WO2019214231A1

WO2019214231A1 - Faulty arc detection method, device and system

Info

Publication number: WO2019214231A1
Application number: PCT/CN2018/120951
Authority: WO
Inventors: 宋德超; 陈翀; 杨赛赛
Original assignee: 珠海格力电器股份有限公司
Priority date: 2018-05-07
Filing date: 2018-12-13
Publication date: 2019-11-14
Also published as: CN110456234A; CN110456234B

Abstract

Provided are a faulty arc detection method, device and system. The faulty arc detection method comprises: acquiring an arc parameter of a circuit where an electrical device is located (S102), wherein the arc parameter is a parameter of an arc generated in the circuit; analyzing the arc parameter by using a first model, and determining the probability that the arc is a normal arc or a faulty arc (S104); and determining the probabilities of the normal arc and the faulty arc by using a second model, and determining whether the arc is a faulty arc (S106).

Description

Method, device and system for detecting fault arc

Technical field

The present application relates to the field of arc fault protection, and in particular to a method, device and system for detecting a fault arc.

Background technique

Electrical equipment generates an electrical arc in the circuit during actual operation. Some of these arcs are “good arcs” generated by the normal operation of the equipment (waveforms such as voltage, current, etc. caused by the motor starting moment, switching action, etc.), and others are “bad arcs” caused by faults (damage of the insulation of the connecting wires) , the fluctuation of voltage, current and other parameters caused by poor electrical contact, etc.), "bad arc" is also the fault arc, which is the main cause of electrical fire. AFCI (short for Arc-Fault Circuit-Interrupter) technology, that is, arc fault segmentation protection technology, is to identify the normal arc and fault arc by identifying the state characteristics of the fault arc in the circuit, and timely and accurate before the arc causes fire. Protection technology for detecting and clearing fault arcs.

At present, the detection technology of arc is very mature. The voltage, current, and photoelectric characteristics can be used as arc detection parameters. The difficulty is how to distinguish between normal arc and fault arc. The traditional feature extraction method has certain effects in specific scenes, but the environment generated by fault arc is more complicated and has many influencing factors. The traditional identification method can not meet the requirements of electrical reliability and stability.

In view of the low accuracy and poor reliability of the detection method of the fault arc in the prior art, an effective solution has not been proposed yet.

Summary of the invention

The embodiment of the present application provides a method, device and system for detecting a fault arc to solve at least the technical problem of low accuracy and poor reliability of the fault arc detection method in the prior art.

In one embodiment of the present application, a method for detecting a fault arc includes: obtaining an arc parameter of a circuit in which the electrical device is located, the arc parameter being a parameter of an arc generated in the circuit; and analyzing the arc parameter using the first model Determine the probability that the arc belongs to the normal arc and the fault arc; use the second model to judge the probability of the normal arc and the fault arc to determine whether the arc belongs to the fault arc.

Optionally, when it is determined that the arc is a fault arc, the control device coupled to the electrical device and the power source operates to shut off power in the circuit and/or arc fault protection of the electrical device.

Optionally, before acquiring the arc parameter of the circuit where the electrical device is located, the method further includes: establishing an initial neural network model; acquiring a plurality of sets of sample data, wherein each of the plurality of sets of sample data includes: an arc parameter and Whether the corresponding arc belongs to the fault arc label; the initial neural network model is trained through multiple sets of sample data to obtain the first model.

Optionally, before acquiring the arc parameter of the circuit where the electrical device is located, the method further includes: transmitting, by the communication device, the historical arc parameter and the historical action data corresponding to the control device to the server, and receiving the optimized first model returned by the server and The optimized second model, wherein the optimized first model and the optimized second model are models obtained by the server based on historical arc parameters and historical motion data, and optimized for the first model and the second model.

Optionally, the arc parameter of the circuit where the electrical device is located includes: detecting an arc state of the arc by the arc signal detector, wherein the arc state includes one or more of the following: current fluctuation, voltage fluctuation, and intensity of the light; The conversion is performed to obtain an arc parameter.

In an embodiment of the present application, a fault arc detecting device is further provided, comprising: an obtaining module configured to acquire an arc parameter of a circuit where the electrical device is located, wherein the arc parameter is a parameter of an arc generated in the circuit; The module is configured to analyze the arc parameter using the first model to determine the probability that the arc belongs to the normal arc and the fault arc; and the second determining module is configured to determine the probability of the normal arc and the fault arc using the second model to determine the arc Whether it is a fault arc.

