Power distribution system harmonic detection method and device based on neural network

Abstract

The invention discloses a power distribution system harmonic detection method and device based on a neural network, and belongs to the technical field of power quality disturbance detection, and the method comprises the steps: S1, respectively obtaining voltage time domain signals at R monitoring points of a power distribution system; s2, the neural network model outputs power quality disturbance event information according to the voltage time domain signal; s3, if the type of the power quality disturbance event is the power harmonic event, acquiring a current time domain signal by a power signal detection instrument; if the event is other event, displaying the electric energy quality disturbance event information; and S4, the probabilistic neural network outputs a harmonic component identification result according to the current time domain signal and displays the harmonic component identification result. According to the invention, the complexity of judging the power quality disturbance event can be effectively reduced, and the accuracy of power harmonic detection of the power distribution system is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power quality disturbance detection, and in particular relates to a method and device for detecting harmonics in a power distribution system based on a neural network. Background Art

[0002] Power quality disturbance refers to the deviation or fluctuation of voltage, current or frequency in the power system. These deviations or fluctuations may have an adverse effect on the normal operation of power equipment, the efficiency of power use and the stability of the power system, usually including voltage swell, voltage sag and power harmonics, etc. In order to ensure the stable operation of the power system and the normal use of power equipment, it is necessary to monitor, analyze and process these power quality disturbances. In the prior art, power quality monitoring devices are installed to monitor the changes in voltage, current and frequency in real time, so as to promptly detect and deal with potential power quality problems. At the same time, some measures can also be taken to prevent and reduce the occurrence of power quality disturbances, such as optimizing the grid structure, improving equipment performance, and strengthening equipment maintenance.

[0003] At present, the methods for judging the type of power quality disturbance events can be divided into two categories according to the signal type. The first category is the time domain waveform discrimination method, which uses artificial intelligence methods to analyze the collected power signal time domain waveform to determine the load type and harmonic source. However, when using artificial intelligence methods for analysis, a large amount of power quality disturbance event data is often required to train the artificial intelligence model in order to accurately obtain the characteristics of power quality disturbance events to distinguish the event type, which is highly complex. The second category is the harmonic spectrum discrimination method, which usually relies on fast Fourier transform to convert the distorted waveform from the time domain to the frequency domain, and then analyze the spectrum to identify the type of disturbance event. However, this method has problems such as spectrum leakage and fence effect when processing non-stationary signals, which may lead to inaccurate analysis results. Moreover, since the entire judgment process cannot be simplified, it is difficult to meet the real-time requirements of power quality disturbance event judgment. In addition, power equipment with nonlinear characteristics is increasingly being applied to distribution systems, and the power harmonics caused by them have become one of the main manifestations of power quality problems. Therefore, how to timely identify power harmonic components after determining a power quality disturbance event so as to accurately eliminate the impact of power harmonics on power quality is also a problem that needs to be solved urgently in this field.

[0004] Therefore, there is an urgent need for a new type of harmonic detection method and device for distribution system, which can quickly detect power quality disturbance events in the distribution system and accurately identify the power harmonic components based on the detection results, thereby achieving rapid response to power disturbance events and improving the stability of distribution system operation and power consumption experience. Summary of the invention

[0005] In view of the defects in the above-mentioned prior art, the present invention provides a method for detecting harmonics in a power distribution system based on a neural network, the method comprising:

[0006] Step S1, setting R monitoring points in the power distribution system, and setting power signal detection instruments at the R monitoring points to respectively obtain voltage time domain signals; R≥2;

[0007] Step S2, preprocessing the voltage time domain signal, wherein the preprocessed voltage time domain signal carries the corresponding monitoring point location information; sequentially inputting the preprocessed voltage time domain signal into the neural network model, wherein the neural network model outputs power quality disturbance event information according to the voltage time domain signal; the power quality disturbance event information includes the monitoring point location information corresponding to the voltage time domain signal and the power quality disturbance event type, and the power quality disturbance event type includes five types: normal, power harmonic event, voltage swell event, voltage sag event, and power outage event;

[0008] Step S3: if the power quality disturbance event type is the power harmonic event, determine the corresponding power signal detection instrument according to the monitoring point location information, and obtain the current time domain signal by the power signal detection instrument; if the power quality disturbance event type is other events, display the power quality disturbance event information;

[0009] Step S4, preprocessing the current time domain signal, inputting the preprocessed current time domain signal into a probabilistic neural network, the probabilistic neural network outputting a harmonic component identification result according to the current time domain signal, and displaying the harmonic component identification result.

