A power distribution transformer anomaly diagnosis system and method

Abstract

The application relates to a power distribution transformer abnormality diagnosis system and method, wherein the system comprises a high-frequency electromagnetic signal probe, a variable-frequency signal source, a transmitting head and a signal receiver; the transmitting head is installed at the bottom of a power distribution transformer, the variable-frequency signal source is connected with the bottom of the power distribution transformer through the transmitting head; the high-frequency electromagnetic signal probe is arranged on the upper part of an oil tank of the power distribution transformer and the surface of a bushing of the oil tank of the power distribution transformer, and the high-frequency electromagnetic signal probe is connected with the signal receiver; and the variable-frequency signal source is connected with the signal receiver. The application can effectively diagnose whether the power distribution transformer is abnormal.

Description

Technical Field

[0001] The present invention relates to the technical field of abnormality diagnosis of distribution transformers, and in particular to a system and method for diagnosing abnormality of distribution transformers. Background Art

[0002] 10kV distribution transformers play a vital role in directly supplying power to loads. Their operating conditions are unstable and fluctuate significantly. During specific periods, they are subject to heavy loads, overloads, asymmetric operation, and harmonics. Their probability of failure and damage is greater than that of main grid transformers. In recent years, occasional short circuits, explosions, and other failures in distribution transformers at power grid companies have continued unabated, seriously impacting the safe and stable transmission and use of electricity.

[0003] Currently, there is no effective means of detecting sporadic abnormal faults in distribution transformers. Because sporadic faults are characterized by rapid fault channel development, concentrated fault energy, and dispersed time periods, routine inspections of distribution transformers, such as electrical parameter monitoring, infrared temperature measurement, and ultraviolet testing, have a very low probability of detecting problems. Online vibration monitoring methods also struggle to detect internal insulation anomalies in a timely manner.

[0004] Therefore, it is urgent to develop a sensitive diagnostic method for electromagnetic insulation abnormalities of distribution transformers to achieve early judgment of internal abnormalities and provide a decision-making basis for preventing occasional failures. Summary of the Invention

[0005] Therefore, the technical problem to be solved by the present invention is to overcome the problem in the prior art that sporadic abnormal faults of distribution transformers cannot be effectively detected.

[0006] To solve the above technical problems, the present invention provides a distribution transformer abnormality diagnosis system, comprising a high-frequency electromagnetic signal probe, a variable frequency signal source, a transmitter and a signal receiver;

[0007] The transmitter head is installed at the bottom of the distribution transformer, and the variable frequency signal source is connected to the bottom of the distribution transformer through the transmitter head;

[0008] The high-frequency electromagnetic signal probe is arranged on the upper part of the oil tank of the distribution transformer and on the surface of the bushing of the oil tank of the distribution transformer, and the high-frequency electromagnetic signal probe is connected to the signal receiver;

[0009] The frequency conversion signal source is connected to the signal receiver.

[0010] In one embodiment of the present invention, the frequency conversion signal source and the signal receiver are connected via a communication line.

[0011] In one embodiment of the present invention, the number of the transmitter head is at least one, and the number of the high-frequency electromagnetic signal probe is at least one.

[0012] To solve the above technical problems, the application provides an abnormal diagnosis method for distribution transformers, which realizes abnormal diagnosis of the distribution transformers by using the abnormal diagnosis system for the distribution transformers.

[0013] The variable frequency signal source sends a variable frequency signal and injects the variable frequency signal into the bottom of the distribution transformer through the transmitting head, and the variable frequency signal source sends the variable frequency signal parameters to the signal receiver through the communication line;

[0014] The variable frequency signal propagates along the metal shell of the distribution transformer from the bottom of the distribution transformer due to the skin effect, and propagates to the upper part of the oil tank of the distribution transformer and the surface of the bushing of the oil tank of the distribution transformer;

[0015] The signal receiver receives the variable frequency signal received by the high-frequency electromagnetic signal probe installed on the upper part of the oil tank of the distribution transformer and the surface of the bushing of the oil tank of the distribution transformer;

[0016] The signal receiver analyzes the variable frequency signals from the high-frequency electromagnetic signal probe and the variable frequency signal source to realize abnormal diagnosis of the distribution transformer.

