Intelligent cable fault positioning diagnosis platform and method

Abstract

The invention discloses an intelligent cable fault positioning diagnosis platform and method, and particularly relates to the technical field of fault positioning diagnosis, and the method comprises the following steps: collecting fault information which comprises cable temperature, environment temperature, cable original resistance value and cable resistance value; calculating a risk coefficient of a cable fault by using a logistic regression algorithm according to the fault information; the time domain reflectometer is used for determining a risk coefficient of a fault of the cable, and when the risk coefficient of the fault of the cable is greater than a set threshold value, the time domain reflectometer emits an electronic pulse, records a high-frequency pulse signal propagation speed and high-frequency pulse signal propagation time, calculates the distance from a fault point to the positioning module, and receives returned pulse information; determining fault information and pulse information, integrating the fault information and the pulse information, and calculating a cable fault reason by using a K-nearest neighbor algorithm; and determining the cause of the cable fault, comparing from the maintenance information database, and screening out proper maintenance information.

Description

Technical Field

[0001] The present invention relates to the field of fault location diagnosis, and more specifically, to an intelligent cable fault location diagnosis platform and method. Background Art

[0002] Cables include: power cables, control cables, compensation cables, shielded cables, high temperature cables, computer cables, signal cables, mining cables, aluminum alloy cables, etc. They are all composed of single or multiple strands of wires and insulation layers, used to connect circuits, electrical appliances, etc.

[0003] With the development of smart grid technology, the demand for rapid fault location and diagnosis is becoming increasingly urgent. Smart power systems need to improve reliability, stability and efficiency through real-time monitoring and data analysis.

[0004] The prior art has the following deficiencies:

[0005] In the past, when fault detection was performed on cables, it was not possible to monitor the cable operation status in real time; the cable operation status was detected at intervals, and the alarm was not issued in time when a cable fault occurred.

[0006] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide an intelligent cable fault location and diagnosis platform and method to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A fault location diagnosis platform and method, comprising the following steps:

[0010] Step S1: Collect fault information, including cable temperature, ambient temperature, original cable resistance, and cable resistance. The risk factor of cable failure is calculated by using a logistic regression algorithm based on the comprehensive fault information.

[0011] Step S2: determining the risk factor of cable failure. When the risk factor of cable failure is greater than a set threshold, the time domain reflectometer emits an electronic pulse, records the propagation speed and propagation time of the high-frequency pulse signal, calculates the distance between the fault point and the positioning module, and receives the return pulse information.

[0012] Step S3: determining fault information and pulse information, and using a K-nearest neighbor algorithm to infer the cause of the cable fault based on the fault information and pulse information;

[0013] Step S4: Determine the cause of the cable fault, compare it with the maintenance information database, and filter out appropriate maintenance information.

[0014] In a preferred embodiment, in step S1, the fault information is collected; the ambient temperature, cable temperature, cable resistance, and original cable resistance are calibrated as W1, W2, R1, and R2, respectively, and the logistic regression algorithm P=1-e is used. -(T1W+T2R) The risk coefficient of cable failure is determined, where P is the risk coefficient of cable failure, W is the temperature difference between the cable temperature and the ambient temperature, W = |W2-W1|; R is the change in cable resistance and the original cable resistance, R = |R2-R1|, and T1 and T2 are the regression coefficients of each variable.

[0015] In a preferred embodiment, in step S2, the fault risk coefficient is confirmed. When the fault risk coefficient P is greater than the maximum threshold set by the system, a signal is sent to the time domain reflectometer to record the propagation speed and propagation time of the high-frequency pulse signal. The propagation speed and propagation time of the high-frequency pulse signal are calibrated as v and t respectively, and the distance to the fault point is calculated by the following formula: D = (v*t) / 2, where D is the distance between the fault point and the positioning module;

[0016] When the fault risk coefficient P is less than the maximum threshold set by the system, no signal is sent to the time domain reflectometer.

