Distance protection method and device fused with full-connection neural network, and electronic equipment
By adopting a fully connected neural network in the power system combined with the method of measuring impedance, the malfunction of the distance protection strategy in abnormal operation is solved, and the accurate identification and processing of faults and abnormal states is achieved, and the stability of the power system is improved. Sex and safety.
Patent Information
- Application Number
- CN202411169304.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-23
- Publication Date
- 2024-12-03
AI Technical Summary
The existing distance protection strategies are susceptible to abnormal operating conditions such as overload, voltage transformer disconnection, oscillation and data errors in power systems, resulting in malfunctions, and there is no effective solution yet.
The method of fused fully connected neural network is adopted to collect three-phase voltage and three-phase current, calculate and measure impedance, and use the fully connected neural network to distinguish fault states and abnormal operating states, accurately judge protection actions and avoid malfunctions.
When a protection line fails, the faulty line is isolated, and the locking operation is identified and performed in abnormal operation states, preventing the protection device from performing tripping operations incorrectly, improving the reliability and accuracy of the system.
Smart Images

Figure CN119070251A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power systems or other related fields, and in particular to a distance protection method and device integrating a fully connected neural network, and electronic equipment thereof. Background Art
[0002] In the field of power system technology, distance protection is also called impedance protection. It is a protection strategy that uses the characteristics of simultaneous changes in voltage and current during short-circuit faults to calculate the ratio of voltage to current, judge the distance from the line fault point to the installation point of the protection device, and determine the protection action based on the distance. The core component of the protection device is the impedance relay. The measured impedance is obtained by calculating the ratio of the voltage applied to the relay to the current flowing through the relay. The measured impedance is proportional to the distance from the fault point to the installation point of the protection device. Compared with current and voltage protection, distance protection has higher sensitivity and can selectively cut off the faulty components through tripping processing, isolating the faulty line from the normally operating power grid.
[0003] In the related art, the existing distance protection strategy is easily affected by abnormal operating conditions such as overload, voltage transformer disconnection (i.e. PT disconnection), oscillation, data error, etc., which may cause the distance protection to malfunction. To address this problem, technicians have configured a variety of anti-malfunction measures in the distance protection strategy, such as: distinguishing overload and single-phase grounding fault based on the relationship between the positive sequence compensation voltage and the phase compensation voltage phase, and implementing overload interlocking processing; distinguishing PT disconnection and single-phase grounding fault based on the relationship between the negative sequence voltage and the fixed value, and implementing PT disconnection interlocking processing; using the difference in impedance change rate when the line oscillates and the line is short-circuited to implement oscillation interlocking processing; adding a check bit after the transmitted data to reduce the probability of data transmission errors. Although the current distance protection strategy is configured with a variety of anti-malfunction measures such as PT disconnection interlocking and oscillation interlocking, it is still unavoidable that the distance protection action malfunctions when the line is in an abnormal operating state.
[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention
[0005] The embodiment of the present invention provides a distance protection method and device and electronic equipment integrating a fully connected neural network, so as to at least solve the technical problem of malfunction of distance protection action when the line is in an abnormal operating state in the related art.
[0006] According to one aspect of an embodiment of the present invention, a distance protection method integrating a fully connected neural network is provided, wherein a protection device is installed in a protection line, and comprises: collecting three-phase voltage and three-phase current at a measuring point in the protection line; obtaining a measurement impedance according to the three-phase voltage and the three-phase current, and obtaining a first operating state of the measuring point based on the measurement impedance and a preset impedance threshold, wherein the first operating state is a fault state or a non-fault state; when the measuring point is in a fault state, judging the position of the measuring point relative to a protection area based on the measurement impedance and the preset setting impedance, and obtaining a first output result, wherein the protection area is a line range that can be covered by the protection device; inputting the three-phase voltage and the three-phase current into a fully connected neural network, and obtaining a second operating state of the measuring point, and obtaining a second output result based on the second operating state, wherein the second operating state includes a fault state and an abnormal operating state; and determining a distance protection action based on the first output result and the second output result.
[0007] Optionally, the step of obtaining a measured impedance according to the three-phase voltage and the three-phase current, and obtaining a first operating state of the measuring point based on the measured impedance and a preset impedance threshold includes: inputting the three-phase voltage and the three-phase current into a first formula to calculate a first measured impedance; obtaining a first impedance threshold of the protection line; and when the first measured impedance is less than the first impedance threshold, determining that the measuring point is in a fault state, and defining the first operating state as a fault state.
[0008] Optionally, the step of obtaining a measured impedance according to the three-phase voltage and the three-phase current, and obtaining the first operating state of the measuring point based on the measured impedance and a preset impedance threshold value, further includes: inputting the three-phase current into a second formula to calculate the zero-sequence current; inputting the zero-sequence current, the three-phase voltage and the three-phase current into a third formula to calculate the second measured impedance; obtaining the second impedance threshold value of the protection line; and when the second measured impedance is less than the second impedance threshold value, determining that the measuring point is in a fault state, and defining the first operating state as a fault state.
[0009] Optionally, based on the measured impedance and the preset set impedance, the position of the measuring point relative to the protection area is determined to obtain the step of obtaining the first output result, including: obtaining the first set impedance and the second set impedance; when the first measured impedance is greater than the first set impedance, determining that the measuring point is outside the protection area; when the first measured impedance is less than or equal to the first set impedance, determining that the measuring point is within the protection area; when the second measured impedance is greater than the second set impedance, determining that the measuring point is outside the protection area; when the second measured impedance is less than or equal to the second set impedance, determining that the measuring point is within the protection area; when it is determined that the measuring point is within the protection area, defining the value of the first output result as the first value; when it is determined that the measuring point is outside the protection area, defining the value of the first output result as the second value.
[0010] Optionally, when it is determined that the measuring point is within the protection area, the method further includes: obtaining a unit impedance of the protection line; and calculating a distance from the measuring point to the protection device based on the measured impedance and the unit impedance.
