Strain prediction method and system of overhead power optical cable, terminal equipment and storage medium

Abstract

The invention discloses a strain prediction method and system for an overhead power optical cable, terminal equipment and a storage medium, and the method comprises the steps: carrying out the future strain value prediction of a to-be-measured optical cable fiber core through a trained strain prediction model according to a real-time temperature value and a real-time strain value of the to-be-measured optical cable fiber core, and obtaining a predicted future strain value, and according to the predicted future strain value, the future strain value of the fiber core of the optical cable to be measured is predicted by constructing the strain prediction model, so that the strain condition of the fiber core of the optical cable to be measured is predicted in advance, and the normal operation and communication quality of the fiber core of the optical cable are guaranteed by taking maintenance measures in time. Therefore, the reliability, the stability and the service level of the network are improved, and the problem that the prior art can only monitor the current strain state of the optical cable fiber core, cannot predict the strain condition of the optical cable fiber core caused by temperature, and cannot perform early warning maintenance on the optical cable fiber core in time is solved.

Description

Technical Field

[0001] The present invention relates to the field of strain prediction of overhead power optical cables, and in particular to a strain prediction method, system, terminal equipment and storage medium of overhead power optical cables. Background Art

[0002] During operation, overhead power lines are affected by factors such as wind, temperature, ice and snow, which can cause changes in line tension. This tension change will be transmitted to the fiber core in the optical cable, causing strain. During the installation of optical cables, if the installation method is improper, such as too small an angle or too many inflection points, the fiber core will be subjected to additional stress and deformation. Overhead power lines may be affected by external forces, such as strong winds, ice, external engineering construction, etc. These external forces will be transmitted to the fiber core in the optical cable, causing strain.

[0003] The strain of the optical cable core will cause the physical structure of the core in the optical cable to change, thus affecting the transmission of the optical signal. This may cause problems such as attenuation of the optical signal, increased delay, and misalignment, thus affecting the communication quality and reliability of the optical cable. When the core strain exceeds its tolerance range, it may cause the core to break. The core break will cause the optical cable to be disconnected, making it impossible to transmit the optical signal, thereby causing communication interruption or seriously affecting the communication quality. The core strain will cause pressure on the outer layer or sheath of the optical cable, resulting in physical damage to the optical cable. This may cause problems such as the degradation of the insulation performance of the optical cable and the entry of external environmental media into the optical cable, thus affecting the service life and stability of the optical cable. The core strain may affect other devices connected to the optical cable. For example, the equipment connected to the optical cable may be affected by electrical failures, communication interruptions, etc. caused by core deformation or breakage.

[0004] Therefore, understanding the strain of the optical cable core and predicting the future trend of the strain of the optical cable core are important for the safe operation of the optical cable. Traditionally, Brillouin Optical Time-Domain Reflectometry is used to monitor the strain of the optical cable core. However, this method can only monitor the strain of the current state and cannot predict the strain state of the optical cable core in advance, and thus cannot issue a timely warning. Summary of the invention

[0005] The present invention provides a strain prediction method, system, terminal equipment and storage medium for an overhead power optical cable, which can solve the problem that the prior art can only monitor the current strain state of the optical cable core but cannot predict the future strain of the optical cable core due to temperature values, and thus cannot timely perform early warning maintenance on the optical cable core.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a strain prediction method for an overhead power optical cable, comprising:

[0007] Obtain the real-time temperature value and real-time strain value of the optical cable core to be tested;

[0008] Inputting the real-time temperature value and real-time strain value of the optical cable core to be tested into the trained strain prediction model, so that the strain prediction model predicts the future strain value according to the temperature value and strain value of the optical cable core to be tested, and obtains the predicted future strain value;

[0009] The model training of the strain prediction model includes: collecting the temperature value and the actual strain value of the optical cable core to be measured at each historical moment, and pre-processing and fusing the temperature value and the actual strain value of the optical cable core to be measured at each historical moment to obtain a temperature-strain historical time series data set;

[0010] According to the temperature-strain historical time series data set, the predicted strain value at each historical moment is calculated through the memory unit in the hidden layer and the output layer of the strain prediction model;

[0011] According to the predicted strain values ​​at each historical moment and the actual strain values ​​at each historical moment, the loss value is calculated through the loss function. According to the loss value, the model parameters of the strain prediction model are optimized until the loss value converges to obtain a trained strain prediction model.

