Optical cable fault diagnosis system and method
By collecting and analyzing the strike signals in the optical cable fault diagnosis system, and building optical cable positioning maps and signal intensity change maps, the problem of difficulty in accurately positioning buried optical cable faults in the existing technology is solved, and efficient and accurate fault diagnosis is achieved.
Patent Information
- Application Number
- CN202411882826.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-19
- Publication Date
- 2025-03-28
AI Technical Summary
The prior art is difficult to accurately locate the optical cable buried underground without damaging the optical cable, resulting in difficulty in on-site work.
A fiber optic cable fault diagnosis system is adopted, including a signal collection module, a fiber optic cable positioning module and a fault diagnosis module. By collecting the knock signal after hitting at the preset knock position, analyzing the signal strength and delay information, building an optical cable positioning map and a signal intensity change map, and then positioning the fault position and diagnosis.
It realizes accurate positioning of fault location without damaging the optical cable, improves the accuracy and efficiency of fault diagnosis, and reduces resource waste and labor costs.
Smart Images
Figure CN119727901A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the field of optical cable fault diagnosis, relates to optical cable maintenance monitoring technology, and specifically provides an optical cable fault diagnosis system and method. Background Art
[0002] Power communication optical cables are various types of composite cables and special optical cables used in power systems to take into account both power transmission and information communication. They are characterized by large scale, wide laying range, and high operation and maintenance pressure. Their operating status is directly related to the safety of transmission lines and communication systems.
[0003] In the prior art, on-site fault diagnosis of a faulty optical cable requires analysis of the optical cable itself. Optical cables are generally buried in the soil, and the optical cables may be damaged again during the excavation process, which is time-consuming and labor-intensive. Existing optical time domain reflectometers require direct access to the optical cable ports for testing. They work by sending short pulses of laser into the optical fiber and measuring the amount of light reflected from different positions of the optical fiber. They can detect obvious joint losses, but for optical cables buried underground, it is impossible to determine minor faults without damaging the cables, making on-site work difficult.
[0004] The present invention provides an optical cable fault diagnosis system and method to solve the above technical problems. Summary of the invention
[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an optical cable fault diagnosis system and method for solving the technical problem in the prior art that the fault cannot be accurately located without damaging the cable due to the need to operate the optical cable.
[0006] To achieve the above-mentioned object, a first aspect of the present invention provides an optical cable fault diagnosis system, comprising: a signal collection module, an optical cable positioning module and a fault diagnosis module;
[0007] Signal collection module: used to collect knocking signals generated after knocking at a preset knocking position; wherein the knocking signals include signal strength and delay information of the knocking signals;
[0008] Optical cable positioning module: used to obtain the optical cable positioning map based on the signal strength analysis in the knocking signal and locate the fault location; construct the signal strength change map based on the knocking signal data;
[0009] Fault diagnosis module: used to diagnose faults based on the optical cable positioning map and the signal strength change map to obtain fault diagnosis information.
[0010] Preferably, the obtaining of the optical cable positioning map based on the signal strength analysis in the knocking signal comprises:
[0011] Extract the signal strength of the knocking signal;
[0012] Mark the extension direction of the optical cable as the horizontal direction, sort the signal strength in the horizontal direction according to the time sequence of the knocking to obtain the sorted horizontal signal strength; determine the vertical direction and the horizontal coordinate of the fault point based on the sorted horizontal signal strength;
[0013] Tap along the vertical direction, mark the signal strength in the vertical direction as the sorted vertical signal strength, and determine the coordinates of the fault point based on the sorted vertical signal strength and the horizontal coordinate of the fault point;
[0014] The optical cable positioning map is constructed by taking the position of the first tapping as the origin, the horizontal coordinate direction as the x-axis, the horizontal tapping direction as the positive direction of the x-axis, the vertical coordinate direction as the y-axis, and the vertical tapping direction as the positive direction of the y-axis.
[0015] Preferably, the determining of the longitudinal direction and the horizontal coordinate of the fault point based on the sorted horizontal signal strengths includes:
[0016] Extract and sort the lateral signal intensity;
[0017] The sorted horizontal signal strengths are numbered as 1, 2, 3...n, respectively, where n is a positive integer;
[0018] Based on the sorted horizontal signal strength and the corresponding number, obtain the added knocking range; perform additional knocking within the added knocking range to obtain the added knocking signal strength, select the added knocking position with the largest knocking signal strength, and mark the distance between the added knocking position and the position corresponding to the sorted horizontal signal strength numbered 1 as the horizontal coordinate of the fault point;
[0019] The direction perpendicular to the horizontal direction is taken as the vertical axis, and the direction of the tapping signal received during the tapping process on the vertical axis is taken as the vertical direction.