[0011] Optionally, the step of obtaining a second output result based on the second operating state includes: when the second operating state is a fault state, defining the value of the second output result as a first value; when the second operating state is an abnormal operating state, defining the value of the second output result as a second value, wherein the abnormal operating state includes at least one of the following: an overload state, a voltage transformer disconnection state, an oscillation state, and a data error state.
[0012] Optionally, based on the first output result and the second output result, the step of determining the distance protection action includes: when the values of the first output result and the second output result are both the first values, controlling the protection device to perform a tripping operation; when the value of the first output result is the second value and the value of the second output result is the first value, controlling the protection device to stop performing the operation; when the value of the second output result is the second value, performing a locking operation to isolate the protection device outside the protection line.
[0013] According to another aspect of an embodiment of the present invention, a distance protection device integrating a fully connected neural network is also provided, including: a collection unit, used to collect three-phase voltage and three-phase current at a measuring point in a protection line; a first acquisition unit, used to obtain a measurement impedance according to the three-phase voltage and the three-phase current, and obtain a first operating state of the measuring point based on the measurement impedance and a preset impedance threshold, wherein the first operating state is a fault state or a non-fault state; a judgment unit, used to judge the position of the measuring point relative to a protection area based on the measurement impedance and a preset setting impedance when the measuring point is in a fault state, and obtain a first output result, wherein the protection area is a line range that can be covered by the protection device; a second acquisition unit, used to input the three-phase voltage and the three-phase current into a fully connected neural network, obtain a second operating state of the measuring point, and obtain a second output result based on the second operating state, wherein the second operating state includes a fault state and an abnormal operating state; a determination unit, based on the first output result and the second output result, determines the distance protection action.
[0014] Optionally, the first acquisition unit includes: a first calculation module, used to input the three-phase voltage and the three-phase current into a first formula to calculate a first measurement impedance; a first acquisition module, used to obtain a first impedance threshold of the protection line; and a first judgment module, used to judge that the measurement point is in a fault state when the first measurement impedance is less than the first impedance threshold, and define the first operating state as a fault state.
[0015] Optionally, the first acquisition unit also includes: a second calculation module, used to input the three-phase current into a second formula to calculate the zero-sequence current; a third calculation module, used to input the zero-sequence current, the three-phase voltage and the three-phase current into a third formula to calculate the second measurement impedance; a second acquisition module, used to obtain a second impedance threshold of the protection line; a second determination module, used to determine that the measurement point is in a fault state when the second measurement impedance is less than the second impedance threshold, and define the first operating state as a fault state.
[0016] Optionally, the judgment unit includes: a third acquisition module, used to acquire the first set impedance and the second set impedance; a third judgment module, used to determine that the measurement point is outside the protection area when the first measured impedance is greater than the first set impedance; a fourth judgment module, used to determine that the measurement point is within the protection area when the first measured impedance is less than or equal to the first set impedance; a fifth judgment module, used to determine that the measurement point is outside the protection area when the second measured impedance is greater than the second set impedance; a sixth judgment module, used to determine that the measurement point is within the protection area when the second measured impedance is less than or equal to the second set impedance; a first definition module, used to define the value of the first output result as a first value when it is determined that the measurement point is within the protection area; and a second definition module, used to define the value of the first output result as a second value when it is determined that the measurement point is outside the protection area.
[0017] Optionally, the judgment unit further includes: a fourth acquisition module, used to acquire the unit impedance of the protection line; and a fourth calculation module, used to calculate the distance from the measurement point to the protection device based on the measured impedance and the unit impedance.
[0018] Optionally, the second acquisition unit includes: a third definition module, used to define the numerical value of the second output result as a first numerical value when the second operating state is a fault state; a fourth definition module, used to define the numerical value of the second output result as a second numerical value when the second operating state is an abnormal operating state, wherein the abnormal operating state includes at least one of the following: an overload state, a voltage transformer disconnection state, an oscillation state, and a data error state.
[0019] Optionally, the determination unit includes: a first control module, used to control the protection device to perform a tripping operation when the values of the first output result and the second output result are both first values; a second control module, used to control the protection device to stop performing the operation when the value of the first output result is the second value and the value of the second output result is the first value; and a third control module, used to perform a locking operation to isolate the protection device outside the protection line when the value of the second output result is the second value.
[0020] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned distance protection methods integrating a fully connected neural network.
[0021] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the above-mentioned distance protection methods integrating a fully connected neural network.
[0022] According to another aspect of an embodiment of the present invention, a computer program product is also provided, including a computer program, which, when executed by a processor, implements the steps of any one of the above-mentioned distance protection methods for integrating a fully connected neural network.
[0023] In the present disclosure, by collecting the three-phase voltage and the three-phase current at the measuring point in the protection line, the measurement impedance is obtained according to the three-phase voltage and the three-phase current, and the first operating state of the measuring point is obtained based on the measured impedance and the preset impedance threshold. When the measuring point is in a fault state, the position of the measuring point relative to the protection area is judged based on the measured impedance and the preset set impedance to obtain a first output result, and then the three-phase voltage and the three-phase current are input into a fully connected neural network to obtain a second operating state of the measuring point, and a second output result is obtained based on the second operating state. Finally, based on the first output result and the second output result, the distance protection action is determined. When a fault occurs in the protection line, the protection device is controlled to perform a tripping operation to isolate the faulty line from the normally operating power grid. When the protection line is in an abnormal operating state, the present disclosure accurately identifies the abnormal operating state, controls the protection device to perform a locking operation, and isolates the protection device from the protection line to prevent the protection device from erroneously performing a tripping operation, thereby solving the technical problem of erroneous distance protection action when the line is in an abnormal operating state in the related art. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:
[0025] Figure 1 is a flow chart of an optional distance protection method integrating a fully connected neural network according to an embodiment of the present invention;
[0026] Figure 2is a model diagram of an optional distance protection method integrating a fully connected neural network according to an embodiment of the present invention;
[0027] Figure 3 is a model diagram of an optional fully connected neural network according to an embodiment of the present invention;
[0028] Figure 4 is a schematic diagram of an optional distance protection method integrating a fully connected neural network according to an embodiment of the present invention;
[0029] Figure 5 is a schematic diagram of an optional distance protection device integrating a fully connected neural network according to an embodiment of the present invention;
[0030] Figure 6 It is a hardware structure block diagram of an electronic device (or mobile device) for a distance protection method integrating a fully connected neural network according to an embodiment of the present invention. DETAILED DESCRIPTION
[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0033] It should be noted that the distance protection method and device integrating a fully connected neural network in the present disclosure can be used in the field of power system technology when a line fails or is in an abnormal operating state and distance protection processing is performed. It can also be used in any field other than the field of power system technology when a line fails or is in an abnormal operating state and distance protection processing is performed. The present disclosure does not limit the application field of the distance protection method and device integrating a fully connected neural network.