Optionally, the apparatus is further configured to: when determining that the arc is a fault arc, act by a control device coupled to the electrical device and the power source to shut off power in the circuit and/or arc fault protection of the electrical device.

Optionally, the foregoing apparatus is further configured to: establish an initial neural network model; acquire a plurality of sets of sample data, wherein each of the plurality of sets of sample data includes: an arc parameter and a label of whether the corresponding arc belongs to a fault arc The initial neural network model is trained through multiple sets of sample data to obtain the first model.

Optionally, the foregoing apparatus is further configured to: send the historical arc parameter and the historical action data corresponding to the control device to the server by using the communication device, and receive the optimized first model and the optimized second model returned by the server, where The optimized first model and the optimized second model are models obtained by the server based on historical arc parameters and historical motion data, and optimized for the first model and the second model.

Optionally, the obtaining module is further configured to: detect an arc state of the arc by the arc signal detector, wherein the arc state includes one or more of the following: current fluctuation, voltage fluctuation, and intensity of the light; converting the arc state to obtain Arc parameters.

In an embodiment of the present application, a fault arc detection system is further provided, comprising: an acquisition device connected to a circuit of the electrical device, configured to acquire an arc parameter of the circuit; and a processor connected to the acquisition device, configured to The first model is used to analyze the arc parameters to determine the probability that the arc belongs to the normal arc and the fault arc, and the second model is used to judge the probability of the normal arc and the fault arc to determine whether the arc belongs to the fault arc.

Optionally, the system further includes: a control device coupled to the power source of the processor, the electrical device, and the circuit, configured to act when the arc is determined to be a fault arc to shut off the power source and/or perform arc fault protection on the electrical device.

Optionally, the processor is further configured to: establish an initial neural network model; acquire a plurality of sets of sample data, wherein each of the plurality of sets of sample data includes: an arc parameter and a label of whether the corresponding arc belongs to a fault arc The initial neural network model is trained through multiple sets of sample data to obtain the first model.

Optionally, the system further includes: a communication device, connected to the processor, configured to send the historical arc parameter and the historical action data corresponding to the control device to the server, and receive the optimized first model and the optimized first returned by the server The second model, wherein the optimized first model and the optimized second model are models obtained by the server based on historical arc parameters and historical motion data, and optimized for the first model and the second model.

Optionally, the collecting device comprises: an arc signal detector configured to detect an arc state of the arc in the circuit, and convert the arc state to obtain an arc parameter, wherein the arc state includes one or more of the following: current fluctuation, voltage Fluctuations and the intensity of light.

In one embodiment of the present application, there is also provided a storage medium, the storage medium comprising a stored program, wherein the device in which the storage medium is located controls the detection method of the fault arc described above when the program is running.

In an embodiment of the present application, there is further provided a processor, the processor being configured to execute a program, wherein the detecting method of detecting the fault arc is executed when the program is running.

In the embodiment of the present application, after acquiring the arc parameter of the circuit where the electrical device is located, the arc parameter may be input into the first model, and the first model is used to analyze the arc parameter to determine the probability that the arc belongs to the normal arc and the fault arc. Then, the probability of the normal arc and the fault arc is further input into the second model, and the probability of the normal arc and the fault arc is judged using the second model to determine whether the arc belongs to the fault arc, thereby achieving the purpose of distinguishing between the normal arc and the fault arc. Because the neural network prediction and the decision model based on probability decision are used to distinguish the normal arc and the fault arc in the actual operation of the electrical equipment, the fault arc in the circuit can be accurately identified, and the arc segment protector can be further avoided in some scenes. The malfunction or malfunction does not act, thereby achieving the technical effect of improving the detection accuracy and reliability, and further improving the reliability and stability of the electrical equipment, thereby solving the low accuracy and reliability of the fault arc detection method in the prior art. Poor technical problems.

DRAWINGS

The accompanying drawings are provided to provide a further understanding of the present application, and are intended to be a part of this application. In the attached picture:

1 is a flow chart of a method for detecting a fault arc according to an embodiment of the present application;

2 is a topological schematic diagram of an alternative method of detecting a fault arc in accordance with one embodiment of the present application;

3 is a schematic flow chart of an optional method for detecting a fault arc according to an embodiment of the present application;

4 is a schematic diagram of a fault arc detecting apparatus according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a fault arc detecting device system according to an embodiment of the present application.

detailed description

The technical solutions in the embodiments of the present application are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present application. It is an embodiment of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope shall fall within the scope of the application.