[0020] Preferably, the method of obtaining the added knocking range based on sorting the lateral signal strengths and the corresponding serial numbers includes:
[0021] Extract and sort the horizontal signal intensity and the corresponding number;
[0022] Determine whether the horizontal signal strength of the sort numbered i is greater than the horizontal signal strength of the sort numbered i-1; if yes, mark the horizontal position state corresponding to the horizontal signal strength of the sort numbered i-1 as the reverse direction of the fault point; if no, mark the horizontal position state corresponding to the horizontal signal strength of the sort numbered i as the forward direction of the fault point;
[0023] Select the position corresponding to the sorted lateral signal strength whose lateral position status is the largest reverse number of the fault point and mark it as the reverse point near the fault point; select the position corresponding to the sorted lateral signal strength whose lateral position status is the smallest forward number of the fault point and mark it as the forward point near the fault point; mark the range between the reverse point near the fault point and the forward point near the fault point as the added knocking range.
[0024] Preferably, the determining the coordinates of the fault point based on the sorted longitudinal signal strength and the horizontal coordinate of the fault point includes:
[0025] Extract and sort the longitudinal signal strength and the horizontal coordinate of the fault point;
[0026] Sort the sorted longitudinal signal strengths in order of size, mark the distance between the knocking position corresponding to the largest sorted longitudinal signal strength and the knocking position corresponding to the sorted transverse signal strength numbered 1 as the vertical coordinate of the fault point, and combine the vertical coordinate of the fault point with the horizontal coordinate of the fault point to obtain the coordinates of the fault point.
[0027] Preferably, constructing a signal strength variation graph based on the knock signal data comprises:
[0028] Extracting the signal strength and delay information of the knocking signal; wherein the delay information includes the knocking time and time delay corresponding to the knocking signal;
[0029] With the tapping time as the horizontal axis and the signal strength of the tapping signal as the vertical axis, a time-varying graph of the signal strength at different tapping positions is constructed;
[0030] The signal strength variation graph is generated by combining the tapping position and the signal strength time variation graph.
[0031] Preferably, the step of combining the tapping position with the signal strength time variation graph to generate a signal strength variation graph includes:
[0032] A1: Extract the tapping position and signal intensity time variation diagram;
[0033] A2: Extract the slope of the signal strength time variation graph to obtain the time variation rate of the signal strength, and determine whether the time variation rate at point t is the same as the time variation rate at point t-1; if yes, mark the corresponding point t as a normal time point; if no, mark the corresponding point t as a time variation point, and jump to A3;
[0034] A3: Record the signal strength corresponding to the time change points corresponding to different tapping positions and mark them as changed signal strength. Take the first tapping position as the origin, the tapping position as the horizontal axis, and the changed signal strength as the vertical axis to construct a signal strength change graph.
[0035] Preferably, the method of diagnosing the fault based on the optical cable positioning diagram and the signal strength change diagram to obtain the fault diagnosis information includes:
[0036] B1: Extract the optical cable positioning map and signal strength change map;
[0037] B2: Determine whether the time change rate of the time change point in the signal strength change graph is greater than 0; if so, mark the corresponding time change point as a low trough time change point; if not, jump to B3;
[0038] B3: Mark the remaining two time change points as time change point A and time change point B respectively, and determine whether the time corresponding to time change point A is greater than the time corresponding to time change point B; if yes, mark time change point B as the front peak time change point, and mark time change point A as the back peak time change point; if no, mark time change point A as the front peak time change point, and mark time change point B as the back peak time change point;
[0039] B4: Divide the time between the front peak time change point and the back peak time change point to obtain the time difference, add the difference between the signal strength corresponding to the front peak time change point and the signal strength corresponding to the trough time change point and the difference between the signal strength corresponding to the back peak time change point and the signal strength corresponding to the trough time change point, and divide by two to obtain the average peak-to-valley difference, and integrate the time difference and the peak-to-valley difference to obtain the fault data;
[0040] B5: Input the fault data into the fault identification model to obtain the fault type, convert the coordinates of the fault point in the optical cable positioning map into fault location information, and integrate the fault location information with the fault type to obtain fault diagnosis information; wherein, the fault identification model is constructed based on the neural network model.