[0012] Furthermore, the temperature values ​​and actual strain values ​​of the optical cable core to be measured at each historical moment are preprocessed and fused to obtain a temperature-strain historical time series data set of the optical cable core to be measured, including:

[0013] Cleaning the temperature value and actual strain value of the optical cable core to be measured at each historical moment to obtain the cleaned temperature value and actual strain value of the optical cable core to be measured at each historical moment;

[0014] The temperature values ​​and actual strain values ​​of the optical cable core to be tested at each historical moment after cleaning are spliced ​​and fused according to the time point to obtain the temperature-strain historical time series data set of the optical cable core to be tested.

[0015] Furthermore, the predicted strain values ​​at each historical moment are calculated through the memory unit in the hidden layer and the output layer of the strain prediction model according to the temperature-strain historical time series data set, including:

[0016] The hidden state at a certain time point in the temperature-strain history time series data set is calculated by using the memory unit to calculate the hidden state at the time point.

[0017] According to the hidden state at that time point, the predicted strain value at each historical moment is calculated through the output layer.

[0018] Furthermore, the hidden state at this time point is calculated by the following formula:

[0019] S t =f(W*S t-1 +U*X t );

[0020] Among them, the S t represents the hidden state at the time point t; f represents the activation function of the hidden layer; W represents the weight of the hidden layer; S t-1 represents the hidden state at the previous time point; U represents the data weight of the input hidden layer; X t Represents the temperature-strain history data at time point t input to the hidden layer.

[0021] Furthermore, the predicted strain value at each historical moment is calculated by the following formula:

[0022] O t =g(V*S t );

[0023] Among them, the O t represents the predicted strain value at each historical moment; g represents the activation function of the output layer; V represents the weight of the output layer; S t represents the hidden state at time point t.

[0024] Further, after the temperature values ​​and actual strain values ​​of the optical cable core to be measured at each historical moment are preprocessed and fused to obtain the temperature-strain historical time series data set of the optical cable core to be measured, the method further includes:

[0025] The temperature-strain historical time series data set of the optical cable core to be tested is subjected to range normalization processing to obtain a standardized temperature-strain time series data set.

[0026] Furthermore, the strain prediction method for an overhead power optical cable further includes:

[0027] The predicted future strain value is compared with the preset strain threshold. When the predicted future strain value is greater than the preset strain threshold, a fault warning is initiated for the optical cable core to be tested. According to the fault warning, maintenance personnel are notified to perform maintenance, and network service operators are notified to adjust network resource allocation.

[0028] Based on the above method embodiment, the present invention provides a corresponding system embodiment;

[0029] An embodiment of the present invention provides a strain prediction system for an overhead power optical cable, comprising: a data acquisition module, a future strain value prediction module, and a model training module;

[0030] The data acquisition module is used to obtain the real-time temperature value and real-time strain value of the optical cable core to be tested;

[0031] The future strain value prediction module is used to input the real-time temperature value and real-time strain value of the optical cable core to be tested into the trained strain prediction model, so that the strain prediction model predicts the future strain value according to the temperature value and strain value of the optical cable core to be tested, and obtains the predicted future strain value;

[0032] The model training module is used to collect the temperature value and the actual strain value of the optical cable core to be measured at each historical moment, and pre-process and fuse the temperature value and the actual strain value of the optical cable core to be measured at each historical moment to obtain the temperature-strain historical time series data set of the optical cable core to be measured. According to the temperature-strain historical time series data set, the predicted strain value at each historical moment is calculated through the memory unit in the hidden layer and the output layer of the strain prediction model. According to the predicted strain value at each historical moment and the actual strain value at each historical moment, the loss value is calculated through the loss function. According to the loss value, the model parameters of the strain prediction model are optimized until the loss value converges to obtain a trained strain prediction model.

[0033] Based on the above-mentioned method embodiment, the present invention provides a corresponding terminal device embodiment, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, a strain prediction method for an overhead power optical cable as described in the present invention is implemented.

[0034] Based on the above method embodiment, the present invention provides a corresponding computer-readable storage medium embodiment, including: a stored computer program, which controls the device where the computer-readable storage medium is located to execute a strain prediction method for an overhead power optical cable as described in the present invention when the computer program is running.