[0010] Furthermore, the neural network model includes a wavelet layer, a hidden layer and an output layer, wherein the wavelet layer is used to extract signal features from the voltage time domain signal, and the hidden layer and the output layer are used to calculate the probability that the signal belongs to the power quality disturbance event type based on the signal features.

[0011] Furthermore, the weight matrix W from the wavelet layer to the hidden layer is WH , specifically:

[0012]

[0013]

[0014]

[0015] x i =x(nT)

[0016] t i =xc (nT)

[0017] Among them, d i is the scale parameter of wavelet transform, x is the voltage time domain signal, x c is the baseband time domain signal, x i is the sampling sequence of the voltage time domain signal, t i is the sampling sequence of the baseband time domain signal, T is the sampling period, n is the number of wavelet nodes included in the wavelet layer, and K is the number of nodes included in the hidden layer.

[0018] Furthermore, the weight matrix W from the hidden layer to the output layer is HO , specifically:

[0019]

[0020]

[0021] Among them, m is the number of output nodes included in the output layer, m=5, corresponding to the above five types of power quality disturbance events, Category1 and Category2 represent category labels.

[0022] Further, the calculating the probability that the signal belongs to the power quality disturbance event type is specifically:

[0023]

[0024]

[0025]

[0026] Among them, σ is the smoothing parameter.

[0027] Furthermore, the probabilistic neural network includes an input layer, a hidden layer and an output layer, wherein the output layer includes 6 output nodes corresponding to the 3rd harmonic, the 5th harmonic, the 7th harmonic, the 9th harmonic, the 11th harmonic and the 13th harmonic respectively.

[0028] Furthermore, after step S4, it also includes: providing an active filter at the corresponding monitoring point, and according to the harmonic component identification result output by the probabilistic neural network, the active filter injects a harmonic current with the same magnitude and opposite direction as the harmonic component to eliminate the harmonic component in the current time domain signal.

[0029] The present invention also provides a power distribution system harmonic detection device based on a neural network, the device comprising:

[0030] A collection module, the collection module is used to set R monitoring points in the power distribution system, and set power signal detection instruments at the R monitoring points to respectively obtain voltage time domain signals; R≥2;

[0031] A detection module, wherein the detection module is used to preprocess the voltage time domain signal, wherein the preprocessed voltage time domain signal carries the corresponding monitoring point location information; the preprocessed voltage time domain signal is sequentially input into a neural network model, wherein the neural network model outputs power quality disturbance event information according to the voltage time domain signal; the power quality disturbance event information includes the monitoring point location information corresponding to the voltage time domain signal and the power quality disturbance event type, wherein the power quality disturbance event type includes five types: normal, power harmonic event, voltage swell event, voltage sag event, and power outage event;

[0032] A judgment module, wherein the judgment module is used to, if the type of the power quality disturbance event is the power harmonic event, determine the corresponding power signal detection instrument according to the monitoring point location information, and obtain the current time domain signal by the power signal detection instrument; if the type of the power quality disturbance event is other events, display the power quality disturbance event information;

[0033] An identification module, wherein the identification module is used to preprocess the current time domain signal, input the preprocessed current time domain signal into a probabilistic neural network, and the probabilistic neural network outputs a harmonic component identification result based on the current time domain signal and displays the harmonic component identification result.

[0034] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the neural network-based power distribution system harmonic detection method as described above is implemented.

[0035] The present invention also provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is used to execute the computer program to implement the aforementioned neural network-based distribution system harmonic detection method.

