WO2024256495A2 - Vorrichtung und verfahren zum erkennen eines lichtbogens in einem gleichstrom-system - Google Patents
Vorrichtung und verfahren zum erkennen eines lichtbogens in einem gleichstrom-system Download PDFInfo
- Publication number
- WO2024256495A2 WO2024256495A2 PCT/EP2024/066285 EP2024066285W WO2024256495A2 WO 2024256495 A2 WO2024256495 A2 WO 2024256495A2 EP 2024066285 W EP2024066285 W EP 2024066285W WO 2024256495 A2 WO2024256495 A2 WO 2024256495A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- arc
- occurred
- jsk
- amplitude values
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02S—GENERATION OF ELECTRIC POWER BY CONVERSION OF INFRARED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
- H02S50/00—Monitoring or testing of PV systems, e.g. load balancing or fault identification
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Definitions
- a photovoltaic system is a system which comprises at least one photovoltaic module, in particular a plurality of photovoltaic modules.
- PV systems photovoltaic systems
- PV plants photovoltaic systems
- Detecting an indication that an arc has occurred in the PV system therefore usually leads to the triggering of an emergency procedure, for example the triggering of an emergency switch. It is sometimes not easy to determine whether an arc has actually occurred or not.
- False-positive triggering i.e. triggering of the The risk of false positives (i.e. initiating an emergency procedure even though there was actually no arc) is therefore accepted in order to minimise false negative triggering (i.e. failure to trigger the emergency procedure even though there was actually an arc).
- an object of the present invention to provide an improved method and an improved device for detecting an arc in a direct current system, in particular a PV system.
- the invention is particularly preferably used to detect a serial arc in a direct current system, in particular a PV system.
- false-positive triggering of emergency procedures should be reduced or avoided, or at least a simple solution should be created for detecting and reversing the false-positive triggering of an emergency procedure.
- a computer-implemented method comprising the steps of: detecting a temporal progression of amplitude values of an electrical quantity of an electrical current from the photovoltaic system, PV system; determining at least one value of a permutation entropy, PE, based on the temporal progression of the amplitude values (or specifically: the temporal progression of the amplitude values); determining at least one value of a Jensen-Shannon complexity, JSK, based on the temporal progression of the amplitude values (or specifically: the temporal progression of the amplitude values); detecting whether an arc has actually occurred in the PV system, based on the at least one specific value of the permutation entropy, PE, and on the at least one specific value of the Jensen-Shannon complexity, JSK.
- JSK The Jensen-Shannon complexity, JSK, can be calculated, for example, as described in “Rosso et al.”.
- the PE can be calculated, for example, using the method described in “Bandt & Pompe”, optionally also using the further development according to “Azami et al.” or according to Unakafova & Keller.
- an indication that an arc may have occurred in the PV system is also recorded. As will be explained in more detail below, this opens up a variety of possibilities for providing particularly safe devices and methods.
- the detection of whether an arc has actually occurred in the PV system only takes place if the indication that an arc may have occurred in the PV system has previously been recorded.
- the detection of the indication and the detection can coincide, or occur completely independently of one another.
- the electrical quantity can be, for example, the electrical current or the electrical voltage, with electrical current being preferred.
- the indication that an arc may have occurred should be understood in particular as an indication on the basis of which an emergency procedure is triggered in the sense of avoiding false-negative measures, i.e. missing triggers despite the presence of an arc.
- the indication is advantageously created or generated in such a way that it is always present when an actual arc has occurred (true positive) but can also occur when an arc has not actually occurred (false positive).
- the detection of whether an arc has occurred is intended to determine whether an arc has actually occurred, ie it should be positive if and only if an arc has actually occurred.
- detecting the indication that an arc may have occurred can involve receiving a signal that reports the (possible) occurrence of an arc.
- the signal can originate from the direct current system (e.g. PV system) itself.
- the device according to the invention and/or the method according to the invention can also include generating the indication themselves.
- the indication in a first step, can be generated according to a first algorithm, the first algorithm being designed in such a way that there are as few false negative results as possible but false positive results are accepted, i.e., in other words, that the indication is generated too often rather than too rarely.
- the detection of whether an arc has occurred can then be carried out according to a second algorithm which, compared to the first algorithm, generates a reduced number of false positive results and, advantageously, does not generate any false positive results at all.
- the execution of the first algorithm can also be referred to as an arc warning
- the execution of the second algorithm can also be referred to as an arc diagnosis.
- the detection of the indication that an arc may have occurred and the detection of whether an arc has occurred can coincide, namely when the indication is already generated with an algorithm that is so sophisticated that it generates no, or practically no, false positive results.
- the present invention provides both 2-stage and 1-stage variants.
- the inventors have found that the permutation entropy, PE, is particularly suitable as an entropy metric for direct current systems, in particular for PV systems. In the following, the invention will therefore be described primarily with reference to the PE as an entropy metric.
- the calculation of the permutation entropy according to the Bandt-Pompe method is particularly suitable. Method, see "Bandt &Pompe".
- JSK Jensen-Shannon complexity
- the permutation entropy indicates, roughly speaking, how strongly certain patterns ⁇ j (English “pattern”) differ within a time series, i.e. a temporal progression, where the patterns ⁇ j are based only on the relative size of values A(t i ) of time series sections to each other ("ordinal representation"). This means that the time series sections (1, 2, 3) and (300, 795, 5900) have the same pattern ⁇ j , namely that the values A(t i ) always increase from one to the next.