[0041] Preferably, the fault identification model is constructed based on a neural network model, including:
[0042] A large amount of historical fault data and corresponding historical fault types are extracted from the historical database, and the historical fault data and the corresponding historical fault types are used as training data and test data. The neural network model is trained by the training data, and the trained neural network model is tested by the test data. The parameters of the neural network model are adjusted according to the test results to obtain a fault recognition model with fault data as input and fault type as output.
[0043] An optical cable fault diagnosis method, applied to the above optical cable fault diagnosis system, is characterized by comprising:
[0044] Step 1: Collecting the knocking signal generated after knocking at the preset knocking position;
[0045] Step 2: Obtain the optical cable positioning map based on the signal strength analysis in the knocking signal and locate the fault position;
[0046] Step 3: Construct a signal strength change graph based on the knock signal data;
[0047] Step 4: Diagnose the fault based on the optical cable positioning diagram and the signal strength change diagram to obtain fault diagnosis information.
[0048] Compared with the prior art, the present invention has the following beneficial effects:
[0049] 1. The present invention collects the knocking signals generated after knocking at a preset knocking position, marks the direction of the optical cable as the horizontal direction, and marks the signal strength corresponding to the horizontal direction as the sorted horizontal signal strength according to the time sequence of the knocking, numbers the sorted horizontal signal strength, divides the added knocking range, adds knocking within the added knocking range, determines the longitudinal direction and the horizontal coordinate of the fault point based on the added knocking signal strength, determines the coordinates of the fault point based on the sorted longitudinal signal strength and the horizontal coordinate of the fault point, constructs an optical cable positioning map and locates the fault position, accurately locates the fault position by analyzing the time delay and intensity change of the Rayleigh scattering signal, and enhances the temporal and spatial correlation of the data; constructs a signal map based on the knocking time and the signal strength of the knocking signal The signal time change graph is extracted, the time change rate of the signal time change graph is extracted, the time change point is obtained, and the signal strength change graph is constructed in combination with the knocking position. This can accurately identify the time point when the signal strength changes significantly, which helps to accurately locate the problem and enhance data correlation and multi-dimensional analysis; according to the time change rate of the time change point in the signal strength change graph, the trough time change point, the front peak time change point and the back peak time change point are obtained, and the fault data is obtained. The fault data is input into the fault identification model to obtain the fault type, and the fault diagnosis information is obtained in combination with the fault point coordinates in the optical cable positioning map. This can more accurately capture the vibration response characteristics of different types, ensure the accuracy of the diagnosis results, help to reasonably allocate resources, and improve work efficiency.
[0050] 2. The present invention obtains the corresponding lateral position state according to the sorted lateral signal strength, determines the added knocking range based on the lateral position state, performs added knocking within the added knocking range, determines the horizontal coordinate of the fault point according to the signal strength of the added knocking, and determines the vertical direction, obtains the coordinates of the fault point based on the sorted vertical signal strength and the horizontal coordinate of the fault point, and constructs a cable positioning map, determines the added knocking range to make the test more targeted, reduces unnecessary knocking operations, improves detection efficiency, and can more accurately determine the coordinate position of the fault point. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] 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.
[0052] Figure 1 The following is a flowchart of an embodiment of the present invention.
[0053] Figure 2 A system composition diagram of an embodiment of the present invention.
[0054] Figure 3 The figure is a complete flow chart of obtaining fault data in one embodiment of the present invention. DETAILED DESCRIPTION
[0055] 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.
[0056] See also Figure 1-Figure 3 , the first aspect of the present invention provides an optical cable fault diagnosis system, including: a signal collection module, an optical cable positioning module and a fault diagnosis module;
[0057] Signal collection module: used to collect the knocking signal generated after knocking at a preset knocking position; wherein the knocking signal includes the signal strength and delay information of the knocking signal.
[0058] Exemplarily, an operator performs regular tapping operations at different locations along the optical cable to generate vibrations, and a receiver collects tapping signals caused by Rayleigh scattering after the tapping, and records the tapping time and tapping position during the tapping.
[0059] Optical cable positioning module: used to obtain the optical cable positioning map based on the signal strength analysis in the knocking signal and locate the fault location; construct the signal strength change map based on the knocking signal data.
