A distribution network fault detection and positioning system based on artificial intelligence

Abstract

The present invention belongs to the field of distribution network fault detection, relates to data analysis technology, and is used to solve the problem that the existing distribution network fault detection and positioning system cannot monitor the data detection accuracy and data transmission status of the detection terminal. Specifically, it is a distribution network fault detection and positioning system based on artificial intelligence, comprising a detection and positioning platform, wherein the detection and positioning platform is communicatively connected with a fault detection module, a detection verification module and a storage module; the fault detection module is used to detect and analyze the fault of the distribution network: the power network node of the distribution network is marked as a transmission node i, and a detection terminal P is set at the transmission node i; the detection data of the detection terminal P is transmitted through a channel P; the present invention can detect and analyze the fault of the distribution network, and improve the accuracy of the distribution network fault detection and positioning analysis result by setting a plurality of detection terminals on the transmission node and expanding the detection data base.

Description

Technical Field

[0001] The present invention belongs to the field of distribution network fault detection and relates to data analysis technology, and specifically is a distribution network fault detection and positioning system based on artificial intelligence. Background Art

[0002] The distribution network refers to a horizontal power transmission network formed by reducing the voltage of high-voltage electric energy through transformers and distributing it from the transmission and distribution substation or busbar. It is an important part of the power system, transmitting the electric energy of the transmission network to the end users, providing a reliable power guarantee for social and economic development.

[0003] The existing distribution network fault detection and positioning system is unable to monitor the data detection accuracy and data transmission status of the detection terminal, resulting in the inability to guarantee the accuracy of power data in the fault monitoring and analysis process, thereby affecting the accuracy of the fault detection and analysis results.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the invention

[0005] The purpose of the present invention is to provide a distribution network fault detection and positioning system based on artificial intelligence, which is used to solve the problem that the existing distribution network fault detection and positioning system cannot monitor the data detection accuracy and data transmission status of the detection terminal;

[0006] The technical problem to be solved by the present invention is: how to provide an artificial intelligence-based distribution network fault detection and positioning system that can monitor the data detection accuracy and data transmission status of the detection terminal.

[0007] The purpose of the present invention can be achieved by the following technical solutions:

[0008] A distribution network fault detection and positioning system based on artificial intelligence, comprising a detection and positioning platform, wherein the detection and positioning platform is communicatively connected with a fault detection module, a detection verification module and a storage module;

[0009] The fault detection module is used to detect and analyze the faults of the distribution network: mark the power network node of the distribution network as a transmission node i, i=1, 2, ..., n, n is a positive integer, set a detection terminal P at the transmission node i, P=1, 2, ..., w, w is a positive integer; the detection data of the detection terminal P is transmitted through the channel P; generate a detection cycle and divide the detection cycle into a number of detection time periods, and obtain the flow difference data LCPi and the pressure difference data YCPi of the transmission node i in the detection period through the detection terminal P; obtain the fault coefficient GZPi corresponding to the detection terminal P at the transmission node i by numerically calculating the flow difference data LCPi and the pressure difference data YCPi, sum and average the fault coefficients GZPi of all detection terminals P at the transmission node i to obtain the fault performance value GBi of the transmission node i, and determine whether the power transmission state of the transmission node i is abnormal through the fault performance value GBi;

[0010] The detection and verification module is used to verify and analyze the fault detection results of the distribution network.

[0011] As a preferred embodiment of the present invention, the process of acquiring the flow difference data LCPi includes: acquiring the maximum current value and the minimum current value of the transmission node i within the detection period through the detection terminal P, and marking the difference between the maximum current value and the minimum current value as the flow difference value LCPi; the process of acquiring the pressure difference data YCPi includes: acquiring the maximum voltage value and the minimum voltage value of the transmission node i within the detection period through the detection terminal P, and marking the difference between the maximum voltage value and the minimum voltage value as the pressure difference value YCPi.

[0012] As a preferred embodiment of the present invention, the specific process of determining whether the power transmission state of the transmission node i is abnormal includes: obtaining the fault manifestation threshold GBmax through the storage module, and comparing the fault manifestation value GBi of the transmission node i with the fault threshold GZmax: if the fault manifestation value GBi is less than the fault manifestation threshold GBmax, then the power transmission state of the transmission node i is determined to be normal; if the fault manifestation value GBi is greater than or equal to the fault manifestation threshold GBmax, then the power transmission state of the transmission node i is determined to be abnormal, and the corresponding transmission node i is marked as an abnormal node, and the abnormal node is sent to the detection and positioning platform, and after receiving the abnormal node, the detection and positioning platform sends the abnormal node to the mobile phone terminal of the administrator.