- Important parameters of the permutation entropy are the pattern length D (also called "embedding dimension”) and the embedding delay ⁇ .
- the pattern length D indicates how long the patterns ⁇ j are that are examined in the permutation entropy PE, so that D! ("D-factorial") gives the number of possible patterns ⁇ j .
- D! (“D-factorial") gives the number of possible patterns ⁇ j .
- time series sections of length D are taken and the patterns ⁇ j therein are examined, in particular counted.
- the inventors have found that a pattern length D between 3 and 7 is particularly advantageous for the present invention.
- the various patterns can be identified, for example, in such a way that within a time series section of length D the smallest value A min is given the value 0, the next largest value is given the value 1, and so on, up to the largest value A max , which is given the value D-1.
- the various possible patterns ⁇ j then correspond exactly to the possible permutations of (0..D-1).
- the permutation entropy can also be calculated as a "multi-scale entropy" (MPE), in particular using the method described in "Azami et al.”
- MPE multi-scale entropy
- JSK Jensen-Shannon complexity
- the difference in the distributions is determined using the Jensen-Shannon divergence.
- the JSK can take on different values between a minimum value and a maximum value, which is given by D!.
- the JKS thus provides additional information for characterizing a time series that is not contained in the PE.
- a time series of tuples PE(t i ), JSK(t i )) is calculated for a plurality of times t i .
- the detection of whether an arc has occurred is advantageously based on the calculated time series.
- the times are advantageously periodically spaced from one another.
- the inventors have found that the PE-JSK parameter level enables particularly reliable detection of whether an arc has occurred or not. It is also advantageous if the permutation entropy, PE, is calculated in a sliding window over the total available time series of amplitude values, i.e. if the counting of patterns etc.
- the size W of this sliding window is another hyperparameter.
- a larger pattern length D allows more complex processes to be described.
- a pattern length D that is too large means that not all possible patterns can occur in a temporal progression of amplitude values of limited length, which in turn hinders the complexity analysis. It is therefore advantageous if W>5D! applies.
- the sliding window is preferably always shifted by a single amplitude value, so that each time only the first time series section leaves the sliding window, and at the end a new, previously unexamined time series section is included in the sliding window. This means that a maximum of two numbers of patterns can change from window to window.
- At least one temporal trajectory of points in a PE-JSK parameter space (“PE-JSK trajectory") is calculated.
- the detection of whether an arc has occurred is advantageously based at least on the calculated temporal trajectory, in particular on variables that can be derived from the trajectory, such as for example, the first derivative/gradient, the second derivative, a spread between minimum and maximum values and/or the like.
- the inventors have found that the properties of this trajectory enable particularly reliable detection of whether or not an arc has occurred.
- the temporal trajectory can also advantageously be generated and calculated according to the Unakafova approach from Unakafova & Keller, i.e., with a sliding time window of size W.
- the calculated time series of tuples and/or the calculated temporal trajectory are input into an artificial intelligence unit, KIE, which carries out the detection of whether an arc has occurred based thereon.
- KIE can comprise a supervised learning or unsupervised learning machine learning model, MLM.
- An MLM that can be used advantageously can, for example, comprise or consist of a cluster analysis method.
- Supervised trained MLMs can, for example, have or consist of an artificial neural network, ANN.
- the input data of the MLM can in particular have PE values and/or JSK values, or be quantities based on PE values and/or JSK values, in particular in one of the variants described herein such as (PE(t i ), JSK(t i )) tuples, trajectories in the PE-JSK parameter space, and/or the like.
- various calculation methods can be used, which can either be hyperparameters (i.e., specified when designing and training the MLM), or as Parameters can be used, i.e., determined by the MLM itself during training.
- Such hyperparameters/parameters are, for example, the pattern length D (also called “embedding dimension”), the window size W, or the embedding delay ⁇ . It can also be provided that several permutation metrics and/or several complexity metrics are used as input data, so that the MLM “learns" during its training which entropy metrics and/or which complexity metrics, and in which combination, form the best basis for deciding whether an arc actually occurred. In particular, several permutation entropies and/or several Jensen-Shannon complexities can be used as input data, each of which can have different hyperparameters.
- an indication that an arc may have occurred is detected, particularly advantageously based on the at least a specific value of the permutation entropy, PE, and/or on the at least one specific value of the Jensen-Shannon complexity, JSK.
- the detection of the indication can also be carried out - as is known in the art - by means of an analysis of the spectral power density of the noise in the DC circuit.
- the method also comprises triggering an emergency procedure (already) in response to the detection of the indication. In this variant, the detection of whether an arc has actually occurred optionally takes place afterwards (ie, later in time).
- the emergency procedure is preferably suspended again when it is detected that no arc has actually occurred.
- the method comprises triggering an emergency procedure (in particular if and only if) it is detected that an arc has actually occurred in the PV system.
- the emergency procedure is not triggered as soon as the indication that an arc may have occurred is detected, but only when an actual arc is detected.
- the detection of the indication and the detection of the arc can also coincide.
- the triggering of the emergency procedure can, for example, include the triggering of an arc fault circuit interrupter (LBFSU, AFCI).
- the emergency procedure can include the system being reactivated if the event does not pose a danger.
- the emergency procedure can also include that, instead of a shutdown, the current is reduced to a value R so that the arc is extinguished, where R is a selectable parameter.