[0017] In a preferred embodiment, in step S1, the fault information and pulse information are matched with the cable model in the software database, and the cause of the cable fault is queried and marked. If the cause of the cable fault is not recorded in the software database, the fault information and pulse information are obtained;

[0018] The software database stores fault information, pulse information and causes of cable faults.

[0019] In a preferred embodiment, in step S3, the received fault information and pulse information are combined into a pulse signal data set, and the fault information is combined into a fault information data set, and the cause of the cable fault is inferred using a K-nearest neighbor algorithm. The specific steps are as follows:

[0020] Define input and output: set pulse information and electrical fault information as input features, and set the cause of cable fault as output feature;

[0021] Select parameter K: Set a parameter K, which can be obtained by taking the average value of pulse information and fault information and multiplying it by the preset reference ratio;

[0022] Determine the cause of the fault: select the pulse information and fault information corresponding to the same type of cable in the pulse signal data set and the fault information data set and take the average value as the nearest neighbor distance;

[0023] Find K nearest neighbors: take the average value of the input features as the feature average value, select the marked cable models with K nearest neighbor distances closest to the feature average value, obtain the cable fault causes of the K nearest neighbor distances and select the average value as the candidate cable fault cause corresponding to the K value;

[0024] Prediction output: Set multiple different K values ​​through a preset number of repetitions and obtain multiple candidate fault causes, calculate their average value and output it as the cause of the cable fault.

[0025] In a preferred embodiment, in step S4, after the cause of the cable fault is confirmed, the cause of the cable fault is compared with the data in the database, and maintenance information that matches the cause of the cable fault is searched for, and the relevant maintenance information and the cause of the fault are transmitted to the monitoring terminal.

[0026] In a preferred embodiment, it includes a fault information collection module, a fault risk coefficient calculation module, a positioning module, a fault analysis module, a maintenance information recommendation module, and a monitoring terminal;

[0027] The fault information collection module receives fault information, including ambient temperature, cable temperature, cable resistance, and original cable resistance; and transmits the fault information to the fault risk coefficient calculation module;

[0028] The fault risk coefficient calculation module collects fault information and generates a cable fault risk coefficient;

[0029] After obtaining the cable failure risk coefficient, the positioning module determines whether the cable failure risk coefficient is greater than the maximum threshold set by the system. If it is greater than the maximum threshold set by the system, the positioning module sends a signal to enable the time domain reflectometer to work, record the pulse signal propagation speed and pulse signal propagation time, and calculate the specific location information of the point when the fault occurs; when the cable failure risk coefficient received by the positioning module is less than the maximum threshold set by the system, a signal is sent to the time domain reflectometer; the specific location information of the fault point is sent to the monitoring terminal;

[0030] The fault analysis module obtains the fault information and pulse information, generates the cause of the fault according to the pulse signal and the fault information, and sends the cause of the fault to the maintenance information recommendation module and the monitoring terminal respectively;

[0031] The maintenance information recommendation module selects appropriate maintenance information according to the cause of the fault and sends the maintenance information to the monitoring terminal;

[0032] The monitoring terminal is used to display the cause of the fault, the specific location information of the fault point, and maintenance information.

[0033] The technical effects and advantages of an intelligent cable fault location diagnosis platform and method of the present invention are as follows:

[0034] The present invention confirms the cable temperature, ambient temperature, original cable resistance and cable resistance, and comprehensively calculates the risk factor of cable failure; detects the cable operation status in real time and finds the cable failure in time.