It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or order. It is to be understood that the data so used may be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "comprises" and "comprises" and "the" and "the" are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to Those steps or units may include other steps or units not explicitly listed or inherent to such processes, methods, products or devices.

In accordance with an embodiment of the present application, an embodiment of a method of detecting a fault arc is provided, it being noted that the steps illustrated in the flowchart of the figures may be performed in a computer system such as a set of computer executable instructions And, although the logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in a different order than the ones described herein.

1 is a flow chart of a method for detecting a fault arc according to an embodiment of the present application. As shown in FIG. 1, the method includes the following steps:

Step S102: Acquire an arc parameter of a circuit where the electrical device is located, and the arc parameter is a parameter of an arc generated in the circuit.

Optionally, the foregoing electrical device may be any device that uses AFCI technology, including but not limited to an air conditioner, a socket, a production operation device, etc.; the above circuit may be a power supply circuit of the electrical device, including a power source for supplying electrical equipment; The arc parameter mentioned above may be in the form of voltage, current, photoelectric form parameters, etc., and when the arc is generated in the circuit, the corresponding arc parameter is collected by the collecting device.

Step S104, analyzing the arc parameters using the first model to determine the probability that the arc belongs to the normal arc and the fault arc.

Optionally, the first model may be a neural network model trained in advance through a large amount of experimental data or historical data, and the confidence probability of the normal arc and the fault arc may be predicted by the neural network, wherein the neural network may adopt different The structure and type, the actual application is determined according to the input arc data format, and may be, but not limited to, one or more of a fully connected neural network, a convolutional neural network, a circulating neural network, and a capsule neural network.

Step S106, using the second model to determine the probability of the normal arc and the fault arc to determine whether the arc belongs to the fault arc.

Optionally, the second model may be a probability decision model, and the probability decision model may be used to perform reliability confirmation analysis on the probability of the output of the neural network model, thereby obtaining a judgment that the arc is ultimately a fault arc or a normal arc, wherein the probability decision is made. One or more of the risk assessment, the statistical distribution, and the empirical formula can be used for decision making, which can be determined according to the actual application scenario and data structure.

In an alternative solution, when an arc is generated in the circuit in which the electrical device is located, it is necessary to distinguish the type of the arc to determine whether the arc is a normal arc or a fault arc, and the arc parameter can be obtained from the circuit through the collecting device in real time. And the fault arc detection algorithm is used to judge whether the arc is a normal arc or a fault arc detection result. Alternatively, the arc parameter collected when the fault arc occurs may be used as an input parameter, firstly predicted by a neural network model. The confidence probability of the normal arc and the fault arc is then determined by the probability decision model to determine whether the fault arc or the normal arc is ultimately achieved.

In the above embodiment of the present application, after acquiring the arc parameter of the circuit where the electrical device is located, the arc parameter may be input into the first model, and the first model is used to analyze the arc parameter to determine the probability that the arc belongs to the normal arc and the fault arc. Then, the probability of the normal arc and the fault arc is further input into the second model, and the probability of the normal arc and the fault arc is judged using the second model to determine whether the arc belongs to the fault arc, thereby achieving the purpose of distinguishing between the normal arc and the fault arc. Because the neural network prediction and the decision model based on probability decision are used to distinguish the normal arc and the fault arc in the actual operation of the electrical equipment, the fault arc in the circuit can be accurately identified, and the arc segment protector can be further avoided in some scenes. The malfunction or malfunction does not act, thereby achieving the technical effect of improving the detection accuracy and reliability, and further improving the reliability and stability of the electrical equipment, thereby solving the low accuracy and reliability of the fault arc detection method in the prior art. Poor technical problems.

Alternatively, when it is determined that the arc is a fault arc, the control device coupled to the electrical equipment and the power source operates to shut off power in the circuit and/or arc fault protection of the electrical device.

Optionally, the above control device may be a protection action device of the electrical device, for example, an arc segment protector, connected to the power source and the electrical device in the circuit.