[0017] In an embodiment of the application, the method of analyzing the variable frequency signals from the high-frequency electromagnetic signal probe and the variable frequency signal source by the signal receiver to realize abnormal diagnosis of the distribution transformer is as follows:

[0018] The wavelet transform is performed on the variable frequency signal received by the high-frequency electromagnetic signal probe to obtain scale and translation characteristics, and the harmonic impedance of the variable frequency signal source is calculated, the response curve of each high-frequency electromagnetic signal probe is obtained according to the scale and translation characteristics and the harmonic impedance, the response curve of each high-frequency electromagnetic signal probe is mixed with the variable frequency signal of the variable frequency signal source, and the mixed signal is input into a preset neural network for identification to realize abnormal diagnosis of the distribution transformer.

[0019] In an embodiment of the application, the method further includes: when the result of the abnormal diagnosis of the distribution transformer is that there is an abnormality, performing quantitative analysis on the distribution transformer, and the formula is as follows:

[0020]

[0021] Wherein, f represents the electromagnetic induction coupling frequency received by the signal receiver, L1 and L2 represent the inductances corresponding to the structure electromagnetic field of the high-frequency electromagnetic signal probe respectively and are constant values, and C1 and C2 represent the capacitances corresponding to the propagation loop and the coupling loop of the high-frequency electromagnetic signal respectively;

[0022] If the distribution transformer has an abnormality, since the value of L1L2 is a constant value, and the local distribution capacitor of the distribution transformer will change with the change of the internal insulation state, therefore, the electromagnetic induction coupling frequency f in the abnormal condition is different from the electromagnetic induction coupling frequency f in the normal condition; by extracting the electromagnetic induction coupling frequency f in the abnormal condition, and dividing by the electromagnetic induction coupling frequency f in the normal condition, the change rate of C1C2 is obtained, and the quantitative analysis of the change abnormality of the distribution transformer is realized through the change rate of C1C2.

[0023] In an embodiment of the present application, the frequency range of the variable frequency signal source is 100 kHz-100 MHz.

[0024] In an embodiment of the present application, the preset neural network is a long short-term memory network LSTM.

[0025] To solve the above technical problems, the present application provides an electronic device, which comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned distribution transformer abnormality diagnosis method when executing the computer program.

[0026] To solve the above technical problems, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement the steps of the above-mentioned distribution transformer abnormality diagnosis method.

[0027] The above technical solution of the present application has the following advantages compared with the prior art:

[0028] The distribution transformer abnormality diagnosis system constructed by the present application can effectively compensate for the poor sensitivity of traditional electric parameter monitoring, infrared temperature measurement, ultraviolet detection, vibration monitoring, and other methods, and can early detect the internal insulation and electromagnetic abnormalities of the distribution transformer.

[0029] The distribution transformer abnormality diagnosis method constructed by the present application can not only diagnose whether the distribution transformer has an abnormality (qualitative analysis) through the long short-term memory network LSTM, but also quantitatively analyze the abnormality of the distribution transformer through the electromagnetic induction coupling frequency when the long short-term memory network LSTM judges that the distribution transformer may have an abnormality. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to make the content of the present application more easily understood, the present application will be further described in detail below according to specific embodiments of the present application and in conjunction with the accompanying drawings.

[0031] Figure 1 is a structure diagram of the distribution transformer abnormality diagnosis system in the embodiment of the present application;

[0032] Figure 2 is a flow chart of the power distribution transformer abnormality diagnosis method in the embodiment of the present application.

[0033] Explanation of the reference signs in the drawings: 1, high-frequency electromagnetic signal probe; 2, transmitting head; 3, variable-frequency signal source; 4, signal receiver; 5, bottom of power distribution transformer; 6, upper part of oil tank of power distribution transformer; 7, surface of sleeve of oil tank of power distribution transformer. DETAILED DESCRIPTION

[0034] The present application will be further described below in conjunction with the drawings and specific embodiments, so that those skilled in the art can better understand the present application and implement it, but the embodiments are not limiting to the present application.

