CN111127793A - Cable anti-theft monitoring method and system, computer readable storage medium - Google Patents
Cable anti-theft monitoring method and system, computer readable storage medium Download PDFInfo
- Publication number
- CN111127793A CN111127793A CN201911360337.2A CN201911360337A CN111127793A CN 111127793 A CN111127793 A CN 111127793A CN 201911360337 A CN201911360337 A CN 201911360337A CN 111127793 A CN111127793 A CN 111127793A
- Authority
- CN
- China
- Prior art keywords
- intrusion
- cable
- alarm
- rayleigh scattering
- backward rayleigh
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/02—Mechanical actuation
- G08B13/12—Mechanical actuation by the breaking or disturbance of stretched cords or wires
- G08B13/122—Mechanical actuation by the breaking or disturbance of stretched cords or wires for a perimeter fence
- G08B13/124—Mechanical actuation by the breaking or disturbance of stretched cords or wires for a perimeter fence with the breaking or disturbance being optically detected, e.g. optical fibers in the perimeter fence
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Burglar Alarm Systems (AREA)
Abstract
The invention relates to a cable anti-theft monitoring method and system and a computer readable storage medium. The method comprises the following steps: coupling pulsed light to the single-mode fiber to produce backward Rayleigh scattering in the single-mode fiber; receiving the backward Rayleigh scattering reflected by the single-mode fiber, and acquiring vibration signals distributed along the single-mode fiber according to the pulse light and the backward Rayleigh scattering; acquiring the intrusion position of the cable to be detected according to the pulse light and the backward Rayleigh scattering, and inputting the vibration signal to a prediction model to acquire the intrusion type of the cable to be detected; according to the intrusion position and the intrusion type, corresponding alarm information is output according to a preset alarm strategy, the intrusion type of the intrusion time can be accurately acquired by using the prediction model, the identification accuracy of the intrusion event is improved, and meanwhile, a corresponding alarm signal can be output according to the intrusion event to warn workers.
Description
Technical Field
The invention relates to the technical field of cable monitoring, in particular to a cable anti-theft monitoring method and system and a computer readable storage medium.
Background
The cable trench is wide in distribution and long in distance, and faults such as cable breakage and short circuit caused by fire, equipment tripping, power failure and the like cause economic loss for power users and also form serious threats to safe operation of a power grid.
Traditionally, firstly, a cable can be monitored based on electrical parameters such as leakage current measurement or capacitance measurement between outer layers of the cable, and the cable monitoring method has the defects that only the cable is subjected to post-event monitoring when the cable is damaged, monitoring cannot be carried out after power failure, and the invasion site and the invasion type of an invasion event cannot be identified; and secondly, the cable can be detected based on the optical fiber vibration sensing monitoring technology, and the intrusion sites and the intrusion types of a plurality of intrusion events cannot be identified.
Disclosure of Invention
Accordingly, it is desirable to provide a cable anti-theft monitoring method and system, and a computer readable storage medium, which can identify intrusion sites and intrusion types of a plurality of intrusion events in real time and have a high identification rate.
A cable anti-theft monitoring method is applied to a cable anti-theft monitoring system, the cable anti-theft monitoring system comprises a single-mode optical fiber synchronously bound with a cable to be tested, and the method comprises the following steps:
coupling pulsed light to the single-mode fiber to produce backward Rayleigh scattering in the single-mode fiber;
receiving the backward Rayleigh scattering reflected by the single-mode fiber, and acquiring vibration signals distributed along the single-mode fiber according to the pulse light and the backward Rayleigh scattering;
acquiring the intrusion position of the cable to be detected according to the pulse light and the backward Rayleigh scattering, and inputting the vibration signal to a prediction model to acquire the intrusion type of the cable to be detected;
and outputting corresponding alarm information according to the preset alarm strategy according to the intrusion position and the intrusion type.
In one embodiment, before inputting the vibration signal to a prediction model to obtain the intrusion type of the cable under test, the method includes:
acquiring a vibration signal training set, wherein the vibration signal training set comprises a plurality of interference vibration signals and a plurality of invasion vibration signals;
and training a cyclic neural network model by using the vibration signal training set to obtain the prediction model.
In one embodiment, the training a recurrent neural network model with the training set of vibration signals to obtain the prediction model includes:
determining a first loss function of the recurrent neural network model according to a plurality of interfering vibration signals in the vibration signal training set;
determining a second loss function of the recurrent neural network model according to the plurality of invading vibration signals in the vibration signal training set;
inputting the vibration signal training set into the recurrent neural network model to optimize the weight of the LSTM network layer until the output value of the first loss function is smaller than a first preset threshold value and the output value of the second loss function is smaller than a second preset threshold value;
and taking the recurrent neural network model corresponding to the condition that the output value of the first loss function is smaller than a first preset threshold value and the output value of the second loss function is smaller than a second preset threshold value as the prediction model.