In an optional solution, after determining that the arc belongs to the fault arc through the neural network model and the probability decision model, the control device can be notified to cut off the power supply and protect the electrical device in time, thereby preventing the fault arc from further deteriorating and causing the electrical fire. To protect the safety of users' lives and property.

Optionally, the plurality of sets of sample data described above may be arc parameter sample data obtained through experimental or historical data.

In an alternative solution, the experimental conditions can be determined according to the AFCI detection standard, and a large number of labeled arc parameter sample data obtained through experimental or historical data can be detected by the instrument during the training phase, or by the camera. An optoelectronic device such as a CCD (which is a charge coupled device image sensor or a Charge Coupled Device) determines whether or not it is a fault arc, and obtains a label of the arc parameter sample data. Taking the parameters of the fault arc just as input, the arc parameters and corresponding labels are sent to the initial neural network model for training, and the optimized prediction model, that is, the first model is obtained.

Optionally, the foregoing communication device may be a networked device such as a WIFI, a GPRS, a 3G network, a 4G network, or a 5G network, for example, a WIFI module, and the communication device may be integrated with the AFCI device in a built-in manner, or may be externally used. The method is connected with the AFCI device; the above server may be a cloud server, and the cloud training algorithm can perform targeted optimization training on the neural network model and the probability decision model.

In an optional solution, the AFCI device can communicate with the cloud server through the communication device, upload the arc data and the control action of the scenario to the cloud server, and target the neural network model and the probability decision model through the cloud server. Sexual optimization training. Then, the cloud server delivers the optimized model to the local program end of the AFCI device, so that the model can be continuously optimized according to the usage scenario and the age of the device for adaptive learning. It is also possible to continuously accumulate fault arc data through big data collection, so that the algorithm model is more and more perfect.

Optionally, obtaining an arc parameter of the circuit where the electrical device is located, including detecting an arc state of the arc by the arc signal detector, wherein the arc state includes one or more of the following: current fluctuation, voltage fluctuation, and intensity of the light; Convert to get the arc parameters.

Optionally, the arc state may be a natural state reflected by the arc, and may be a reaction of current, voltage fluctuation, light intensity change, etc., and cannot be directly used.

In an alternative, the arc state of the circuit in which the electrical device is located can be first detected by the arc signal detector and converted to a digital signal as input data for the neural network model.

2 is a topological schematic diagram of an optional fault arc detecting method according to an embodiment of the present application, and FIG. 3 is a schematic flowchart of an optional fault arc detecting method according to an embodiment of the present application. A preferred embodiment of the present application will be described in detail below with reference to FIGS. 2 and 3.

As shown in FIG. 2, the detection method can take the arc parameter when the arc is generated in the operation of the device as the input from the circuit where the device is located, and predict through the neural network model to obtain the fault arc probability and the normal arc probability. Then, the reliability confirmation analysis is carried out through the probability decision model to obtain the detection result of whether the fault arc or the normal arc is finally obtained.

As shown in FIG. 3, the electrical device is connected to the power source through a circuit, and an arc signal detector in the AFCI device is connected to the circuit, and the arc parameter can be obtained from the circuit in real time; the fault arc determination algorithm model includes a neural network model and a probability decision model. The input arc parameter can be judged to output a normal arc or a fault arc; if it is a fault arc, the corresponding action is performed by the protection action device: the power supply is cut off or the electrical device is protected; the AFCI device can be connected to the cloud server through the networked device. The connection realizes data uploading of the arc parameter of the AFCI device and the control action of the protection action device, and the delivery of the neural network model and the probability decision model after the cloud server training and optimization.

Through the above scheme, by using the fault arc determination model of neural network prediction and probability decision, the fault arc and the normal arc in the actual operation of the device are distinguished, and the fault arc in the circuit is accurately identified. Combined with the fault arc control method, the power supply is cut off in time to prevent faults from further causing electrical fires and protecting people's lives and property.

According to an embodiment of the present application, an embodiment of a fault arc detecting device is also provided.

4 is a schematic diagram of a fault arc detecting apparatus according to an embodiment of the present application. As shown in FIG. 4, the apparatus includes:

The acquisition module 42 is configured to obtain an arc parameter of a circuit in which the electrical device is located, the arc parameter being a parameter of an arc generated in the circuit.

The first determining module 44 is configured to analyze the arc parameters using the first model to determine the probability that the arc belongs to the normal arc and the fault arc.