[0035] Embodiment one

[0036] Referring to Figure 1 The present application relates to a power distribution transformer abnormality diagnosis system, the measurement object is a 10kV power distribution transformer, the abnormality diagnosis system comprises a high-frequency electromagnetic signal probe 1, a variable-frequency signal source 3, a transmitting head 2 and a signal receiver 4.

[0037] The transmitting head 2 is installed at the bottom 5 of the power distribution transformer, the variable-frequency signal source 3 is connected with the bottom 5 of the power distribution transformer through the transmitting head 2; the high-frequency electromagnetic signal probe 1 is arranged at the upper part 6 of the oil tank of the power distribution transformer and the surface 7 of the sleeve of the oil tank of the power distribution transformer, the high-frequency electromagnetic signal probe 1 is connected with the signal receiver 4; the variable-frequency signal source 3 is connected with the signal receiver 4.

[0038] Further, the variable-frequency signal source 3 and the signal receiver 4 are connected through a communication line, the communication line can be a 3-group 6-core independent shielded twisted shielded line, which is used to provide power supply and RS485 communication.

[0039] Further, the number of the transmitting heads 2 is at least one, and the number of the high-frequency electromagnetic signal probes 1 is at least one.

[0040] Embodiment two

[0041] Please refer to Figure 2 The present embodiment provides a power distribution transformer abnormality diagnosis method, which comprises:

[0042] The variable-frequency signal source 3 sends out a variable-frequency signal and injects it into the bottom 5 of the power distribution transformer through the transmitting head 2, at the same time, the variable-frequency signal source 3 sends the variable-frequency signal parameters to the signal receiver 4 through the communication line;

[0043] The variable-frequency signal propagates from the bottom 5 of the power distribution transformer along the metal shell of the power distribution transformer due to the skin effect, and propagates to the upper part 6 of the oil tank of the power distribution transformer and the surface 7 of the sleeve of the oil tank of the power distribution transformer;

[0044] The variable frequency signal received by the high-frequency electromagnetic signal probe 1 installed on the upper part 6 of the oil tank of the distribution transformer and the sleeve surface 7 of the oil tank of the distribution transformer is received by the signal receiver 4;

[0045] The variable frequency signal from the high-frequency electromagnetic signal probe 1 and the variable frequency signal source 3 is analyzed by the signal receiver 4 to realize abnormal diagnosis of the distribution transformer.

[0046] Further, the method of analyzing the variable frequency signal from the high-frequency electromagnetic signal probe 1 and the variable frequency signal source 3 by the signal receiver 4 to realize abnormal diagnosis of the distribution transformer is:

[0047] The variable frequency signal received by the high-frequency electromagnetic signal probe 1 is wavelet transformed to obtain scale and translation features, and the harmonic impedance of the variable frequency signal source is calculated. According to the scale and translation features, the harmonic impedance of each high-frequency electromagnetic signal probe 1 is obtained. The response curve of each high-frequency electromagnetic signal probe 1 (the response curve indicates the degree of influence of the signal source on the propagation path), the response curve of each high-frequency electromagnetic signal probe 1 is mixed with the variable frequency signal of the variable frequency signal source 3, and input into a preset neural network (such as a long short-term memory network LSTM) for recognition, to realize abnormal diagnosis (including high risk, medium risk, low risk, normal) of the distribution transformer.

[0048] It is worth mentioning that the abnormal diagnosis method of the distribution transformer constructed in this embodiment can not only diagnose whether the distribution transformer may exist abnormally (qualitative analysis) through the long short-term memory network LSTM, but also quantitatively analyze the abnormality of the distribution transformer when the long short-term memory network LSTM judges that the distribution transformer may exist abnormally.