- the triggering of the emergency procedure can also include that a shutdown device is triggered, for example at least one relay is opened by an inverter of the PV system in order to thereby interrupt the flow of current.
- the recorded temporal progression of the amplitude values is subjected to pre-filtering in order to generate a filtered temporal progression of the amplitude values.
- the determination of the at least one value of the permutation entropy, PE, based on the filtered temporal progression of the amplitude values and/or the determination of the at least one value of the Jensen-Shannon complexity, JSK, is then advantageously carried out based on the filtered temporal progression of the amplitude values.
- the pre-filtering can, for example, comprise: - filtering out periodic signals; and/or - masking out frequency ranges in the temporal progression of the amplitude values which are not relevant or less relevant or disadvantageous for the detection of an arc.
- the filtering out of periodic signals can, for example, be carried out using statistical methods or Autocorrelation can take place.
- Frequency ranges to be masked out can be masked out by means of a spectral or temporal filter function, which can be based in particular on a Fourier analysis and/or a wavelet analysis.
- a spectral or temporal filter function which can be based in particular on a Fourier analysis and/or a wavelet analysis.
- the "temporal course of the amplitude values" can thus be understood here to mean either the raw temporal course of the amplitude values, as recorded, or (preferably) the filtered temporal course of amplitude values. For reasons of brevity, both variants are not repeated at every point.
- the invention provides a device for detecting an arc in a photovoltaic system, comprising: an inverter for generating alternating current from a direct current received from a photovoltaic system, comprising at least one measuring module which is designed to record a temporal course of amplitude values of an electrical quantity of the received direct current; and wherein the device further comprises: a calculation module which is configured to determine at least one value of a permutation entropy, PE, of the temporal course of amplitude values and to determine at least one value of a Jensen-Shannon complexity, JSK, of the temporal course of amplitude values; a detection module which is configured to detect whether an arc has occurred in the PV system based on the at least one specific value of the permutation entropy, PE, and on the at least one specific value of the Jensen-Shannon complexity, JSK; and a protective device by means of which an emergency procedure for protecting the photovoltaic system against an arc can be triggered.
- a calculation module which
- the device (either as part of the inverter or outside of it) can have a warning module which is designed to generate an indication that an arc could have occurred in the photovoltaic system, PV system.
- a warning module which is designed to generate an indication that an arc could have occurred in the photovoltaic system, PV system.
- the advantages of having such an indication have already been explained in detail above and will be explained in more detail below.
- the device according to the invention can advantageously be operated with the method according to the method according to the invention, as well as the method can be carried out with the device according to the invention. All variants, options, further developments and embodiments described in relation to the method are therefore also applicable to the device according to the invention and vice versa. All components of the device, in particular the various modules and/or devices, can advantageously all be integrated into the inverter, so that the device is compact, robust and largely autonomous.
- modules can be outsourced, for example to a remote server, a cloud-based computing device, or the like.
- the various modules or devices can each be available in hardware and/or software.
- the modules are implemented as software that is executed or can be executed by a computer system.
- the designation as a module or device does not mean that a clearly separate module or a separate program code section must necessarily be present. Rather, the modules and devices describe functions that can also be realized or implemented together and/or interwoven with one another.
- the computer system (or: the computing device) can include any circuit or combination of circuits.
- the computer system can include one or more processors, which can be of any type.
- processor may mean any type of computing circuit or computing device, such as (but not limited to) a microprocessor, a microcontroller, a complex instruction set microprocessor (CISC), a reduced instruction set microprocessor (RISC), a very long instruction word (VLIW) microprocessor, a graphics processing unit (GPU), a digital signal processor (DSP), a multi-core processor, a field programmable gate array (FPGA), or any other type of processor or processing circuit.
- CISC complex instruction set microprocessor
- RISC reduced instruction set microprocessor
- VLIW very long instruction word
- GPU graphics processing unit
- DSP digital signal processor
- FPGA field programmable gate array
- circuits may be a custom-built circuit, an application specific integrated circuit (ASIC), or the like, such as one or more circuits (e.g., a communications circuit) for use in wireless devices such as cellular phones, tablet computers, laptop computers, two-way radios, and similar electronic systems.
- the computer system may comprise one or more storage devices, which may comprise one or more storage elements suitable for the respective application, such as a main memory in the form of a random access memory (RAM), one or more hard disks and/or one or more drives that (can) handle removable media, such as CDs, flash memory cards, DVDs and the like.
- RAM random access memory
- drives that (can) handle removable media, such as CDs, flash memory cards, DVDs and the like.
- the detection module also has an artificial intelligence submodule, KIS, which implements an artificial intelligence unit, KIE, which is trained and configured to detect whether an arc has occurred based on the at least one specific value of the JSK and the at least one value of the PE.
- KIS artificial intelligence submodule
- KIE an artificial intelligence unit
- the device also has a cloud-based computing device, wherein the inverter also has a communication interface for bidirectional communication with the cloud-based computing device, and wherein the computing module and/or the detection module is implemented by the cloud-based computing device.
- the device can in particular comprise a plurality of inverters, which can also be connected to several or different PV systems.
- the computing module and/or the detection module can be provided centrally, while, for example, the protective device can be provided separately in each individual inverter, or at least in each individual PV system.
- the detection module comprises an artificial intelligence submodule, KIS, which requires high computing power and which can advantageously be updated regularly with additional training.