[0035] The present invention determines whether a cable fault occurs by measuring the risk factor of the cable fault. If a fault occurs, a high-frequency pulse is emitted to obtain the propagation speed and propagation time of the high-frequency pulse signal, and the distance of the fault is calculated according to the propagation speed and propagation time of the high-frequency pulse signal, and the reflected pulse signal is received at the same time; the cause of the cable fault is analyzed by comprehensively analyzing the amplitude and frequency included in the reflected pulse signal with the cable temperature, ambient temperature, original resistance value of the cable, and cable resistance value;

[0036] Filter maintenance information according to the cause of the cable fault; and display the maintenance information, cable temperature, ambient temperature, original cable resistance, cable resistance, and distance from the fault on the monitoring terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0038] Figure 1 This is a flow chart of an intelligent cable fault location and diagnosis method of the present invention;

[0039] Figure 2 The present invention is a structural schematic diagram of an intelligent cable fault location and diagnosis platform. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0041] Example 1

[0042] The present invention provides Figure 2 An intelligent cable fault location and diagnosis platform shown includes a fault information collection module, a fault risk coefficient calculation module, a location module, a fault analysis module, a maintenance information recommendation module, and a monitoring terminal;

[0043] The fault information acquisition module detects the cable status in real time and receives fault information, including ambient temperature, cable temperature, cable resistance, and original cable resistance. The infrared temperature sensor points the infrared temperature sensor to the cable surface, measures the radiation temperature of the cable, and collects the cable temperature. The thermocouple temperature sensor is exposed to the environment and collects the ambient temperature. The resistance detection sensor applies a small alternating current (generally a low-frequency signal) and measures the voltage at both ends of the cable, and uses Ohm's law (R=U / I) to indirectly derive the cable resistance value and collect the cable resistance. The original resistance value of the cable is input independently according to different types of cables.

[0044] The fault risk coefficient calculation module collects fault information; the ambient temperature, cable temperature, cable resistance, and original cable resistance are calibrated as W1, W2, R1, and R2 respectively, and the logistic regression algorithm P=1-e is used. -(T1W+T2R) Determine the risk coefficient of cable failure, where P is the risk coefficient of cable failure, W is the temperature difference between the cable temperature and the ambient temperature, W = |W2-W1|, the larger the W is, the greater the temperature difference between the cable temperature and the ambient temperature is, the greater the risk coefficient of cable failure is, otherwise the smaller the risk coefficient of cable failure is; R is the change between the cable resistance and the original cable resistance, R = |R2-R1|, the larger the R is, the greater the difference between the cable resistance and the original resistance is; the greater the difference between the cable resistance and the original resistance is, the greater the risk coefficient of cable failure is, otherwise the smaller the risk coefficient of cable failure is; T1 and T2 are the regression coefficients of each variable (the larger the coefficient is, the greater the risk coefficient of cable failure is);

[0045] The acquired fault information and the risk factor of the cable failure are packaged and sent to the fault analysis module via wireless communication, and the risk factor of the cable failure is sent to the fault location module via wireless communication.

[0046] Fault location module, when the cable fault risk factor P received by the location module is greater than the maximum threshold set by the system, the location module sends a signal to make the time domain reflectometer work, emit a high-frequency pulse signal, and record the propagation speed and propagation time of the high-frequency pulse signal at the same time, and calibrate the propagation speed and propagation time of the high-frequency pulse signal as v and t respectively, and calculate the distance to the fault point by the following formula: D = (v*t) / 2, where D is the distance between the fault point and the location module;

[0047] When the cable failure risk factor P received by the positioning module is less than the maximum threshold set by the system, no signal is sent to the time domain reflectometer.

[0048] The time domain reflectometer contains a pulse generating circuit, which is usually a pulse generator controlled by a fast switch (such as a transistor or field effect tube). When the positioning module starts working, the pulse generator generates a short-time broadband electrical pulse. This pulse signal is usually a very short voltage pulse with a duration of nanoseconds (usually 1-100 nanoseconds). These pulses have a certain amplitude and a specific waveform. The generated pulse signal is sent to the line or line to be tested through the transmission line. The pulse propagates along the test line until it encounters an impedance mismatch, such as a joint, an open circuit or a short circuit. When the pulse signal encounters an impedance mismatch, part of the signal will be reflected back to the positioning module. The reflected signal will vary depending on the different impedance mismatches. For example, an open circuit will produce a strong reflection signal, while a short circuit may cause a different reflection pattern. The reflected pulse information is received, which includes frequency, amplitude, and phase.