The second determining module 46 is configured to determine the probability of the normal arc and the fault arc using the second model to determine whether the arc is a fault arc.

In accordance with an embodiment of the present application, an embodiment of a fault arc detection system is also provided.

FIG. 5 is a schematic diagram of a fault arc detecting device system according to an embodiment of the present application. As shown in FIG. 5, the system includes:

The collecting device 52 is connected to the circuit where the electrical device is located, and is arranged to acquire the arc parameter of the circuit.

The processor 54 is coupled to the acquisition device and configured to analyze the arc parameter using the first model, determine the probability that the arc belongs to the normal arc and the fault arc, and determine the probability of the normal arc and the fault arc using the second model to determine Whether the arc is a fault arc.

Optionally, as shown in FIG. 3, the foregoing processor may include a fault arc determination algorithm model, including a first model and a second model; and the first model may be a nerve trained in advance through a large amount of experimental data or historical data. The network model can predict the confidence probability of normal arc and fault arc through neural network. The neural network can adopt different structures and types. The actual application is determined according to the input arc data format, which can be but not limited to the fully connected nerve. One or more of network, convolutional neural network, cyclic neural network, and capsule neural network; the second model described above may be a probability decision model, and the probability decision model may be used to perform reliability confirmation analysis on the probability of the neural network model output. Therefore, the determination of whether the arc is ultimately a fault arc or a normal arc is obtained, wherein the probability decision can be determined by using one or more of risk assessment, statistical distribution, and empirical formula, and can be determined according to actual application scenarios and data structures. .

In the above embodiment of the present application, after the arc parameter of the circuit where the electrical device is located is acquired by the collecting device, the arc parameter may be input into the first model by the processor, and the arc parameter is analyzed by using the first model to determine that the arc is normal. The probability of the arc and the fault arc, and then further input the probability of the normal arc and the fault arc into the second model, and use the second model to judge the probability of the normal arc and the fault arc to determine whether the arc belongs to the fault arc, thereby realizing the distinction between the normal arc and The purpose of the fault arc. Because the neural network prediction and the decision model based on probability decision are used to distinguish the normal arc and the fault arc in the actual operation of the electrical equipment, the fault arc in the circuit can be accurately identified, and the arc segment protector can be further avoided in some scenes. The malfunction or malfunction does not act, thereby achieving the technical effect of improving the detection accuracy and reliability, and further improving the reliability and stability of the electrical equipment, thereby solving the low accuracy and reliability of the fault arc detection method in the prior art. Poor technical problems.

Optionally, the system further comprises:

The control device is coupled to the power source of the processor, the electrical device, and the circuit, and is configured to act when the arc is determined to be a fault arc to shut off the power source and/or provide arc fault protection for the electrical device.

Optionally, the system further comprises:

The communication device is connected to the processor, configured to send the historical arc parameter and the historical action data corresponding to the control device to the server, and receive the optimized first model and the optimized second model returned by the server, wherein the optimized A model and an optimized second model are models obtained by the server based on historical arc parameters and historical motion data, and optimized for the first model and the second model.

In an optional solution, the AFCI device can communicate with the cloud server through the communication device, upload the arc data and the control action of the scenario to the cloud server, and target the neural network model and the probability decision model through the cloud server. Sexual optimization training. Then, the cloud server delivers the optimized model to the local program end of the AFCI device, so that the model can be continuously optimized according to the usage scenario and the age of the device for adaptive learning. It is also possible to continuously accumulate fault arc data through big data collection, and make the algorithm model more and more perfect.

Optionally, the collecting device comprises:

An arc signal detector is arranged to detect an arc state of the arc in the circuit and to convert the arc state to obtain an arc parameter, wherein the arc state comprises one or more of the following: current fluctuation, voltage fluctuation, and light intensity.

According to an embodiment of the present application, there is also provided an embodiment of a storage medium comprising a stored program, wherein the device in which the storage medium is located controls the detection method of the above-described fault arc when the program is running.

Optionally, in the present embodiment, the storage medium is arranged to store program code for performing the steps of: obtaining an arc parameter of a circuit in which the electrical device is located, the arc parameter being a parameter of an arc generated in the circuit; using the first model pair The arc parameters are analyzed to determine the probability that the arc belongs to the normal arc and the fault arc; the second model is used to judge the probability of the normal arc and the fault arc to determine whether the arc belongs to the fault arc.