[0034] The following embodiments of the present invention can be applied to various distance protection systems / applications / devices that integrate fully connected neural networks. The present invention collects the three-phase voltage and three-phase current at the measuring point in the protection line, obtains the measurement impedance according to the three-phase voltage and the three-phase current, determines whether the measuring point has a fault according to the measurement impedance, and in the case of a fault at the measuring point, determines the position of the measuring point relative to the protection area, obtains a first output result, and then inputs the three-phase voltage and the three-phase current into the fully connected neural network to obtain a second output result. According to the first output result and the second output result, the distance protection action is determined. When a fault occurs in the protection line, the protection device is controlled to perform a tripping operation to isolate the faulty line from the normally operating power grid. When the protection line is in an abnormal operating state, the present invention accurately identifies the abnormal operating state, controls the protection device to perform a locking operation, and isolates the protection device from the protection line to prevent the protection device from mistakenly performing a tripping operation.
[0035] The present invention is described in detail below in conjunction with various embodiments.
[0036] Embodiment 1
[0037] According to an embodiment of the present invention, an embodiment of a distance protection method integrating a fully connected neural network is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.
[0038] Figure 1 is a flow chart of an optional distance protection method integrating a fully connected neural network according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:
[0039] Step S101, collecting three-phase voltages and three-phase currents at measurement points in the protection line.
[0040] Step S102, obtaining a measured impedance according to the three-phase voltage and the three-phase current, and obtaining a first operating state of the measuring point based on the measured impedance and a preset impedance threshold, wherein the first operating state is a fault state or a non-fault state.
[0041] Step S103, when the measuring point is in a fault state, based on the measured impedance and the preset set impedance, the position of the measuring point relative to the protection area is determined to obtain a first output result, wherein the protection area is the line range that can be covered by the protection device.
[0042] Step S104, inputting the three-phase voltage and the three-phase current into a fully connected neural network to obtain a second operating state of the measuring point, and obtaining a second output result based on the second operating state, wherein the second operating state includes a fault state and an abnormal operating state.
[0043] Step S105: determining a distance protection action based on the first output result and the second output result.
[0044] The steps provided by the distance protection method integrating the fully connected neural network can be performed by collecting the three-phase voltage and the three-phase current at the measuring point in the protection line, obtaining the measured impedance according to the three-phase voltage and the three-phase current, and obtaining the first operating state of the measuring point based on the measured impedance and the preset impedance threshold. When the measuring point is in a fault state, the position of the measuring point relative to the protection area is judged based on the measured impedance and the preset set impedance to obtain a first output result, and then the three-phase voltage and the three-phase current are input into the fully connected neural network to obtain the second operating state of the measuring point, and the second output result is obtained based on the second operating state. Finally, based on the first output result and the second output result, the distance protection action is determined. When a fault occurs in the protection line, the protection device is controlled to perform a tripping operation to isolate the faulty line from the normally operating power grid. When the protection line is in an abnormal operating state, the embodiment of the present invention accurately identifies the abnormal operating state, controls the protection device to perform a locking operation, and isolates the protection device from the protection line to prevent the protection device from erroneously performing a tripping operation, thereby solving the technical problem of erroneous distance protection action when the line is in an abnormal operating state in the related art.
[0045] The embodiment of the present invention is described in detail below in combination with the above steps.
[0046] Figure 2 is a model diagram of an optional distance protection method integrating a fully connected neural network according to an embodiment of the present invention. Figure 2 In this method, the model includes three parts: input signal module, protection principle module and protection export module. The protection principle module includes the existing distance protection module and the fully connected neural network module. Figure 2In the invention, the input signal module is used to output the three-phase voltage and three-phase current at the measuring point of the protection line to the protection principle module, the existing distance protection module is used to determine whether a fault occurs at the measuring point and to determine the position of the fault point relative to the protection area covered by the protection device, the fully connected neural network module is used to distinguish whether the measuring point is in a fault state or an abnormal operation state, and the protection output module is used to receive the outputs of the existing distance protection module and the fully connected neural network module, and to determine the distance protection action.
[0047] Step S101, collecting three-phase voltages and three-phase currents at measurement points in the protection line.
[0048] It should be noted that the power grid usually uses an AC circuit, and AC power is transmitted using three-phase wires. When the line is very long, a measuring point is usually set in the middle, and then relays, current transformers and voltage transformers are set up. The current transformers and voltage transformers are used to measure the three-phase voltage and three-phase current at the relay, that is, the three-phase voltage and three-phase current at the measuring point.
[0049] At the same time, protection devices are installed at different locations of the line. When a line is very long, there will be several protection devices. These protection devices can be installed at the same location as the measurement point or at different locations. Each protection device has a protection area. In the corresponding protection area, the protection device can perform a tripping operation to isolate the line in the fault section from the normal operating power grid.
[0050] Step S102, obtaining a measured impedance according to the three-phase voltage and the three-phase current, and obtaining a first operating state of the measuring point based on the measured impedance and a preset impedance threshold, wherein the first operating state is a fault state or a non-fault state.