In one embodiment, outputting corresponding alarm information according to the intrusion position and the intrusion type and according to a preset alarm strategy includes:
constructing a corresponding relation between the intrusion position and the intrusion type and a preset alarm strategy;
determining a preset alarm strategy corresponding to the current intrusion position and the intrusion type;
and outputting an alarm signal according to the determined preset alarm strategy, wherein the alarm signal carries the intrusion position.
In one embodiment, the method further comprises:
generating an alarm database according to the alarm signal, wherein the alarm database at least comprises alarm time, an intrusion position and an intrusion type of executing the alarm signal each time;
and distributing and managing management resources along the circuit to be tested according to the alarm database.
In one embodiment, the acquiring the intrusion position of the cable to be tested according to the pulse light and the backward rayleigh scattering includes:
and acquiring the intrusion position of the cable to be tested according to the time delay of the pulsed light and the backward Rayleigh scattering based on an optical time domain reflection technology.
In one embodiment, the preset alarm policy includes:
presenting the alarm signal by means of sound, light or image;
and outputting the alarm information to a mobile terminal of a preset account based on a wireless network.
The application also provides a cable theftproof monitoring system for detect the temperature signal of the cable that awaits measuring, the system includes:
the single-mode optical fiber is synchronously bound with the cable to be tested;
the light source module is coupled with the single-mode optical fiber and used for coupling pulsed light to the single-mode optical fiber so as to generate backward Rayleigh scattering in the single-mode optical fiber;
the optical detection module is coupled with the single-mode optical fiber and used for receiving the backward Rayleigh scattering reflected by the single-mode optical fiber and acquiring vibration signals distributed along the single-mode optical fiber according to the pulse light and the backward Rayleigh scattering;
the processing module is respectively connected with the light source module and the light detection module and is used for acquiring the intrusion position of the cable to be detected according to the pulse light and the backward Rayleigh scattering and outputting an alarm instruction;
the type acquisition module is respectively connected with the processing module and the optical detection module and used for inputting the vibration signal to a prediction model so as to acquire the intrusion type of the cable to be detected;
and the alarm module is connected with the processing module and used for outputting corresponding alarm information according to the intrusion position and the intrusion type and a preset alarm strategy.
The present application further provides a cable anti-theft monitoring system, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the cable anti-theft monitoring method.
The present application also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the cable theft monitoring method as described above.
According to the cable anti-theft monitoring method and system and the computer readable storage medium, pulsed light is coupled to the single-mode optical fiber to generate backward Rayleigh scattering in the single-mode optical fiber; receiving the backward Rayleigh scattering reflected by the single-mode fiber, and acquiring vibration signals distributed along the single-mode fiber according to the pulse light and the backward Rayleigh scattering; acquiring the intrusion position of the cable to be detected according to the pulse light and the backward Rayleigh scattering, and inputting the vibration signal to a prediction model to acquire the intrusion type of the cable to be detected; according to the intrusion position and the intrusion type, corresponding alarm information is output according to a preset alarm strategy, the intrusion type of the intrusion time can be accurately acquired by using the prediction model, the identification accuracy of the intrusion event is improved, and meanwhile, a corresponding alarm signal can be output according to the intrusion event to warn workers.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings of the embodiments can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a cable theft monitoring method according to an embodiment;
FIG. 2 is a schematic flow chart illustrating a process of training a recurrent neural network model to obtain the predictive model using the training set of vibration signals according to an embodiment;
fig. 3 is a structural framework diagram of a cable theft monitoring system in one embodiment.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, and in order to provide a better understanding of the present invention. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. This invention can be embodied in many different forms than those herein described and many modifications may be made by those skilled in the art without departing from the spirit of the invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise. In the description of the present invention, "a plurality" means at least one, e.g., one, two, etc., unless specifically limited otherwise.