[0049] This embodiment also includes: when the result of the abnormal diagnosis of the distribution transformer is that there is an abnormality, then the distribution transformer is quantitatively analyzed, and the formula is:

[0050]

[0051] Where f represents the electromagnetic induction coupling frequency received by the signal receiver, L1 and L2 represent the corresponding inductances of the two high-frequency electromagnetic signals in the propagation loop and the coupling loop, respectively. Since the inductances L1 and L2 are related to the loop structure parameters, usually before breakdown occurs, the loop does not change, i.e. L1 and L2 are relatively fixed values; C1 and C2 represent the corresponding capacitances of the high-frequency electromagnetic signals in the propagation loop and the coupling loop, respectively, which usually change with the change of the internal insulation condition of the transformer.

[0052] If the power distribution transformer has an abnormality or a fault detected by the LSTM, it is assumed that the value of L1L2 is a constant value, and the local distribution capacitance of the power distribution transformer changes (i.e., the internal capacitance of the power distribution transformer changes) with the change of the internal insulation state (intermittent burst discharge abnormality, local insulation deterioration, dampness, partial discharge, etc.). Therefore, the electromagnetic induction coupling frequency f in the abnormal condition is different from the electromagnetic induction coupling frequency f in the normal condition. By extracting the electromagnetic induction coupling frequency f in the abnormal condition and dividing it by the electromagnetic induction coupling frequency f in the normal condition (which can be measured in advance), the change rate of C1C2 can be calculated. By the change rate of C1C2, quantitative analysis of the change abnormality of the power distribution transformer can be realized, and problems such as intermittent burst discharge abnormality, local insulation deterioration, dampness, partial discharge, etc. can be found, even the abnormality and problem of stealing the power distribution transformer.

[0053] Further, the variable frequency signal source 3 emits a variable frequency signal with a frequency range of 100 kHz-100 MHz.

[0054] Embodiment Three

[0055] The embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the power distribution transformer abnormality diagnosis method in embodiment two when executing the computer program.

[0056] Embodiment Four

[0057] The embodiment provides a computer readable storage medium, which stores a computer program, and the computer program is executable by a processor to implement the steps of the power distribution transformer abnormality diagnosis method in embodiment two.

[0058] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application can be implemented in various computer languages, such as object-oriented programming language C++ and procedural language C, RUST, etc.

[0059] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The flowchart and / or block diagram in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to the present application. In this regard, each flowchart block and / or block in the Figures can represent a module, segment, or portion of code, which comprises one or more executable Figure 1 The flowchart and / or block diagram in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to the present application. In this regard, each flowchart block and / or block in the Figures can represent a module, segment, or portion of code, which comprises one or more executable

[0060] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the Figure 1 The flowchart and / or block diagram in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to the present application. In this regard, each flowchart block and / or block in the Figures can represent a module, segment, or portion of code, which comprises one or more executable Figure 1 The flowchart and / or block diagram in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to the present application. In this regard, each flowchart block and / or block in the Figures can represent a module, segment, or portion of code, which comprises one or more executable

[0061] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The flowchart and / or block diagram in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to the present application. In this regard, each flowchart block and / or block in the Figures can represent a module, segment, or portion of code, which comprises one or more executable Figure 1 The flowchart and / or block diagram in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to the present application. In this regard, each flowchart block and / or block in the Figures can represent a module, segment, or portion of code, which comprises one or more executable

[0062] While the preferred embodiments of the application have been described, additional variations and modifications can be employed, as will be appreciated by those of ordinary skill in the art once advised of the essential inventive concepts. Therefore, the scope of the application should be determined with reference to the appended claims and equivalents thereof.

[0063] Obviously, the embodiments described above are only examples for clear illustration, and are not intended to limit the embodiments. Based on the above description, other different forms of changes or variations can also be made by those of ordinary skill in the art. Here, all the embodiments are not required to be exhausted, and the obvious changes or variations derived therefrom are still within the protection scope of the present application.

