CN116647272A - Method for determining alarm position based on autonomous learning - Google Patents
Method for determining alarm position based on autonomous learning Download PDFInfo
- Publication number
- CN116647272A CN116647272A CN202310411505.6A CN202310411505A CN116647272A CN 116647272 A CN116647272 A CN 116647272A CN 202310411505 A CN202310411505 A CN 202310411505A CN 116647272 A CN116647272 A CN 116647272A
- Authority
- CN
- China
- Prior art keywords
- event
- test
- line
- optical fiber
- otdr
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Optical Communication System (AREA)
Abstract
The application provides a method for determining an alarm position based on autonomous learning, which is applied to an OTDR module in optical cable monitoring, and comprises the following steps: based on the OTDR module, establishing an optical fiber line event feature information database through an autonomous learning algorithm; the OTDR module is configured with a standard curve; the standard curve represents the initial state of the line to be tested and comprises test parameters for carrying out OTDR test on the line to be tested and a threshold value for alarming the optical cable line; and when the line to be tested fails, determining an alarm position according to the optical fiber line event characteristic information database. The application can avoid the problem of inaccurate positioning of the fault point of the optical fiber line caused by the uncertainty of the OTDR module on event identification under the condition of not increasing the time spent on detecting the fault point of the optical fiber line, and can improve the accuracy of the fault positioning of the optical fiber line.
Description
Technical Field
The application relates to the technical field of optical cable monitoring, in particular to a method for determining an alarm position based on autonomous learning.
Background
Laser is transmitted in the optical fiber, rayleigh scattering and Fresnel reflection can occur, and an OTDR technology obtains optical fiber line attenuation and link conditions by detecting the Rayleigh scattering and the Fresnel reflection. In the optical cable monitoring system, an optical cable line is monitored by using an OTDR technology, and the general method is that the initial state of the line is obtained through an OTDR test at the beginning of opening the optical fiber line, the initial state is used as a standard curve to be configured into equipment, then the line is subjected to a cyclic test by using the same parameters, the test result is compared with the standard curve, and the fault position can be timely and accurately detected when the optical cable line breaks down.
In order to find out the fault position of the optical fiber line in time, an OTDR module for optical cable monitoring generally only adopts one pulse width for testing. In a complex line, the optical fiber fusion points or connectors are relatively close to each other, the performance on the OTDR curve is that loss points are relatively dense, if only one pulse width test is adopted, event missing report and false report can occur, and the insertion loss calculation is inaccurate. The method is characterized in that uncertainty exists in identification of certain events by an OTDR algorithm during multiple loop tests. And particularly, if the event point is not reported or the insertion loss is calculated inaccurately, the event information obtained by the current test is directly compared with the event of the standard curve, and an error analysis result is caused when the optical cable breaks down.
Disclosure of Invention
In order to overcome the defects of the prior art, the application aims to provide a method for determining the alarm position based on autonomous learning, which can avoid the problem of inaccurate positioning of the fault point of the optical fiber line caused by the uncertainty of the OTDR module on event identification under the condition of not increasing the time consumed for detecting the fault point of the optical fiber line and can improve the accuracy of the fault positioning of the optical fiber line.
In order to achieve the above object, the present application provides the following solutions:
a method for determining an alarm position based on autonomous learning, applied to an OTDR module in optical cable monitoring, the method comprising:
based on the OTDR module, establishing an optical fiber line event feature information database through an autonomous learning algorithm; the OTDR module is configured with a standard curve; the standard curve represents the initial state of the line to be tested and comprises test parameters for carrying out OTDR test on the line to be tested and a threshold value for alarming the optical cable line;
and when the line to be tested fails, determining an alarm position according to the optical fiber line event characteristic information database.