[0051] In the embodiment of the present invention, the three-phase voltage and the three-phase current at the measuring point are collected and obtained through step S101, and then the measured impedance at the measuring point can be obtained based on the three-phase voltage and the three-phase current, and then the first operating state of the measuring point is obtained based on the measured impedance and the preset impedance threshold. Among them, the preset impedance threshold is selected based on experience, and it can reflect whether a fault occurs at the measuring point of the line. When the measured impedance of the measuring point is greater than or equal to the preset impedance threshold, it is considered that the measuring point of the line is in a non-fault state. When the measured impedance of the measuring point is less than the preset impedance threshold, it is considered that a fault occurs at the measuring point of the line, that is, the measuring point of the line is in a fault state.
[0052] Optionally, the step of obtaining a measured impedance according to the three-phase voltage and the three-phase current, and obtaining a first operating state of the measuring point based on the measured impedance and a preset impedance threshold includes: inputting the three-phase voltage and the three-phase current into a first formula to calculate a first measured impedance; obtaining a first impedance threshold of the protection line; and when the first measured impedance is less than the first impedance threshold, determining that the measuring point is in a fault state, and defining the first operating state as a fault state.
[0053] In the embodiment of the present invention, there are two strategies for judging whether a fault occurs at a line measurement point, namely, a phase-to-phase judgment strategy and a grounding judgment strategy. The phase-to-phase judgment strategy can identify whether a phase-to-phase short circuit fault occurs between the three phases A, B, and C of the measurement point, while the grounding judgment strategy can identify whether a single-phase short circuit or a single-phase grounding fault occurs among the three phases A, B, and C of the measurement point. The two strategies are carried out simultaneously to judge whether a phase-to-phase short circuit, a single-phase short circuit, or a single-phase grounding fault occurs at the measurement point. As long as one of the faults occurs, the first operating state of the measurement point will be defined as a fault state.
[0054] When the phase judgment strategy is adopted, the three-phase voltage and the three-phase current need to be input into the first formula to calculate the first measurement impedance. The first formula is:
[0055]
[0056] In the first formula, Z AB Indicates the phase impedance between phase A and phase B, Z BC It represents the phase impedance between phase B and phase C, Z CA Represents the phase impedance between phase C and phase A, Z AB , Z BC , Z CA All are measuring impedance. Respectively represent the voltage of phase A, phase B, and phase C, Represent the current of phase A, phase B, and phase C respectively.
[0057] After the measured impedance is obtained, a first impedance threshold is obtained. The first impedance threshold is obtained based on experience and can measure whether a phase-to-phase short circuit fault occurs between phases A, B, and C. AB , Z BC , Z CA Compared with the first impedance threshold, if the measured impedance Z AB is less than the first impedance threshold, it is determined that a phase-to-phase short circuit fault between phase A and phase B has occurred at the measurement point; if the measured impedance Z BC is less than the first impedance threshold, it is determined that a phase-to-phase short circuit fault between phase B and phase C has occurred at the measurement point; if the measured impedance Z CAIf the measured impedance is less than the first impedance threshold, it is determined that a phase-to-phase short circuit fault between phase C and phase A has occurred at the measurement point, and multiple phase-to-phase short circuits may also occur at the same time. According to the above description, as long as a phase-to-phase short circuit fault occurs, that is, as long as the measured impedance is less than the first impedance threshold, the embodiment of the present invention will determine that the measurement point is in a fault state, and define the first operating state as a fault state.
[0058] Optionally, the step of obtaining a measured impedance according to the three-phase voltage and the three-phase current, and obtaining the first operating state of the measuring point based on the measured impedance and a preset impedance threshold value, further includes: inputting the three-phase current into a second formula to calculate the zero-sequence current; inputting the zero-sequence current, the three-phase voltage and the three-phase current into a third formula to calculate the second measured impedance; obtaining the second impedance threshold value of the protection line; and when the second measured impedance is less than the second impedance threshold value, determining that the measuring point is in a fault state, and defining the first operating state as a fault state.
[0059] In the embodiment of the present invention, when the grounding judgment strategy is adopted, the three-phase current needs to be input into the second formula first to calculate the zero-sequence current. The second formula is:
[0060]
[0061] In the second formula, Respectively represent the current of phase A, phase B, and phase C, Represents zero-sequence current. Zero-sequence current is the vector sum of the three-phase currents. When the line is operating normally, the value of the zero-sequence current is 0. When a short-circuit fault occurs in the line, a short-circuit current flows through the line, which makes the vector sum of the three-phase currents not equal to 0, that is, the value of the zero-sequence current is not 0.
[0062] After the zero-sequence current is obtained, the zero-sequence current, the three-phase voltage and the three-phase current are input into the third formula to calculate the second measurement impedance. The third formula is:
[0063]
[0064] In the third formula, Z A Indicates the impedance of phase A, Z B Indicates the impedance of phase B, Z C Indicates the impedance of phase C, Z A , Z B , Z C All are measuring impedance. Respectively represent the voltage of phase A, phase B, and phase C, Respectively represent the current of phase A, phase B, and phase C, represents zero-sequence current, K represents compensation coefficient, and the compensation coefficient is determined according to line parameters.
[0065] After the measured impedance is obtained, the second impedance threshold is obtained. The second impedance threshold is obtained based on experience and can measure whether a single-phase short circuit or single-phase grounding fault occurs in the three phases A, B, and C. A , Z B , Z C Compared with the second impedance threshold, if the measured impedance Z A If the measured impedance Z is less than the second impedance threshold, it is determined that a phase A short circuit or phase A grounding fault has occurred at the measurement point; B If the measured impedance Z is less than the second impedance threshold, it is determined that a phase B short circuit or phase B grounding fault has occurred at the measurement point; C If the measured impedance is less than the second impedance threshold, it is determined that a C-phase short circuit or a C-phase ground fault has occurred at the measurement point, and multiple single-phase short circuits or single-phase ground faults may also occur at the same time. According to the foregoing, as long as a single-phase short circuit or a single-phase ground fault occurs (that is, as long as the measured impedance is less than the second impedance threshold), the embodiment of the present invention will determine that the measurement point is in a fault state, and define the first operating state as a fault state.