[0049] It can be seen from the formula that when the propagation time of the high-frequency pulse signal remains unchanged, the faster the propagation speed of the high-frequency pulse signal is, the farther the distance between the fault point and the positioning module is, and vice versa; when the propagation speed of the high-frequency pulse signal remains unchanged, the longer the propagation time of the high-frequency pulse signal is, the farther the distance between the fault point and the positioning module is, and vice versa;

[0050] The location of the fault point can be accurately determined based on the distance between the fault point and the positioning module. For example, when the calculated distance between the fault point and the positioning module is one kilometer, since the position of the positioning module is fixed, the cable fault point is one kilometer along the cable direction. The maintenance personnel can accurately find the cable fault point for maintenance; at the same time, the reflected pulse signal is received, and the reflected pulse signal is sent to the fault analysis module via wireless communication, and the precisely located location information is sent to the monitoring terminal for display via wireless communication.

[0051] Fault analysis module, the fault analysis module is set in the network server, and transmits data through wireless communication; the fault analysis module receives the fault information and pulse information, merges the pulse signal into a pulse signal data set, merges the fault information into a fault information data set, and uses the K-nearest neighbor algorithm to infer the cause of the cable fault. The specific steps are as follows:

[0052] Define input and output: set pulse information and electrical fault information as input features, and set the cause of the cable fault as output features; it should be explained that both input features and output features are de-unitized data.

[0053] Select parameter K: Set a parameter K, which can be obtained by multiplying the average value of frequency, amplitude and cable temperature, ambient temperature, original cable resistance, and cable resistance by the preset reference ratio;

[0054] Determine the cause of the fault: select the pulse information and fault information corresponding to the same type of cable in the pulse signal data set and the fault information data set and take the average value as the nearest neighbor distance;

[0055] Find K nearest neighbors: take the average value of the input features as the feature average value, select the marked cable models with K nearest neighbor distances closest to the feature average value, obtain the cable fault causes of the K nearest neighbor distances and select the average value as the candidate cable fault cause corresponding to the K value;

[0056] Prediction output: Set multiple different K values ​​through a preset number of repetitions and obtain multiple candidate fault causes, calculate their average value and output it as the cause of the cable fault.

[0057] The cause of the cable fault is marked and entered into the software database together with the fault information and pulse information.

[0058] It should be noted that the software database involved in this example is a database that stores fault information, pulse information and the cause of the fault. It is mainly used to match and identify the acquired fault information and pulse information with the fault information and pulse information in the database. The K-nearest neighbor algorithm is a supervised learning algorithm that can be used for classification and regression tasks. The K-nearest neighbor algorithm can quickly calculate the output based on the pulse signal and fault information as input features and the comparison features in the software database. It is fast and convenient, and greatly saves the time cost of calculating the cause of the cable fault. The value of the parameter K and the number of repetitions of the set K value in the predicted output can be set according to the user's required accuracy requirements, and the setting method is not unique; the pulse signal data set and the fault information data set are pure digital sets that do not contain units.

[0059] The maintenance information recommendation module is set in the network server. After receiving the cause of the cable fault through wireless communication, the maintenance information recommendation module compares the cause of the cable fault with the data in the database, searches for maintenance information that matches the cause of the cable fault, and transmits the relevant maintenance information and the cause of the fault to the monitoring terminal to facilitate maintenance personnel to perform maintenance.