Preferably, the establishing, based on the OTDR module, a fiber line event feature information database through an autonomous learning algorithm includes:
performing OTDR test on the optical fiber line by using the OTDR module, and storing a test result in the OTDR module as the standard curve;
selecting a group of test pulse widths according to the measuring range of the standard curve; the number of the test pulse widths of the group is M, and each test pulse width is tested N times;
taking the event position as a unique identifier, establishing a buffer area for the insertion loss of each event, wherein the buffer unit SIZE buf_size=m×n;
counting the maximum value, the minimum value and the average value of the interpolation loss in the buffer area;
defining an insertion loss invalid value identifier, an event disappearance identifier and a cache area storage index;
acquiring the characteristic information of the whole line by utilizing the OTDR module through automatic learning; the automatic learning process is as follows: performing multiple tests by using the test pulse width based on the OTDR module, obtaining fiber line characteristic information from a test result, and updating a buffer area according to the fiber line characteristic information to obtain the fiber line event characteristic information database; the total test times are BUF_SIZE times until the whole test buffer area is filled;
in the learning process, each event in each test result is processed according to the following steps:
updating insertion loss in a buffer area by using insertion loss of an event obtained by current test, if the insertion loss of the current event is invalid or can not be calculated, writing an identification of the insertion loss invalid value in the position of the index stored in the buffer area, and if the insertion loss of the current event is valid, filling an event insertion loss value in the position of the index stored in the buffer area, wherein index=index+1;
updating statistics of effective insertion loss in the cache area: maximum, minimum and average;
checking the buffer area, and processing the event which does not exist in the current test result but exists in the database according to the following steps: filling event disappearance identification in the position of the storage index of the buffer area: event_fade_flag, index=index+1;
if index > = buf_size, this phase ends and all event information characteristic information is stored in the OTDR module.
Preferably, when the line to be tested fails, determining an alarm position according to the optical fiber line event feature information database includes:
carrying out OTDR test on the line to be tested by using the OTDR module, and storing a test result in the OTDR module as a standard curve;
based on an OTDR module, performing cyclic OTDR test on the line to be tested by using parameters of a standard curve;
when the line loss to be measured exceeds the alarm threshold, all events in the OTDR test are processed according to the following steps to determine the fault position of the optical fiber line:
retrieving the event feature information from the fiber circuit event feature information database according to the current event position;
if the event feature information does not exist, judging that the event belongs to a new event, wherein the insertion loss of the new event exceeds an alarm threshold, if the event position is an optical fiber line fault, otherwise, jumping to a step of searching the event feature information from the optical fiber line event feature information database according to the current event position, and continuing to judge the next event;
if the event characteristic information exists, calculating the difference between the event insertion loss obtained by the current test and the insertion loss average value in the optical fiber line event characteristic information database, wherein the value of the difference is larger than an alarm threshold value, and the event point is the optical fiber fault position; otherwise, jumping to the step of judging the next event according to the current event position;
traversing all alarm events, and defining the alarm event with the highest alarm level as an optical fiber line fault point.
Preferably, the standard curve contains test parameters, curve point information, event point information, chain length, chain loss, and alarm thresholds.
Preferably, the test parameters include span, wavelength, pulse width, refractive index, non-reflection threshold, end threshold, and test duration.
Preferably, the test pulse width is tested 16 or 32 times.
Preferably, the pulse width has a value of 5 to 200000.
According to the specific embodiment provided by the application, the application discloses the following technical effects:
the application provides a method for determining an alarm position based on autonomous learning, which is applied to an OTDR module in optical cable monitoring, and comprises the following steps: based on the OTDR module, establishing an optical fiber line event feature information database through an autonomous learning algorithm; the OTDR module is configured with a standard curve; the standard curve represents the initial state of the line to be tested and comprises test parameters for carrying out OTDR test on the line to be tested and a threshold value for alarming the optical cable line; and when the line to be tested fails, determining an alarm position according to the optical fiber line event characteristic information database. The application can avoid the problem of inaccurate positioning of the fault point of the optical fiber line caused by the uncertainty of the OTDR module on event identification under the condition of not increasing the time spent on detecting the fault point of the optical fiber line, and can improve the accuracy of the fault positioning of the optical fiber line.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method according to an embodiment of the present application;
FIG. 2 is a flowchart of a database construction step according to an embodiment of the present application;
fig. 3 is a schematic diagram of an alarm position determining step according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The terms "first," "second," "third," and "fourth" and the like in the description and in the claims and drawings are used for distinguishing between different objects and not necessarily for describing a particular sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, inclusion of a list of steps, processes, methods, etc. is not limited to the listed steps but may alternatively include steps not listed or may alternatively include other steps inherent to such processes, methods, products, or apparatus.
The application aims to provide a method for determining an alarm position based on autonomous learning, which can improve the accuracy of optical fiber line fault positioning.
In order that the above-recited objects, features and advantages of the present application will become more readily apparent, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description.