Alternatively, in the present embodiment, the storage medium may also be provided as program code for storing various preferred or optional method steps provided by the detection method of the fault arc.

According to an embodiment of the present application, there is also provided an embodiment of a processor, the processor being configured to execute a program, wherein the method for detecting the fault arc described above is executed while the program is running.

The various functional modules provided by the embodiments of the present application may be operated in an electrical device or the like, or may be stored as part of a storage medium.

Thus, embodiments of the present application can provide an electrical device.

In this embodiment, the electrical device is configured to execute the following steps in the method for detecting a fault arc: acquiring an arc parameter of a circuit in which the electrical device is located, the arc parameter being a parameter of an arc generated in the circuit; and using the first model to the arc parameter An analysis is performed to determine the probability that the arc belongs to the normal arc and the fault arc; the probability of the normal arc and the fault arc is judged using the second model to determine whether the arc is a fault arc.

Optionally, the electrical device can include: one or more processors, memory, and transmission devices.

The memory can be used to store the software program and the module, such as the fault arc detection method and the program instruction/module corresponding to the device in the embodiment of the present application, and the processor executes various programs by running the software program and the module stored in the memory. Functional application and data processing, that is, the detection method of the above-mentioned fault arc. The memory may include a high speed random access memory, and may also include non-volatile memory such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory. In some examples, the memory can further include memory remotely located relative to the processor, which can be connected to the terminal over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The above transmission device is for receiving or transmitting data via a network. Specific examples of the above network may include a wired network and a wireless network. In one example, the transmission device includes a Network Interface Controller (NIC) that can be connected to other network devices and routers via a network cable to communicate with the Internet or a local area network. In one example, the transmission device is a Radio Frequency (RF) module for communicating with the Internet wirelessly.

Wherein, in particular, the memory is used to store the arc parameters, the first model and the second model, and the application.

The processor can call the memory stored information and the application by the transmitting device to execute the program code of the method steps of each of the alternative or preferred embodiments of the above method embodiments.

In the above-mentioned embodiments of the present application, the descriptions of the various embodiments are different, and the parts that are not detailed in a certain embodiment can be referred to the related descriptions of other embodiments.

In the several embodiments provided by the present application, it should be understood that the disclosed technical contents may be implemented in other manners. The device embodiments described above are only schematic. For example, the division of the unit may be a logical function division. In actual implementation, there may be another division manner, for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, unit or module, and may be electrical or otherwise.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application, in essence or the contribution to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium. A number of instructions are included to cause a computer device (which may be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and the like. .

The above description is only a preferred embodiment of the present application, and it should be noted that those skilled in the art can also make several improvements and retouchings without departing from the principles of the present application. It should be considered as the scope of protection of this application.

Industrial applicability

The technical solution provided by the embodiment of the present application can be applied to the operation process of the electrical device, and the arc parameter of the circuit where the electrical device is located is used, and the arc parameter is analyzed by using the first model to determine the probability that the arc belongs to the normal arc and the fault arc. And using the second model to judge the probability of the normal arc and the fault arc, and determining whether the arc belongs to the fault arc, can solve the problem that the fault detection method of the prior art has low accuracy and poor reliability, and realizes the problem in the circuit. The fault arc is accurately identified, and the arc segment protector is further prevented from causing malfunction or failure in some scenes, thereby improving the detection accuracy and reliability, and further improving the reliability and stability of the electrical equipment.

Claims

A method for detecting a fault arc includes:

Obtaining an arc parameter of a circuit in which the electrical device is located, the arc parameter being a parameter of an arc generated in the circuit;

The arc parameter is analyzed using a first model to determine the probability that the arc belongs to a normal arc and a fault arc;

A probability of the normal arc and the fault arc is determined using a second model to determine if the arc is a fault arc.
The method according to claim 1, wherein when it is determined that said arc belongs to a fault arc, a control device connected to said electric device and said power source operates to cut off power in said circuit and/or to said electric The device performs arc fault protection.
The method of claim 2, wherein before the obtaining an arc parameter of the circuit in which the electrical device is located, the method further comprises:

Establish an initial neural network model;

Obtaining a plurality of sets of sample data, wherein each of the plurality of sets of sample data includes: an arc parameter and a label of whether the corresponding arc belongs to a fault arc;