Claims

1. A method for diagnosing abnormality of a distribution transformer, characterized by: The distribution transformer abnormality diagnosis system is used to implement abnormality diagnosis of distribution transformers, including: A variable frequency signal source (3) is used to emit a variable frequency signal and is injected into the bottom (5) of the distribution transformer through a transmitter (2). At the same time, the variable frequency signal source (3) transmits the variable frequency signal parameters to a signal receiver (4) through a communication line. The variable frequency signal propagates from the bottom (5) of the distribution transformer along the metal casing of the distribution transformer due to the skin effect, and propagates to the upper part (6) of the oil tank of the distribution transformer and the bushing surface (7) of the oil tank of the distribution transformer; Using a signal receiver (4) to receive a variable frequency signal received by a high-frequency electromagnetic signal probe (1) installed on an upper portion (6) of the oil tank of the distribution transformer and a bushing surface (7) of the oil tank of the distribution transformer; The signal receiver (4) analyzes the variable frequency signal from the high-frequency electromagnetic signal probe (1) and the variable frequency signal source (3) to achieve abnormal diagnosis of the distribution transformer; When the abnormality diagnosis result of the distribution transformer indicates that there is an abnormality, a quantitative analysis of the distribution transformer is performed, and the formula is: Where f represents the electromagnetic induction coupling frequency received by the signal receiver, L1 and L2 represent two inductors corresponding to the electromagnetic field of the high-frequency electromagnetic signal probe structure and are both constant, C1 and C2 represent the corresponding capacitances of the high-frequency electromagnetic signal in the propagation loop and coupling loop respectively; If there is an abnormality in the distribution transformer, since the values ​​of L1L2 are fixed and the local distributed capacitance of the distribution transformer changes with the internal insulation state, the electromagnetic induction coupling frequency f under abnormal conditions is different from the electromagnetic induction coupling frequency f under normal conditions. By extracting the electromagnetic induction coupling frequency f under abnormal conditions and dividing it by the electromagnetic induction coupling frequency f under normal conditions, the change rate of C1C2 is obtained, and the change rate of C1C2 is used to quantitatively analyze the abnormal changes in the distribution transformer. in, The distribution transformer abnormality diagnosis system comprises a high-frequency electromagnetic signal probe (1), a variable frequency signal source (3), a transmitter (2) and a signal receiver (4); The transmitter head (2) is installed on the bottom (5) of the distribution transformer, and the variable frequency signal source (3) is connected to the bottom (5) of the distribution transformer through the transmitter head (2); The high-frequency electromagnetic signal probe (1) is arranged on the upper part (6) of the oil tank of the distribution transformer and the bushing surface (7) of the oil tank of the distribution transformer, and the high-frequency electromagnetic signal probe (1) is connected to the signal receiver (4); The frequency conversion signal source (3) is connected to the signal receiver (4); The frequency conversion signal source (3) and the signal receiver (4) are connected via a communication line; The number of the transmitting heads (2) is at least one, and the number of the high-frequency electromagnetic signal probes (1) is at least one.

2. The method for diagnosing abnormality of a distribution transformer according to claim 1, wherein: The method for diagnosing abnormalities of a distribution transformer by analyzing the variable frequency signals from the high-frequency electromagnetic signal probe (1) and the variable frequency signal source (3) through the signal receiver (4) is as follows: Wavelet transform is performed on the variable frequency signal received by the high-frequency electromagnetic signal probe (1) to obtain scale and translation characteristics, and each harmonic impedance of the variable frequency signal source is calculated at the same time. The response curve of each high-frequency electromagnetic signal probe (1) is obtained based on the scale and translation characteristics and each harmonic impedance. The response curve of each high-frequency electromagnetic signal probe (1) is mixed with the variable frequency signal of the variable frequency signal source (3) for characteristics, and input into a preset neural network for identification, thereby realizing abnormal diagnosis of the distribution transformer.

3. The method for diagnosing abnormality of a distribution transformer according to claim 1, wherein: The frequency conversion signal source (3) emits a frequency conversion signal with a frequency range of 100kHz-100MHz.

4. The method for diagnosing abnormality of a distribution transformer according to claim 2, wherein: The preset neural network is a long short-term memory network LSTM.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the distribution transformer abnormality diagnosis method according to any one of claims 1 to 4 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the distribution transformer abnormality diagnosis method according to any one of claims 1 to 4 are implemented.

Images