[0035] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0036] The present invention predicts the future strain value of the optical cable core to be tested according to the real-time temperature value and real-time strain value of the optical cable core to be tested by a trained strain prediction model, obtains the predicted future strain value, and according to the predicted future strain value, that is, the present invention predicts the future strain value of the optical cable core to be tested by constructing a strain prediction model, thereby predicting the strain condition of the optical cable core to be tested in advance, so that maintenance measures can be taken in time to ensure the normal operation and communication quality of the optical cable core, thereby improving the reliability, stability and service level of the network, and solving the problem that the prior art can only monitor the current strain state of the optical cable core, but cannot predict the strain of the optical cable core caused by temperature, and thus cannot timely perform early warning maintenance on the optical cable core. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 : A flow chart of the steps of a strain prediction method for an overhead power optical cable provided by an embodiment of the present invention;

[0038] Figure 2 : A flow chart of the model training steps of the strain prediction model provided in an embodiment of the present invention;

[0039] Figure 3 : A structural diagram of a strain prediction model provided by an embodiment of the present invention;

[0040] Figure 4 : A schematic diagram of a hidden layer of a strain prediction model provided in an embodiment of the present invention;

[0041] Figure 5 , which is a strain prediction result diagram of a strain prediction method based on an overhead power optical cable provided in an embodiment of the present invention;

[0042] Figure 6 : A system structure diagram of a strain prediction system for an overhead power optical cable provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] In the description of the present invention, it should be understood that the term "first" is only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features.

[0045] Embodiment 1:

[0046] Reference Figure 1 , is a flowchart of a strain prediction method for an overhead power optical cable provided by an embodiment of the present invention, the method comprising at least the following steps:

[0047] Step S1: obtaining the real-time temperature value and real-time strain value of the optical cable core to be tested;

[0048] In this embodiment, the real-time temperature value and the real-time strain value of the optical cable core to be tested are collected by a temperature sensor and a strain sensor respectively.

[0049] Step S2: inputting the real-time temperature value and real-time strain value of the optical cable core to be tested into the trained strain prediction model, so that the strain prediction model predicts the future strain value according to the temperature value and strain value of the optical cable core to be tested, and obtains the predicted future strain value;

[0050] In this embodiment, the predicted future strain value is compared with the preset strain threshold. When the predicted future strain value is greater than the preset strain threshold, a fault warning is initiated for the optical cable core to be tested, and maintenance personnel are notified to perform maintenance based on the fault warning, and the network service operator is notified to adjust the network resource allocation.

[0051] In this embodiment, refer to Figure 2 , is a flow chart of the model training steps of the strain prediction model provided in an embodiment of the present invention, wherein the model training of the strain prediction model includes at least the following steps:

[0052] Step A1: collecting the temperature value and actual strain value of the optical cable core to be measured at each historical moment, and pre-processing and fusing the temperature value and actual strain value of the optical cable core to be measured at each historical moment to obtain a temperature-strain historical time series data set;

[0053] In this embodiment, the temperature value and the actual strain value of the optical cable core to be measured at each historical moment are preprocessed and fused to obtain a temperature-strain historical time series data set of the optical cable core to be measured, including:

[0054] Performing data cleaning on the temperature value and actual strain value of the optical cable core to be measured at each historical moment to obtain the cleaned temperature value and actual strain value of the optical cable core to be measured at each historical moment; wherein the data cleaning includes but is not limited to missing value processing, abnormal value processing and repeated value processing;

[0055] The temperature values ​​and actual strain values ​​of the optical cable core to be tested at each historical moment after cleaning are spliced ​​and fused according to the time point to obtain the temperature-strain historical time series data set of the optical cable core to be tested.

[0056] In this embodiment, after the temperature values ​​and actual strain values ​​of the optical cable core to be measured at each historical moment are preprocessed and fused to obtain the temperature-strain historical time series data set of the optical cable core to be measured, the following further includes:

[0057] The temperature-strain historical time series data set of the optical cable core to be tested is subjected to range normalization processing to obtain a standardized temperature-strain time series data set; wherein the range normalization is maximum and minimum normalization.

[0058] Step A2: According to the temperature-strain historical time series data set, the predicted strain value at each historical moment is calculated through the memory unit in the hidden layer and the output layer of the strain prediction model;

[0059] In this embodiment, refer to Figure 3 :Structural diagram of strain prediction model provided by the embodiment of the present invention, refer to Figure 4 : A schematic diagram of the hidden layer of the strain prediction model provided in an embodiment of the present invention, wherein a standardized temperature-strain time series data set is obtained through the input layer of the strain prediction model and sent to the hidden layer of the strain prediction model, and the temperature-strain historical data at a certain time point in the temperature-strain historical time series data set and its corresponding hidden state at the previous time point are calculated through the memory unit of the hidden layer, and the predicted strain value at each historical moment is calculated according to the hidden state at the time point through the output layer; wherein the hidden layer of the strain prediction model includes a plurality of memory units; and the strain prediction model includes but is not limited to an RNN neural network model.