- the protective device is designed to trigger the emergency procedure in response to detecting the indication that an arc may have occurred.
- the detection module is advantageously designed to then detect whether an arc has actually occurred, and the protective device is in turn advantageously designed to suspend the emergency procedure again if the detection module detects that no arc has actually occurred.
- the suspension (or resetting) of the emergency procedure can be counted by means of a counter, which can be arranged in the inverter, for example. It can be provided that when a predefined threshold value (either absolute or per predefined time period) of the counter is reached, the emergency procedure (or a shutdown procedure that goes beyond this in the scope of protection) is triggered in such a way that it cannot be automatically suspended again (for example as described above).
- the intervention of a human technician can be a prerequisite for suspending the emergency procedure (or shutdown procedure).
- a signal can be automatically sent out requesting the intervention of the human technician.
- the protective device is designed to trigger the emergency procedure if the detection module has detected that an arc has actually occurred in the PV system.
- the invention provides a computer program product which comprises executable program code which, when executed, is designed to carry out the method according to the invention.
- the invention provides a non-volatile, computer-readable data storage medium which comprises executable program code which, when executed, is designed to carry out the method according to the invention.
- the invention provides a data stream which comprises executable program code (or is designed to generate executable program code) which, when executed, is designed to carry out the method according to the invention.
- FIG. 2 is a schematic representation of the PE-JSK parameter space to explain the functioning of the devices according to Fig. 1;
- Fig. 3 is a schematic representation to explain a device according to a further embodiment of the present invention;
- Fig. 4 is a schematic flow diagram to explain a method according to yet another embodiment of the present invention;
- Fig. 5 is a schematic flow diagram to explain a method according to yet another embodiment of the present invention;
- Fig. 6 is a schematic block diagram to explain a computer program product according to another embodiment of the present invention;
- Fig. 7 is a schematic block diagram to explain a data storage medium 500 according to another embodiment of the present invention.
- identical or functionally identical elements and devices have been provided with the same reference numerals - unless otherwise stated.
- Fig. 1 shows a schematic representation to explain a device 100 for detecting an arc in a photovoltaic system 200 according to an embodiment of the present invention.
- the photovoltaic system 200 can have one or more photovoltaic modules 210 (PV modules) which generate direct current 71 from sunlight.
- the PV system 200 is only rudimentarily shown in Fig. 1. It is understood that such a PV system can comprise one or more strings, each of which has a plurality of PV modules 210.
- An inverter 110 of the device 100 is designed and configured to receive the direct current 71 from the photovoltaic system 200 and to convert it into an alternating current 72, for example by means of power electronics 112.
- the inverter 110 also comprises at least one measuring module 114 and, in this embodiment, also a warning module 116.
- the measuring module 114 is designed to detect a temporal progression of amplitude values, A(t i ), of an electrical quantity of the received direct current 71, preferably in particular of the electrical current (hereinafter partially
- the measuring module 114 can comprise, for example, a power line communication (PLC) transformer and a current converter which is designed to read the PLC transformer.
- PLC power line communication
- the warning module 116 is designed to generate an indication that an arc may have occurred in the photovoltaic system 200. As has already been described in detail above, such an indication can arise in many different ways, for example, as in the prior art based on noise in the current domain, i.e. in the current signal. In other embodiments, the warning module 116 can also be arranged outside the inverter 110, in which case the inverter 110 is designed to receive the indication from the warning module 116.
- the device 100 also comprises a calculation module 120, which is set up to determine at least one value of a permutation entropy, PE, of the temporal course of amplitude values A(t i ) and to determine at least one value of a Jensen-Shannon complexity, JSK, of the temporal course of amplitude values A(t i ).
- PE permutation entropy
- JSK Jensen-Shannon complexity
- the device 100 also comprises a detection module 130, which is set up to detect whether an arc has occurred in the PV system 200, based on the at least one specific value of the permutation entropy, PE, and on the at least one specific value of the Jensen-Shannon complexity, JSK
- the device 100 additionally also comprises a protective device 140, by means of which an emergency procedure for protecting the PV system 200 and the surrounding infrastructure can be triggered if an arc occurs.
- the emergency procedure can in particular involve triggering a circuit breaker to interrupt an electrical power line on which the arc has occurred.
- the protective device 140 is only shown schematically in Fig. 1. It is understood that this can have a large number of control and circuit components that are also arranged wholly or partially in the PV system 200.
- the PV system 200 itself can thus also be understood as part of the device 100 according to the invention.
- the triggering of the emergency procedure by the protective device 140 merely comprises (or consists of) the sending of an emergency signal, for example to one or more circuit breakers of the PV system 200, or an internal or integrated protective device of the PV system 200 itself.
- the protective device 140 is shown as being arranged in the inverter 110, for example in the same housing.
- the protective device 140 can also be designed or arranged separately from the inverter 110, for example as part of a central control and/or monitoring system, which can thus also be part of the device 100 according to the invention.
- the device 100 is set up so that the protective device 140 triggers the emergency procedure as soon as the warning module 116 has detected the indication of the possible occurrence of an arc.
- the possibility of a false-positive triggering of the emergency procedure is consciously accepted in order to reduce the number of false-negative triggerings, if possible to zero.
- the detection module 130 determines whether an arc was actually present (true-positive triggering) or not (false-positive triggering).
- a large number of different methods have already been described above, based on which values in connection with the Jensen-Shannon complexity and the permutation entropy can be used by the detection module 130 to detect whether an arc is actually present or not.