Fig. 1 is a flowchart of a method provided by an embodiment of the present application, and as shown in fig. 1, the present application provides a method for determining an alarm position based on autonomous learning, which is applied to an OTDR module in optical cable monitoring, and the method includes:
step 100: based on the OTDR module, establishing an optical fiber line event feature information database through an autonomous learning algorithm; the OTDR module is configured with a standard curve; the standard curve represents the initial state of the line to be tested and comprises test parameters for carrying out OTDR test on the line to be tested and a threshold value for alarming the optical cable line;
step 200: and when the line to be tested fails, determining an alarm position according to the optical fiber line event characteristic information database.
Specifically, the method in this embodiment includes two stages: : an OTDR module establishes an optical fiber line event characteristic information database through learning; when two optical fiber lines fail, an alarm position is determined by using an optical fiber line event information database. After the OTDR module configures a standard curve, selecting a group of test pulse widths (other test parameters use standard curve test parameters) according to the standard curve range for testing, entering a first stage (learning mode), extracting line characteristic information according to a test result, and establishing an optical fiber line characteristic information database; after the first stage is completed, the OTDR module uses the test parameters (including pulse width) of the standard curve to carry out cyclic test, and when the loss of the optical fiber line exceeds the alarm threshold value, the alarm position and the alarm level are confirmed through the second stage flow. The first stage is automated immediately after the standard curve is configured, and the time consumption is determined by the selected pulse width group, the number of single pulse width tests and the test time, and is typically several tens of minutes to several hours. The first stage is negligible in time relative to the life cycle of the cable monitoring for years.
Referring to fig. 2, a fiber line event feature information database is established, comprising the steps of:
1) Performing OTDR test on the optical fiber line by using an OTDR module, and storing a test result as a standard curve (representing the initial state of the line and including a line loss alarm threshold value) in the OTDR module;
2) And determining the learning times and distributing the buffer area. According to the standard curve range, a group of test pulse widths is selected, and the number of the group of pulse widths is M. Each pulse width is tested N times. The total number of tests was m×n. Taking the event position as a unique identifier, establishing a buffer area for insertion loss (characteristic information) of each event, wherein the buffer unit SIZE buf_size=m×n; counting the maximum value, the minimum value and the average value of the interpolation loss in the buffer area; an insertion loss invalid value identifier, an insl_invalid_flag, an event disappearance identifier, an event_fade_flag and a buffer area are defined, and an index is stored.
3) And the OTDR module acquires the characteristic information of the whole line through automatic learning. The learning process is as follows: the OTDR module performs a plurality of tests using 2) the pulse widths in the pulse width group (other test parameters than pulse widths using the test parameters of the standard curve). And obtaining the characteristic information of the optical fiber line from the test result, and updating the buffer area (characteristic information database). The total test times are BUF_SIZE times until the whole test buffer area is filled.
4) In the learning process, each event in each test result is processed according to the following steps:
a) And updating the insertion loss in the buffer area by using the insertion loss of the event obtained by the current test. If the insertion loss of the current event is invalid or cannot be calculated, writing in an insl_invalid_flag at the index position of the buffer area; if the current event insertion loss is effective, filling an event insertion loss value in the index position; index=index+1.
b) Updating statistics of effective insertion loss in the cache area: maximum, minimum, average (maximum and minimum removed when calculating the average);
5) Checking the buffer area, and processing the event which does not exist in the current test result but exists in the database according to the following steps: filling event vanishing marks in the index position of the buffer area: event_fade_flag, index=index+1.
6) If index > = buf_size, this phase ends and all event information characteristic information is stored in the OTDR module.
Referring to fig. 2, the fiber line fault location is confirmed using a fiber line event feature information database, comprising the steps of:
1) Performing OTDR test on the optical fiber line by using an OTDR module, and storing a test result as a standard curve (representing the initial state of the line and including a line loss alarm threshold value) in the OTDR module;
2) The OTDR module performs a cyclical OTDR test on the optical cable line using the standard curve parameters.