The initial neural network model is trained by the plurality of sets of sample data to obtain the first model.
The method of claim 3, wherein prior to obtaining an arc parameter of a circuit in which the electrical device is located, the method further comprises:

Transmitting, by the communication device, the historical arc parameter and the historical action data corresponding to the control device to the server, and receiving the optimized first model and the optimized second model returned by the server, wherein the optimized first The model and the optimized second model are models obtained by the server after optimizing the first model and the second model based on the historical arc parameter and the historical action data.
The method of claim 1 wherein obtaining an arc parameter of a circuit in which the electrical device is located comprises:

The arc state of the arc is detected by an arc signal detector, wherein the arc state includes one or more of the following: current fluctuation, voltage fluctuation, and intensity of light;

The arc state is converted to obtain the arc parameter.
A fault arc detecting device includes:

An acquisition module configured to obtain an arc parameter of a circuit in which the electrical device is located, the arc parameter being a parameter of an arc generated in the circuit;

a first determining module configured to analyze the arc parameter using a first model to determine a probability that the arc belongs to a normal arc and a fault arc;

The second determining module is configured to determine the probability of the normal arc and the fault arc using the second model to determine whether the arc belongs to a fault arc.
The apparatus according to claim 6, wherein said apparatus is further arranged to, when determining that said arc belongs to a fault arc, act by a control means connected to said electrical equipment and said power source to cut off said circuit The power source and/or the arc fault protection of the electrical equipment.
The apparatus of claim 7 wherein said apparatus is further configured to:

Establish an initial neural network model;

Obtaining a plurality of sets of sample data, wherein each of the plurality of sets of sample data includes: an arc parameter and a label of whether the corresponding arc belongs to a fault arc;

The initial neural network model is trained by the plurality of sets of sample data to obtain the first model.
The apparatus of claim 8 wherein said apparatus is further configured to:

Transmitting, by the communication device, the historical arc parameter and the historical action data corresponding to the control device to the server, and receiving the optimized first model and the optimized second model returned by the server, wherein the optimized first The model and the optimized second model are models obtained by the server after optimizing the first model and the second model based on the historical arc parameter and the historical action data.
The apparatus of claim 6 wherein said obtaining module is further configured to:

The arc state of the arc is detected by an arc signal detector, wherein the arc state includes one or more of the following: current fluctuation, voltage fluctuation, and intensity of light;

The arc state is converted to obtain the arc parameter.
A fault arc detection system includes:

The collecting device is connected to the circuit where the electrical device is located, and is configured to obtain an arc parameter of the circuit;

a processor coupled to the acquisition device, configured to analyze the arc parameter using a first model, determine a probability that the arc belongs to a normal arc and a fault arc, and use the second model to normal arc and fault The probability of the arc is judged to determine if the arc is a fault arc.
The system of claim 11 wherein said system further comprises:

a control device coupled to the processor, the electrical device, and the electrical power source in the circuit, configured to act when the arc is determined to be a fault arc to shut off the power source and/or cause an arc fault to the electrical device protection.
The system of claim 12 wherein said processor is further configured to:

Establish an initial neural network model;

Obtaining a plurality of sets of sample data, wherein each of the plurality of sets of sample data includes: an arc parameter and a label of whether the corresponding arc belongs to a fault arc;

The initial neural network model is trained by the plurality of sets of sample data to obtain the first model.
The system of claim 13 wherein said system further comprises:

The communication device is connected to the processor, configured to send the historical arc parameter and the historical action data corresponding to the control device to the server, and receive the optimized first model and the optimized second model returned by the server, The optimized first model and the optimized second model are that the server optimizes the first model and the second model based on the historical arc parameter and the historical action data. The model obtained afterwards.
The system of claim 11 wherein said collecting means comprises:

An arc signal detector configured to detect an arc state of an arc in the circuit and to convert the arc state to obtain the arc parameter, wherein the arc state comprises one or more of the following: current fluctuation, voltage Fluctuations and the intensity of light.
A storage medium, the storage medium comprising a stored program, wherein the device in which the storage medium is located controls the detection method of the fault arc according to any one of claims 1 to 5 while the program is running.
A processor, the processor being configured to run a program, wherein the program is operative to perform the method of detecting a fault arc according to any one of claims 1 to 5.