[0060] The monitoring terminal includes an alarm module, a display module and an input module. When the fault information is transmitted to the monitoring terminal, the alarm module flashes and starts to alarm to remind the maintenance personnel; the display module is an LED screen, which is used to display the received fault location information, fault cause and maintenance information on the screen, so as to facilitate the maintenance personnel to find the fault and perform repairs; the input module is a keyboard that can be used for typing, which is connected to the database in the maintenance information recommendation module; it is used to input the maintenance information of the maintenance personnel into the database of the maintenance information recommendation module, and is used to supplement the database in the maintenance information recommendation module, so that the maintenance information pushed by the maintenance information recommendation module is more comprehensive.

[0061] The present invention confirms the cable temperature, the ambient temperature, the original resistance of the cable, and the cable resistance, and comprehensively calculates the cable failure risk coefficient based on the cable temperature, the ambient temperature, the original resistance of the cable, and the cable resistance.

[0062] Confirm whether the cable has a fault based on the cable fault risk factor. If a fault occurs, emit a high-frequency pulse to obtain the high-frequency pulse signal propagation speed and high-frequency pulse signal propagation time, calculate the fault distance based on the high-frequency pulse signal propagation speed and high-frequency pulse signal propagation time, and receive the reflected pulse signal at the same time; analyze the cause of the cable fault based on the amplitude and frequency included in the reflected pulse signal, the cable temperature, the ambient temperature, the original resistance of the cable, and the cable resistance;

[0063] Filter maintenance information according to the cause of the cable fault; and display the maintenance information, cable temperature, ambient temperature, original cable resistance, cable resistance, and distance from the fault on the monitoring terminal.

[0064] Example 2

[0065] The present invention provides Figure 1 An intelligent cable fault location and diagnosis method is shown, comprising the following steps:

[0066] Step S1: Collect fault information, including cable temperature, ambient temperature, original cable resistance, and cable resistance. The risk factor of cable failure is calculated by using a logistic regression algorithm based on the comprehensive fault information.

[0067] Step S2: Determine the risk factor of cable failure. When the risk factor of cable failure is greater than a set threshold, the time domain reflectometer emits an electronic pulse, records the propagation speed and propagation time of the high-frequency pulse signal, calculates the distance between the fault point and the positioning module, and receives the return pulse information.

[0068] Step S3: determining fault information and pulse information, and using a K-nearest neighbor algorithm to infer the cause of the cable fault based on the fault information and pulse information;

[0069] Step S4: Determine the cause of the cable fault, compare it with the maintenance information database, and filter out appropriate maintenance information.

[0070] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0071] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as 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 devices or units, which can be electrical, mechanical or other forms.

[0072] 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 network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0073] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0074] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent cable fault location and diagnosis method, characterized in that: The following steps are involved: Step S1: Collect fault information, including cable temperature, ambient temperature, original cable resistance, and cable resistance. The risk factor of cable failure is calculated by using a logistic regression algorithm based on the comprehensive fault information. Step S2: Determine the risk factor of cable failure. When the risk factor of cable failure is greater than a set threshold, the time domain reflectometer emits an electronic pulse, records the propagation speed and propagation time of the high-frequency pulse signal, calculates the distance between the fault point and the positioning module, and receives the return pulse information. Step S3: determining fault information and pulse information, and using a K-nearest neighbor algorithm to infer the cause of the cable fault based on the fault information and pulse information; Step S4: Determine the cause of the cable fault, compare it with the maintenance information database, and filter out appropriate maintenance information.

2. The intelligent cable fault location and diagnosis method according to claim 1, characterized in that: In step S1, the fault information is collected; the ambient temperature, cable temperature, cable resistance, and original cable resistance are calibrated as W1, W2, R1, and R2, respectively, and the logistic regression algorithm P=1-e is used. -(T1W+T2R) Determine the risk factor of cable failure, where P is the risk factor of cable failure, W is the temperature difference between the cable temperature and the ambient temperature, W = |W2-W1|; R is the change between the cable resistance and the original cable resistance, R = |R2-R1|, T1 and T2 are the regression coefficients of each variable.