3) And the loss of the optical fiber line exceeds an alarm threshold, all events in the OTDR test are processed according to the following steps, and the fault position of the optical fiber line is determined:
a) Retrieving the event feature information from an event feature information database (cache) according to the current event location;
b) If the event characteristic information does not exist, judging that the event belongs to a newly added event, if the insertion loss exceeds an alarm threshold, the event position is an optical fiber line fault, otherwise, jumping to a) to continuously judge the next event.
c) The event characteristic information exists, the difference between the insertion loss of the event obtained by the current test and the average value of the insertion loss in the database is calculated, and the value of the difference is larger than the alarm threshold value, and the event point is the optical fiber fault position. Otherwise, jumping to a), and judging the next event;
d) Traversing all alarm events, and defining the alarm event with the highest alarm level as an optical fiber line fault point.
The test parameters in this embodiment include a measurement range, a wavelength, a pulse width, a refractive index, a non-reflection threshold, an end threshold, and a test duration. Selecting a group of pulse widths according to the measuring range, wherein the measuring range pulse widths correspond to the following steps:
table 1 range pulse width correspondence
Further, the number of times N of each pulse width test is generally 16 or 32, but is not limited to 16 or 32. The pulse width is selected from table 1 according to the standard curve range, but the pulse width in table 1 is not limited to be used alone.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other.
The principles and embodiments of the present application have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present application and the core ideas thereof; also, it is within the scope of the present application to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the application.
Claims (7)
1. A method for determining an alarm location based on autonomous learning, applied to an OTDR module in optical cable monitoring, the method comprising:
based on the OTDR module, establishing an optical fiber line event feature information database through an autonomous learning algorithm; the OTDR module is configured with a standard curve; the standard curve represents the initial state of the line to be tested and comprises test parameters for carrying out OTDR test on the line to be tested and a threshold value for alarming the optical cable line;
and when the line to be tested fails, determining an alarm position according to the optical fiber line event characteristic information database.
2. The method for determining an alarm position based on autonomous learning of claim 1, wherein the establishing an optical fiber line event feature information database based on the OTDR module by an autonomous learning algorithm comprises:
performing OTDR test on the optical fiber line by using the OTDR module, and storing a test result in the OTDR module as the standard curve;
selecting a group of test pulse widths according to the measuring range of the standard curve; the number of the test pulse widths of the group is M, and each test pulse width is tested N times;
taking the event position as a unique identifier, establishing a buffer area for the insertion loss of each event, wherein the buffer unit SIZE buf_size=m×n;
counting the maximum value, the minimum value and the average value of the interpolation loss in the buffer area;
defining an insertion loss invalid value identifier, an event disappearance identifier and a cache area storage index;
acquiring the characteristic information of the whole line by utilizing the OTDR module through automatic learning; the automatic learning process is as follows: performing multiple tests by using the test pulse width based on the OTDR module, obtaining fiber line characteristic information from a test result, and updating a buffer area according to the fiber line characteristic information to obtain the fiber line event characteristic information database; the total test times are BUF_SIZE times until the whole test buffer area is filled;
in the learning process, each event in each test result is processed according to the following steps:
updating insertion loss in a buffer area by using insertion loss of an event obtained by current test, if the insertion loss of the current event is invalid or can not be calculated, writing an identification of the insertion loss invalid value in the position of the index stored in the buffer area, and if the insertion loss of the current event is valid, filling an event insertion loss value in the position of the index stored in the buffer area, wherein index=index+1;
updating statistics of effective insertion loss in the cache area: maximum, minimum and average;
checking the buffer area, and processing the event which does not exist in the current test result but exists in the database according to the following steps: filling event disappearance identification in the position of the storage index of the buffer area: event_fade_flag, index=index+1;
if index > = buf_size, this phase ends and all event information characteristic information is stored in the OTDR module.
3. The method for determining an alarm position based on autonomous learning of claim 1, wherein determining an alarm position based on the fiber circuit event feature information database when the line under test fails, comprises:
carrying out OTDR test on the line to be tested by using the OTDR module, and storing a test result in the OTDR module as a standard curve;
based on an OTDR module, performing cyclic OTDR test on the line to be tested by using parameters of a standard curve;
when the line loss to be measured exceeds the alarm threshold, all events in the OTDR test are processed according to the following steps to determine the fault position of the optical fiber line:
retrieving the event feature information from the fiber circuit event feature information database according to the current event position;
if the event feature information does not exist, judging that the event belongs to a new event, wherein the insertion loss of the new event exceeds an alarm threshold, if the event position is an optical fiber line fault, otherwise, jumping to a step of searching the event feature information from the optical fiber line event feature information database according to the current event position, and continuing to judge the next event;
if the event characteristic information exists, calculating the difference between the event insertion loss obtained by the current test and the insertion loss average value in the optical fiber line event characteristic information database, wherein the value of the difference is larger than an alarm threshold value, and the event point is the optical fiber fault position; otherwise, jumping to the step of judging the next event according to the current event position;
traversing all alarm events, and defining the alarm event with the highest alarm level as an optical fiber line fault point.