The embodiment of the application provides a cable anti-theft monitoring method, which is applied to a cable anti-theft monitoring system, wherein the cable anti-theft monitoring system comprises a single-mode optical fiber synchronously bound with a cable to be detected. When the single-mode optical fiber is used as a sensing medium for detecting the intrusion event, a standard multi-core communication optical cable can be adopted, the single-mode optical fiber only occupies one core optical fiber of the multi-core communication optical cable, and the rest cores can be used for expanding optical communication and can be continuously used for expanding and compatible functions of safety monitoring systems such as a cable temperature monitoring system and the like. The conventional standard multi-core communication optical cable is mostly 4-96 cores, and the cable anti-theft monitoring method based on the single-mode optical fiber only occupies one core optical fiber in the multi-core communication optical cable, so that the sharing of optical cable resources can be easily realized, and the repeated investment and waste of independently laying multi-mode optical cables are avoided. Meanwhile, the cable anti-theft monitoring based on the single mode fiber has the advantages of more stable performance, longer monitoring distance, compatibility with an optical communication line, adaptation to the development trend of composite cables, wider application range and the like due to the communication advantages of the single mode fiber. The method has the advantages of reducing the complexity of the system and the input cost when being applied in a large range, and simultaneously reserving space for system expansion.
As shown in fig. 1, in one embodiment, the cable theft monitoring method includes steps 102-108. Wherein the content of the first and second substances,
In one embodiment, the light source module of the cable theft monitoring system (referred to as the system in the embodiment of the present application) may emit pulsed light with a preset power. The light source module can be a laser generator and is used for emitting laser signals. The light source module is coupled with the single-mode optical fiber, can couple the emitted laser signal to the single-mode optical fiber and transmits the laser signal in the single-mode optical fiber. The laser signal may be narrow linewidth laser pulse light. When the pulse power of the narrow-linewidth laser pulse light reaches a certain threshold value, backward Rayleigh scattering can be generated in the single-mode fiber.
Specifically, in order to ensure the unidirectional transmission of light during the laser emission process, an isolator is added into the system, polarization damage is eliminated through a polarization scrambler, so that the peak value of pulsed light output by a laser generator is kept stable, and the coupler realizes the coupling of the pulsed light.
And 104, receiving the backward Rayleigh scattering reflected by the single-mode fiber, and acquiring a vibration signal distributed along the single-mode fiber according to the pulse light and the backward Rayleigh scattering.
When an intrusion event occurs, the induced vibration will cause the structural parameters such as the refractive index of the single mode fiber at the intrusion position to change, so that the phase of the backward scattering light at the intrusion position changes. The light detection module of the system can receive the pulse light output by the light source module and the backward scattering light with changed phase, and the pulse light and the backward scattering light interfere to generate an interference signal. The interference signal carries a vibration signal distributed along the single-mode optical fiber.
And 106, acquiring the intrusion position of the cable to be detected according to the pulse light and the backward Rayleigh scattering, and inputting the vibration signal to a prediction model to acquire the intrusion type of the cable to be detected.
In one embodiment, the acquiring the intrusion position of the cable to be tested according to the pulse light and the backward rayleigh scattering includes: and acquiring the intrusion position of the cable to be tested according to the time delay of the pulsed light and the backward Rayleigh scattering based on an optical time domain reflection technology.
Specifically, based on a phase-sensitive optical time domain reflectometry (Φ -OTDR), the system can calculate the intrusion position of the single-mode fiber cable to be tested, where the intrusion event occurs, according to the time difference between the time of emitting pulsed light and the time of receiving backward rayleigh scattering and the speed of light. Because the single mode fiber and the cable to be tested are synchronously bound, the intrusion event of the single mode fiber can be used as the intrusion event of the cable to be tested.
In one embodiment, the vibration signal is input to a prediction model to obtain the intrusion type of the cable to be tested. The intrusion type may include a manual mining event, a machine mining event, and the like.
In particular, the predictive model may include a plurality of recurrent neural network models. For example, the prediction model may include a model for noise event prediction of the vibration signal, and a model for intrusion event prediction of the vibration signal. Each vibration signal corresponds to one position information, a plurality of interference vibration signals and a plurality of invasion vibration signals at different positions can be utilized to train the recurrent neural network model, the obtained vibration signals are predicted, and the predicted results are summarized to obtain the invasion type of the invasion event.
And step 108, outputting corresponding alarm information according to the intrusion position and the intrusion type and a preset alarm strategy.
In one embodiment, the system may pre-store a corresponding relationship between the intrusion position and the intrusion type and a preset alarm policy, and then determine the preset alarm policy to be executed currently from the corresponding relationship according to the intrusion position and the intrusion type at the current intrusion time, and further output corresponding alarm information according to the determined preset alarm policy to prompt maintenance personnel, so as to monitor or investigate the intrusion event in the field.