[0066] Step S103, when the measuring point is in a fault state, based on the measured impedance and the preset set impedance, the position of the measuring point relative to the protection area is determined to obtain a first output result, wherein the protection area is the line range that can be covered by the protection device.
[0067] In an embodiment of the present invention, after determining that a fault has occurred at a measuring point, it is also necessary to determine the position of the faulty measuring point relative to the protection area, that is, whether the faulty measuring point is located outside or within the protection area. The protection area is the line range that can be covered by the protection device. Each protection device has a corresponding protection area. Within the corresponding protection area, the protection device can isolate the line in the faulty section from the normally operating power grid by performing a tripping operation.
[0068] The embodiment of the present invention determines the position of the measuring point relative to the protection area based on the measured impedance and the preset set impedance. After determining the position of the measuring point relative to the protection area, a first output result is obtained. The first output result reflects whether the measuring point is located outside the protection area or inside the protection area. The first output result will be used in the subsequent step of determining the distance protection action.
[0069] Optionally, based on the measured impedance and the preset set impedance, the position of the measuring point relative to the protection area is determined to obtain the step of obtaining the first output result, including: obtaining the first set impedance and the second set impedance; when the first measured impedance is greater than the first set impedance, determining that the measuring point is outside the protection area; when the first measured impedance is less than or equal to the first set impedance, determining that the measuring point is within the protection area; when the second measured impedance is greater than the second set impedance, determining that the measuring point is outside the protection area; when the second measured impedance is less than or equal to the second set impedance, determining that the measuring point is within the protection area; when it is determined that the measuring point is within the protection area, defining the value of the first output result as the first value; when it is determined that the measuring point is outside the protection area, defining the value of the first output result as the second value.
[0070] In the embodiment of the present invention, it can be seen from step S102 that there are two strategies for determining whether a fault occurs at a line measurement point, namely, a phase-to-phase determination strategy and a grounding determination strategy, and the measurement impedances calculated by the two strategies are different, and the corresponding preset setting impedances may be the same or may be different.
[0071] When the measured impedance is calculated by the phase-to-phase judgment strategy, the first set impedance is obtained. When the first measured impedance is greater than the first set impedance, the measurement point is determined to be outside the protection area. When the first measured impedance is less than or equal to the first set impedance, the measurement point is determined to be within the protection area. When the measured impedance is calculated by the grounding judgment strategy, the second set impedance is obtained. When the second measured impedance is greater than the second set impedance, the measurement point is determined to be outside the protection area. When the second measured impedance is less than or equal to the second set impedance, the measurement point is determined to be within the protection area. Among them, the first set impedance and the second set impedance are selected based on experience. In different scenarios, the two may be the same or different.
[0072] After determining the position of the measuring point relative to the protection area, the embodiment of the present invention assigns a value to the first output result. When the measuring point is within the protection area, the value of the first output result is defined as the first value, and when the measuring point is outside the protection area, the value of the first output result is defined as the second value. In the embodiment of the present invention, the first value is 1 and the second value is 0. The first output result reflects whether the measuring point is outside or within the protection area, and will be used in the subsequent step of determining the distance protection action.
[0073] Optionally, when it is determined that the measuring point is within the protection area, the method further includes: obtaining a unit impedance of the protection line; and calculating a distance from the measuring point to the protection device based on the measured impedance and the unit impedance.
[0074] In the embodiment of the present invention, when it is determined that the measuring point is within the protection area, it is also necessary to obtain the distance from the measuring point to the protection device. When a fault occurs at the measuring point, the measured impedance is equal to the distance from the measuring point to the protection device. For example, when a phase-to-phase short circuit occurs between phase A and phase B, Z AB =Z1l k , where Z1 represents the unit impedance of the protection line. The unit impedance Z1 is determined by the conductor material of the line. k Indicates the distance from the measuring point to the protective device.
[0075] The distance from the measuring point to the protection device will determine the strategy ultimately adopted when controlling the protection device to perform a tripping operation, that is, the distance from the measuring point to the protection device is used to determine which section of the protection area the fault occurs in, and then the tripping strategy is determined based on the section. The tripping strategies include distance section I protection strategy, distance section II protection strategy, and distance section III protection strategy. The protection range, protection operation and action time limit of each protection strategy are different. The protection range of the distance section I protection strategy is 80%-85% of the total length of the protected line. When a fault occurs within the protection range of section I, the protection device will immediately perform a tripping operation to isolate the faulty line from the normally operating power grid; the protection range of the distance section II protection strategy is the total length of the protected line and 30%-40% of the next section of the line. In conjunction with the distance section I protection strategy of the next section of the line, the tripping operation is performed with a delay; the protection range of the distance section III protection strategy usually includes the total length of the protected line and the next section of the line. By coordinating with the protection strategy of the next section of the line, the tripping operation is performed with a delay. Among them, the action time limit of the distance section III protection strategy of the protection line is usually longer than the action time limit of the distance section II protection strategy of the next section of the line.
[0076] Step S104, inputting the three-phase voltage and the three-phase current into a fully connected neural network to obtain a second operating state of the measuring point, and obtaining a second output result based on the second operating state, wherein the second operating state includes a fault state and an abnormal operating state.
[0077] In an embodiment of the present invention, after obtaining the first output result of the existing distance protection module, the second operating state of the measuring point can be obtained by inputting the three-phase voltage and the three-phase current into a fully connected neural network, and then the second output result can be obtained based on the second operating state.
[0078] A fully connected neural network consists of an input layer, a hidden layer, an output layer, and an activation function. The input layer and the output layer include many different layers of interconnected neurons. Information is transmitted in only one direction in a fully connected neural network, starting from the input layer and passing through several hidden layers before entering the output layer and outputting the network's prediction results. The number of neurons in the input layer depends on the dimension of the input data, and the number of neurons in the output layer depends on the output task. The activation function is used to introduce nonlinear factors so that the fully connected neural network can fit complex nonlinear relationships.
[0079] In the embodiment of the present invention, 7 hidden layers are selected, and the activation function is the tanh function, with a value range of [-1, 1]. Taking the first hidden layer as an example, the hidden layer receives the information provided by the input layer, and obtains the summary information of the hidden layer in the form of weighted summation, and then acts on the activation function as the input of the next hidden layer. The next hidden layer performs the same operation, and this operation is performed layer by layer until the data is passed to the final output layer. The fully connected neural network can extract useful features from the input information and classify these features.
[0080] Figure 3 is a model diagram of an optional fully connected neural network according to an embodiment of the present invention, Figure 3 In the fully connected neural network, the input is a 12-dimensional vector, which refers to the amplitude and phase angle of the three-phase voltage and three-phase current. The input three-phase voltage and three-phase current information passes through 7 hidden layers and reaches the output layer. Figure 3 In the hidden layer shown, k is the weight, b is the bias, and the activation function is the tanh function. The fully connected neural network finally outputs one of the five-dimensional vectors O1 to O5. The five-dimensional vector uses five three-bit binary numbers to indicate the type of the second operating state, that is, a fault state or an abnormal operating state. The fault state is marked as (100), and the abnormal operating state includes an overload state, a voltage transformer disconnection state, an oscillation state, and a data error state. Among them, the overload state is marked as (000), the voltage transformer disconnection state is marked as (010), the oscillation state is marked as (011), and the data error state is marked as (001). The fully connected neural network will eventually output one of the binary numbers to characterize the second operating state of the measurement point.
[0081] Optionally, the step of obtaining a second output result based on the second operating state includes: when the second operating state is a fault state, defining the value of the second output result as a first value; when the second operating state is an abnormal operating state, defining the value of the second output result as a second value, wherein the abnormal operating state includes at least one of the following: an overload state, a voltage transformer disconnection state, an oscillation state, and a data error state.
[0082] In the embodiment of the present invention, after the second operating state is obtained, the value of the second output result is defined according to the second operating state. The embodiment of the present invention distinguishes the fault state or the abnormal operating state according to the highest digit in the binary number identifier. For example, if the highest digit of the fault state identifier (100) is 1, the second operating state is a fault state; if the highest digit of the overload state identifier (000), the voltage transformer disconnection state identifier (010), the oscillation state identifier (011) and the data error state identifier (001) is 0, the second operating state is an abnormal operating state.
[0083] When the second operating state is a fault state, the value of the second output result is defined as the first value; when the second operating state is an abnormal operating state, the value of the second output result is defined as the second value. It should be noted that in the embodiment of the present invention, the first value is 1 and the second value is 0.
[0084] Step S105: determining a distance protection action based on the first output result and the second output result.
[0085] In the embodiment of the present invention, the distance protection action is ultimately determined according to the first output result and the second output result.
[0086] Optionally, based on the first output result and the second output result, the step of determining the distance protection action includes: when the values of the first output result and the second output result are both the first values, controlling the protection device to perform a tripping operation; when the value of the first output result is the second value and the value of the second output result is the first value, controlling the protection device to stop performing the operation; when the value of the second output result is the second value, performing a locking operation to isolate the protection device outside the protection line.
[0087] In an embodiment of the present invention, when the values of the first output result and the second output result are both the first values, the protection device is controlled to perform a tripping operation, that is, when a fault occurs at the measuring point and the fault point is located within the protection area, the protection device will perform a tripping operation to isolate the faulty line outside the normally operating power grid; when the value of the first output result is the second value and the value of the second output result is the first value, the protection device is controlled to stop performing the operation, that is, when a fault occurs at the measuring point but the fault point is located outside the protection area, the protection device will not perform any operation; when the value of the second output result is the second value and the value of the first output result is an arbitrary value, a locking operation is performed, that is, when the measuring point is in an abnormal operating state, the embodiment of the present invention will perform a locking operation, which cuts off the protection circuit where the protection device is located through the auxiliary switch, isolates the protection device outside the protection line, and prevents the protection device from erroneously performing a tripping operation.
[0088] Figure 4 is a schematic diagram of an optional distance protection method integrating a fully connected neural network according to an embodiment of the present invention. Figure 4 middle, Respectively represent the voltage of phase A, phase B, and phase C, Represents the current of phase A, phase B, and phase C respectively. The three-phase voltage and three-phase current are input into the existing distance protection module in the protection principle module to obtain Z AB , Z BC , Z CA , Z A , Z B , Z C Measure impedance and output the first output result. The first output result indicates whether a fault occurs at the measurement point and the position of the fault point relative to the protection area. At the same time, the fully connected neural network in the three-phase voltage and three-phase current input protection principle module outputs the second output result. The second output result indicates that the measurement point is in a fault state or an abnormal operation state. The abnormal operation state includes an overload state, a voltage transformer disconnection state, an oscillation state, and a data error state. Finally, based on the first output result and the second output result, determine the distance protection action. When a fault occurs at the measurement point and the fault point is within the protection area, the protection device performs a tripping operation (corresponding to Figure 4 When a fault occurs at the measuring point but the fault point is outside the protection area, the protection device will not perform any operation (corresponding to Figure 4 The protection in the measurement point does not work); when the measurement point is in an abnormal operation state, the embodiment of the present invention will perform a locking operation (corresponding to Figure 4 protection lock in the ).
[0089] The embodiment of the present invention determines the distance protection action. When a fault occurs in the protection line, the protection device is controlled to perform a tripping operation to isolate the faulty line outside the normally operating power grid. When the protection line is in an abnormal operating state, the embodiment of the present invention accurately identifies the abnormal operating state, controls the protection device to perform a locking operation, and isolates the protection device outside the protection line to prevent the protection device from erroneously performing a tripping operation.