4. The method for determining alert location based on autonomous learning of claim 1, wherein the standard curve contains test parameters, curve point information, event point information, chain length, chain loss, and alert thresholds.
5. The method for determining alert location based on autonomous learning of claim 1, wherein the test parameters include span, wavelength, pulse width, refractive index, non-reflective threshold, end threshold, and test duration.
6. The method for determining an alert location based on autonomous learning of claim 1, wherein the test pulse width is tested 16 or 32 times.
7. The method for determining an alarm position based on autonomous learning according to claim 1, wherein the pulse width has a value of 5 to 200000.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310411505.6A CN116647272A (en) | 2023-04-18 | 2023-04-18 | Method for determining alarm position based on autonomous learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310411505.6A CN116647272A (en) | 2023-04-18 | 2023-04-18 | Method for determining alarm position based on autonomous learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116647272A true CN116647272A (en) | 2023-08-25 |
Family
ID=87617721
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310411505.6A Pending CN116647272A (en) | 2023-04-18 | 2023-04-18 | Method for determining alarm position based on autonomous learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116647272A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117353807A (en) * | 2023-12-04 | 2024-01-05 | 唐山市艾科特科技有限公司 | Optical cable remote monitoring system and method based on artificial intelligence |
-
2023
- 2023-04-18 CN CN202310411505.6A patent/CN116647272A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117353807A (en) * | 2023-12-04 | 2024-01-05 | 唐山市艾科特科技有限公司 | Optical cable remote monitoring system and method based on artificial intelligence |
| CN117353807B (en) * | 2023-12-04 | 2024-03-05 | 唐山市艾科特科技有限公司 | Optical cable remote monitoring system and method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111459695A (en) | Root cause positioning method and device, computer equipment and storage medium | |
| CN109474333B (en) | Electric power optical cable real-time monitoring protection system based on deep learning | |
| CN103782149A (en) | OTDR trace analysis in PON systems | |
| CN106485805A (en) | A kind of pipeline inspection management method and system | |
| CN111143438A (en) | Workshop field data real-time monitoring and anomaly detection method based on stream processing | |
| CN114446020B (en) | Linkage early warning management method, system, storage medium and equipment | |
| CN116647272A (en) | Method for determining alarm position based on autonomous learning | |
| CN111814954A (en) | Optical fiber quality analysis method and device, electronic equipment and storage medium | |
| CN103675357B (en) | The method of anemoscope fault pre-alarming and system | |
| CN112887017A (en) | Positioning method and positioning system for optical cable connecting tower | |
| CN115021804B (en) | Long-distance communication optical cable fault positioning method and related device | |
| CN115882938A (en) | Optical network fault monitoring system | |
| CN118200950B (en) | Method and system for inspecting telecommunication base station | |
| CN114759978A (en) | Optical cable maintenance method, device and system | |
| CN113326612A (en) | Power distribution network reliability assessment method and device | |
| CN114994460A (en) | Cable insulation performance prediction device and method | |
| CN117977816B (en) | Intelligent power supply system for electric power safety | |
| CN116318383A (en) | Optical cable monitoring method, device, equipment and storage medium | |
| CN116488721A (en) | Intelligent positioning method for optical cable line faults | |
| CN111130634A (en) | Method and system for identifying loss event in OPGW (optical fiber composite overhead ground wire) | |
| CN117955558A (en) | Optical cable fault positioning method and device, electronic equipment and storage medium | |
| CN117353807B (en) | Optical cable remote monitoring system and method based on artificial intelligence | |
| CN110278025A (en) | Fiber-optic monitoring method, apparatus and system | |
| CN116647273A (en) | Sectional type optical cable intelligent diagnosis system, method, equipment and storage medium | |
| CN112001466A (en) | Radio frequency identification system, method and device of intelligent cable |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |