in the calculation, so that during training, connections between different variables are recognized, namely between state values that are detected at different times and second variables that are detected once or also at different times.
[0134] In a third training step, the predicted future state of the voltage network 12 or the protective device 16 at a third time is compared with the actual state of the voltage network 12 or the protective device 16 at the third time, wherein the latter is included in the training data set. By means of the comparison, the deviation between the predicted future state of the voltage network 12 or the protective device 16 and the actual state of the voltage network 12 or the protective device 16 is determined. In this respect, it is determined in the training how accurate the prediction of the artificial intelligence 50 has been, i.e. how well the prediction matches the actual state.
[0135] In a fourth training step, the determined deviation between the predicted future state of the voltage network 12 or the protective device 16 and the actual state of the voltage network 12 or the protective device 16 is fed back to the artificial intelligence 50 to be trained, in order to adjust the weighting factors of the artificial intelligence 50 to be trained if the deviation is outside a tolerance range. The tolerance range can be predetermined and / or set by the user.
[0136] Subsequently, at least the third training step is repeated, wherein the deviation determined in the comparison of the third training step gradually decreases. After a certain number of repetitions (iterations), the deviation is so small that it is within the tolerance range, so that the deviation is no longer fed back. Then, the artificial intelligence 50 has reached a state of at least (pre) training for the training data set, so that the artificial intelligence can be used.
[0137] The artificial intelligence 50 can then be further trained with the same training steps in corresponding iterations, so that the artificial intelligence 50 is trained, for example, for further variables, in particular characteristic variables of the voltage network 12 and / or different variable pairs.
[0138] In particular, the training of the artificial intelligence 50 can also include the input of more than two different variables, for example up to eight different variables or more. Therefore, the corresponding training set used for this purpose has more data that is provided and input.
[0139] Typically, the training step is repeated for a plurality of different data of a plurality of different actual states and / or variables of the voltage network 12 or the protection device 16 in order to train the artificial intelligence 50. In the last training step, as already described, the weighting factors of the artificial intelligence 50 to be trained are adjusted in such a way that the corresponding predicted future state of the voltage network 12 or the protection device 16 is always within the tolerance range.
[0140] The artificial intelligence 50 used in the method for monitoring the voltage network 12 has been trained according to the aforementioned training method, so that it is a trained artificial intelligence 50 which determines or predicts the future state of the voltage network 12 or the protection device 16 at least based on the state values that have been detected by the protection device 16.
[0141] The processor unit 34 , which includes the trained artificial intelligence 50 , therefore outputs an evaluation result, for example a predicted future state of the voltage network 12 or of the protective device 16 , in a fifth step S5 .
[0142] The evaluation results can be transmitted to the protective device 16, which receives the data via the communication interface 26 and forwards it to the display 36, so that the evaluation results or their data representation are output, in particular displayed, on the protective device 16 itself. In addition to the evaluation results, treatment recommendations can also be included.
[0143] As an alternative to protective device 16 , the evaluation result can also be transmitted to a separately designed display device 38 , so that the evaluation result and possible treatment recommendations are output on display device 38 , in particular on a display 42 of display device 38 .
[0144] Since the evaluation unit 30 is designed separately from the protective device 16 , it can be designed as a high-performance computer. In any case, the evaluation unit 30 can perform a computationally intensive evaluation in order to subsequently transmit the evaluation results to the protective device 16 itself or to a separately designed display device 38 .
Claims
1. A monitoring system for monitoring a voltage network (12), wherein: The monitoring system (10) has a protection device (16) to be incorporated into a voltage network (12), the protection device comprising at least one protection component (18) for triggering, the protection device (16) having at least one communication interface (26) which is configured to transmit a status value of the protection device (16) to an evaluation unit (30) which is configured separately from the protection device (16), and the evaluation unit (30) is configured to perform an evaluation, thereby providing an outsourced evaluation.
2. The monitoring system according to claim 1, characterized in that: The state value of the protection device (16) is a measured value detected by the protection device (16) or a value indicating a triggering state of a triggering protection component (18) of the protection device (16).
3. The monitoring system according to claim 1 or 2, characterized in that: The protection device (16) is an overvoltage protection device.
4. A monitoring system according to any one of the preceding claims, characterised in that The monitoring system (10) comprises an evaluation unit (30) which is constructed separately from the protection device (16), the evaluation unit having at least one communication interface (32) which is configured to communicate with a communication interface (26) of the protection device (16), in particular, each of the communication interfaces (26, 32) being constructed as a bidirectional communication interface.
5. A monitoring system according to any one of the preceding claims, characterised in that The evaluation unit (30) is configured to acquire input data from at least one database (44) or a measuring device (46, 48).
6. A monitoring system according to any one of the preceding claims, characterised in that The evaluation unit (30) has at least one processor unit (34) which is configured to process at least a status value received from the protective device (16).
7. The monitoring system according to claim 6, characterized in that: The processor unit (34) comprises an artificial intelligence (50) which is configured to predict a state of the voltage network (12) and / or a state of the protection device (16) based on state values obtained from the protection device (16).
8. A monitoring system according to any one of the preceding claims, characterised in that The separately designed evaluation unit (30) is provided for determining an evaluation result, in particular an output value and / or a state, based on a state value of the protective device (16).
9. The monitoring system according to claim 8, characterized in that: The separately designed evaluation unit (30) is provided for transmitting the determined evaluation result to the protective device (16) or to a display device (38).
10. A monitoring system according to any one of the preceding claims, characterised in that The protection device (16) has at least one display (36) which is configured to display an evaluation result of the evaluation unit (30), and in particular, the display (36) is connected to a communication interface (26) of the protection device (16) in a signal-transmitting manner.
11. The monitoring system according to claim 10, characterized in that: There is no direct signal transmission between the at least one triggered protective component (18) and the display (36).
12. A monitoring system according to any one of the preceding claims, characterised in that The protective device (16) has a housing (24) in which at least the triggering protective component (18) and the communication interface (26) are at least partially accommodated.
13. A method for monitoring a voltage network (12) by means of a monitoring system (10), the method comprising the following steps: The state value is detected by means of a protective device (16) which is integrated into the voltage network (12) to be monitored, transmitting the detected state value to an evaluation unit (30) which is designed separately from the protective device (16), and The transmitted status value is processed by means of an evaluation unit (30), so that an outsourced evaluation takes place.
14. The method according to claim 13, characterized in that The evaluation unit (30) determines an evaluation result, the evaluation unit (30) transmits the evaluation result back to the protective device (16) or to a display device (38), and the evaluation result is output.