[0013] As a preferred embodiment of the present invention, the specific process of the detection and verification module for verifying and analyzing the fault detection results of the distribution network includes: obtaining the detection deviation value of the transmission node, obtaining the detection deviation threshold through the storage module, comparing the detection deviation value with the detection deviation threshold, and judging whether the power transmission state of the transmission node i meets the requirements through the comparison result; forming a transmission set of channel P by the fault coefficients GZPi corresponding to the detection terminal P in all transmission nodes, removing the fault coefficients GZPi corresponding to the faulty node from the transmission set, performing variance calculation on all elements in the transmission set after removal to obtain the transmission deviation value, obtaining the transmission deviation threshold through the storage module, comparing the transmission deviation value with the transmission deviation threshold, and judging whether the power data transmission of channel P meets the requirements through the comparison result.

[0014] As a preferred embodiment of the present invention, the process of obtaining the detection deviation value of the transport node i includes: obtaining the fault coefficient GZPi corresponding to the detection terminal P in all transport nodes i at the end of the detection period, forming a detection set of the transport node i by the fault coefficients GZPi corresponding to all detection terminals P in the same transport node i, and performing variance calculation on all elements in the detection set to obtain the detection deviation value.

[0015] As a preferred embodiment of the present invention, the specific process of comparing the detection deviation value with the detection deviation threshold includes: if the detection deviation value is less than the detection deviation threshold, it is determined that the power data collection in the transmission node i meets the requirements, and the corresponding transmission node i is marked as a qualified node; if the detection deviation value is greater than or equal to the detection deviation threshold, it is determined that the power data collection in the transmission node i does not meet the requirements, and the corresponding transmission node i is marked as a faulty node; the faulty node is sent to the detection and positioning platform, and after receiving the faulty node, the detection and positioning platform sends the faulty node to the mobile terminal of the administrator.

[0016] As a preferred embodiment of the present invention, the specific process of comparing the transmission deviation value with the transmission deviation threshold includes: if the transmission deviation value is less than the transmission deviation threshold, it is determined that the power data transmission of channel P meets the requirements; if the transmission deviation value is greater than or equal to the transmission deviation threshold, it is determined that the power data transmission of channel P does not meet the requirements, and the corresponding channel P is marked as an abnormal channel, and the abnormal channel is sent to the detection and positioning platform. After receiving the abnormal channel, the detection and positioning platform sends the abnormal channel to the mobile phone terminal of the administrator.

[0017] As a preferred embodiment of the present invention, the working method of the distribution network fault detection and positioning system based on artificial intelligence includes the following steps:

[0018] Step 1: Detect and analyze the fault of the distribution network: mark the power network node of the distribution network as a transmission node i, i = 1, 2, ..., n, n is a positive integer, set a detection terminal P at the transmission node i, P = 1, 2, ..., w, w is a positive integer; the detection data of the detection terminal P is transmitted through the channel P;

[0019] Step 2: Generate a detection cycle and divide the detection cycle into several detection periods, obtain the flow difference data LCPi and the pressure difference data YCPi of the transmission node i in the detection period through the detection terminal P, and perform numerical calculation to obtain the fault coefficient GZPi corresponding to the detection terminal P at the transmission node i;

[0020] Step 3: sum and average the fault coefficients GZPi of all detection terminals P at the transmission node i to obtain the fault performance value GBi of the transmission node i, and determine whether the power transmission state of the transmission node i is normal based on the fault performance value GBi;

[0021] Step 4: Verify and analyze the fault detection results of the distribution network and obtain a detection set. Calculate the variance of all elements in the detection set to obtain a detection deviation value. Mark the transmission node i as a qualified node or a faulty node based on the detection deviation value.

