Artificial intelligence-based pipeline optical cable laying status monitoring method and system

Abstract

The present invention proposes an artificial intelligence-based pipeline optical cable installation status monitoring method and system. The method includes: obtaining optical cable vibration signals and generating a vibration feature dataset based on the optical cable vibration signals; constructing a mechanical equilibrium equation based on the vibration features of the vibration feature dataset to calculate the stress state of the optical cable under different pipeline environments; obtaining the current installation tension, generating a control strategy, adjusting the installation tension, and obtaining an updated tension value; constructing an anomaly detection model based on spatiotemporal features to generate anomaly scores and identify in real time whether the optical cable has anomalies; and generating an updated installation strategy and construction quality report based on the corrected tension control signal. The present invention can effectively solve the problems of stress anomalies, monitoring lag, and lack of intelligent optimization in the existing technology, and improve the safety, stability, and construction efficiency of optical cable installation.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence technology, and in particular relates to a pipeline optical cable laying status monitoring method and system based on artificial intelligence. Background Art

[0002] Optical cable laying is a critical component of modern communications infrastructure construction, widely used in urban underground communication pipelines, submarine optical cable transmission, optical fiber composite cables (OPGW) in high-voltage power systems, and communication networks along railways and highways. Traditional optical cable laying methods typically rely on manual experience or semi-automated equipment, combined with external monitoring methods such as tension monitors and fiber Bragg grating (FBG) sensors to assess laying quality. However, in long-distance, highly complex pipeline environments, these traditional methods suffer from multiple technical drawbacks, impacting the construction quality and long-term reliability of the optical cables.

[0003] First, traditional tension control methods rely on fixed empirical values ​​or external sensors and cannot be adjusted adaptively, resulting in abnormal cable stress. During the cable laying process, the cable needs to overcome multiple factors such as pipe bending, friction, and intersection resistance. Its stress situation is nonlinear, and relying solely on fixed tension values ​​is difficult to adapt to complex laying environments. This can easily lead to the following problems: (1) Overstretching - when the pulling force is too large, the optical fiber may undergo plastic deformation, affecting the long-term signal transmission quality;

[0004] (2) Looseness or accumulation: When the pulling force is insufficient, the optical cable may bend or knot in the pipeline, affecting subsequent construction and stability. In addition, although some current automated equipment is equipped with a tension control system, most of them use PID or preset models, which cannot be dynamically adjusted according to the real-time environment during the actual laying process and lack intelligent adaptability.

[0005] Secondly, the monitoring methods for the laying status of optical cables rely on external sensors, which makes it difficult to provide efficient and low-cost real-time feedback during the laying process. Currently, commonly used optical fiber status monitoring methods include fiber Bragg grating (FBG), distributed fiber sensing (DTS / DAS), laser radar (LiDAR) scanning, and visual inspection. Although these methods can evaluate the status of optical cables to a certain extent, they have the following problems: (1) High cost - FBG sensors require additional installation and maintenance, and equipment such as LiDAR is expensive and not suitable for large-scale laying scenarios; (2) Complex installation - These monitoring devices need to be installed in conjunction with optical cable laying equipment and can only be used under specific working conditions. For example, LiDAR can usually only be used for short-distance visual pipelines and is difficult to apply to narrow underground pipelines or submarine optical cables; (3) Data update lag - Traditional monitoring systems mostly adopt a post-detection mode, that is, quality assessment is carried out after the optical cable is laid. It is impossible to make real-time adjustments during the construction process, resulting in problems that are difficult to remedy when they are discovered. Therefore, the current optical cable laying monitoring technology has significant limitations in long distances, complex terrain, and dynamic environments, and cannot meet the needs of modern high-precision optical cable construction.

[0006] Furthermore, current optical cable installation quality optimization technologies mostly focus on independent tension control or single state monitoring, lacking a unified intelligent optimization system that integrates installation state sensing and dynamic tension control. The installation quality of optical cables in ducts is directly affected by real-time tension. Without real-time sensing of the cable's stress and state changes during installation, effective control is difficult. Therefore, a low-cost, high-precision, and adaptively adjustable optical cable installation state monitoring and intelligent tension control solution would greatly improve the safety, stability, and construction efficiency of optical cable installation, and is a key area where current technological breakthroughs are urgently needed. Summary of the Invention

[0007] The purpose of the present invention is to design an artificial intelligence-based pipeline optical cable laying status monitoring method and system. The laying status is perceived through the micro-vibration signal of the optical cable itself, and combined with optical cable-pipeline interaction mechanics modeling + AI adaptive tension control, the laying process is dynamically optimized to solve the problems of abnormal force, status monitoring lag, high sensor dependence, etc. existing in traditional methods.

[0008] In order to achieve the above-mentioned object, in a first aspect of the present invention, a pipeline optical cable laying status monitoring method based on artificial intelligence is provided, and the method comprises:

[0009] Acquire an optical cable vibration signal and generate a vibration feature data set based on the optical cable vibration signal; the vibration feature data set includes vibration features at different spatial positions;

[0010] Based on the vibration characteristics of the vibration feature dataset, a mechanical equilibrium equation is constructed to calculate the stress state of the optical cable in different pipeline environments, thereby obtaining the stress state of the optical cable during installation. The stress state includes friction force distribution, bending stress, and optimal traction force.

[0011] Obtaining the current laying tension, establishing a tension adjustment control model based on the optimal pulling force to generate a control strategy for the current laying tension, adjusting the laying tension to obtain an updated tension value; the tension adjustment control model dynamically adjusts the current laying tension based on the tension adaptive adjustment factor so that the output tension of the optical cable pulling equipment meets the dynamic optimization target;

[0012] An anomaly detection model based on spatiotemporal characteristics is constructed to generate anomaly scores, identifying in real time whether there are any anomalies in the optical cable. When an anomaly is detected, the laying tension or the movement of the laying equipment is adjusted to obtain a corrected tension control signal.

[0013] Based on the corrected tension control signal, combined with the stable stress state in the actual engineering process, whether there are abnormal intervention adjustments, and whether it meets the standardized construction requirements, the construction quality score and the corresponding construction influencing factors are determined. Finally, based on the construction quality score and the corresponding construction influencing factor matrix composed of the construction influencing factors, an updated laying strategy and construction quality report are generated.