[0090] The following is a detailed description in conjunction with another embodiment.
[0091] Embodiment 2
[0092] A distance protection device integrating a fully connected neural network provided in this embodiment includes multiple implementation units, each of which corresponds to each implementation step in the above-mentioned embodiment 1.
[0093] Figure 5 is a schematic diagram of an optional distance protection device integrating a fully connected neural network according to an embodiment of the present invention, such as Figure 5As shown, the distance protection device integrating the fully connected neural network may include: a collection unit 50, a first acquisition unit 51, a judgment unit 52, a second acquisition unit 53, and a determination unit 54.
[0094] The acquisition unit 50 is used to acquire the three-phase voltage and the three-phase current at the measuring point in the protection line;
[0095] A first acquisition unit 51 is used to obtain a measured impedance according to the three-phase voltage and the three-phase current, and obtain a first operating state of the measuring point based on the measured impedance and a preset impedance threshold, wherein the first operating state is a fault state or a non-fault state;
[0096] The judging unit 52 is used to judge the position of the measuring point relative to the protection area based on the measured impedance and the preset setting impedance when the measuring point is in a fault state, and obtain a first output result, wherein the protection area is the line range that can be covered by the protection device;
[0097] A second acquisition unit 53 is used to input the three-phase voltage and the three-phase current into a fully connected neural network to obtain a second operating state of the measurement point, and obtain a second output result based on the second operating state, wherein the second operating state includes a fault state and an abnormal operating state;
[0098] The determination unit 54 determines a distance protection action based on the first output result and the second output result.
[0099] The distance protection device integrating the fully connected neural network can collect the three-phase voltage and the three-phase current at the measuring point in the protection line through the collection unit 50, obtain the measurement impedance according to the three-phase voltage and the three-phase current through the first acquisition unit 51, obtain the first operating state of the measurement point based on the measurement impedance and the preset impedance threshold, and judge the position of the measurement point relative to the protection area based on the measurement impedance and the preset set impedance when the measurement point is in a fault state through the judgment unit 52 to obtain a first output result, and then input the three-phase voltage and the three-phase current into the fully connected neural network through the second acquisition unit 53 to obtain the second operating state of the measurement point, and obtain the second output result based on the second operating state. Finally, the distance protection action is determined based on the first output result and the second output result by the determination unit 54. When a fault occurs in the protection line, the protection device is controlled to perform a tripping operation to isolate the faulty line from the normally operating power grid. When the protection line is in an abnormal operating state, the abnormal operating state is accurately identified, and the protection device is controlled to perform a locking operation to isolate the protection device from the protection line to prevent the protection device from erroneously performing a tripping operation, thereby solving the technical problem of erroneous distance protection action when the line is in an abnormal operating state in the related art.
[0100] Optionally, the first acquisition unit 51 includes: a first calculation module, used to input the three-phase voltage and the three-phase current into a first formula to calculate a first measurement impedance; a first acquisition module, used to obtain a first impedance threshold of the protection line; a first judgment module, used to judge that the measurement point is in a fault state when the first measurement impedance is less than the first impedance threshold, and define the first operating state as a fault state.
[0101] Optionally, the first acquisition unit 51 also includes: a second calculation module, used to input the three-phase current into a second formula to calculate the zero-sequence current; a third calculation module, used to input the zero-sequence current, the three-phase voltage and the three-phase current into a third formula to calculate the second measurement impedance; a second acquisition module, used to obtain a second impedance threshold of the protection line; a second determination module, used to determine that the measurement point is in a fault state when the second measurement impedance is less than the second impedance threshold, and define the first operating state as a fault state.
[0102] Optionally, the judgment unit 52 includes: a third acquisition module, used to acquire the first set impedance and the second set impedance; a third determination module, used to determine that the measurement point is outside the protection area when the first measured impedance is greater than the first set impedance; a fourth determination module, used to determine that the measurement point is within the protection area when the first measured impedance is less than or equal to the first set impedance; a fifth determination module, used to determine that the measurement point is outside the protection area when the second measured impedance is greater than the second set impedance; a sixth determination module, used to determine that the measurement point is within the protection area when the second measured impedance is less than or equal to the second set impedance; a first definition module, used to define the value of the first output result as a first value when it is determined that the measurement point is within the protection area; and a second definition module, used to define the value of the first output result as a second value when it is determined that the measurement point is outside the protection area.
[0103] Optionally, the judgment unit 52 further includes: a fourth acquisition module, used to acquire the unit impedance of the protection line; and a fourth calculation module, used to calculate the distance from the measurement point to the protection device based on the measured impedance and the unit impedance.
[0104] Optionally, the second acquisition unit 53 includes: a third definition module, used to define the numerical value of the second output result as a first numerical value when the second operating state is a fault state; a fourth definition module, used to define the numerical value of the second output result as a second numerical value when the second operating state is an abnormal operating state, wherein the abnormal operating state includes at least one of the following: an overload state, a voltage transformer disconnection state, an oscillation state, and a data error state.
[0105] Optionally, the determination unit 54 includes: a first control module, used to control the protection device to perform a tripping operation when the values of the first output result and the second output result are both first values; a second control module, used to control the protection device to stop performing the operation when the value of the first output result is the second value and the value of the second output result is the first value; and a third control module, used to perform a locking operation to isolate the protection device outside the protection line when the value of the second output result is the second value.
[0106] The above-mentioned distance protection device integrating a fully connected neural network may also include a processor and a memory. The above-mentioned acquisition unit 50, the first acquisition unit 51, the judgment unit 52, the second acquisition unit 53, the determination unit 54, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.
[0107] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters can be adjusted to control the protection device to perform a tripping operation when a fault occurs in the protection line, so as to isolate the faulty line from the normally operating power grid, and to accurately identify the abnormal operation state when the protection line is in an abnormal operation state, control the protection device to perform a locking operation, and isolate the protection device from the protection line to prevent the protection device from performing a tripping operation by mistake.