[0060] Exemplarily, the extension direction of the optical cable is marked as the horizontal direction, and several knocks are performed along the direction of the optical cable. The signal strengths of the knocking signals received after the horizontal knocking are sorted in order from the earliest to the latest according to the time sequence of the knocking to obtain the sorted horizontal signal strengths. The sorted horizontal signal strengths are numbered 1, 2, 3...n, respectively, where n is a positive integer.
[0061] Determine whether the lateral signal strength of the sort numbered 2 is greater than the lateral signal strength of the sort numbered 1. If it is determined that the lateral signal strength of the sort numbered 2 is greater than the lateral signal strength of the sort numbered 1, it means that the distance between the knocking position corresponding to the lateral signal strength of the sort numbered 2 and the fault position is less than the distance between the knocking position corresponding to the lateral signal strength of the sort numbered 1 and the fault position. Mark the lateral position state corresponding to the lateral signal strength of the sort numbered 1 as the reverse direction of the fault point, take the lateral position state corresponding to the lateral signal strength of the sort numbered 1 as the origin, take the knocking position direction corresponding to the lateral signal strength of the sort numbered 2 in the direction of the origin as the horizontal positive direction, and the fault position is located in the horizontal positive direction of the origin; continue to determine whether the lateral signal strength of the sort numbered 3 is greater than that of the sort numbered 2 The sorted lateral signal strength is sorted until the lateral position state is the sorted lateral signal strength in the positive direction of the fault point. In this embodiment, the sorted lateral signal strength numbered 6 is less than the sorted lateral signal strength numbered 5, indicating that the horizontal coordinate of the fault position is between the knocking position corresponding to the sorted lateral signal strength numbered 6 and the knocking position corresponding to the sorted lateral signal strength numbered 5, and is closer to the knocking position of the sorted lateral signal strength numbered 5. Through the detailed analysis of the sorted lateral signal strengths and their numbers, the accuracy of determining the coordinates of the fault point is significantly improved, making the fault judgment more reliable and reducing the possibility of misjudgment. By comparing the signal strengths of adjacent numbers during knocking, the marks are dynamically adjusted to ensure that each round of knocking is purposeful, thereby improving the detection efficiency.
[0062] Select the position corresponding to the sorted lateral signal strength with the largest reverse number of the fault point in the lateral position state and mark it as the reverse point adjacent to the fault point, select the position corresponding to the sorted lateral signal strength with the smallest forward number of the fault point in the lateral position state and mark it as the forward point adjacent to the fault point; the operator adds a knock between the knock position corresponding to the sorted lateral signal strength numbered 6 and the knock position corresponding to the sorted lateral signal strength numbered 5, and obtains several added knock signal strengths, selects the added knock position with the largest added knock signal strength, and this position is closest to the fault position in the lateral direction, marks the distance between the added knock position and the position corresponding to the sorted lateral signal strength numbered 1 as the horizontal coordinate of the fault point, and the distance from the reverse point adjacent to the fault point to the forward point adjacent to the fault point is marked as the horizontal coordinate of the fault point. The horizontal direction is taken as the horizontal direction, the vertical axis is taken as the vertical axis, and the direction of the knocking signal received during the knocking process on the vertical axis is taken as the vertical direction; the horizontal direction is taken as the x-axis, the horizontal knocking direction is taken as the positive direction of the x-axis, the vertical direction is taken as the y-axis, and the vertical knocking direction is taken as the positive direction of the y-axis to construct an optical cable positioning map. The knocking range narrows the range of fault knocking, and can concentrate the test in the key area where the fault is most likely to exist, avoiding aimless and extensive testing on the entire optical cable path, concentrating resources and time to perform more detailed detection within a specific range, which can significantly improve detection efficiency and reduce unnecessary workload. Concentrated testing can also make the received signal clearer and improve the signal-to-noise ratio, thereby enhancing the reliability of the diagnosis result.
[0063] It should be noted that when collecting knocking signals in the first round, it is necessary to knock along the direction of the optical cable arrangement as much as possible, and keep the same distance from the direction of the optical cable arrangement; when adding knocking, the knocking positions between the reverse point close to the fault point and the forward point close to the fault point should be covered as much as possible to ensure that the horizontal coordinate of the fault point can be accurately found.