[0014] Preferably, the step of acquiring the optical cable vibration signal and generating a vibration feature data set based on the optical cable vibration signal specifically includes:

[0015] Through distributed acoustic sensing technology, the dynamic change part of Rayleigh scattering is extracted as the original signal. The local window demeaning filtering method is used to suppress the background noise of the original signal to obtain the denoised vibration signal.

[0016] Performing short-time Fourier transform on the denoised vibration signal using a multi-scale signal analysis method to obtain time-frequency characteristics;

[0017] Adaptive frequency band filtering is performed on the time-frequency features to enhance the focus on the laying-related signals, thereby obtaining filtered time-frequency features, and then extracting key vibration features from the filtered time-frequency features; the key vibration features include instantaneous amplitude, instantaneous frequency, and energy distribution;

[0018] Based on the extracted key vibration features, a local weighted smoothing strategy is used to eliminate the influence of local outliers, and a piecewise normalization strategy is used to normalize the key features processed by the local weighted smoothing strategy to obtain the normalized vibration features and form a vibration feature dataset.

[0019] Preferably, the segmented normalization strategy includes:

[0020] Calculate the local mean μ per 100 meters of optical cable l and standard deviation σ l .

[0021] Preferably, the vibration characteristics of the vibration characteristic data set are used to construct a mechanical equilibrium equation, calculate the stress state of the optical cable in different pipeline environments, and obtain the stress state of the optical cable during the laying process, including:

[0022] Obtain a vibration characteristic dataset and introduce an adaptive adjustment item based on vibration energy distribution to determine the impact of optical cable vibration on stress, including:

[0023]

[0024] Where T(x) is the pulling force of the optical cable at position x; μ is the friction coefficient of the inner wall of the pipe; F f (x) is the friction force between the optical cable and the pipe; M b (x) is the bending stress generated by the cable at the bend; E s (x) is the vibration energy distribution; γ is the vibration-stress coupling coefficient, which represents the influence of the optical cable vibration energy on the stress state;

[0025] According to the fact that the friction force between the optical cable and the pipeline is mainly determined by the contact pressure P(x) and the friction coefficient μ between the optical cable and the pipeline, a dynamic correction term based on the vibration characteristics is set to make the friction force F between the optical cable and the pipeline f (x) It can adaptively adjust according to the vibration characteristics of the optical cable to obtain the corrected friction force between the optical cable and the pipeline;

[0026] Based on the influence of cable vibration on the force and the corrected friction between the cable and the pipe, the optimal traction force range T of the cable under different laying environments is determined. opt ,include:

[0027]

[0028] Where L is the total length of the optical cable; β is the adjustment parameter for the influence of local vibration of the optical cable on the traction force, P(x) is the normal pressure of the optical cable at position x, A(x) is the instantaneous amplitude of the optical cable at position x, and A max It is the maximum amplitude during the laying process.

[0029] Preferably, the tension adjustment control model is established based on the optimal traction force to generate a control strategy for the current laying tension, and the laying tension is adjusted to obtain an updated tension value, including:

[0030] The force adaptive adjustment factor λ(x) is introduced to dynamically adjust to the dynamic changes of the force environment during the laying process; the force adaptive adjustment factor λ(x) is expressed as:

[0031]

[0032] Among them, λ(x) is the tension adaptive adjustment factor; k1, k2, k3 are adjustment coefficients, which control the influence of different factors on the adjustment rate; E s (x) is the vibration energy of the optical cable at point x; E max dF is the maximum vibration energy value during the entire laying process f (x) / dx is the spatial gradient of friction force, which is used to correct the stability of tension adjustment in the friction force mutation area;

[0033] Based on the force adaptive adjustment factor λ(x), a smooth adjustment term ΔT(x) is used to adjust the output tension of the optical cable pulling equipment to meet the dynamic optimization goal.

[0034] updating the control signal of the traction device according to the smooth adjustment term ΔT(x), so that it acts on the actual tension control during the laying process to obtain an updated laying tension;

[0035] The updated laying tension, the force adaptive adjustment factor and the recorded historical tension change data are combined and output as an adjusted tension control strategy.

[0036] Preferably, the force adaptive adjustment factor λ(x) is used to ensure that the current laying tension value T cur Departure from the optimal traction range T opt When the current laying tension value T cur Automatic adjustment is performed, and / or, when the optical cable vibrates violently locally, the tension is corrected to reduce the vibration effect, and / or, in areas where the friction force changes sharply, the adjustment coefficient k3 ensures that the system does not experience sudden tension changes, avoiding overloading or slipping of the optical cable;

[0037] The tension control strategy includes:

[0038] Slow adjustment phase: When |T cur -T opt When | is small, λ(x) is close to 1, and the adjustment rate is low, avoiding overcorrection;

[0039] Rapid adjustment phase: When |T cur -T opt | Large, or local vibration is severe (E s (x) is larger), λ(x) becomes larger, and the adjustment rate is accelerated;

[0040] Adjustment of friction force mutation area: When dF f When (x) / dx changes dramatically, the adjustment factor λ(x) limits the adjustment range to prevent sudden tightening or loosening of the optical cable.

[0041] Preferably, the anomaly detection model based on temporal and spatial features is constructed to generate an anomaly score and identify in real time whether an optical cable has an anomaly, including:

[0042] A dynamic anomaly scoring function is constructed by integrating the cable tension change trend, vibration abnormality, and friction mutation characteristics to determine the anomaly score, which is used to measure the abnormality of the current state of the cable. The anomaly score Γ(x, t) is set as follows:

[0043]

[0044] Where Γ(x, t) is the abnormality score, which is used to measure the abnormality of the current state of the optical cable; w1, w2, and w3 are weight parameters, which respectively adjust the influence of tension change, vibration energy, and friction force mutation; dT new / dx is the spatial gradient of tension along the optical cable; E s (x) is the vibration energy of the optical cable at point x; dF f (x) / dx is the spatial rate of change of friction force;

[0045] A dynamic threshold for adaptive adjustment items based on historical anomaly trends is set according to the anomaly score to determine anomalies; when the anomaly score is greater than the dynamic threshold, the adjustment mechanism is triggered.