- Fig. 2 shows the PE-JSK parameter space, with the (normalized) permutation entropy (symbol H in equation (3) above) on the horizontal axis and the Jensen-Shannon complexity on the vertical axis.
- this PE-JSK parameter space various signaling systems can be found and classified based on their position.
- the entire PE-JSK parameter space is shown at the top right of Fig. 2, and a section of it in the high PE region is shown in the main image of Fig. 2.
- White noise for example, is found at end point 5, i.e. at the point with maximum entropy and minimum complexity.
- Periodic signals for example, are found at start point 4 (where start and end points are only named in relation to an increasing entropy scale).
- the curves marked with "min” and “max” represent mathematically determined limit curves for the parameter space, i.e. all conceivable points, in particular for PV systems 200, are located within the space enclosed by the two curves.
- a point in the PE-JSK parameter space can now be determined from the time series of the amplitude values A(t i ) using the Unakafova approach and/or a method with non-overlapping windows for a large number of points in time T j , whereby the (sliding) window within which patterns are classified is shifted for each point in time T j .
- the points determined in this way result in a trajectory 3 in the PE-JSK parameter space.
- the noise behavior of the well-known "pink noise” in the PE-JSK parameter space is also shown with a star (marking/legend "P3").
- the "pink noise” has a 1/f noise characteristic, in contrast to the constant noise characteristic of a "white noise”.
- the PV system 200 In normal operation (or: control operation), the PV system 200 has a characteristic noise behavior corresponding to a characterizing point 1 in the PE-JSK parameter space (marking/legend "P1" in Fig. 2).
- Arcs also have a very characteristic noise behavior and thus generate a noise signal that differs from other interference signals (such as the shading of modules, radio signals, electromagnetic interference, switching processes in the inverter, modules with active Electronics and the like). Therefore, when an actual arc occurs, the noise behavior changes suddenly.
- the clarity of the change in behavior is advantageously improved by the preprocessing by the preprocessing module 115 described above.
- experiments by the inventors have shown that the PV system 200 in a fault state with an arc (marking/legend "P2" in Fig. 2) is characterized by a significantly shifted point 2.
- the trajectory 3 between point 1 and point 2 can assume a considerable size, in particular per time difference.
- the detection module 130 can thus detect that an arc has actually occurred, for example, by recording the path length of the trajectory 3 per unit of time (path length change rate), wherein a path length change rate above a predetermined limit value means that a sudden change in the characterization of the PV system 200 has occurred. In some variants, this can already trigger the emergency procedure by the protective device 140. Of course, other decision criteria for whether an arc has actually occurred can be used alternatively or in addition. As can also be seen from Fig. 2, the occurrence of the arc can, for example, cause the characterizing point 1 to shift in the direction of the end point 5.
- the detection module 130 decides on the occurrence of an arc if the path length change rate is above the predetermined limit value and/or (preferably “and”) if the characterizing point 1 or 2 reduces its distance from the end point 5. It can also be provided that this only applies if the distance is reduced by at least a certain absolute value and/or by at least a certain percentage value.
- Another possibility for detecting an arc or for checking the plausibility or confirming the detection of an arc can include the detection module 130 determining a noise characteristic of the characterizing point 2 in the PE-JSK parameter space. As can be seen in Fig. 2, the point 2 can in particular have a 1/f noise behavior, ie a noise characteristic similar to or exactly like “pink noise”.
- the detection module 130 is designed and configured to carry out a rule-based detection of whether an arc has actually occurred.
- the exact design of the detection rules of the detection module 130 depends on the size, design and arrangement of the PV system 200 and the other power electronics components involved, but can be easily determined by a person skilled in the art with knowledge of the present invention.
- the result of the test (or: detection) detected by the detection module 130 is communicated to the protective device 140, e.g. in a push or pull method via an internal data bus of the inverter 110.
- the emergency procedure can be immediately suspended (or cancelled) by the protective device 140. It can be provided that the protective device 140 sends a signal immediately, or after the emergency procedure has been triggered a predetermined number of times and suspended again due to a false-positive triggering, via a communication interface 145 of the protective device 140 to request intervention by a technician. For example, it may be necessary to adapt the detection rules or to check the PV system 200 with attention to a fault other than an arc.
- Fig. 3 shows a schematic representation of a device 100' according to a further embodiment of the present invention.
- the device 100' is a variant of the device 100 and differs from it primarily in the form and operation of the computing module 120 and, above all, the detection module 130. In the device 100', the computing module 120 and the detection module 130 are not located within the inverter 110.
- the computing module 120 and the detection module 130 are implemented by a cloud-based computing device 300.
- the inverter 110 has a communication interface 150 for bidirectional communication with the cloud-based computing device 300, in particular with a bidirectional communication interface 350 of the cloud-based computing device 300. All necessary signals can be exchanged via the communication interfaces 150, 350.
- the measured values of the measuring module 114, the indication of the warning module 116, and a signal which indicates the result of the detection of whether an arc has actually occurred or not can be exchanged or transmitted via this.
- implementing the computing module 120 and/or detection module 130 in the cloud-based computing device 300 has the advantage that it can have considerably more computing power than, for example, the inverter 110.
- a single cloud-based computing device 300 can advantageously implement the computing module 120 and/or the detection module 130 for a large number of inverters 110 and/or PV systems 200, especially since it is not expected that indications of arcing will be detected everywhere at the same time.
- the cloud-based computing device 300 can be set up with sufficient computing power for these tasks, while the inverter 110 itself can be kept compact.
- the detection module 130 has an artificial intelligence submodule, KIS 135, which implements an artificial intelligence entity, in particular a machine learning model, MLM.
- the possibilities and the possible designs of such an MLM have already been explained in detail above.
- a detection module 130 with artificial intelligence submodule, KIS 135, to be arranged in the inverter 110 itself, as in Fig. 1, it is preferred if the artificial intelligence submodule, KIS 135, is implemented on a cloud-based computing device 300 due to the usually greater computing power.
- the artificial intelligence submodule, KIS 135, can determine in other ways whether an arc has occurred or not, in addition to or as an alternative to the detection rules described with reference to Fig. 2.
- the KIS 135 can comprise at least one supervised trained MLM and/or at least one unsupervised trained MLM.
- the recognition module 130 can perform a dimensionality reduction between the creation of the variables and derived quantities based on PE and JSK (including variables and derived quantities based on the PE-JSK trajectory) on the one hand and the detection of whether an arc has occurred on the other hand.
- This can be done, for example, using methods based on matrix factorization such as principal component analysis (PCA) or using graph-based methods such as (preferably) uniform manifold approximation and projection (UMAP) or an equivalent method.
- PCA principal component analysis
- UMAP uniform manifold approximation and projection
- An assessment i.e. determining whether an arc has occurred
- the artificial intelligence Submodule 135 or by the statistics submodule
- the following pipeline can advantageously be provided: 1.
- An artificial neural network, KNN as a possible supervised trained MLM, can for example be trained in particular with a large number of data, the data being annotated (or labeled) with the information as to whether or not an arc has occurred in the corresponding time windows W.
- the artificial neural network, KNN is thus trained to detect the occurrence of the arc, possibly also in ways that go beyond the detection rules mentioned as examples.
- the present invention thus also provides a method for using an artificial neural network, KNN, to detect whether an arc has occurred in a direct current system. or not.
- input data is provided which each have values of the permutation entropy and the Jensen-Shannon complexity over time, and which are annotated with the information where an arc has occurred and where not.
- a loss function is provided which penalizes it if the artificial neural network, KNN, does not recognize in a time series according to the annotations whether an arc has occurred or not.
- the artificial neural network, KNN is then trained in several epochs, across many data sets, i.e. its parameters are automatically optimized in order to minimize the loss function over the training data sets.
- the artificial intelligence sub-module, KIS 135, can use at least one machine learning model, MLM, such as a KNN, “Logistic Regression”, a decision tree (“Decision Trees”), and/or a “Support Vector Machine”, alternatively or additionally also at least one statistical method.
- the KIS 135 can alternatively implement an unsupervised trained MLM. It is advantageous for this to cluster PE and JSK and/or derived quantities based on them (mean values, derivatives, maximum and minimum values and the like) using the known methods “Uniform Manifold Approximation and Projection”, UMAP, and “Density-Based Spatial Clustering of Applications with Noise”, DBSCAN. Based on this, signals during operation of the PV system (i.e.
- Fig. 4 shows a schematic flow chart to illustrate a method according to a further embodiment of the present invention, ie a computer-implemented method for detecting an arc in a photovoltaic system 200.
- the method according to Fig. 4 can be carried out with the embodiments of the device according to the invention, in particular with the devices 100; 100', but also independently thereof. Accordingly, the method according to Fig. 4 can be modified according to variants, modifications, options and further developments described above with reference to the device according to the invention, and vice versa.
- a temporal course of amplitude values, A(t i ), of an electrical quantity of an electrical current from the PV system 200 is recorded, in particular measured. This takes place, for example, as described above in general and with reference to the measuring module 114.
- this step S200 can be carried out within (or by) an inverter 110.
- preprocessing can be carried out, in particular as described above with reference to the preprocessing module 115.
- the further method steps can then be carried out based on the preprocessed (eg filtered) temporal course of amplitude values, A(t i ), without this needing to be explicitly explained additionally.
- a step S300 at least one value of a permutation entropy, PE, of the temporal course of the amplitude values A(t i ) is determined.
- a step S400 at least one value of a Jensen-Shannon complexity, JSK, of the temporal course of the amplitude values A(t i ) is determined.
- the steps S300 and/or S400 can in particular be carried out, for example, as described above generally and with reference to the computing module 120. In particular, the steps S300 and/or S400 can be carried out within (or by) an inverter 110 or by a cloud-based computing device 300.
- post-processing can take place in a step S450, for example as described above with reference to the computing module 120.
- at least one variable derived from PE and/or JSK can be calculated, for example a mean value, a derivative, a trajectory, a gradient, a minimum value, a maximum value and/or the like.
- steps that speak of "based on the JSK" and/or “based on the PE” also include that the steps can be indirectly based on the JSK and/or the PE and can thus be based in particular on at least one variable derived from JSK and/or PE.
- a dimensionality reduction e.g.
- step S500 it is detected whether an arc has actually occurred in the PV system, based on the at least one specific value of the permutation entropy, PE, and on the at least one specific value of the Jensen-Shannon complexity, JSK, or specifically on quantities derived from PE and/or JSK. This is advantageously done, for example, as described above in general and with reference to the detection module 130.
- step S500 can be carried out within (or by) an inverter 110 or by a cloud-based computing device 300.
- Fig. 5 shows a schematic flow chart to illustrate a method according to yet another embodiment of the present invention, ie a computer-implemented method for detecting an arc in a photovoltaic system 200.
- the method according to Fig. 5 can also be carried out with the embodiments of the device according to the invention, in particular with the devices 100; 100', but also independently thereof. Accordingly, the method according to Fig.
- step S200 an indication is detected that an arc may have occurred in the PV system 200, for example as described above generally and with reference to the warning module 116.
- this step S200 can be carried out within (or by) an inverter 110.
- step S300-S500 are only carried out if the indication was previously detected in step S200 ("+" sign in Fig. 5). In this way, unnecessary consumption of computing power can be avoided. This is particularly advantageous if these steps are carried out by a central computing device, e.g. a cloud-based computing device 300. If no indication is detected (“-” sign in Fig. 5), step S100 is continued (which can always be understood as being carried out continuously anyway). In any case, however, in the method according to Fig. 5, in response to the indication being detected, the emergency procedure is triggered in step S600. Ideally, this takes place immediately after the indication is detected S200, before or at the same time as steps S300-S500 are started.
- step S500 If it is now recognized in step S500 that no arc has actually occurred (“-” sign in Fig. 5), i.e. a false positive has been triggered, the emergency procedure is suspended again (or withdrawn) in a step S700 and the method continues with step S100. If, on the other hand, it is recognized in step S500 that an arc has actually occurred (“+” sign in Fig. 5), a protective procedure can be carried out in an optional step S800, the measures of which either extend those of the emergency procedure (e.g. make them permanent) and/or go beyond it in scope. This can be done, for example, as explained above in general and with reference to the protective device 140.
- Fig. 6 shows a schematic block diagram for explaining a computer program product 400 according to a further embodiment of the present invention.
- the computer program product 400 comprises executable program code 450 which, when executed, is designed to carry out the inventive method, in particular according to Fig. 4 or Fig. 5.
- Fig. 7 shows a schematic block diagram for explaining a non-volatile, computer-readable data storage medium 500 according to a further embodiment of the present invention.
- the data storage medium 500 comprises executable program code 550 which, when executed, is designed to carry out the inventive method, in particular according to Fig. 4 or Fig. 5.
Landscapes
- Photovoltaic Devices (AREA)
- Measurement Of Current Or Voltage (AREA)
Abstract
Description
Claims
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2024302859A AU2024302859A1 (en) | 2023-06-13 | 2024-06-12 | Device and method for detecting an arc in a direct-current system |
| IL325287A IL325287A (en) | 2023-06-13 | 2024-06-12 | Device and method for detecting an electric arc in a direct current system |
| EP24732689.5A EP4728637A2 (de) | 2023-06-13 | 2024-06-12 | Vorrichtung und verfahren zum erkennen eines lichtbogens in einem gleichstrom-system |
| CN202480039350.0A CN121399851A (zh) | 2023-06-13 | 2024-06-12 | 用于识别直流系统中的电弧的装置和方法 |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP23178979.3A EP4478606A1 (de) | 2023-06-13 | 2023-06-13 | Vorrichtung und verfahren zum erkennen eines lichtbogens in einem gleichstrom-system |
| EP23178979.3 | 2023-06-13 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| WO2024256495A2 true WO2024256495A2 (de) | 2024-12-19 |
| WO2024256495A3 WO2024256495A3 (de) | 2025-02-27 |
Family
ID=86764696
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/EP2024/066285 Ceased WO2024256495A2 (de) | 2023-06-13 | 2024-06-12 | Vorrichtung und verfahren zum erkennen eines lichtbogens in einem gleichstrom-system |
Country Status (5)
| Country | Link |
|---|---|
| EP (2) | EP4478606A1 (de) |
| CN (1) | CN121399851A (de) |
| AU (1) | AU2024302859A1 (de) |
| IL (1) | IL325287A (de) |
| WO (1) | WO2024256495A2 (de) |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934423B (zh) * | 2019-04-25 | 2020-04-21 | 山东大学 | 基于并网逆变器运行数据的光伏电站功率预测方法及系统 |
| CN113852349B (zh) * | 2021-09-17 | 2023-03-31 | 中新能(无锡)智慧能源有限公司 | 一种5g光伏电站的远程监控方法及系统 |
-
2023
- 2023-06-13 EP EP23178979.3A patent/EP4478606A1/de not_active Withdrawn
-
2024
- 2024-06-12 EP EP24732689.5A patent/EP4728637A2/de active Pending
- 2024-06-12 CN CN202480039350.0A patent/CN121399851A/zh active Pending
- 2024-06-12 AU AU2024302859A patent/AU2024302859A1/en active Pending
- 2024-06-12 IL IL325287A patent/IL325287A/en unknown
- 2024-06-12 WO PCT/EP2024/066285 patent/WO2024256495A2/de not_active Ceased
Non-Patent Citations (4)
| Title |
|---|
| C. BANDTB. POMPE: "Permutation entropy: a natural complexity measure for time series", PHYS. REV. LETT., vol. 88, no. 17, 2002, pages 174102, XP003020550, DOI: 10.1103/PhysRevLett.88.174102 |
| H. AZAMI ET AL.: "Improved multiscale permutation entropy for biomedical signal analysis: Interpretation and application to electroencephalogram recordings", BIOMED. PROCESS. CONTROL, vol. 23, 2016, pages 28 - 41 |
| O. ROSSO ET AL.: "Distinguishing noise from chaos", PHYS. REV. LETT, vol. 99, no. 15, 2007, pages 154102 |
| V.A. UNAKAFOVAK. KELLER: "Efficiently measuring complexity on the basis of real-world Data", ENTROPY, vol. 15, no. 10, 2013, pages 4392 - 4415 |
Also Published As
| Publication number | Publication date |
|---|---|
| IL325287A (en) | 2026-02-01 |
| CN121399851A (zh) | 2026-01-23 |
| WO2024256495A3 (de) | 2025-02-27 |
| EP4728637A2 (de) | 2026-04-22 |
| AU2024302859A1 (en) | 2026-01-29 |
| EP4478606A1 (de) | 2024-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE202022103434U1 (de) | Ein auf einem Enzephalogramm (EEG) basierendes Gerät zur Erkennung von epileptischen Anfällen | |
| DE112021004808T5 (de) | Erkennen von malware durch analyse verteilter telemetriedaten | |
| DE112016007498T5 (de) | Untersuchungseinrichtung und untersuchungsverfahren | |
| DE112013003277T5 (de) | Erkennen von Anomalien in Echtzeit in mehreren Zeitreihendaten mit automatisierter Schwellenwertbildung | |
| EP4165484B1 (de) | Überwachungsvorrichtung und verfahren zur anomaliedetektion | |
| EP4196805B1 (de) | Batteriemanagementsystem zum klassifizieren eines batteriemoduls | |
| DE202022100822U1 (de) | Ein hybrides System zur automatischen Entfernung von Augenblinzel-Artefakten aus Elektroenzephalogrammsignalen | |
| DE602005005516T2 (de) | Verfahren und einrichtung zur erkennung des elektrischen bogenphänomens auf mindestens einem elektrischen kabel | |
| DE202017005070U1 (de) | Computersystem und Computerprogramm zur computerimplementierten Erkennung von Anomalien in Ereignisströmen | |
| DE102021204040A1 (de) | Verfahren, Vorrichtung und Computerprogramm zur Erstellung von Trainingsdaten im Fahrzeug | |
| DE102019127622B4 (de) | Abwehrgenerator, Verfahren zur Verhinderung eines Angriffs auf eine KI-Einheit und computerlesbares-Speichermedium | |
| DE102017219269A1 (de) | Klassifizierung mit automatischer Auswahl aussichtsreicher Lerndaten | |
| WO2024256495A2 (de) | Vorrichtung und verfahren zum erkennen eines lichtbogens in einem gleichstrom-system | |
| EP3861681A1 (de) | System und verfahren zur fehlererkennung und fehlerursachen-analyse in einem netzwerk von netzwerkkomponenten | |
| DE102025115916A1 (de) | Verfahren und vorrichtung zum analysieren mehrkanaliger zeitreihen-signale mithilfe eines deep-learning-modells | |
| EP3997637A1 (de) | Identifizieren von ungenutzten servern | |
| DE102020212514A1 (de) | Verfahren zur Ermittlung eines Ausgabesignals mittels eines maschinellen Lernsystems | |
| WO2024184080A1 (de) | Verfahren zum erkennen von rauch in bildern einer umgebung und verfahren zum trainieren eines maschinenlernalgorithmus | |
| EP2284576B1 (de) | Verfahren und System zur Vorhersage von Ereignissen | |
| DE102024104333A1 (de) | Adaptiv zentrierte darstellung für nulltreffer-anomaliedetektionsverfahren | |
| DE102023135293A1 (de) | Verfahren und vorrichtung zum diagnostizieren eines fehlers | |
| DE102021201833A1 (de) | Vorrichtung zur Verarbeitung von mindestens einem Eingangsdatensatz unter Verwendung eines neuronalen Netzes sowie Verfahren | |
| EP3454154A1 (de) | Automatisierte erkennung von statistischen abhängigkeiten zwischen prozessmeldungen | |
| EP4323862A1 (de) | Verfahren zur qualitätssicherung eines systems | |
| DE102021207493A1 (de) | Verfahren zur Unterstützung eines Betriebs eines Fahrzeuges mit einer Sensoreinheit, Computerprogrammprodukt sowie System |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 24732689 Country of ref document: EP Kind code of ref document: A2 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 325287 Country of ref document: IL |
|
| WWE | Wipo information: entry into national phase |
Ref document number: AU2024302859 Country of ref document: AU |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 202617003127 Country of ref document: IN |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2024732689 Country of ref document: EP |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 2024732689 Country of ref document: EP Effective date: 20260113 |
|
| ENP | Entry into the national phase |
Ref document number: 2024732689 Country of ref document: EP Effective date: 20260113 |
|
| ENP | Entry into the national phase |
Ref document number: 2024302859 Country of ref document: AU Date of ref document: 20240612 Kind code of ref document: A |
|
| WWP | Wipo information: published in national office |
Ref document number: 202617003127 Country of ref document: IN |
|
| ENP | Entry into the national phase |
Ref document number: 2024732689 Country of ref document: EP Effective date: 20260113 |
|
| WWP | Wipo information: published in national office |
Ref document number: 325287 Country of ref document: IL |
|
| ENP | Entry into the national phase |
Ref document number: 2024732689 Country of ref document: EP Effective date: 20260113 |
|
| WWP | Wipo information: published in national office |
Ref document number: 2024732689 Country of ref document: EP |