[0060] In this embodiment, the hidden state at this time point is calculated by the following formula:

[0061] S t =f(W*S t-1 +U*X t );

[0062] Among them, the S t represents the hidden state at the time point t; f represents the activation function of the hidden layer; W represents the weight of the hidden layer; S t-1 represents the hidden state at the previous time point; U represents the data weight of the input hidden layer; X t Represents the temperature-strain history data at time point t input to the hidden layer.

[0063] In this embodiment, the predicted strain value at each historical moment is calculated by the following formula:

[0064] O t =g(V*S t );

[0065] Among them, the O t represents the predicted strain value at each historical moment; g represents the activation function of the output layer; V represents the weight of the output layer; S t represents the hidden state at time point t.

[0066] Step A3: According to the predicted strain values ​​at each historical moment and the actual strain values ​​at each historical moment, the loss value is calculated by the loss function. According to the loss value, the model parameters of the strain prediction model are optimized until the loss value converges to obtain a trained strain prediction model.

[0067] In this embodiment, the loss function includes but is not limited to a mean square error function and a mean absolute error function.

[0068] In this embodiment, the model parameter optimization methods include but are not limited to stochastic gradient descent optimization algorithm, small batch gradient descent algorithm and Adam algorithm.

[0069] In this embodiment, refer to Figure 5 , which is a strain prediction result diagram of a strain prediction method based on an overhead power optical cable provided in an embodiment of the present invention. According to the strain prediction result diagram, it can be seen that the future strain value calculated by the strain prediction method based on an overhead power optical cable is consistent with the true strain value.

[0070] Embodiment 2:

[0071] Reference Figure 6 : A system structure diagram of a strain prediction system for an overhead power optical cable provided by an embodiment of the present invention, the system comprising: a data acquisition module, a future strain value prediction module and a model training module;

[0072] The data acquisition module is used to obtain the real-time temperature value and real-time strain value of the optical cable core to be tested;

[0073] The future strain value prediction module is used to input the real-time temperature value and real-time strain value of the optical cable core to be tested into the trained strain prediction model, so that the strain prediction model predicts the future strain value according to the temperature value and strain value of the optical cable core to be tested, and obtains the predicted future strain value;

[0074] The model training module is used to collect the temperature value and the actual strain value of the optical cable core to be measured at each historical moment, and pre-process and fuse the temperature value and the actual strain value of the optical cable core to be measured at each historical moment to obtain the temperature-strain historical time series data set of the optical cable core to be measured. According to the temperature-strain historical time series data set, the predicted strain value at each historical moment is calculated through the memory unit in the hidden layer and the output layer of the strain prediction model. According to the predicted strain value at each historical moment and the actual strain value at each historical moment, the loss value is calculated through the loss function. According to the loss value, the model parameters of the strain prediction model are optimized until the loss value converges to obtain a trained strain prediction model.

[0075] Based on the above method embodiment, another embodiment is provided;

[0076] Another embodiment of the present invention provides a strain prediction terminal device for an overhead power optical cable, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements a strain prediction method for an overhead power optical cable as described in any one of the above method embodiments of the present invention.

[0077] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the strain prediction terminal device of the overhead power optical cable.

[0078] The strain prediction terminal device of the overhead power optical cable can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The strain prediction terminal device of the overhead power optical cable can include, but is not limited to, a processor and a memory. Those skilled in the art can understand that, for example, the strain prediction terminal device of the overhead power optical cable can also include an input and output device, a network access device, a bus, etc.

[0079] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the strain prediction terminal device of the overhead power optical cable, and uses various interfaces and lines to connect the various parts of the strain prediction terminal device of the overhead power optical cable.

[0080] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the strain prediction terminal device of the overhead power optical cable by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0081] Based on the above method embodiment, another embodiment is provided;

[0082] Another embodiment of the present invention provides a storage medium, including a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute a strain prediction method for an overhead power optical cable as described in any one of the above method embodiments of the present invention.

[0083] Wherein, the above-mentioned storage medium is a computer-readable storage medium. The module / unit integrated with the strain prediction system / terminal equipment of the overhead power optical cable can be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as an independent product. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0084] It should be noted that the above-mentioned terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that the above-mentioned terminal device is merely an example and does not constitute a limitation on the terminal device. It may include more or fewer components, or a combination of certain components, or different components.