[0046] Preferably, the laying adjustment mechanism includes:

[0047] If a sudden change in tension is detected, i.e. |dT new If / dx| is too large, reduce the traction force of the traction equipment and slowly adjust T new Make it gradually return to the optimal traction range T opt ;

[0048] If a local vibration anomaly is detected, E s (x) If it is too large, reduce the laying speed and adjust the angle of the optical cable entering the pipe to reduce the impact of local vibration;

[0049] If a sudden change in friction force is detected, i.e. |dF f If (x) / dx| is too large, suspend laying and check whether there are any obstacles inside the pipeline or whether the optical cable is entangled.

[0050] Preferably, the adjustment range of the construction quality score is expressed as:

[0051] When the tension is stable during the laying process, that is, the adjusted laying tension T adj(x) Close to the optimal traction range T opt When , the score increases;

[0052] When the frequency of abnormal intervention adjustment is low, that is, the abnormal score Γ(x,t) is low, the score is improved;

[0053] When the tension changes smoothly along the cable, that is, |dT adj When / dx| is low, the score increases;

[0054] The construction influencing factor matrix records the contribution of different factors to the construction quality score.

[0055] In a second aspect of the present invention, a pipeline optical cable laying status monitoring system based on artificial intelligence is provided, the system comprising:

[0056] An optical cable vibration signal acquisition module is used to acquire the optical cable vibration signal and generate a vibration feature data set based on the optical cable vibration signal; the vibration feature data set includes vibration features at different spatial positions;

[0057] The optical cable vibration signal analysis module is used to construct a mechanical equilibrium equation based on the vibration characteristics of the vibration feature data set, calculate the stress state of the optical cable in different pipeline environments, and obtain the stress state of the optical cable during installation; wherein the stress state includes friction force distribution, bending stress, and optimal traction force;

[0058] A laying adjustment module is used to obtain the current laying tension, establish a tension adjustment control model based on the optimal pulling force, generate a control strategy for the current laying tension, adjust the laying tension, and obtain an updated tension value; the tension adjustment control model dynamically adjusts the current laying tension based on the tension adaptive adjustment factor, so that the output tension of the optical cable pulling equipment meets the dynamic optimization target;

[0059] The laying optimization module is used to build an anomaly detection model based on spatiotemporal characteristics to generate anomaly scores, identify in real time whether there are any anomalies in the optical cable, and adjust the laying tension or the movement of the laying equipment when an anomaly is detected to obtain a corrected tension control signal.

[0060] The monitoring report generation module is used to determine the construction quality score and the corresponding construction influencing factors based on the corrected tension control signal, combined with the stable stress state in the actual engineering process, whether there are abnormal intervention adjustments, and whether it meets the standardized construction requirements. Finally, based on the construction quality score and the corresponding construction influencing factor matrix composed of the construction influencing factors, an updated laying strategy and construction quality report are generated.

[0061] The beneficial technical effects of the present invention are at least as follows:

[0062] (1) Optical cable’s own vibration signal sensing technology enables real-time monitoring of the installation status without external sensors.

[0063] This invention innovatively uses the optical cable's own micro-vibration signals (generated by factors such as pipeline friction, traction tension, and bending stress) to sense the installation status, eliminating the need for external sensors. Vibration patterns, frequency changes, and strain information along the optical cable are acquired through distributed optical fiber sensing (DAS) or fiber Rayleigh scattering analysis. Signal processing combined with machine learning methods are used to construct normal vibration patterns, allowing real-time detection of twisting, excessive bending, abnormal stress, and other issues in the optical cable. This approach overcomes the limitations of traditional external sensor reliance, reduces installation costs, and improves the universality and real-time nature of installation monitoring.

[0064] (2) Optical cable-pipeline interaction mechanical modeling and AI intelligent tension control to achieve real-time laying optimization.

[0065] The present invention uses finite element analysis (FEM) + deep learning to construct an interactive mechanical model of the optical cable in the pipeline, and predicts the optimal tension range under different laying environments (such as pipeline curvature, friction coefficient, and traction resistance). Combined with reinforcement learning (RL) + adaptive PID control, an intelligent tension control system is constructed, which can dynamically adjust the tension of the traction equipment according to real-time vibration signal feedback during the laying process, ensuring that the optical cable is always in the optimal tension range, and preventing the optical cable from being broken, loosened, or bent and damaged. Compared with the traditional fixed tension mode, the intelligent control system of the present invention has self-learning capabilities, can adapt to different laying environments, and improve construction efficiency.

[0066] (3) Real-time anomaly detection and adaptive optimization to improve installation quality and safety.

[0067] This invention combines time-series signal analysis with AI anomaly detection technology to build a laying status database. It also employs deep learning methods like Transformer / LSTM to identify anomalies such as sudden tension changes and cable twisting. Once an anomaly is detected, the system automatically adjusts the laying speed, optimizes the pulling tension, and sends an early warning signal to construction personnel, preventing construction problems before they occur, rather than detecting them afterward.

[0068] Through these innovations, the present invention provides a comprehensive solution for monitoring the state of optical cable installation and intelligent tension control. This solution effectively addresses existing issues such as abnormal force distribution, delayed monitoring, and a lack of intelligent optimization, improving the safety, stability, and efficiency of optical cable installation. This solution is suitable for a variety of complex installation scenarios, including urban pipeline networks, submarine optical cables, long-distance fiber-optic communications, and high-voltage cables, and has broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without inventive effort.

[0070] Figure 1 This is a flow chart of the pipeline optical cable laying status monitoring method based on artificial intelligence of the present invention.

[0071] Figure 2 This is a framework diagram of the pipeline optical cable laying status monitoring system based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0072] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0073] In one or more embodiments, Figure 1 As shown, a pipeline optical cable laying status monitoring method based on artificial intelligence is disclosed, and the method includes the following steps S1-S5:

[0074] S1. Obtain an optical cable vibration signal and generate a vibration feature data set based on the optical cable vibration signal; the vibration feature data set includes vibration features at different spatial positions.

[0075] Specifically, during the installation of optical cables, the cables generate weak vibration signals due to force, friction, and bending. These vibration signals can be detected using distributed acoustic sensing (DAS) technology to extract the dynamic changes in Rayleigh scattering. In this paper, the original signal is assumed to be S(t, x), where t is time and x is the position along the cable. To eliminate the influence of environmental noise, a local window demeaning filter method is first used to suppress background noise:

[0076]

[0077] in, is the denoised vibration signal; W is the local window size; and S(t,x) is the original vibration signal. This method ensures that the long-term trend components in the signal are weakened, retaining only the short-term dynamic vibration characteristics.

[0078] Furthermore, in order to capture the core information of the cable stress state, the present invention adopts a multi-scale signal analysis method. Perform short-time Fourier transform (STFT) to generate time-frequency features:

[0079]

[0080] Among them, F(t,f,x) is the time-frequency feature; w(t) is the window function; and f is the frequency component.

[0081] In order to enhance the focus on the laying-related signals, the present invention performs adaptive frequency band filtering on F(t,f,x):

[0082] F′(t,f,x)=F(t,f,x)·1(f∈[f min ,f max ])(3)

[0083] Among them, F′(t,f,x) is the time-frequency feature after filtering; [f min ,f max ] is the frequency range related to the stress on the optical cable.

[0084] Afterwards, key vibration features are extracted, including the instantaneous amplitude:

[0085]

[0086] Instantaneous frequency:

[0087]

[0088] And the energy distribution:

[0089] E s (x)=∫ t A 2 (t,x)dt (6)

[0090] Where A(t,x) is the instantaneous amplitude; f s (t,x) is the instantaneous frequency; E s (x) is the energy distribution.

[0091] Furthermore, since the vibration signal along the optical cable is spatially non-uniform, the present invention establishes a spatiotemporal consistency correction model to eliminate the influence of local outliers. To this end, the present invention proposes a local weighted smoothing strategy:

[0092]

[0093] in, is the optimized vibration characteristic; X s (x) is the original vibration characteristic; is the Gaussian weight based on spatial distance; N is the smoothing window size; and σ is a parameter that controls the degree of smoothing. This method ensures that the information of adjacent points is reasonably integrated, thereby improving the spatial continuity of the signal.

[0094] Furthermore, due to the large difference in signal amplitude under different laying environments, the present invention Perform standardization. Use the segmented normalization strategy to calculate the local mean μ for every 100 meters of optical cable. l and standard deviation σ l , the normalized transformation is as follows:

[0095]

[0096] in, is the normalized vibration characteristic; μ l is the local mean; σ l This ensures that the data in different installation areas are within the same numerical range, which is suitable for subsequent stress modeling.

[0097] Finally, the present invention organizes and outputs The data set contains vibration characteristics at different spatial locations and provides information for subsequent cable-pipeline interaction mechanical modeling. This data set is the foundation of the entire intelligent tension control system.

[0098] S2. Based on the vibration characteristics of the vibration feature data set, a mechanical equilibrium equation is constructed to calculate the stress state of the optical cable in different pipeline environments, and the stress state of the optical cable during the installation process is obtained; wherein the stress state includes friction force distribution, bending stress, and optimal traction force.

[0099] Specifically, during the cable laying process, the cable is subjected to traction force T(x), friction force F f (x) and bending stress M b The present invention is based on the vibration characteristics obtained in step 1. A mechanical equilibrium equation is constructed to calculate the stress state of the optical cable in different pipeline environments. In order to more accurately describe the stress state of the optical cable, this paper introduces an adaptive adjustment term based on vibration energy distribution on the basis of the traditional model to consider the influence of optical cable vibration on the stress:

[0100]

[0101] Where T(x) is the pulling force of the optical cable at position x; μ is the friction coefficient of the inner wall of the pipe; F f (x) is the friction force between the optical cable and the pipe; M b (x) is the bending stress generated by the cable at the bend; E s (x) is the vibration energy distribution calculated in step 1; γ is the vibration-force coupling coefficient, which represents the influence of the optical cable vibration energy on the force state. This formula adds γE to the traditional mechanical equation. sItem (x) utilizes the spatial distribution information of the optical cable vibration energy to enable the model to more accurately reflect the stress conditions of the optical cable in different pipeline environments. In particular, when the optical cable stress is abnormal and causes drastic changes in vibration energy, this item can provide additional adjustment capabilities.

[0102] Furthermore, the friction force F f (x) is primarily determined by the contact pressure P(x) between the optical cable and the pipe and the friction coefficient μ. However, in complex installation environments, friction depends not only on these traditional factors but is also affected by the local vibration amplitude of the optical cable. To correct this, the present invention incorporates a dynamic correction term based on vibration characteristics into the traditional friction model, enabling it to adaptively adjust to the vibration characteristics of the optical cable:

[0103]

[0104] Where P(x) is the normal pressure of the optical cable at position x; A(x) is the instantaneous amplitude of the optical cable at position x, which comes from the feature extraction in step 1; A max is the maximum vibration amplitude during installation, used for normalization; α is the vibration-friction correction factor. This correction ensures that the calculated friction force is adjusted accordingly in areas of the cable with large local vibration amplitude, thereby more accurately reflecting the stress state during installation.

[0105] Furthermore, based on the mechanical equilibrium equation and the friction correction model, the present invention can calculate the optimal pulling force range T of the optical cable under different laying environments. opt , which is used for subsequent intelligent tension control. This optimization process not only considers traditional force calculations but also incorporates the vibration characteristics of the optical cable to ensure that the tension is always maintained within a safe range during the laying process:

[0106]

[0107] Where L is the total length of the optical cable installation; β is the adjustment parameter for the effect of local cable vibration on the traction force; this formula combines friction, bending stress, and cable vibration characteristics, allowing the optimal traction force calculation to dynamically adapt to different installation environments.

[0108] Finally, the stress state Y of the optical cable during the laying process is obtained f , including the friction force distribution F f (x), bending stress M b (x) and the optimal traction force T opt , used for the intelligent tension control system of step S3.

[0109] S3. Obtain the current laying tension, establish a tension adjustment control model based on the optimal traction force, generate a control strategy for the current laying tension, adjust the laying tension, and obtain an updated tension value; the tension adjustment control model dynamically adjusts the current laying tension based on the tension adaptive adjustment factor, so that the output tension of the optical cable traction equipment meets the dynamic optimization target.