[0064] A signal strength time variation graph is constructed with the knocking time as the horizontal axis and the signal strength of the knocking signal as the vertical axis; the slope in the signal strength time variation graph is extracted to obtain the time change rate of the signal strength, and it is determined whether the time change rate at point t is the same as the time change rate at point t-1. In this embodiment, it is determined that the time change rate at point t in the signal strength time variation graph is different from the standard time change rate, indicating that a knocking signal from the fault position in the optical cable is received at point t. Point t is marked as a time change point, and the time point when the signal strength changes significantly is accurately identified, the time when the fault problem is detected and the corresponding changes are accurately obtained. Through the time change rate analysis, the accuracy of determining the coordinates of the fault point is significantly improved, and the time point when the signal strength changes significantly can be accurately identified.
[0065] It should be noted that during the signal transmission process, obstacles such as rocks or pipes that may exist inside the soil will affect the signal transmission process, resulting in slight fluctuations in signal strength. Therefore, when judging the time change rate between point t and point t-1, if there is a small difference, it can be ignored. Alternatively, a difference threshold can be set. If the difference is less than the difference threshold, it can be ignored. If the difference is greater than the threshold, the corresponding time point is marked as a time change point.
[0066] The signal strength corresponding to the time change points corresponding to different tapping positions is recorded and marked as the changed signal strength. The signal strength change graph is constructed with the first tapping position as the origin, the tapping position as the horizontal axis, and the changed signal strength as the vertical axis.
[0067] Fault diagnosis module: used to diagnose faults based on the optical cable positioning map and the signal strength change map to obtain fault diagnosis information.
[0068] Exemplarily, three time change points will appear in the signal strength time change graph, which are sorted in chronological order to determine whether the time change rate of the time change point is greater than 0. If the time change rate of the time change point is greater than 0, the corresponding time change point will be marked as a trough time change point. However, the time change rates of two time change points are less than 0, so the two time change points are distinguished based on their time, and the time change point closer in time is marked as the front-peak time change point, and the time change point closer in time is marked as the back-peak time change point; the time difference between the front-peak time change point and the back-peak time change point is calculated. , add the difference between the signal strength corresponding to the front peak time change point and the signal strength corresponding to the trough time change point and the difference between the signal strength corresponding to the rear peak time change point and the signal strength corresponding to the trough time change point, and divide the sum by two to get the average peak-to-valley difference, integrate the time difference and the peak-to-valley difference to get the fault data, use the time difference to estimate the fault distance, and use the average peak-to-valley difference to evaluate the fault impact, so that fault detection is more accurate, and the average peak-to-valley difference, as an indicator of fault severity, can help maintenance personnel better understand the impact range and possible consequences of the fault, so as to formulate a more reasonable maintenance plan.
[0069] A large amount of historical fault data and corresponding historical fault types are extracted from the historical database, and the historical fault data and the corresponding historical fault types are used as training data and test data. The neural network model is trained by the training data, and the trained neural network model is tested by the test data. The parameters of the neural network model are adjusted according to the test results to obtain a fault recognition model whose input data is the fault data and whose output data is the fault type; the fault data is input into the fault recognition model to obtain the corresponding fault type; the coordinates of the fault point in the optical cable positioning diagram in this embodiment are (50, 20), indicating that the fault point is 50 meters in the positive direction of the horizontal coordinate and 20 meters in the positive direction of the vertical coordinate of the first knocking position, which is converted into the fault location information as 20 meters from the first corner of the starting point of the optical cable. The fault diagnosis information is obtained by combining the fault location information and the fault type, and the fault diagnosis information is sent to the display module. The staff can perform precise maintenance on the optical cable fault according to the fault diagnosis information, and can more accurately capture different types of vibration response characteristics to ensure the accuracy of the diagnosis results.
[0070] It should be noted that if the specific location of the fault underground needs to be determined, the propagation time can be obtained by recording the difference between the time of the knocking and the time of receiving the knocking signal, and the distance L between the knocking position and the fault position can be calculated by the formula L=C×CT / 2N, and then the depth H of the fault point can be calculated in combination with the position of the fault point; where C represents the propagation speed of light, N represents the refractive index of the optical fiber, and CT represents the propagation time.
[0071] An optical cable fault diagnosis method, applied to the above optical cable fault diagnosis system, is characterized by comprising:
[0072] Step 1: Collecting the knocking signal generated after knocking at the preset knocking position;
[0073] Step 2: Obtain the optical cable positioning map based on the signal strength analysis in the knocking signal and locate the fault position;
[0074] Step 3: Construct a signal strength change graph based on the knock signal data;
[0075] Step 4: Diagnose the fault based on the optical cable positioning map and the signal strength change map to obtain fault diagnosis information.