[0022] Step 5: The fault coefficients GZPi corresponding to the detection terminal P in all transmission nodes constitute the transmission set of channel P, and the fault coefficients GZPi corresponding to the faulty nodes are removed from the transmission set. The variance of all elements in the transmission set after removal is calculated to obtain the transmission deviation value, and the transmission deviation value is used to determine whether the power data transmission of channel P meets the requirements.

[0023] The present invention has the following beneficial effects:

[0024] 1. The fault detection module can detect and analyze the faults of the distribution network. By setting up multiple detection terminals on the transmission nodes, and then sending the detection data of the detection terminals to the fault detection module through a dedicated channel, the accuracy of the distribution network fault detection and positioning analysis results can be improved by expanding the detection data base;

[0025] 2. The detection results of each detection terminal in the transmission node are calculated, and then the detection results of all detection terminals are integrated and calculated to obtain the fault performance value of the transmission node. The abnormal degree of power transmission status of the transmission node is fed back through the fault performance value, and an early warning is issued in time when the abnormal degree of power transmission does not meet the requirements;

[0026] 3. The detection verification module can be used to verify and analyze the fault detection results of the distribution network. The detection deviation value is obtained by calculating the deviation degree of the detection results of all detection terminals in the same transmission node. The operating status of the detection terminal is monitored by the detection deviation value. At the same time, the data transmission status of the channel is monitored by the transmission deviation value. When any abnormality occurs at the data acquisition end, an early warning can be issued in time, thereby ensuring the accuracy of the fault detection and analysis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 is a system block diagram of Embodiment 1 of the present invention;

[0029] Figure 2 This is a flow chart of the method of Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0030] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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 are within the scope of protection of the present invention.

[0031] Embodiment 1

[0032] like Figure 1 As shown, a distribution network fault detection and positioning system based on artificial intelligence includes a detection and positioning platform, and the detection and positioning platform is communicatively connected with a fault detection module, a detection verification module and a storage module.

[0033] The fault detection module is used to detect and analyze the faults of the distribution network: the power network node of the distribution network is marked as a transmission node i, i=1, 2, ..., n, n is a positive integer, and a detection terminal P is set at the transmission node i, P=1, 2, ..., w, w is a positive integer; the detection data of the detection terminal P is transmitted through the channel P; the faults of the distribution network are detected and analyzed, by setting multiple detection terminals on the transmission node, and then sending the detection data of the detection terminal to the fault detection module through a dedicated channel, and the accuracy of the distribution network fault detection and positioning analysis results is improved by expanding the base of the detection data; A detection cycle is generated and divided into several detection time periods, and the flow difference data LCPi and the pressure difference data YCPi of the transmission node i in the detection time period are obtained through the detection terminal P. The process of obtaining the flow difference data LCPi includes: obtaining the maximum current value and the minimum current value of the transmission node i in the detection time period through the detection terminal P, and marking the difference between the maximum current value and the minimum current value as the flow difference value LCPi; the process of obtaining the pressure difference data YCPi includes: obtaining the maximum voltage value and the minimum voltage value of the transmission node i in the detection time period through the detection terminal P, and marking the difference between the maximum voltage value and the minimum voltage value as the pressure difference value. The difference YCPi; the fault coefficient GZPi corresponding to the detection terminal P at the transmission node i is obtained by the formula GZPi=α1*LCPi+α2*YCPi, the fault coefficients GZPi of all detection terminals P at the transmission node i are summed and averaged to obtain the fault performance value GBi of the transmission node i, the fault performance threshold GBmax is obtained through the storage module, and the fault performance value GBi of the transmission node i is compared with the fault threshold GZmax: if the fault performance value GBi is less than the fault performance threshold GBmax, it is determined that the power transmission state of the transmission node i is normal; if the fault performance value GBi is less than the fault performance threshold GBmax, it is determined that the power transmission state of the transmission node i is normal; if the fault performance value GB If i is greater than or equal to the fault manifestation threshold GBmax, the power transmission state of the transmission node i is determined to be abnormal, the corresponding transmission node i is marked as an abnormal node, and the abnormal node is sent to the detection and positioning platform. After receiving the abnormal node, the detection and positioning platform sends the abnormal node to the mobile terminal of the manager; the detection result of each detection terminal in the transmission node is calculated, and then the detection results of all detection terminals are integrated and calculated to obtain the fault manifestation value of the transmission node. The abnormal degree of the power transmission state of the transmission node is fed back through the fault manifestation value, and a warning is issued in time when the abnormal degree of power transmission does not meet the requirements.