[0036] The present invention first uses a neural network to judge the type of power quality disturbance events at multiple monitoring points. On the basis of determining that the type of power quality disturbance event is a power harmonic event, the power harmonic component is identified, which can comprehensively and accurately determine the power quality disturbance event, thereby improving the effectiveness of power harmonic component detection. When using a neural network to judge the type of power quality disturbance event, by combining wavelet transform and probabilistic neural network, that is, using wavelet transform as the input layer of the probabilistic neural network, the input layer realizes a filter-like function, and can directly extract signal features from the input time domain signal, thereby avoiding the problems of spectrum leakage and fence effect that may be caused by the use of fast Fourier transform for time-frequency conversion in advance. In addition, the above-mentioned neural network has a fast learning speed, does not need to correct the iterative process of the network weight matrix, and only needs to pay attention to the smoothing parameters, which effectively reduces the complexity of power quality disturbance event judgment. When identifying the power harmonic component, the present invention sets the probabilistic neural network to detect the odd harmonics of the nonlinear load, effectively improving the accuracy of power harmonic detection in the distribution system, and facilitating the elimination of subsequent harmonic components. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present disclosure will become readily understood. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0038] Figure 1 The flowchart shows a method for detecting harmonics in a power distribution system based on a neural network according to an embodiment of the present invention.

[0039] Figure 2 FIG. 2 is a diagram showing a neural network according to an embodiment of the present invention.

[0040] Figure 3 It is a schematic diagram showing the structure of a harmonic detection device for a power distribution system based on a neural network according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0043] It should be understood that although the terms first, second, third, etc. may be used to describe ... in the embodiments of the present invention, these ... should not be limited to these terms. These terms are only used to distinguish .... For example, without departing from the scope of the embodiments of the present invention, the first ... may also be referred to as the second ..., and similarly, the second ... may also be referred to as the first ....

[0044] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0045] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0046] It should also be noted that the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the commodity or device including the elements.

[0047] Power quality disturbances mainly include voltage swells, voltage sags, power harmonics, power outages and other events.

[0048] Specifically, voltage swell refers to the sudden rise of the effective value of voltage to more than 110% of the rated value in a short period of time. This phenomenon is usually caused by a damaged voltage regulator, a sudden reduction in the load on the damaged circuit, etc.

[0049] Voltage sag: Also known as voltage transient, voltage fluctuation or voltage drop, it refers to the phenomenon of short-term voltage reduction in the power system. It is usually caused by grid failure, sudden load change, equipment failure or other interference. The duration of voltage sag can vary from a few milliseconds to a few seconds, and its amplitude may also vary, but it is generally manifested as a drop in the effective value of the voltage to a certain percentage of the rated value (such as between 10% and 90%).

[0050] Power harmonics refer to the phenomenon of electrical waveform distortion in power systems where the frequency is an integer multiple of the fundamental frequency (usually 50Hz or 60Hz). Power harmonics are mainly caused by various factors such as nonlinear loads, power electronic devices, centralized isolators, and resonant circuits in power systems. Common nonlinear loads include UPS, switching power supplies, rectifiers, frequency converters, inverters, etc.

[0051] In order to detect power quality disturbance events and harmonics in the distribution system, Figure 1 As shown, the present invention discloses a method for detecting harmonics in a power distribution system based on a neural network, the method comprising:

[0052] Step S1, setting R monitoring points in the power distribution system, and setting power signal detection instruments at the R monitoring points to respectively obtain voltage time domain signals; R≥2.

[0053] Taking the IEEE 14-BUS node system as an example, multiple monitoring points are set in the system according to the possible power quality disturbance events in the system to ensure that each monitoring point can represent a key area or important node in the system, and the location distribution of the monitoring points should cover the entire system as much as possible to fully reflect the power quality status of the system. In this embodiment, the number of monitoring points is 8. Power signal detection instruments are set at the locations of the 8 monitoring points to obtain voltage time domain signals in a specific time period. Although there is a method in the prior art to directly determine the type of power quality disturbance events using power signal detection instruments, the detection accuracy and comprehensiveness are not satisfactory. Therefore, in the present invention, a power signal detection instrument is used to collect voltage time domain signals, and the voltage time domain signals are analyzed by the neural network model proposed in the present invention to improve the accuracy of the judgment of the type of disturbance event.

[0054] Step S2, preprocessing the voltage time domain signal, wherein the preprocessed voltage time domain signal carries the corresponding monitoring point location information; sequentially inputting the preprocessed voltage time domain signal into the neural network model, wherein the neural network model outputs power quality disturbance event information according to the voltage time domain signal.

[0055] The preprocessing of the voltage time domain signal refers to filtering the voltage time domain signal using a passive filter (such as an LC filter composed of an inductor and a capacitor) or an active filter (such as a filter based on an operational amplifier) ​​to filter out additional noise. Since the active filter can introduce additional amplification capabilities, it has more advantages in processing complex signals. In this embodiment, the active filter is used to preprocess the voltage time domain signal.

[0056] In step S2, the preprocessing of the voltage time domain signal also includes combining the monitoring point location information corresponding to the voltage time domain signal with the voltage time domain signal to achieve adding the monitoring point location information to the voltage time domain signal. The reason is that in this embodiment, 8 locations where power quality disturbance events may occur are monitored, and the monitoring results of the above-mentioned different monitoring locations need to be distinguished, that is, the location where the power quality disturbance event occurs can be accurately and quickly located, and at the same time, when it is determined that the power quality disturbance event is a power harmonic event, it is convenient to quickly start the power signal detection instrument at the corresponding position to collect the voltage time domain signal to identify the power harmonic component.

[0057] In this embodiment, the monitoring point sequence number or the monitoring point position coordinates can be used as the monitoring point position information. In a possible implementation, when the monitoring point sequence number is used as the monitoring point position information, a possible form of adding the monitoring point position information to the voltage time domain signal is as follows:

[0058] Monitoring point number 1: voltage time domain signal 1;

[0059] Monitoring point number 2: voltage time domain signal 2;

[0060] …

[0061] Monitoring point number 8: voltage time domain signal 8.

[0062] In this embodiment, the power quality disturbance event information output by the neural network model includes the monitoring point location information corresponding to the voltage time domain signal and the power quality disturbance event type. Through the monitoring point location information, the location where the power quality disturbance event occurs can be quickly located, and the specific type of the power quality disturbance event can be grasped.

[0063] In this embodiment, the power quality disturbance event types include five types: normal, power harmonic events, voltage swell events, voltage sag events, and power outage events. In this field, power quality disturbance types include steady-state disturbances and transient disturbances, and steady-state disturbances and transient disturbances include various different situations. Therefore, in a possible implementation, the power quality disturbance event types can be expanded according to the common situations of power quality disturbance events in the power distribution system.

[0064] In step S2, Figure 2 As shown, the neural network model is realized by combining wavelet transform and probabilistic neural network. Figure 2 In the embodiment, the neural network model includes a wavelet layer, a hidden layer and an output layer, wherein the wavelet layer is used to extract signal features from the voltage time domain signal, and the hidden layer and the output layer are used to calculate the probability that the signal belongs to the type of power quality disturbance event based on the signal features.

[0065] In the above neural network model, the wavelet layer can act as a filter to filter out the fundamental frequency components in the input voltage time domain signal, obtain the signal characteristics through wavelet transform, and effectively retain the characteristics of power quality interference events. In addition, since the wavelet transform has the ability to characterize the local characteristics of the signal in both the time domain and the frequency domain, it is particularly conducive to detecting the transient and singular points of the signal. Therefore, the wavelet layer can capture the slight changes in the input voltage time domain signal and improve the accuracy of judging power quality interference events.