[0076] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.
[0077] Working principle of the present invention:
[0078] The present invention collects knocking signals generated after knocking at a preset knocking position, takes the extension direction of the optical cable as the horizontal direction, and sorts the signal strength in the horizontal direction to obtain the sorted horizontal signal strength, obtains an added knocking range based on the sorted horizontal signal strength and the corresponding number, adds knocking within the added knocking range, and obtains the vertical direction of the horizontal coordinate of the fault point based on the added knocking signal strength, knocks along the vertical direction to obtain the sorted vertical signal strength, determines the coordinates of the fault point based on the sorted vertical signal strength, and constructs an optical cable positioning map; constructs a signal strength time change map according to the knocking time and signal strength, obtains the time change point according to the time change rate in the signal strength time change map, and constructs a signal strength change map, obtains the trough time change point, the front peak time change point and the rear peak time change point based on the signal strength change map, and obtains fault data based on the trough time change point, the front peak time change point and the rear peak time change point, inputs the fault data into a fault recognition model to obtain the fault type, and obtains fault diagnosis information in combination with the fault point coordinates in the optical cable positioning map.
[0079] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.
Claims
1. An optical cable fault diagnosis system, characterized in that: include: Signal collection module, optical cable positioning module and fault diagnosis module; Signal collection module: used to collect knocking signals generated after knocking at a preset knocking position; wherein the knocking signals include signal strength and delay information of the knocking signals; Optical cable positioning module: used to obtain the optical cable positioning map based on the signal strength analysis in the knocking signal and locate the fault location; construct the signal strength change map based on the knocking signal data; Fault diagnosis module: used to diagnose faults based on the optical cable positioning map and the signal strength change map to obtain fault diagnosis information.
2. An optical cable fault diagnosis system according to claim 1, characterized in that: The method of obtaining the optical cable positioning map based on the signal strength analysis in the knocking signal includes: Extracting the signal strength of the knocking signal; Mark the extension direction of the optical cable as the horizontal direction, sort the signal strength in the horizontal direction according to the time sequence of the knocking to obtain the sorted horizontal signal strength; determine the vertical direction and the horizontal coordinate of the fault point based on the sorted horizontal signal strength; Tap along the vertical direction, mark the signal strength in the vertical direction as the sorted vertical signal strength, and determine the coordinates of the fault point based on the sorted vertical signal strength and the horizontal coordinate of the fault point; The optical cable positioning map is constructed by taking the position of the first tapping as the origin, the horizontal coordinate direction as the x-axis, the horizontal tapping direction as the positive direction of the x-axis, the vertical coordinate direction as the y-axis, and the vertical tapping direction as the positive direction of the y-axis.
3. An optical cable fault diagnosis system according to claim 2, characterized in that: The determining of the longitudinal direction and the horizontal coordinate of the fault point based on the sorted horizontal signal strengths includes: Extract and sort the lateral signal intensity; The sorted lateral signal strengths are numbered as 1, 2, 3...n, respectively, where n is a positive integer; Based on the sorted horizontal signal strength and the corresponding number, obtain the added knocking range; perform additional knocking within the added knocking range to obtain the added knocking signal strength, select the added knocking position with the largest knocking signal strength, and mark the distance between the added knocking position and the position corresponding to the sorted horizontal signal strength numbered 1 as the horizontal coordinate of the fault point; The direction perpendicular to the horizontal direction is taken as the vertical axis, and the direction of the tapping signal received during the tapping process on the vertical axis is taken as the vertical direction.
4. An optical cable fault diagnosis system according to claim 3, characterized in that: The method of obtaining the added knocking range based on sorting the lateral signal strength and the corresponding serial number includes: Extract and sort the horizontal signal intensity and the corresponding number; Determine whether the horizontal signal strength of the sort numbered i is greater than the horizontal signal strength of the sort numbered i-1; if yes, mark the horizontal position state corresponding to the horizontal signal strength of the sort numbered i-1 as the reverse direction of the fault point; if no, mark the horizontal position state corresponding to the horizontal signal strength of the sort numbered i as the forward direction of the fault point; Select the position corresponding to the sorted lateral signal strength whose lateral position status is the largest reverse number of the fault point and mark it as the reverse point near the fault point; select the position corresponding to the sorted lateral signal strength whose lateral position status is the smallest forward number of the fault point and mark it as the forward point near the fault point; mark the range between the reverse point near the fault point and the forward point near the fault point as the added knocking range.
5. The optical cable fault diagnosis system according to claim 2, characterized in that: The determining of the coordinates of the fault point based on the sorted longitudinal signal strength and the horizontal coordinate of the fault point includes: Extract and sort the longitudinal signal strength and the horizontal coordinate of the fault point; Sort the sorted longitudinal signal strengths in order of size, mark the distance between the knocking position corresponding to the largest sorted longitudinal signal strength and the knocking position corresponding to the sorted transverse signal strength numbered 1 as the vertical coordinate of the fault point, and combine the vertical coordinate of the fault point with the horizontal coordinate of the fault point to obtain the coordinates of the fault point.
6. The optical cable fault diagnosis system according to claim 1, characterized in that: The step of constructing a signal strength variation graph based on the knock signal data includes: Extracting the signal strength and delay information of the knocking signal; wherein the delay information includes the knocking time and time delay corresponding to the knocking signal; With the tapping time as the horizontal axis and the signal strength of the tapping signal as the vertical axis, a time-varying graph of the signal strength at different tapping positions is constructed; The signal strength variation graph is generated by combining the tapping position and the signal strength time variation graph.
7. An optical cable fault diagnosis system according to claim 6, characterized in that: The signal strength variation graph is generated by combining the tapping position and the signal strength time variation graph, including: A1: Extract the tapping position and signal intensity time variation diagram; A2: Extract the slope of the signal strength time variation graph to obtain the time variation rate of the signal strength, and determine whether the time variation rate at point t is the same as the time variation rate at point t-1; if yes, mark the corresponding point t as a normal time point; if no, mark the corresponding point t as a time variation point, and jump to A3; A3: Record the signal strength corresponding to the time change points corresponding to different tapping positions and mark them as changed signal strength. Take the first tapping position as the origin, the tapping position as the horizontal axis, and the changed signal strength as the vertical axis to construct a signal strength change graph.
8. The optical cable fault diagnosis system according to claim 1, characterized in that: The method of diagnosing the fault based on the optical cable positioning diagram and the signal strength change diagram to obtain the fault diagnosis information includes: B1: Extract the optical cable positioning map and signal strength change map; B2: Determine whether the time change rate of the time change point in the signal strength change graph is greater than 0; if so, mark the corresponding time change point as a low trough time change point; if not, jump to B3; B3: Mark the remaining two time change points as time change point A and time change point B respectively, and determine whether the time corresponding to time change point A is greater than the time corresponding to time change point B; if yes, mark time change point B as the front peak time change point, and mark time change point A as the back peak time change point; if no, mark time change point A as the front peak time change point, and mark time change point B as the back peak time change point; B4: Divide the time between the front peak time change point and the back peak time change point to obtain the time difference, add the difference between the signal strength corresponding to the front peak time change point and the signal strength corresponding to the trough time change point and the difference between the signal strength corresponding to the back peak time change point and the signal strength corresponding to the trough time change point, and divide by two to obtain the average peak-to-valley difference, and integrate the time difference and the peak-to-valley difference to obtain the fault data; B5: Input the fault data into the fault identification model to obtain the fault type, convert the coordinates of the fault point in the optical cable positioning map into fault location information, and integrate the fault location information with the fault type to obtain fault diagnosis information; wherein, the fault identification model is constructed based on the neural network model.
9. An optical cable fault diagnosis system according to claim 8, characterized in that: The fault identification model is constructed based on a neural network model and includes: A large amount of historical fault data and corresponding historical fault types are extracted from the historical database, and the historical fault data and the corresponding historical fault types are used as training data and test data. The neural network model is trained by the training data, and the trained neural network model is tested by the test data. The parameters of the neural network model are adjusted according to the test results to obtain a fault recognition model with fault data as input and fault type as output.
10. An optical cable fault diagnosis method, applied to an optical cable fault diagnosis system as claimed in any one of claims 1 to 9, characterized in that: include: Step 1: Collecting the knocking signal generated after knocking at the preset knocking position; Step 2: Obtain the optical cable positioning map based on the signal strength analysis in the knocking signal and locate the fault position; Step 3: Construct a signal strength change graph based on the knock signal data; Step 4: Diagnose the fault based on the optical cable positioning diagram and the signal strength change diagram to obtain fault diagnosis information.