[0034] The detection verification module is used to verify and analyze the fault detection results of the distribution network: at the end of the detection period, the fault coefficient GZPi corresponding to the detection terminal P in all transmission nodes i is obtained, and the fault coefficient GZPi corresponding to all detection terminals P in the same transmission node i constitutes the detection set of the transmission node i, and the variance of all elements in the detection set is calculated to obtain the detection deviation value, and the detection deviation threshold is obtained through the storage module, and the detection deviation value is compared with the detection deviation threshold: if the detection deviation value is less than the detection deviation threshold, it is determined that the power data collection in the transmission node i meets the requirements, and the corresponding transmission node i is marked as a qualified node; if the detection deviation value is greater than or equal to the detection deviation threshold, it is determined that the power data collection in the transmission node i does not meet the requirements, and the corresponding transmission node i is marked as a faulty node; the faulty node is sent to the detection and positioning platform, and the detection and positioning platform sends the faulty node to the mobile terminal of the manager after receiving the faulty node; the fault coefficient GZPi corresponding to the detection terminal P in all transmission nodes constitutes the transmission set of the channel P, and the faulty node is marked as a qualified node. The fault coefficient GZPi corresponding to the faulty node is removed from the transmission set, and the variance of all elements in the transmission set after removal is calculated to obtain the transmission deviation value. The transmission deviation threshold is obtained through the storage module, and the transmission deviation value is compared with the transmission deviation threshold: if the transmission deviation value is less than the transmission deviation threshold, it is determined that the power data transmission of channel P meets the requirements; if the transmission deviation value is greater than or equal to the transmission deviation threshold, it is determined that the power data transmission of channel P does not meet the requirements, and the corresponding channel P is marked as an abnormal channel, and the abnormal channel is sent to the detection and positioning platform. After receiving the abnormal channel, the detection and positioning platform sends the abnormal channel to the mobile terminal of the manager; the fault detection results of the distribution network are verified and analyzed, and the detection deviation value is obtained by calculating the deviation degree of the detection results of all detection terminals in the same transmission node. The running status of the detection terminal is monitored by the detection deviation value, and the data transmission status of the channel is monitored by the transmission deviation value. When any abnormality occurs at the data acquisition end, an early warning can be given in time, thereby ensuring the accuracy of the fault detection and analysis results.

[0035] Embodiment 2

[0036] like Figure 2 As shown, a distribution network fault detection and positioning method based on artificial intelligence includes the following steps:

[0037] Step 1: Detect and analyze the fault of the distribution network: mark the power network node of the distribution network as a transmission node i, i = 1, 2, ..., n, n is a positive integer, set a detection terminal P at the transmission node i, P = 1, 2, ..., w, w is a positive integer; the detection data of the detection terminal P is transmitted through the channel P;

[0038] Step 2: Generate a detection cycle and divide the detection cycle into several detection periods, obtain the flow difference data LCPi and the pressure difference data YCPi of the transmission node i in the detection period through the detection terminal P, and perform numerical calculation to obtain the fault coefficient GZPi corresponding to the detection terminal P at the transmission node i;

[0039] Step 3: sum and average the fault coefficients GZPi of all detection terminals P at the transmission node i to obtain the fault performance value GBi of the transmission node i, and determine whether the power transmission state of the transmission node i is normal based on the fault performance value GBi;

[0040] Step 4: Verify and analyze the fault detection results of the distribution network and obtain a detection set. Calculate the variance of all elements in the detection set to obtain a detection deviation value. Mark the transmission node i as a qualified node or a faulty node based on the detection deviation value.

[0041] Step 5: The fault coefficients GZPi corresponding to the detection terminal P in all transmission nodes constitute the transmission set of channel P, and the fault coefficients GZPi corresponding to the faulty nodes are removed from the transmission set. The variance of all elements in the transmission set after removal is calculated to obtain the transmission deviation value, and the transmission deviation value is used to determine whether the power data transmission of channel P meets the requirements.