[0066] The hidden layer and output layer in the above neural network model follow the hidden layer and output layer in the probabilistic neural network. The probabilistic neural network has a fast learning speed during training, only needs to be set once, does not need to iteratively correct the network weight matrix, and only needs to focus on the adjustment of smoothing parameters. It has strong adaptive and self-learning capabilities, and can continuously optimize its own parameters during the training process to improve the accuracy of classification. This enables it to maintain a high recognition rate when facing new types of disturbances.

[0067] In the above neural network model of this embodiment, the weight matrix W from the wavelet layer to the hidden layer is WH , specifically:

[0068]

[0069]

[0070]

[0071] x i =x(nT)

[0072] t i =x c (nT)

[0073] Among them, d i is the scale parameter of wavelet transform, x is the voltage time domain signal, x c is the baseband time domain signal, x i is the sampling sequence of the voltage time domain signal, t iis the sampling sequence of the baseband time domain signal, T is the sampling period, n is the number of wavelet nodes included in the wavelet layer, and K is the number of nodes included in the hidden layer.

[0074] The weight matrix W from the hidden layer to the output layer HO , specifically:

[0075]

[0076]

[0077] Among them, m is the number of output nodes included in the output layer, m=5, corresponding to the above five types of power quality disturbance events, Category1 and Category2 represent category labels.

[0078] In the above neural network model of this embodiment, the probability that the input voltage time domain signal belongs to the power quality disturbance event type is calculated as follows:

[0079]

[0080]

[0081]

[0082] Among them, σ is the smoothing parameter.

[0083] In this embodiment, when training the above neural network model, the voltage time domain signal of the known power quality disturbance event type is used as training data, and the training set is divided into a training set and a test set. Among them, the known power quality disturbance event type includes the five disturbance event types in this embodiment. During the training process, the smoothing parameters are fine-tuned to improve the model performance. And the neural network model is evaluated according to the accuracy, recall rate and F1 score indicators to determine whether its performance meets the requirements.

[0084] Step S3: If the power quality disturbance event type is the power harmonic event, determine the corresponding power signal detection instrument according to the monitoring point location information, and obtain the current time domain signal by the power signal detection instrument; if the power quality disturbance event type is other events, display the power quality disturbance event information.

[0085] In this embodiment, after obtaining the power quality disturbance event type output by the neural network model, different power quality disturbance event types are processed respectively. Among the five types of power quality disturbance event in this embodiment, power harmonic events belong to steady-state disturbances, voltage sags, voltage swells and power outage events belong to transient disturbances, and no further processing is required if the power quality is normal. Therefore, in the case of transient disturbances, i.e., voltage sags, voltage swells and power outage events, the judgment results of the above power quality disturbance event types are output and the corresponding monitoring point location information is displayed, and the user processes the power quality disturbance event in a timely manner according to the power quality disturbance event type and the monitoring point location information.

[0086] When it is determined to be a steady-state disturbance, that is, a power harmonic event, the power signal detection instrument corresponding to the monitoring point location obtains the current time domain signal according to the monitoring point location information associated with the power harmonic event, so as to identify the power harmonic component.

[0087] Step S4, preprocessing the current time domain signal, inputting the preprocessed current time domain signal into a probabilistic neural network, the probabilistic neural network outputting a harmonic component identification result according to the current time domain signal, and displaying the harmonic component identification result.

[0088] In this embodiment, the current time domain signal is preprocessed, specifically, a filter is used to perform filtering processing to reduce noise. Subsequently, the preprocessed current time domain signal is input into a probabilistic neural network for harmonic component identification.

[0089] After research, the inventor found that power conversion equipment, such as nonlinear loads such as rectifiers, frequency converters and inverters, is the main source of harmonics in the power grid. Usually, power conversion equipment exhibits the characteristics of odd harmonics, and the frequencies with heavier harmonics are basically located at the 3rd, 5th, 7th, 9th, 11th and 13th harmonics. Therefore, in order to accurately identify the power harmonic components, in the probabilistic neural network of the above steps, its output layer is adjusted and set to 6 output nodes, corresponding to the judgment of the 3rd, 5th, 7th, 9th, 11th and 13th harmonics respectively. The input layer and hidden layer of the probabilistic neural network are conventional forms known in the art. By improving the probabilistic neural network, the power harmonic components can be judged more accurately, and a rapid response to power harmonic events can be achieved.

[0090] In this embodiment, the method of acquiring the probabilistic neural network training data is different according to the different application scenarios of the power distribution system. In one possible implementation, for a system including an arc lamp, or a scenario where the load such as high-speed rail power consumption changes dramatically over time, the current time domain signal is acquired once every 1 minute at a predetermined period for 2 hours. For conventional power systems, the predetermined period is to acquire the current time domain signal once every 15 minutes for 24 hours. By acquiring training data in a targeted manner, the accuracy of the probabilistic neural network in identifying harmonic components is further improved.

[0091] In this embodiment, the training process and application method of the probabilistic neural network are the same as the conventional methods in the art and will not be described in detail here.

[0092] After identifying the specific power harmonic components, the identification results are displayed to the user. In a possible implementation, the user can provide an active filter at the corresponding monitoring point, and according to the harmonic component identification results output by the probabilistic neural network, the active filter injects a harmonic current with the same magnitude and opposite direction as the harmonic component to eliminate the harmonic components in the current time domain signal.

[0093] In another embodiment of the present invention, a power distribution system harmonic detection device based on a neural network is also provided. Figure 3 As shown, the device 300 includes:

[0094] A collection module 301, the collection module is used to set R monitoring points in the power distribution system, and set power signal detection instruments at the R monitoring points to respectively obtain voltage time domain signals; R≥2;

[0095] A detection module 302, the detection module is used to pre-process the voltage time domain signal, the pre-processed voltage time domain signal carries the corresponding monitoring point location information; the pre-processed voltage time domain signal is sequentially input into the neural network model, the neural network model outputs power quality disturbance event information according to the voltage time domain signal; the power quality disturbance event information includes the monitoring point location information corresponding to the voltage time domain signal and the power quality disturbance event type, and the power quality disturbance event type includes five types: normal, power harmonic event, voltage swell event, voltage sag event, and power outage event;

[0096] A judgment module 303, wherein the judgment module is used to, if the type of the power quality disturbance event is the power harmonic event, determine the corresponding power signal detection instrument according to the monitoring point location information, and obtain the current time domain signal by the power signal detection instrument; if the type of the power quality disturbance event is other events, display the power quality disturbance event information;

[0097] The identification module 304 is used to preprocess the current time domain signal, input the preprocessed current time domain signal into a probabilistic neural network, and output a harmonic component identification result according to the current time domain signal, and display the harmonic component identification result.

[0098] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0099] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0100] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0101] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of boxes in the block diagram and / or the flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0102] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0103] The above introduces the preferred embodiments of the present invention, which is intended to make the spirit of the present invention clearer and easier to understand, but is not intended to limit the present invention. All modifications, substitutions, and improvements made within the spirit and principles of the present invention should be included in the scope of protection outlined by the claims attached to the present invention.

Claims

1. A method for detecting harmonics in a power distribution system based on a neural network, characterized in that: The method comprises: Step S1, setting R monitoring points in the power distribution system, and setting power signal detection instruments at the R monitoring points to respectively obtain voltage time domain signals; R≥2; Step S2, preprocessing the voltage time domain signal, wherein the preprocessed voltage time domain signal carries the corresponding monitoring point location information; sequentially inputting the preprocessed voltage time domain signal into the neural network model, wherein the neural network model outputs power quality disturbance event information according to the voltage time domain signal; the power quality disturbance event information includes the monitoring point location information corresponding to the voltage time domain signal and the power quality disturbance event type, and the power quality disturbance event type includes five types: normal, power harmonic event, voltage swell event, voltage sag event, and power outage event; Step S3: if the power quality disturbance event type is the power harmonic event, determine the corresponding power signal detection instrument according to the monitoring point location information, and obtain the current time domain signal by the power signal detection instrument; if the power quality disturbance event type is other events, display the power quality disturbance event information; Step S4, preprocessing the current time domain signal, inputting the preprocessed current time domain signal into a probabilistic neural network, the probabilistic neural network outputting a harmonic component identification result according to the current time domain signal, and displaying the harmonic component identification result.