In the cable anti-theft monitoring method, pulsed light is coupled to the single-mode optical fiber to generate backward rayleigh scattering in the single-mode optical fiber; receiving the backward Rayleigh scattering reflected by the single-mode fiber, and acquiring vibration signals distributed along the single-mode fiber according to the pulse light and the backward Rayleigh scattering; acquiring the intrusion position of the cable to be detected according to the pulse light and the backward Rayleigh scattering, and inputting the vibration signal to a prediction model to acquire the intrusion type of the cable to be detected; according to the intrusion position and the intrusion type, corresponding alarm information is output according to a preset alarm strategy, the intrusion type of the intrusion time can be accurately acquired by using the prediction model, the identification accuracy of the intrusion event is improved, and meanwhile, a corresponding alarm signal can be output according to the intrusion event to warn workers.
In one embodiment, before inputting the vibration signal to a prediction model to obtain the intrusion type of the cable under test, the method includes: acquiring a vibration signal training set, wherein the vibration signal training set comprises a plurality of interference vibration signals and a plurality of invasion vibration signals; and training a cyclic neural network model by using the vibration signal training set to obtain the prediction model.
Specifically, before the intrusion type of the cable intrusion event to be detected is obtained by using the prediction model, a large number of interference vibration signals and intrusion vibration signals are collected to be used as a training set. The interference vibration signal can be a vibration signal caused by automobile passing, animal passing and the like; the intrusion vibration signal may be a vibration signal caused by pulling the single mode fiber, mechanically (e.g., an excavator, a pile driver, a rock breaker, etc.) excavating the single mode fiber. A large number of interfering and intrusive vibration signals may be collected for a plurality of test points distributed along a cable to be tested. For example, a plurality of test points are distributed along the cable to be tested, the number of the test points can be set to be M, and a plurality of interference vibration signals and intrusion vibration signals can be collected at each test point. The sum of the number of the interference vibration signals and the number of the intrusion vibration signals is 1000, and the 1000 interference vibration signals and the 1000 intrusion vibration signals are used as a training set.
And inputting 1000 interference vibration signals and intrusion vibration signals into the cyclic neural network model according to the sequence of the test points distributed along the cable to be tested so as to train the cyclic neural network. The method comprises the steps of coding 1000 interference vibration signals and intrusion vibration signals into a data matrix required by a cyclic neural network according to the sequence of a plurality of test points distributed along a cable to be tested, inputting the data matrix corresponding to 800 interference vibration signals and intrusion vibration signals into the cyclic neural network according to the sequence of the plurality of test points distributed along the cable to be tested for training, using the remaining 200 data matrices corresponding to the interference vibration signals and the intrusion vibration signals as a check set, and using a trained cyclic neural network model as a prediction model.
As shown in fig. 2, in one embodiment, the training a recurrent neural network model with the training set of vibration signals to obtain the prediction model includes:
and step 208, taking the recurrent neural network model corresponding to the condition that the output value of the first loss function is smaller than a first preset threshold value and the output value of the second loss function is smaller than a second preset threshold value as the prediction model.
Particularly, among them, a Long Short Term Memory (LSTM) is a recurrent neural network with a complex structure. A fully connected recurrent neural network typically includes: input layer, hidden layer and output layer. The input layer is an input layer, the hidden layer is a hidden layer, the hidden layer can have multiple layers, and the output layer is an output layer. In a standard LSTM network structure, 4 values are required for input, and 1 value is output, wherein there are 3 forgetting gate concepts, i.e., input gate, forget gate, and output gate, and since there are 4 parameters for input, the number of parameters is usually 4 times that of a general neural network. LSTM can effectively prevent the gradient disappearance problem by gating control.
The first loss function and the second loss function are indexes for measuring the performance of the expected result predicted by the prediction model. And acquiring a first loss function of the recurrent neural network model according to a difference value between the actual value and the predicted value of the interference vibration signals of the test points distributed along the cable to be tested in the training set, wherein the first loss function can be a Mean Squared Error (MSE) function. And acquiring a second loss function of the recurrent neural network model according to the difference value between the actual value and the predicted value of the intrusion vibration signals of the test points distributed along the cable to be tested in the training set, wherein the second loss function can be a Mean Squared Error (MSE) function.
And (4) inputting the training set into the recurrent neural network model to optimize the weight of the LSTM network layer until the output value of the first loss function is smaller than a first preset threshold value and the output value of the second loss function is smaller than a second preset threshold value. In the process, output values of the first loss function and the second loss function are continuously detected, and when the output value of the first loss function is smaller than a first preset threshold and the output value of the second loss function is smaller than a second preset threshold, the prediction model is determined according to the weight of the LSTM network layer corresponding to the condition that the output value of the first loss function is smaller than the first preset threshold and the output value of the second loss function is smaller than the second preset threshold.
In one embodiment, outputting corresponding alarm information according to the intrusion position and the intrusion type and according to a preset alarm strategy includes: constructing a corresponding relation between an intrusion site, an intrusion type and a preset alarm strategy; determining a preset alarm strategy corresponding to the current intrusion site and the intrusion type; and outputting an alarm signal according to the determined preset alarm strategy, wherein the alarm signal carries the intrusion position.
Specifically, the system can pre-construct and store the corresponding relation between the intrusion site, the intrusion type and the preset alarm strategy. Illustratively, when a relationship between the three is established, f (intrusion site and intrusion type) is preset as an alarm policy. The relationship may be fixed in the form of a mapping table. The relationship may be system provided, recommended, or customized by the user.
Wherein, the preset alarm strategy can comprise presenting the alarm signal in a sound, light or image mode; and outputting the alarm information to a mobile terminal of a preset account based on a wireless network.
Illustratively, when the intrusion type of the intrusion event is a mining intrusion type and the intrusion location is within a preset range from the system control center, the corresponding preset alarm policy is to present the alarm signal in a sound, light or image manner so as to warn the staff at the intrusion location. When the intrusion type of the intrusion event is an artificial intrusion type, the corresponding preset alarm strategy is a mobile terminal which outputs the alarm information to a preset account based on a wireless network so as to remind a worker holding the mobile terminal to go to an intrusion site for investigation, thereby preventing the occurrence of the event of artificially stealing the cable.
In one embodiment, the cable anti-theft monitoring method further includes: generating an alarm database according to the alarm signal, wherein the alarm database at least comprises alarm time, an intrusion position and an intrusion type of executing the alarm signal each time; and distributing and managing management resources along the circuit to be tested according to the alarm database.
Specifically, when an alarm signal occurs, the alarm signal may be stored in an alarm database. The alarm information stored in the alarm database can carry the alarm time, the intrusion position and the intrusion type of executing the alarm signal every time. Illustratively, in a preset time period, if the number of times of the alarm signal is m, the database may analyze which time period and which cable-laid lines have a higher frequency of the intrusion event according to the m alarm signals stored in the database according to the alarm time, the intrusion position, and the intrusion type in which the m alarm signals are correspondingly stored, and then allocate and manage management resources along the circuit-laid lines to be tested according to the information. The management resources may include human resources and material resources. For example, more management resources can be configured for monitoring the intrusion site during the time period when the intrusion time frequently occurs, so as to prevent the intrusion event from occurring.
In one embodiment, the cable anti-theft monitoring method further includes: acquiring current geographic information of a user; and generating guiding information according to the geographic information and the intrusion position so as to guide the user to reach the location of the intrusion event. Specifically, the guidance information includes at least one of map information, text navigation information, and voice navigation information describing a location where the target navigation element is located from a current location. When an intrusion event occurs, the user can be guided to reach the location of the intrusion event so as to rapidly solve the intrusion event.
It should be understood that although the various steps in the flow charts of fig. 1-2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
As shown in fig. 3, an embodiment of the present application further provides a cable duct temperature detection system based on a single-mode fiber, which is used for detecting a temperature signal of a cable to be detected, and the system includes:
and the single-mode optical fiber 310 is synchronously bound with the cable to be tested. When the single-mode fiber 310 is used as a sensing medium for intrusion event detection, a standard multi-core communication cable can be adopted, the single-mode fiber 310 only occupies one core fiber of the multi-core communication cable, and the rest cores can be used for extended optical communication and can be continuously used for the function expansion compatibility of safety monitoring systems such as a cable temperature monitoring system and the like. The conventional standard multi-core communication optical cable is mostly 4-96 cores, and the cable anti-theft monitoring method based on the single-mode optical fiber 310 only occupies one core optical fiber in the multi-core communication optical cable, so that the sharing of optical cable resources can be easily realized, and the repeated investment and waste of independently laying multi-mode temperature measurement optical cables are avoided.
And a light source module 320 coupled to the single-mode fiber 310, for coupling pulsed light to the single-mode fiber 310 to generate backward rayleigh scattering in the single-mode fiber 310. The light source module 320 is coupled to the single-mode fiber 310, and can couple the emitted laser signal to the single-mode fiber 310 and transmit the laser signal in the single-mode fiber 310. The laser signal may be narrow linewidth laser pulse light. When the pulse power of the narrow-linewidth laser pulse light reaches a certain threshold, backward rayleigh scattering occurs in the single-mode fiber 310. For example, the light source module 320 may be a pulse laser, and the pulse laser may emit pulse light with a preset power and stability.
The optical detection module 330 is coupled to the single-mode fiber 310, and configured to receive the backward rayleigh scattering reflected by the single-mode fiber 310, and acquire a vibration signal distributed along the single-mode fiber 310 according to the pulse light and the backward rayleigh scattering. The optical detection module 330 may be a photodetector, and can convert the received optical signal into an electrical signal, and then output the electrical signal to the processing module 340 for processing.
The processing module 340 is connected to the light source module 320 and the light detection module 330, respectively, and configured to obtain an intrusion position of the cable to be detected according to the pulsed light and the backward rayleigh scattering, and output an alarm instruction.
A type obtaining module 350, connected to the processing module 340 and the optical detection module 330, respectively, and configured to input the vibration signal to a prediction model to obtain an intrusion type of the cable to be tested.
In one embodiment, the type obtaining module 350 further includes:
the system comprises a training set unit, a processing unit and a control unit, wherein the training set unit is used for acquiring a vibration signal training set, and the vibration signal training set comprises a plurality of interference vibration signals and a plurality of invasion vibration signals;
and the prediction model unit is used for training a cyclic neural network model by utilizing the vibration signal training set to obtain the prediction model.
Specifically, the prediction model unit may determine a first loss function of the recurrent neural network model according to a plurality of interfering vibration signals in the training set of vibration signals; determining a second loss function of the recurrent neural network model according to the plurality of invading vibration signals in the vibration signal training set; inputting the vibration signal training set into the recurrent neural network model to optimize the weight of the LSTM network layer until the output value of the first loss function is smaller than a first preset threshold value and the output value of the second loss function is smaller than a second preset threshold value; and taking the recurrent neural network model corresponding to the condition that the output value of the first loss function is smaller than a first preset threshold value and the output value of the second loss function is smaller than a second preset threshold value as the prediction model.
And the alarm module 360 is connected with the processing module and used for outputting corresponding alarm information according to the intrusion position and the intrusion type and a preset alarm strategy. For example, the alarm module 360 may include a display unit, a light emitting unit, a speaker, and the like capable of performing an audible and visual alarm operation. Wherein, the alarm signal can be presented in the form of sound, light and image.
The single-mode optical fiber 310, the light source module 320, and the light detection module 330330 may be coupled by the same coupler.
The present application further provides a cable duct temperature detection system based on a single-mode optical fiber 310, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the cable anti-theft monitoring method in any of the above embodiments.
The present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the cable theft monitoring method according to any of the above embodiments.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features. It should be noted that "in one embodiment," "for example," "as another example," and the like, are intended to illustrate the application and are not intended to limit the application.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A cable anti-theft monitoring method is characterized by being applied to a cable anti-theft monitoring system, wherein the cable anti-theft monitoring system comprises a single-mode optical fiber synchronously bound with a cable to be tested, and the method comprises the following steps:
coupling pulsed light to the single-mode fiber to produce backward Rayleigh scattering in the single-mode fiber;
receiving the backward Rayleigh scattering reflected by the single-mode fiber, and acquiring vibration signals distributed along the single-mode fiber according to the pulse light and the backward Rayleigh scattering;
acquiring the intrusion position of the cable to be detected according to the pulse light and the backward Rayleigh scattering, and inputting the vibration signal to a prediction model to acquire the intrusion type of the cable to be detected;
and outputting corresponding alarm information according to the preset alarm strategy according to the intrusion position and the intrusion type.
2. The method of claim 1, wherein before inputting the vibration signal to a predictive model to obtain the intrusion type of the cable under test, the method comprises:
acquiring a vibration signal training set, wherein the vibration signal training set comprises a plurality of interference vibration signals and a plurality of invasion vibration signals;
and training a cyclic neural network model by using the vibration signal training set to obtain the prediction model.
3. The method of claim 2, wherein training a recurrent neural network model using the training set of vibration signals to obtain the predictive model comprises:
determining a first loss function of the recurrent neural network model according to a plurality of interfering vibration signals in the vibration signal training set;
determining a second loss function of the recurrent neural network model according to the plurality of invading vibration signals in the vibration signal training set;
inputting the vibration signal training set into the recurrent neural network model to optimize the weight of the LSTM network layer until the output value of the first loss function is smaller than a first preset threshold value and the output value of the second loss function is smaller than a second preset threshold value;
and taking the recurrent neural network model corresponding to the condition that the output value of the first loss function is smaller than a first preset threshold value and the output value of the second loss function is smaller than a second preset threshold value as the prediction model.
4. The method of claim 1, wherein outputting corresponding alarm information according to the intrusion position and the intrusion type and according to a preset alarm strategy comprises:
constructing a corresponding relation between the intrusion position and the intrusion type and a preset alarm strategy;
determining a preset alarm strategy corresponding to the current intrusion position and the intrusion type;
and outputting an alarm signal according to the determined preset alarm strategy, wherein the alarm signal carries the intrusion position.
5. The method of claim 4, further comprising:
generating an alarm database according to the alarm signal, wherein the alarm database at least comprises alarm time, an intrusion position and an intrusion type of executing the alarm signal each time;
and distributing and managing management resources along the circuit to be tested according to the alarm database.
6. The method of claim 1, wherein the obtaining the intrusion position of the cable under test according to the pulse light and the backward Rayleigh scattering comprises:
and acquiring the intrusion position of the cable to be tested according to the time delay of the pulsed light and the backward Rayleigh scattering based on an optical time domain reflection technology.
7. The method of claim 1, wherein the pre-set alarm strategy comprises:
presenting the alarm signal by means of sound, light or image;
and outputting the alarm information to a mobile terminal of a preset account based on a wireless network.
8. A cable theft monitoring system for detecting a temperature signal of a cable under test, the system comprising:
the single-mode optical fiber is synchronously bound with the cable to be tested;
the light source module is coupled with the single-mode optical fiber and used for coupling pulsed light to the single-mode optical fiber so as to generate backward Rayleigh scattering in the single-mode optical fiber;
the optical detection module is coupled with the single-mode optical fiber and used for receiving the backward Rayleigh scattering reflected by the single-mode optical fiber and acquiring vibration signals distributed along the single-mode optical fiber according to the pulse light and the backward Rayleigh scattering;
the processing module is respectively connected with the light source module and the light detection module and is used for acquiring the intrusion position of the cable to be detected according to the pulse light and the backward Rayleigh scattering and outputting an alarm instruction;
the type acquisition module is respectively connected with the processing module and the optical detection module and used for inputting the vibration signal to a prediction model so as to acquire the intrusion type of the cable to be detected;
and the alarm module is connected with the processing module and used for outputting corresponding alarm information according to the intrusion position and the intrusion type and a preset alarm strategy.
9. A cable theft monitoring system comprising a memory and a processor, the memory having stored therein a computer program which, when executed by the processor, causes the processor to carry out the steps of the cable theft monitoring method according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the cable theft monitoring method according to one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911360337.2A CN111127793A (en) | 2019-12-25 | 2019-12-25 | Cable anti-theft monitoring method and system, computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911360337.2A CN111127793A (en) | 2019-12-25 | 2019-12-25 | Cable anti-theft monitoring method and system, computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111127793A true CN111127793A (en) | 2020-05-08 |
Family
ID=70502558
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911360337.2A Pending CN111127793A (en) | 2019-12-25 | 2019-12-25 | Cable anti-theft monitoring method and system, computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111127793A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112803341A (en) * | 2020-12-31 | 2021-05-14 | 国网浙江省电力有限公司嘉兴供电公司 | Non-invasive cable anti-breaking monitoring device and method |
| CN112883521A (en) * | 2021-01-12 | 2021-06-01 | 中国科学院声学研究所南海研究站 | Seabed photoelectric composite cable external force invasion monitoring system applied to seabed observation network |
| CN113063489A (en) * | 2021-02-24 | 2021-07-02 | 戴天智能科技（上海）有限公司 | Vibration detection system with AI self-learning algorithm |
| CN114241266A (en) * | 2021-12-21 | 2022-03-25 | 国网甘肃省电力公司酒泉供电公司 | Processing method and system for intelligent early warning of optical cable |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102879876A (en) * | 2012-09-03 | 2013-01-16 | 深圳供电局有限公司 | Sensing optical cable for monitoring cable |
| CN103616089A (en) * | 2013-12-04 | 2014-03-05 | 威海北洋电气集团股份有限公司 | Optical fiber temperature vibration sensor and comprehensive monitoring system and method |
| CN203799460U (en) * | 2014-02-08 | 2014-08-27 | 上海波汇通信科技有限公司 | Tunnel cable intrusion detection system based on optical fiber sensing |
| CN110455397A (en) * | 2018-05-07 | 2019-11-15 | 光子瑞利科技（北京）有限公司 | A kind of shop equipment failure optical fiber sensing method and system based on LSTM |
| CN110570613A (en) * | 2019-09-18 | 2019-12-13 | 广州亓行智能科技有限公司 | Fence vibration intrusion positioning and mode identification method based on distributed optical fiber system |
-
2019
- 2019-12-25 CN CN201911360337.2A patent/CN111127793A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102879876A (en) * | 2012-09-03 | 2013-01-16 | 深圳供电局有限公司 | Sensing optical cable for monitoring cable |
| CN103616089A (en) * | 2013-12-04 | 2014-03-05 | 威海北洋电气集团股份有限公司 | Optical fiber temperature vibration sensor and comprehensive monitoring system and method |
| CN203799460U (en) * | 2014-02-08 | 2014-08-27 | 上海波汇通信科技有限公司 | Tunnel cable intrusion detection system based on optical fiber sensing |
| CN110455397A (en) * | 2018-05-07 | 2019-11-15 | 光子瑞利科技（北京）有限公司 | A kind of shop equipment failure optical fiber sensing method and system based on LSTM |
| CN110570613A (en) * | 2019-09-18 | 2019-12-13 | 广州亓行智能科技有限公司 | Fence vibration intrusion positioning and mode identification method based on distributed optical fiber system |
Non-Patent Citations (1)
| Title |
|---|
| 郑志军 等: ""一种复杂模式识别问题的求解方法"", 《计算机工程》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112803341A (en) * | 2020-12-31 | 2021-05-14 | 国网浙江省电力有限公司嘉兴供电公司 | Non-invasive cable anti-breaking monitoring device and method |
| CN112883521A (en) * | 2021-01-12 | 2021-06-01 | 中国科学院声学研究所南海研究站 | Seabed photoelectric composite cable external force invasion monitoring system applied to seabed observation network |
| CN113063489A (en) * | 2021-02-24 | 2021-07-02 | 戴天智能科技（上海）有限公司 | Vibration detection system with AI self-learning algorithm |
| CN113063489B (en) * | 2021-02-24 | 2023-01-13 | 戴天智能科技（上海）有限公司 | Vibration detection system with AI self-learning algorithm |
| CN114241266A (en) * | 2021-12-21 | 2022-03-25 | 国网甘肃省电力公司酒泉供电公司 | Processing method and system for intelligent early warning of optical cable |
| CN114241266B (en) * | 2021-12-21 | 2023-11-28 | 国网甘肃省电力公司酒泉供电公司 | Optical cable intelligent early warning processing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111127793A (en) | Cable anti-theft monitoring method and system, computer readable storage medium | |
| US11768127B2 (en) | Fiber optic virtual sensing system and method | |
| US11112332B2 (en) | Optical fiber monitoring method, and optical fiber monitoring system | |
| CN104040598B (en) | Interferometer type optical fiber interference detecting apparatus and detection method thereof | |
| US7852780B1 (en) | Method and system for provisioning facility-based displays in support of repairing outside network facilities | |
| CN103647601A (en) | Fiber monitoring system | |
| CN113438018A (en) | Optical cable fault detection method and device | |
| CN109474333B (en) | Electric power optical cable real-time monitoring protection system based on deep learning | |
| CN110149143A (en) | Test optical fiber data processing method, device, computer equipment and storage medium | |
| EP4135218A1 (en) | Long-distance optical fiber measurement method, apparatus, device and system, and storage medium | |
| CN109995426B (en) | Optical cable skin length positioning method and optical fiber vibration detection system | |
| CN113595624A (en) | Method for monitoring optical fiber running state | |
| CN114613116B (en) | External damage prevention early warning method, device, equipment and storage medium | |
| CN111141412A (en) | Cable temperature and anti-theft dual-monitoring method and system and readable storage medium | |
| CN114295324B (en) | Fault detection method, device, equipment and storage medium | |
| CN115882938A (en) | Optical network fault monitoring system | |
| CN104601232B (en) | Optical cable monitoring system, device and method | |
| CN203675113U (en) | Optical fiber monitoring system | |
| CN112964301A (en) | Monitoring method, device, system, equipment and storage medium of power pipeline | |
| CN211234916U (en) | Optical cable state monitoring system based on DAS and OTDR | |
| CN117118508A (en) | Digital twin system oriented to power communication cable and operation method | |
| CN105448014B (en) | Comprehensive wiring method and attack early warning method based on enclosure wall perimeter security system | |
| CN110034818B (en) | Device and system for monitoring optical cable based on intelligent optical fiber distribution system | |
| CN108226819A (en) | A kind of ground magnetic field monitoring system and method based on fiber grating | |
| CN104021637B (en) | Cable antitheft method based on distributed cable sensing and cable antitheft device based on distributed cable sensing |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200508 |
|
| RJ01 | Rejection of invention patent application after publication |