[0042] A distribution network fault detection and positioning system based on artificial intelligence, when working, the power network node of the distribution network is marked as a transmission node i, i = 1, 2, ..., n, n is a positive integer, and a detection terminal P is set at the transmission node i, P = 1, 2, ..., w, w is a positive integer; the detection data of the detection terminal P is transmitted through a channel P; a detection cycle is generated and the detection cycle is divided into a plurality of detection time periods, and the flow difference data LCPi and the pressure difference data YCPi of the transmission node i in the detection period are obtained through the detection terminal P, and numerical calculation is performed to obtain the fault coefficient GZPi corresponding to the detection terminal P at the transmission node i; the fault coefficients GZPi of all detection terminals P at the transmission node i are summed and averaged to obtain The fault performance value GBi of the transmission node i is used to determine whether the power transmission status of the transmission node i is normal; the fault detection results of the distribution network are verified and analyzed to obtain a detection set, the variance of all elements in the detection set is calculated to obtain a detection deviation value, and the transmission node i is marked as a qualified node or a faulty node through the detection deviation value; the fault coefficients GZPi corresponding to the detection terminal P in all transmission nodes constitute the transmission set of the channel P, the fault coefficients GZPi corresponding to the faulty node are removed from the transmission set, the variance of all elements in the transmission set after removal is calculated to obtain the transmission deviation value, and the transmission deviation value is used to determine whether the power data transmission of the channel P meets the requirements.

[0043] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0044] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula close to the real value. The coefficients in the formula are set by technicians in this field according to the actual situation; for example: formula GZPi = α1*LCPi + α2*YCPi; technicians in this field collect multiple groups of sample data and set corresponding fault coefficients for each group of sample data; substitute the set fault coefficients and the collected sample data into the formula, any three formulas constitute a three-variable linear equation group, screen the calculated coefficients and take the average, and obtain the values ​​of α1 and α2 as 2.68 and 2.15 respectively;

[0045] The size of the coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the coefficient depends on the amount of sample data and the preliminary setting of the corresponding fault coefficient for each set of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantized value, such as the fault coefficient is proportional to the value of the flow difference data.

[0046] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0047] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A distribution network fault detection and positioning system based on artificial intelligence, characterized in that: It includes a detection and positioning platform, which is communicatively connected with a fault detection module, a detection and verification module and a storage module; The fault detection module is used to detect and analyze the faults of the distribution network: mark the power network node of the distribution network as a transmission node i, i=1, 2, ..., n, n is a positive integer, set a detection terminal P at the transmission node i, P=1, 2, ..., w, w is a positive integer; the detection data of the detection terminal P is transmitted through the channel P; generate a detection cycle and divide the detection cycle into a number of detection time periods, and obtain the flow difference data LCPi and the pressure difference data YCPi of the transmission node i in the detection period through the detection terminal P; obtain the fault coefficient GZPi corresponding to the detection terminal P at the transmission node i by numerically calculating the flow difference data LCPi and the pressure difference data YCPi, sum and average the fault coefficients GZPi of all detection terminals P at the transmission node i to obtain the fault performance value GBi of the transmission node i, and determine whether the power transmission state of the transmission node i is abnormal through the fault performance value GBi; The detection and verification module is used to verify and analyze the fault detection results of the distribution network; The specific process of the detection and verification module verifying and analyzing the fault detection results of the distribution network includes: obtaining the detection deviation value of the transmission node, obtaining the detection deviation threshold through the storage module, comparing the detection deviation value with the detection deviation threshold, and judging whether the power transmission state of the transmission node i meets the requirements through the comparison result; the fault coefficients GZPi corresponding to the detection terminal P in all transmission nodes constitute the transmission set of the channel P, the fault coefficients GZPi corresponding to the faulty node are removed from the transmission set, and the variance of all elements in the transmission set after removal is calculated to obtain the transmission deviation value, and the transmission deviation threshold is obtained through the storage module, and the transmission deviation value is compared with the transmission deviation threshold, and judging whether the power data transmission of the channel P meets the requirements through the comparison result; The process of obtaining the detection deviation value of the transport node i includes: obtaining the fault coefficients GZPi corresponding to the detection terminals P in all transport nodes i at the end of the detection period, forming a detection set of the transport node i by the fault coefficients GZPi corresponding to all detection terminals P in the same transport node i, and performing variance calculation on all elements in the detection set to obtain the detection deviation value; The specific process of comparing the detection deviation value with the detection deviation threshold includes: if the detection deviation value is less than the detection deviation threshold, it is determined that the power data collection in the transmission node i meets the requirements, and the corresponding transmission node i is marked as a qualified node; if the detection deviation value is greater than or equal to the detection deviation threshold, it is determined that the power data collection in the transmission node i does not meet the requirements, and the corresponding transmission node i is marked as a faulty node; the faulty node is sent to the detection and positioning platform, and after receiving the faulty node, the detection and positioning platform sends the faulty node to the mobile terminal of the manager; The specific process of comparing the transmission deviation value with the transmission deviation threshold includes: if the transmission deviation value is less than the transmission deviation threshold, it is determined that the power data transmission of channel P meets the requirements; if the transmission deviation value is greater than or equal to the transmission deviation threshold, it is determined that the power data transmission of channel P does not meet the requirements, and the corresponding channel P is marked as an abnormal channel, and the abnormal channel is sent to the detection and positioning platform. After receiving the abnormal channel, the detection and positioning platform sends the abnormal channel to the mobile terminal of the administrator; By setting up multiple detection terminals on the transmission node i, and then sending the detection data of the detection terminals to the fault detection module through a dedicated channel, the accuracy of the distribution network fault detection and positioning analysis results can be improved by expanding the detection data base.