2. The method for detecting harmonics in a power distribution system based on a neural network according to claim 1, characterized in that: The neural network model includes a wavelet layer, a hidden layer and an output layer, wherein the wavelet layer is used to extract signal features from the voltage time domain signal, and the hidden layer and the output layer are used to calculate the probability that the signal belongs to the type of power quality disturbance event based on the signal features.

3. The method for detecting harmonics in a power distribution system based on a neural network according to claim 2, characterized in that: The weight matrix W from the wavelet layer to the hidden layer WH , specifically: x i =x(nT) t i =x c (nT) Among them, d i is the scale parameter of wavelet transform, x is the voltage time domain signal, x c is the baseband time domain signal, x i is the sampling sequence of the voltage time domain signal, t i is the sampling sequence of the baseband time domain signal, T is the sampling period, n is the number of wavelet nodes included in the wavelet layer, and K is the number of nodes included in the hidden layer.

4. The method for detecting harmonics in a power distribution system based on a neural network according to claim 3, characterized in that: The weight matrix W from the hidden layer to the output layer HO , specifically: Among them, m is the number of output nodes included in the output layer, m=5, corresponding to the above five types of power quality disturbance events, Category1 and Category2 represent category labels.

5. The method for detecting harmonics in a power distribution system based on a neural network according to claim 4, characterized in that: The calculating of the probability that the signal belongs to the power quality disturbance event type is specifically as follows: Among them, σ is the smoothing parameter.

6. A method for detecting harmonics in a power distribution system based on a neural network according to claim 1, characterized in that: The probabilistic neural network includes an input layer, a hidden layer and an output layer, wherein the output layer includes 6 output nodes corresponding to the 3rd harmonic, the 5th harmonic, the 7th harmonic, the 9th harmonic, the 11th harmonic and the 13th harmonic respectively.

7. The method for detecting harmonics in a power distribution system based on a neural network according to claim 1, characterized in that: After step S4, it also includes: providing an active filter at the corresponding monitoring point, and according to the harmonic component identification result output by the probabilistic neural network, the active filter injects a harmonic current with the same magnitude and opposite direction as the harmonic component to eliminate the harmonic component in the current time domain signal.

8. A harmonic detection device for a power distribution system based on a neural network, characterized in that: The device comprises: A collection module, the collection module is used to set R monitoring points in the power distribution system, and set power signal detection instruments at the R monitoring points to respectively obtain voltage time domain signals; R≥2; A detection module, wherein the detection module is used to preprocess the voltage time domain signal, wherein the preprocessed voltage time domain signal carries the corresponding monitoring point location information; the preprocessed voltage time domain signal is sequentially input into a neural network model, wherein the neural network model outputs power quality disturbance event information according to the voltage time domain signal; the power quality disturbance event information includes the monitoring point location information corresponding to the voltage time domain signal and the power quality disturbance event type, wherein the power quality disturbance event type includes five types: normal, power harmonic event, voltage swell event, voltage sag event, and power outage event; A judgment module, wherein the judgment module is used to, if the type of the power quality disturbance event is the power harmonic event, determine the corresponding power signal detection instrument according to the monitoring point location information, and obtain the current time domain signal by the power signal detection instrument; if the type of the power quality disturbance event is other events, display the power quality disturbance event information; An identification module, wherein the identification module is used to preprocess the current time domain signal, input the preprocessed current time domain signal into a probabilistic neural network, and the probabilistic neural network outputs a harmonic component identification result based on the current time domain signal and displays the harmonic component identification result.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the neural network-based harmonic detection method for a power distribution system as described in any one of claims 1 to 7 is implemented.

10. An electronic device, comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is used to execute the computer program to implement the neural network-based distribution system harmonic detection method as described in any one of claims 1 to 7.

Images