[0110] Specifically, the input of this step comes from step S2, including the friction force distribution F of the optical cable f (x), bending stress M b (x) and the optimal traction range T opt The current laying tension is T cur , you need to adjust its value to make it stable at T opt The force environment changes dynamically during the laying of optical cables, and the traditional PID control cannot adapt to this nonlinear situation. Therefore, the present invention introduces a force adaptive adjustment factor λ(x) for dynamic adjustment during the laying process:

[0111]

[0112] Among them, λ(x) is the tension adaptive adjustment factor; k1, k2, k3 are adjustment coefficients, which control the influence of different factors on the adjustment rate; E s (x) is the vibration energy of the optical cable at point x, which comes from step S1; E max The maximum vibration energy value during the entire laying process is used for normalization; dF f (x) / dx is the spatial gradient of the friction force, which comes from step S2 and is used to correct the stability of the tension adjustment in the friction force mutation area.

[0113] As can be understood, this factor ensures:

[0114] When T cur Deviation T opt When the system automatically adjusts;

[0115] When the local vibration of the optical cable is severe (i.e. E s (x) is large), the system appropriately adjusts the tension to reduce the impact of vibration;

[0116] In areas where friction changes dramatically, the k3 term ensures that the system does not experience sudden tension changes that could overload or cause the cable to slip.

[0117] Furthermore, based on λ(x), the output tension of the optical cable pulling equipment is adjusted to meet the dynamic optimization target. In order to avoid mechanical shock caused by drastic adjustment, the present invention uses a smooth adjustment term ΔT(x) for optimization to make the adjustment process smoother:

[0118]

[0119] Where ΔT(x) is the tension adjustment amount; η is the adjustment rate coefficient, which ensures that the system adjustment will not be too fast and cause oscillation; ρ is the smoothing coefficient, which is used to control the smoothness of the traction adjustment to avoid large fluctuations; d 2 T cur / dx 2 It indicates the second-order spatial rate of change of tension along the optical cable, ensuring smoothness of tension adjustment and avoiding excessive tension fluctuations over short distances.

[0120] As can be understood, this formula ensures that:

[0121] The cable tension adjustment can not only quickly adapt to the laying environment, but also avoid damage to the cable caused by violent fluctuations;

[0122] The smoothness of tension changes is controlled by the ρ term, which reduces the impact load of the traction equipment and improves the stability of the construction equipment.

[0123] Furthermore, based on ΔT(x), the present invention updates the control signal of the traction device so that it acts on the actual tension control during the laying process. The updated tension value is defined as T new :

[0124] T new =T cur +ΔT(x)(14)

[0125] Among them, T new For the updated laying tension, ensure that it gradually approaches T opt ; The adjustment process is real-time and is dynamically optimized based on the current stress conditions of the optical cable.

[0126] Preferably, the specific control strategy includes:

[0127] Slow adjustment phase: When |T cur -T opt When | is small, λ(x) is close to 1, and the adjustment rate is low, avoiding overcorrection.

[0128] Rapid adjustment phase: When |T cur -T opt | Large, or local vibration is severe (E s (x) is larger), λ(x) becomes larger, and the adjustment rate is accelerated.

[0129] Adjustment of friction force mutation area: When dF f When (x) / dx changes dramatically, the adjustment factor λ(x) limits the adjustment range to prevent sudden tightening or loosening of the optical cable.

[0130] Preferably, finally, the present invention obtains the optimized tension control strategy M c ,include:

[0131] Updated laying tension T new , used to adjust traction equipment in real time;

[0132] Adjustment factor λ(x), used for adaptive adjustment of the feedback system;

[0133] Record historical tension change data T hist , for subsequent step 4 to perform abnormality detection and laying adjustments to ensure the stability of the entire laying process.

[0134] This control solution ensures that the tension of the optical cable is always within a safe range during the laying process, and can be adaptively adjusted according to the dynamic changes in the actual laying environment, while reducing the impact load on construction equipment and improving construction quality.

[0135] S4. Build an anomaly detection model based on spatiotemporal characteristics to generate anomaly scores, identify in real time whether there are anomalies in the optical cable, and adjust the laying tension or the movement mode of the laying equipment when an anomaly is detected to obtain a corrected tension control signal.

[0136] Specifically, the input of this step comes from step 3, including the updated laying tension T new , adjustment factor λ(x), and historical tension change data T hist In order to detect abnormalities during the laying process, the present invention needs to establish an anomaly detection model based on spatiotemporal characteristics to identify abnormal force, distortion, or blockage of the optical cable in real time. To this end, the present invention introduces a dynamic anomaly scoring function Γ(x, t) that comprehensively considers the tension change trend, vibration abnormality, and friction force mutation characteristics of the optical cable:

[0137]

[0138] Where Γ(x, t) is the abnormality score, which is used to measure the abnormality of the current state of the optical cable; w1, w2, and w3 are weight parameters, which respectively adjust the influence of tension change, vibration energy, and friction force mutation; dT new / dx is the spatial gradient of tension along the optical cable, which comes from step S3; E s (x) is the vibration energy of the optical cable at point x, which comes from step 1; dF f (x) / dx is the spatial rate of change of friction force, which comes from step 2.

[0139] As can be understood, this scoring function ensures that:

[0140] When T new When the change is too fast (ie |dT new / dx| is large), the system detects possible tension abnormality;

[0141] When the local vibration of the optical cable is severe (i.e. E s (x) is large), the system identifies possible uneven force on the optical cable or external force interference;

[0142] In the area where the friction force changes sharply (i.e. |dF f (x) / dx| is larger), the system warns that the optical cable may be subject to excessive friction or jamming.

[0143] Furthermore, based on the calculation results of Γ(x,t), the system sets a dynamic threshold Γ th (t) is used to determine abnormal situations. Since the optical cable laying environment may change over time, a fixed threshold may lead to misjudgment. Therefore, the present invention introduces an adaptive adjustment term ΔΓ(t) based on historical abnormal trends:

[0144] Γ th (t) = Γ th (t-1)+βΔΓ(t)(16)

[0145] Among them, Γ th (t) is the anomaly detection threshold at the current moment; Γ th (t-1) is the threshold value of the previous moment; β is the adjustment coefficient; ΔΓ(t) is obtained from the statistics of past abnormal distribution to ensure that the system can adaptively adjust the detection sensitivity. th (t), the system triggers the laying adjustment mechanism.

[0146] Furthermore, when an anomaly is detected, the system needs to adjust the laying tension or the movement of the laying equipment to ensure that the optical cable is not overstressed or blocked. The adjustment strategy is as follows:

[0147] If a sudden change in tension (|dT new / dx| is too large), the system reduces the traction of the traction equipment and slowly adjusts T new Make it gradually return to T opt .

[0148] If a local vibration abnormality is detected (E s (x) is too large), the system reduces the laying speed and adjusts the angle at which the optical cable enters the pipe to reduce the impact of local vibration.

[0149] If a sudden change in friction force (|dF f If (x) / dx| is too large), the system will suspend laying and check whether there are any obstacles inside the pipeline or whether the optical cable is entangled.

[0150] Finally, the system outputs abnormal adjustment results, including:

[0151] Corrected tension control signal T adj ;

[0152] Record the anomaly score Γ(x,t) and the corresponding adjustment plan;

[0153] The abnormality detection results are fed back to step S5 for subsequent construction quality assessment and optimization to improve the stability and safety of future optical cable laying.

[0154] S5. Based on the corrected tension control signal, combined with the stable stress state in the actual engineering process, whether there are any abnormal intervention adjustments, and whether it complies with standardized construction requirements, determine the construction quality score and the corresponding construction influencing factors. Finally, based on the construction quality score and the corresponding construction influencing factors, the construction influencing factor matrix is ​​used to generate an updated laying strategy and construction quality report.

[0155] Specifically, the input of this step comes from step 4, including the corrected tension control signal T adj , anomaly score Γ(x, t) and corresponding adjustment plan. The core of construction quality lies in evaluating whether the cable laying process maintains a stable stress state, whether there are abnormal intervention adjustments, and whether it meets standardized construction requirements. To this end, the present invention defines a construction quality scoring function Q, which comprehensively considers the cable tension stability, abnormal intervention frequency, and laying uniformity:

[0156]

[0157] Where Q is the construction quality score, ranging from [0, 1], and the closer the value is to 1, the higher the construction quality; α1, α2, and α3 are weight coefficients, which are used to measure tension stability, abnormal frequency, and laying uniformity, respectively; T opt is the optimal traction force range, derived from step S2; T adj (x) is the adjusted laying tension, which comes from step S4; Γ(x,t) is the abnormality score, which comes from step S4; L is the total length of the optical cable; T max ′ is the maximum allowable tension change rate, which is used for normalization.

[0158] As can be understood, this scoring function ensures that:

[0159] When the tension is stable during the laying process (T adj (x) is close to T opt ), the score increases;

[0160] When the frequency of abnormal intervention adjustments is low (Γ(x,t) is low), the score increases;

[0161] When the tension changes steadily along the cable (|dT adj / dx| is low), the score increases.

[0162] Furthermore, based on the Q calculation results, the present invention further analyzes which factors have the greatest impact on construction quality in order to optimize future construction strategies. The construction impact factor matrix V is defined to record the contribution of different factors to Q:

[0163]

[0164] Among them, each component represents the sensitivity of different factors to the construction quality score; if If the value is larger, it means that tension control is the key influencing factor; if If the frequency of abnormal adjustments is large, it means that the construction quality is greatly affected; if If the matrix is ​​large, it indicates that the uniformity of the laying is the main influencing factor. After the matrix is ​​calculated, it will be used to analyze the construction optimization direction and provide adjustment suggestions.

[0165] Furthermore, based on the construction score Q and the impact factor matrix V, the system generates optimization suggestions, including:

[0166] If Q is lower than the set threshold, analyze V to find the most significant factors and provide targeted adjustment suggestions, such as optimizing the tension control parameter λ(x) or lowering the abnormal adjustment trigger threshold Γ th (t);

[0167] If the construction score is close to 1, record the current laying strategy and use it as a reference for future construction in similar pipeline environments;

[0168] Update tension control strategy M c , optimize the initial control parameters for the next construction to reduce the frequency of intervention and adjustment and improve construction stability.

[0169] Finally, the system generates a construction quality report, including:

[0170] Construction score Q and key influencing factors;

[0171] Analysis of construction anomalies and suggestions for adjustment strategies;

[0172] The construction history data is stored to optimize the optical cable laying in similar environments in the future and form an intelligent construction experience database.

[0173] In one or more embodiments, Figure 2 As shown, a pipeline optical cable laying status monitoring system based on artificial intelligence is disclosed, and the system includes:

[0174] The optical cable vibration signal acquisition module 101 is used to obtain the optical cable vibration signal and generate a vibration feature data set based on the optical cable vibration signal; the vibration feature data set includes vibration features at different spatial positions;

[0175] The optical cable vibration signal analysis module 102 is used to construct a mechanical equilibrium equation based on the vibration characteristics of the vibration characteristic data set, calculate the stress state of the optical cable in different pipeline environments, and obtain the stress state of the optical cable during installation; wherein the stress state includes friction force distribution, bending stress, and optimal traction force;

[0176] The laying adjustment module 103 is used to obtain the current laying tension, establish a tension adjustment control model based on the optimal pulling force, generate a control strategy for the current laying tension, adjust the laying tension, and obtain an updated tension value. The tension adjustment control model dynamically adjusts the current laying tension based on the tension adaptive adjustment factor so that the output tension of the optical cable pulling equipment meets the dynamic optimization target.

[0177] The laying optimization module 104 is used to construct an anomaly detection model based on spatiotemporal characteristics to generate an anomaly score, identify in real time whether there is an anomaly in the optical cable, and adjust the laying tension or the movement mode of the laying equipment when an anomaly is detected to obtain a corrected tension control signal;

[0178] The monitoring report generation module 105 is used to determine the construction quality score and the corresponding construction influencing factors based on the corrected tension control signal, combined with the stable stress state in the actual engineering process, whether there are abnormal intervention adjustments, and whether it meets the standardized construction requirements. Finally, based on the construction quality score and the corresponding construction influencing factor matrix composed of the construction influencing factors, an updated laying strategy and construction quality report are generated.

[0179] It is worth noting that the specific workflow of the artificial intelligence-based pipeline optical cable laying status monitoring system provided in the embodiment of the present invention is the same as the workflow of the artificial intelligence-based pipeline optical cable laying status monitoring method described in the above embodiment, and will not be repeated here.

[0180] Compared with the prior art, the artificial intelligence-based pipeline optical cable laying status monitoring system provided by the embodiment of the present invention obtains the optical cable vibration signal and generates a vibration feature data set based on the optical cable vibration signal; the vibration feature data set contains vibration features at different spatial positions; based on the vibration features of the vibration feature data set, a mechanical equilibrium equation is constructed to calculate the stress state of the optical cable in different pipeline environments, and obtain the stress state of the optical cable during the laying process; wherein, the stress state includes friction force distribution, bending stress and optimal traction force; the current laying tension is obtained, and a tension adjustment control model is established based on the optimal traction force to generate a control strategy for the current laying tension, adjust the laying tension, and obtain an updated tension value; the tension adjustment control model The model dynamically adjusts the current laying tension based on the tension adaptive adjustment factor, so that the output tension of the optical cable pulling equipment meets the dynamic optimization target; constructs an anomaly detection model with spatiotemporal characteristics to generate anomaly scores, and identifies in real time whether there are anomalies in the optical cable. When an anomaly is detected, the laying tension or the movement mode of the laying equipment is adjusted to obtain a corrected tension control signal; based on the corrected tension control signal, combined with the stable stress state in the actual engineering process, whether there is an abnormal intervention adjustment, and whether it meets the standardized construction requirements, the construction quality score and the corresponding construction influencing factors are determined. Finally, based on the construction quality score and the corresponding construction influencing factor matrix composed of the construction influencing factors, an updated laying strategy and construction quality report are generated.

[0181] The embodiment of the present invention also provides an artificial intelligence-based pipeline optical cable laying status monitoring device, comprising 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, the steps in the embodiment of the artificial intelligence-based pipeline optical cable laying status monitoring method are implemented, for example Figure 1 or, the processor implements the functions of the modules in the above-mentioned system embodiments when executing the computer program.

[0182] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the artificial intelligence-based pipeline and optical cable laying status monitoring device.

[0183] The AI-based pipeline optical cable installation status monitoring device can be a computing device such as a desktop computer, laptop, PDA, or cloud server. The AI-based pipeline optical cable installation status monitoring device can include, but is not limited to, a processor and memory. Those skilled in the art will appreciate that the AI-based pipeline optical cable installation status monitoring device can also include input / output devices, network access devices, buses, and the like.

[0184] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASAC), 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 artificial intelligence-based pipeline and optical cable laying status monitoring device, and utilizes various interfaces and lines to connect various parts of the entire artificial intelligence-based pipeline and optical cable laying status monitoring device.

[0185] The memory can be used to store the computer programs and / or modules. The processor realizes the various functions of the artificial intelligence-based pipeline optical cable laying status monitoring device by running or executing the computer programs and / or modules 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, at least one application required for a function, etc.; the data storage area can store data created according to the operation of the air-conditioning controller, 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 (SmartMedaaCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0186] Wherein, if the module integrated in the pipeline optical cable laying status monitoring equipment based on artificial intelligence is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process 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, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. 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 may include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0187] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0188] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A pipeline optical cable laying status monitoring method based on artificial intelligence, characterized in that: The method comprises: Acquire an optical cable vibration signal and generate a vibration feature data set based on the optical cable vibration signal; the vibration feature data set includes vibration features at different spatial positions; Based on the vibration characteristics of the vibration feature dataset, a mechanical equilibrium equation is constructed to calculate the stress state of the optical cable in different pipeline environments, thereby obtaining the stress state of the optical cable during installation. The stress state includes friction force distribution, bending stress, and optimal traction force. Obtaining the current laying tension, establishing a tension adjustment control model based on the optimal pulling force to generate a control strategy for the current laying tension, adjusting the laying tension to obtain an updated tension value; the tension adjustment control model dynamically adjusts the current laying tension based on the tension adaptive adjustment factor so that the output tension of the optical cable pulling equipment meets the dynamic optimization target; An anomaly detection model based on spatiotemporal characteristics is constructed to generate anomaly scores, identifying in real time whether there are any anomalies in the optical cable. When an anomaly is detected, the laying tension or the movement of the laying equipment is adjusted to obtain a corrected tension control signal. Based on the corrected tension control signal, combined with the stable stress state in the actual engineering process, whether there are abnormal intervention adjustments, and whether it meets the standardized construction requirements, the construction quality score and the corresponding construction influencing factors are determined. Finally, based on the construction quality score and the corresponding construction influencing factor matrix composed of the construction influencing factors, an updated laying strategy and construction quality report are generated.

2. The method for monitoring the state of pipeline optical cable laying based on artificial intelligence according to claim 1, characterized in that: The obtaining of the optical cable vibration signal and generating a vibration feature data set based on the optical cable vibration signal specifically includes: Through distributed acoustic sensing technology, the dynamic change part of Rayleigh scattering is extracted as the original signal. The local window demeaning filtering method is used to suppress the background noise of the original signal to obtain the denoised vibration signal. Performing short-time Fourier transform on the denoised vibration signal using a multi-scale signal analysis method to obtain time-frequency characteristics; Adaptive frequency band filtering is performed on the time-frequency features to enhance the focus on the laying-related signals, thereby obtaining filtered time-frequency features, and then extracting key vibration features from the filtered time-frequency features; the key vibration features include instantaneous amplitude, instantaneous frequency, and energy distribution; Based on the extracted key vibration features, a local weighted smoothing strategy is used to eliminate the influence of local outliers, and a piecewise normalization strategy is used to normalize the key features processed by the local weighted smoothing strategy to obtain the normalized vibration features and form a vibration feature dataset.

3. The method for monitoring the state of pipeline optical cable laying based on artificial intelligence according to claim 2, characterized in that: The segment normalization strategy includes: Calculate the local mean value per 100 meters of optical cable and standard deviation .

4. The method for monitoring the state of pipeline optical cable laying based on artificial intelligence according to claim 1, characterized in that: The vibration characteristics of the vibration characteristic data set are used to construct a mechanical equilibrium equation, calculate the stress state of the optical cable in different pipeline environments, and obtain the stress state of the optical cable during the laying process, including: Obtain a vibration characteristic dataset and introduce an adaptive adjustment item based on vibration energy distribution to determine the impact of optical cable vibration on stress, including: ； in, For the optical cable in position The traction force at is the friction coefficient of the inner wall of the pipe; is the friction between the optical cable and the pipe; It is the bending stress generated by the optical cable at the bend; For optical cables The vibration energy at is the vibration-stress coupling coefficient, which represents the influence of the cable vibration energy on the stress state; According to the friction between the optical cable and the pipeline and the contact pressure between the optical cable and the pipeline and friction coefficient Determine and set the dynamic correction term based on vibration characteristics so that the friction between the optical cable and the pipe It can adaptively adjust according to the vibration characteristics of the optical cable to obtain the corrected friction force between the optical cable and the pipeline; Based on the influence of cable vibration on the force and the corrected friction between the cable and the pipe, the optimal pulling force range of the cable under different laying environments is determined. ,include: ； in, The total length of the optical cable laid; is the adjustment parameter for the effect of local vibration of the optical cable on the traction force, For the optical cable in position The normal pressure at For optical cables The instantaneous amplitude of the position, It is the maximum amplitude during the laying process.

5. The method for monitoring the state of pipeline optical cable laying based on artificial intelligence according to claim 4, characterized in that: The method of establishing a tension adjustment control model based on the optimal traction force to generate a control strategy for the current laying tension and adjust the laying tension to obtain an updated tension value includes: Introducing force adaptive adjustment factor , used to dynamically adjust to the dynamic changes of the stress environment during the laying process; the stress adaptive adjustment factor , expressed as: ； in, is the tension adaptive adjustment factor; is the adjustment coefficient, which controls the impact of different factors on the adjustment rate; For optical cables The vibration energy at It is the maximum vibration energy value during the entire laying process; is the spatial gradient of friction, which is used to correct the stability of tension adjustment in the friction mutation area; is the current laying tension value; Force-based adaptive adjustment factor , using smoothing adjustment Adjust the output tension of the optical cable pulling equipment to meet the dynamic optimization target; According to the smooth adjustment item Update the control signal of the traction equipment so that it acts on the actual tension control during the laying process to obtain the updated laying tension; The updated laying tension, the force adaptive adjustment factor and the recorded historical tension change data are combined and output as an adjusted tension control strategy.

6. The method for monitoring the state of pipeline optical cable laying based on artificial intelligence according to claim 5, characterized in that: The force adaptive adjustment factor Used to ensure the current laying tension value Departure from the optimal traction range When the current laying tension value Automatic adjustment, and / or, to ensure that when the optical cable vibrates violently locally, the tension is corrected to reduce the vibration effect, and / or, in areas where the friction force changes sharply, the adjustment coefficient This ensures that the system does not experience sudden tension changes, preventing the optical cable from overloading or slipping; The tension control strategy includes: Slow adjustment phase: When When smaller, Close to 1, the adjustment rate is slow, avoiding overcorrection; Rapid adjustment phase: Large, or local vibration is severe When it is larger, Become larger and speed up the adjustment rate; Adjustment of friction mutation area: When When the change is drastic, the adjustment factor Limit the adjustment range to prevent sudden tensioning or slackening of the cable.

7. The method for monitoring the state of pipeline optical cable laying based on artificial intelligence according to claim 5, characterized in that: The anomaly detection model based on spatiotemporal features generates an anomaly score to identify in real time whether an optical cable has an anomaly, including: A dynamic anomaly scoring function is constructed by integrating the tension change trend, vibration abnormality and friction mutation characteristics of the optical cable to determine the abnormality score, which is used to measure the abnormality of the current state of the optical cable; wherein the abnormality score The settings are as follows: ； in, Abnormality score, used to measure the abnormality of the current state of the optical cable; are weight parameters, which respectively adjust the effects of tension change, vibration energy and friction force mutation; is the spatial gradient of tension along the cable; For optical cables The vibration energy at A dynamic threshold for adaptive adjustment items based on historical anomaly trends is set according to the anomaly score to determine anomalies; when the anomaly score is greater than the dynamic threshold, the adjustment mechanism is triggered.

8. The method for monitoring the state of pipeline optical cable laying based on artificial intelligence according to claim 7, characterized in that: The laying adjustment mechanism includes: If a sudden change in tension is detected, If it is too large, reduce the traction of the traction equipment and adjust it slowly. Gradually return to the optimal traction range ; If a local vibration anomaly is detected, If it is too large, reduce the laying speed and adjust the angle of the optical cable entering the pipe to reduce the impact of local vibration; If a sudden change in friction force is detected, If it is too large, suspend laying and check whether there are any obstacles inside the pipeline or whether the optical cable is entangled.

9. The method for monitoring the state of pipeline optical cable laying based on artificial intelligence according to claim 7, characterized in that: The adjustment range of the construction quality score is expressed as: When the tension is stable during the laying process, that is, the adjusted laying tension Close to the optimal traction range When , the score increases; When the frequency of abnormal intervention adjustment is low, that is, the abnormal score When it is low, the score increases; When the tension changes smoothly along the cable, When it is low, the score increases; The construction influencing factor matrix records the contribution of different factors to the construction quality score.

10. The artificial intelligence-based pipeline optical cable laying status monitoring system is characterized by: The system comprises: An optical cable vibration signal acquisition module is used to acquire the optical cable vibration signal and generate a vibration feature data set based on the optical cable vibration signal; the vibration feature data set includes vibration features at different spatial positions; The optical cable vibration signal analysis module is used to construct a mechanical equilibrium equation based on the vibration characteristics of the vibration feature data set, calculate the stress state of the optical cable in different pipeline environments, and obtain the stress state of the optical cable during installation; wherein the stress state includes friction force distribution, bending stress, and optimal traction force; A laying adjustment module is used to obtain the current laying tension, establish a tension adjustment control model based on the optimal pulling force, generate a control strategy for the current laying tension, adjust the laying tension, and obtain an updated tension value; the tension adjustment control model dynamically adjusts the current laying tension based on the tension adaptive adjustment factor, so that the output tension of the optical cable pulling equipment meets the dynamic optimization target; The laying optimization module is used to build an anomaly detection model based on spatiotemporal characteristics to generate anomaly scores, identify in real time whether there are any anomalies in the optical cable, and adjust the laying tension or the movement of the laying equipment when an anomaly is detected to obtain a corrected tension control signal. The monitoring report generation module is used to determine the construction quality score and the corresponding construction influencing factors based on the corrected tension control signal, combined with the stable stress state in the actual engineering process, whether there are abnormal intervention adjustments, and whether it meets the standardized construction requirements. Finally, based on the construction quality score and the corresponding construction influencing factor matrix composed of the construction influencing factors, an updated laying strategy and construction quality report are generated.

Images