[0085] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A strain prediction method for an overhead power optical cable, characterized in that: include: Obtain the real-time temperature value and real-time strain value of the optical cable core to be tested; Inputting the real-time temperature value and real-time strain value of the optical cable core to be tested into the trained strain prediction model, so that the strain prediction model predicts the future strain value according to the temperature value and strain value of the optical cable core to be tested, and obtains the predicted future strain value; The model training of the strain prediction model includes: collecting the temperature value and the actual strain value of the optical cable core to be measured at each historical moment, and pre-processing and fusing the temperature value and the actual strain value of the optical cable core to be measured at each historical moment to obtain a temperature-strain historical time series data set; According to the temperature-strain historical time series data set, the predicted strain value at each historical moment is calculated through the memory unit in the hidden layer and the output layer of the strain prediction model; According to the predicted strain values ​​at each historical moment and the actual strain values ​​at each historical moment, the loss value is calculated through the loss function. According to the loss value, the model parameters of the strain prediction model are optimized until the loss value converges to obtain a trained strain prediction model.

2. The strain prediction method of an overhead power optical cable according to claim 1, characterized in that: The temperature value and actual strain value of the optical cable core to be measured at each historical moment are pre-processed and fused to obtain a temperature-strain historical time series data set of the optical cable core to be measured, including: Cleaning the temperature value and actual strain value of the optical cable core to be measured at each historical moment to obtain the cleaned temperature value and actual strain value of the optical cable core to be measured at each historical moment; The temperature values ​​and actual strain values ​​of the optical cable core to be tested at each historical moment after cleaning are spliced ​​and fused according to the time point to obtain the temperature-strain historical time series data set of the optical cable core to be tested.

3. The strain prediction method for an overhead power optical cable according to claim 1, characterized in that: The method of calculating the predicted strain value at each historical moment through the memory unit in the hidden layer and the output layer of the strain prediction model according to the temperature-strain historical time series data set includes: The hidden state at a certain time point in the temperature-strain history time series data set is calculated by using the memory unit to calculate the hidden state at the time point. According to the hidden state at that time point, the predicted strain value at each historical moment is calculated through the output layer.

4. The strain prediction method for an overhead power optical cable according to claim 3, characterized in that: The hidden state at this time point is calculated by the following formula: S t =f(W*S t-1 +U*X t ); Among them, the S t represents the hidden state at the time point t; f represents the activation function of the hidden layer; W represents the weight of the hidden layer; S t-1 represents the hidden state at the previous time point; U represents the data weight of the input hidden layer; X t Represents the temperature-strain history data at time point t input to the hidden layer.

5. The strain prediction method for an overhead power optical cable according to claim 3, characterized in that: The predicted strain value at each historical moment is calculated by the following formula: O t =g(V*S t ); Among them, the O t represents the predicted strain value at each historical moment; g represents the activation function of the output layer; V represents the weight of the output layer; S t represents the hidden state at time point t.

6. The strain prediction method of an overhead power optical cable according to claim 1, characterized in that: After the temperature values ​​and actual strain values ​​of the optical cable core to be measured at each historical moment are preprocessed and fused to obtain the temperature-strain historical time series data set of the optical cable core to be measured, the method further includes: The temperature-strain historical time series data set of the optical cable core to be tested is subjected to range normalization processing to obtain a standardized temperature-strain time series data set.

7. The strain prediction method of an overhead power optical cable according to claim 1, characterized in that: Also includes: The predicted future strain value is compared with the preset strain threshold. When the predicted future strain value is greater than the preset strain threshold, a fault warning is initiated for the optical cable core to be tested. According to the fault warning, maintenance personnel are notified to perform maintenance, and network service operators are notified to adjust network resource allocation.

8. A strain prediction system for an overhead power optical cable, characterized in that: include: Data acquisition module, future strain value prediction module and model training module; The data acquisition module is used to obtain the real-time temperature value and real-time strain value of the optical cable core to be tested; The future strain value prediction module is used to input the real-time temperature value and real-time strain value of the optical cable core to be tested into the trained strain prediction model, so that the strain prediction model predicts the future strain value according to the temperature value and strain value of the optical cable core to be tested, and obtains the predicted future strain value; The model training module is used to collect the temperature value and the actual strain value of the optical cable core to be measured at each historical moment, and pre-process and fuse the temperature value and the actual strain value of the optical cable core to be measured at each historical moment to obtain the temperature-strain historical time series data set of the optical cable core to be measured. According to the temperature-strain historical time series data set, the predicted strain value at each historical moment is calculated through the memory unit in the hidden layer and the output layer of the strain prediction model. According to the predicted strain value at each historical moment and the actual strain value at each historical moment, the loss value is calculated through the loss function. According to the loss value, the model parameters of the strain prediction model are optimized until the loss value converges to obtain a trained strain prediction model.

9. A strain prediction terminal device for an overhead power optical cable, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements a strain prediction method for an overhead power optical cable as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute the strain prediction method for an overhead power optical cable according to any one of claims 1 to 7.

Images