3. The intelligent cable fault location and diagnosis method according to claim 1, characterized in that: In step S2, the fault risk coefficient is confirmed. When the fault risk coefficient P is greater than the maximum threshold set by the system, a signal is sent to the time domain reflectometer to record the propagation speed and propagation time of the high-frequency pulse signal. The propagation speed and propagation time of the high-frequency pulse signal are calibrated as v and t respectively, and the distance to the fault point is calculated by the following formula: D = (v*t) / 2, where D is the distance between the fault point and the positioning module; When the fault risk coefficient P is less than the maximum threshold set by the system, no signal is sent to the time domain reflectometer.

4. The intelligent cable fault location and diagnosis method according to claim 1, characterized in that: In step S1, the fault information and pulse information are matched with the cable model in the software database, and the cause of the cable fault is queried and marked. If the cause of the cable fault is not recorded in the software database, the fault information and pulse information are obtained; The software database stores fault information, pulse information and causes of cable faults.

5. The intelligent cable fault location and diagnosis method according to claim 4, characterized in that: In step S3, the received fault information and pulse information are combined into a pulse signal data set, and the fault information is combined into a fault information data set. The cause of the cable fault is inferred using the K-nearest neighbor algorithm. The specific steps are as follows: Define input and output: set pulse information and electrical fault information as input features, and set the cause of cable fault as output feature; Select parameter K: Set a parameter K, which can be obtained by taking the average value of pulse information and fault information and multiplying it by the preset reference ratio; Determine the cause of the fault: select the pulse information and fault information corresponding to the same type of cable in the pulse signal data set and the fault information data set and take the average value as the nearest neighbor distance; Find K nearest neighbors: take the average value of the input features as the feature average value, select the marked cable models with K nearest neighbor distances closest to the feature average value, obtain the cable fault causes of the K nearest neighbor distances and select the average value as the candidate cable fault cause corresponding to the K value; Prediction output: Set multiple different K values ​​through a preset number of repetitions and obtain multiple candidate fault causes, calculate their average value and output it as the cause of the cable fault.

6. The intelligent cable fault location and diagnosis method according to claim 1, characterized in that: In step S4, after the cause of the cable fault is confirmed, the cause of the cable fault is compared with the data in the database, and maintenance information matching the cause of the cable fault is searched, and the relevant maintenance information and the cause of the fault are transmitted to the monitoring terminal.

7. An intelligent cable fault location and diagnosis platform, used to implement an intelligent cable fault location and diagnosis method according to any one of claims 1 to 6, characterized in that: It includes fault information collection module, fault risk coefficient calculation module, positioning module, fault analysis module, maintenance information recommendation module and monitoring terminal; Fault information collection module, receiving fault information, including ambient temperature, cable temperature, cable resistance, and original cable resistance; Transmitting fault information to a fault risk coefficient calculation module; The fault risk coefficient calculation module collects fault information and generates a cable fault risk coefficient; After obtaining the cable failure risk coefficient, the positioning module determines whether the cable failure risk coefficient is greater than the maximum threshold set by the system. If it is greater than the maximum threshold set by the system, the positioning module sends a signal to enable the time domain reflectometer to work, record the pulse signal propagation speed and pulse signal propagation time, and calculate the specific location information of the point when the fault occurs; when the cable failure risk coefficient received by the positioning module is less than the maximum threshold set by the system, a signal is sent to the time domain reflectometer; the specific location information of the fault point is sent to the monitoring terminal; The fault analysis module obtains the fault information and pulse information, and generates the cause of the fault according to the pulse signal and fault information; Send the cause of the fault to the maintenance information recommendation module and the monitoring terminal respectively; The maintenance information recommendation module selects appropriate maintenance information according to the cause of the fault and sends the maintenance information to the monitoring terminal; The monitoring terminal is used to display the cause of the fault, the specific location information of the fault point, and maintenance information.

Images