[0108] The above-mentioned memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (fl ash RAM), and the memory includes at least one storage chip.
[0109] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, and the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the distance protection method integrating a fully connected neural network of any one of the above-mentioned embodiments.
[0110] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement the distance protection method integrating a fully connected neural network of any one of the above-mentioned embodiments one.
[0111] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the distance protection method integrating a fully connected neural network described in each embodiment of the present application.
[0112] The present application also provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the distance protection method integrating a fully connected neural network described in each embodiment of the present application are implemented.
[0113] Figure 6 1 is a hardware structure block diagram of an electronic device (or mobile device) for a distance protection method integrating a fully connected neural network according to an embodiment of the present invention. Figure 6 As shown, the electronic device may include one or more ( Figure 6 602a, 602b, ..., 602n are used to illustrate) processor 602 (processor 602 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), and memory 604 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a keyboard, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 6 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 6 More or fewer components as shown, or with Figure 6 Different configurations are shown.
[0114] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.
[0115] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0116] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.
[0117] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0118] In addition, each functional unit in each embodiment of the present invention 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-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0119] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.
[0120] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A distance protection method integrating a fully connected neural network, characterized in that: The protection device is installed in the protection line, including: Collecting three-phase voltage and three-phase current at the measuring points in the protection circuit; Obtaining a measured impedance according to the three-phase voltage and the three-phase current, and obtaining a first operating state of the measuring point based on the measured impedance and a preset impedance threshold, wherein the first operating state is a fault state or a non-fault state; When the measuring point is in a fault state, based on the measured impedance and the preset set impedance, the position of the measuring point relative to the protection area is determined to obtain a first output result, wherein the protection area is a line range that can be covered by the protection device; Inputting the three-phase voltage and the three-phase current into a fully connected neural network to obtain a second operating state of the measurement point, and obtaining a second output result based on the second operating state, wherein the second operating state includes a fault state and an abnormal operating state; A distance protection action is determined based on the first output result and the second output result.
2. The distance protection method according to claim 1, characterized in that: The step of obtaining a measured impedance according to the three-phase voltage and the three-phase current, and obtaining a first operating state of the measuring point based on the measured impedance and a preset impedance threshold comprises: Input the three-phase voltage and the three-phase current into a first formula to calculate a first measurement impedance; Acquire a first impedance threshold of the protection circuit; When the first measured impedance is less than the first impedance threshold, it is determined that the measuring point is in a fault state, and the first operating state is defined as the fault state.
3. The distance protection method according to claim 1, characterized in that: The step of obtaining a measured impedance according to the three-phase voltage and the three-phase current, and obtaining a first operating state of the measuring point based on the measured impedance and a preset impedance threshold value, further includes: Input the three-phase current into a second formula to calculate the zero-sequence current; Inputting the zero-sequence current, the three-phase voltage and the three-phase current into a third formula to calculate a second measurement impedance; Acquire a second impedance threshold of the protection circuit; When the second measured impedance is less than the second impedance threshold, it is determined that the measuring point is in a fault state, and the first operating state is defined as the fault state.
4. The distance protection method according to claim 2 or 3, characterized in that: The step of determining the position of the measuring point relative to the protection area based on the measured impedance and the preset setting impedance to obtain a first output result comprises: Obtaining a first set impedance and a second set impedance; When the first measured impedance is greater than the first set impedance, it is determined that the measuring point is outside the protection area; when the first measured impedance is less than or equal to the first set impedance, it is determined that the measuring point is within the protection area; When the second measured impedance is greater than the second set impedance, it is determined that the measuring point is outside the protection area; when the second measured impedance is less than or equal to the second set impedance, it is determined that the measuring point is within the protection area; In a case where it is determined that the measuring point is located within the protection area, defining a value of the first output result as a first value; In a case where it is determined that the measurement point is outside the protection area, a value of the first output result is defined as a second value.
5. The distance protection method according to claim 1, characterized in that: When it is determined that the measuring point is within the protection area, the method further includes: Obtaining the unit impedance of the protection line; Based on the measured impedance and the unit impedance, a distance from the measuring point to the protection device is calculated.
6. The distance protection method according to claim 1, characterized in that: The step of obtaining a second output result based on the second operating state comprises: When the second operating state is a fault state, defining the value of the second output result as a first value; When the second operating state is an abnormal operating state, the value of the second output result is defined as a second value, wherein the abnormal operating state includes at least one of the following: an overload state, a voltage transformer disconnection state, an oscillation state, and a data error state.
7. The distance protection method according to claim 1, characterized in that: The step of determining a distance protection action based on the first output result and the second output result includes: When the values of the first output result and the second output result are both the first values, controlling the protection device to perform a tripping operation; When the value of the first output result is the second value and the value of the second output result is the first value, controlling the protection device to stop performing the operation; When the value of the second output result is the second value, a locking operation is performed to isolate the protection device from the protection circuit.
8. A distance protection device integrating a fully connected neural network, characterized in that: include: A collection unit, used for collecting three-phase voltage and three-phase current at a measuring point in the protection circuit; a first acquisition unit, configured to obtain a measured impedance according to the three-phase voltage and the three-phase current, and obtain a first operating state of the measurement point based on the measured impedance and a preset impedance threshold, wherein the first operating state is a fault state or a non-fault state; A judgment unit, configured to judge, when the measuring point is in a fault state, a position of the measuring point relative to a protection area based on the measured impedance and a preset setting impedance, and obtain a first output result, wherein the protection area is a line range that can be covered by the protection device; a second acquisition unit, configured to input the three-phase voltage and the three-phase current into a fully connected neural network to obtain a second operating state of the measurement point, and obtain a second output result based on the second operating state, wherein the second operating state includes a fault state and an abnormal operating state; A determination unit determines a distance protection action based on the first output result and the second output result.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the distance protection method of integrating a fully connected neural network as described in any one of claims 1 to 7.
10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the distance protection method of the fused fully connected neural network as described in any one of claims 1 to 7.