2. The distribution network fault detection and positioning system based on artificial intelligence according to claim 1 is characterized in that: The process of acquiring the flow difference data LCPi includes: acquiring the maximum current value and the minimum current value of the transmission node i during the detection period through the detection terminal P, and marking the difference between the maximum current value and the minimum current value as the flow difference value LCPi; the process of acquiring the pressure difference data YCPi includes: acquiring the maximum voltage value and the minimum voltage value of the transmission node i during the detection period through the detection terminal P, and marking the difference between the maximum voltage value and the minimum voltage value as the pressure difference value YCPi.

3. The distribution network fault detection and positioning system based on artificial intelligence according to claim 2 is characterized in that: The specific process of determining whether the power transmission state of the transmission node i is abnormal includes: obtaining the fault performance threshold GBmax through the storage module, and comparing the fault performance value GBi of the transmission node i with the fault threshold GZmax: if the fault performance value GBi is less than the fault performance threshold GBmax, then the power transmission state of the transmission node i is determined to be normal; if the fault performance value GBi is greater than or equal to the fault performance threshold GBmax, then the power transmission state of the transmission node i is determined to be abnormal, and the corresponding transmission node i is marked as an abnormal node, and the abnormal node is sent to the detection and positioning platform. After receiving the abnormal node, the detection and positioning platform sends the abnormal node to the mobile terminal of the administrator.

4. A distribution network fault detection and positioning system based on artificial intelligence according to any one of claims 1 to 3, characterized in that: The working method of the distribution network fault detection and positioning system based on artificial intelligence includes the following steps: Step 1: Detect and analyze the fault of the distribution network: mark the power network node of the distribution network as a transmission node i, i=1, 2, ..., n, n is a positive integer, set a detection terminal P at the transmission node i, P=1, 2, ..., w, w is a positive integer; the detection data of the detection terminal P is transmitted through the channel P; Step 2: Generate a detection cycle and divide the detection cycle into several detection periods, obtain the flow difference data LCPi and the pressure difference data YCPi of the transmission node i in the detection period through the detection terminal P, and perform numerical calculation to obtain the fault coefficient GZPi corresponding to the detection terminal P at the transmission node i; Step 3: sum and average the fault coefficients GZPi of all detection terminals P at the transmission node i to obtain the fault performance value GBi of the transmission node i, and determine whether the power transmission state of the transmission node i is normal based on the fault performance value GBi; Step 4: Verify and analyze the fault detection results of the distribution network and obtain a detection set. Calculate the variance of all elements in the detection set to obtain a detection deviation value. Mark the transmission node i as a qualified node or a faulty node based on the detection deviation value. Step 5: The fault coefficients GZPi corresponding to the detection terminal P in all transmission nodes constitute the transmission set of channel P, and the fault coefficients GZPi corresponding to the faulty nodes are removed from the transmission set. The variance of all elements in the transmission set after removal is calculated to obtain the transmission deviation value, and the transmission deviation value is used to determine whether the power data transmission of channel P meets the requirements.

Images