Geological disaster monitoring method and system based on distributed optical fiber vibration sensing system

Abstract

The invention relates to the technical field of geological disaster monitoring, in particular to a geological disaster monitoring method and system based on a distributed optical fiber vibration sensing system, and aims to solve the problem of how to solve the interference of the change of an optical fiber and the change of an external environment on a geological disaster prediction result in optical fiber transformation. In order to solve the problem, the geological disaster monitoring method provided by the invention comprises the following steps: determining an area to be expanded according to a monitoring demand and a system distribution path of an original optical fiber; determining an actual distribution path of newly added optical fibers according to the landform characteristics and the geological risk level of the to-be-expanded area; after the newly-added optical fiber is installed, correcting the characteristic data according to the loss condition of the original optical fiber and the transmission characteristics of the newly-added optical fiber, and constructing a prediction model according to the corrected data; and combining the prediction model with the environment information, and determining the type of a disaster occurring in the target area.

Description

Technical Field

[0001] The present invention relates to the technical field of geological disaster monitoring, and in particular, to a geological disaster monitoring method and system based on a distributed optical fiber vibration sensing system. Background Art

[0002] Geological disasters, especially disasters such as landslides, collapses, and debris flows, seriously threaten the safety of human life and property, and usually occur suddenly and are difficult to predict. Due to their suddenness and destructiveness, how to effectively and timely monitor geological disasters has become an important research direction in the current geological disaster prevention and mitigation work.

[0003] Distributed optical fiber sensing technology uses optical fiber as the transmission medium and sensing unit of signals. By detecting the changes in parameters such as the intensity, phase, and polarization state of optical signals in the optical fiber under the action of an external field, continuous distributed measurement of external parameters along the optical fiber is achieved, thus becoming the most ideal non-destructive health monitoring technology for large-scale facilities in many fields. In recent years, due to its excellent performance, such as anti-electromagnetic interference, distributed measurement, high precision, and high reliability, optical fiber sensing technology has become an important direction for geological disaster monitoring. The prior art (CN118960857B) provides a geological disaster monitoring method and system based on a distributed optical fiber sensor, which uses the distributed optical fiber sensor to monitor geological disasters such as landslides and earthquakes, and predicts the location, grade, and duration of disasters in real time by analyzing the changes in optical fiber signals. However, when the original optical fiber is modified to expand the monitoring network, the following technical problems exist: the optical fiber itself is "unstable", that is, adding new optical fiber during the modification process will cause the optical fiber network topology reconstruction of the original optical fiber, and the coupling distortion of the scattered signal mode will intensify, resulting in the original prediction model being unable to accurately capture the disaster characteristics; environmental interference is "difficult to distinguish", that is, the external environment where the optical fiber is located after modification has changed, and the interference generated by the new environment is easily mixed with the real disaster precursor signal, resulting in false alarms or missed alarms.

[0004] Therefore, there is an urgent need for a distributed optical fiber vibration sensing system that can effectively solve the interference of the changes in the optical fiber itself and the external environment during optical fiber modification on the prediction result and improve the prediction accuracy of geological disasters. Summary of the Invention

[0005] The problem solved by the present invention is: in the optical fiber modification, how to solve the interference of the changes in the optical fiber itself and the external environment on the geological disaster prediction result, so as to improve the prediction accuracy of the distributed optical fiber vibration sensing system.

[0006] To solve the above problems, an embodiment of the present invention provides a geological disaster monitoring method based on a distributed optical fiber vibration sensing system. The geological disaster monitoring method includes: obtaining the monitoring requirements in the target area, and determining the area to be expanded according to the monitoring requirements and the system distribution path of the original optical fiber in the distributed optical fiber vibration sensing system; determining the actual distribution path of the new optical fiber according to the geomorphic features and geological risk levels of the area to be expanded; conducting virtual disaster scenario tests on the system distribution path to obtain the characteristic data corresponding to each geological disaster scenario; when the new optical fiber is installed, correcting the characteristic data according to the loss situation of the original optical fiber and the transmission characteristics of the new optical fiber, and constructing a prediction model based on the corrected data; combining the prediction model with environmental information to determine the type of disaster occurring in the target area.

[0007] Compared with the prior art, the technical effects achieved by adopting this technical solution are as follows: The clarification of the monitoring requirements and the acquisition of the system distribution path help to guide the design of the actual distribution path of the new optical fiber, ensure that the expanded optical fiber vibration sensing system matches the actual requirements, avoid redundancy or omission. The accurate identification of the area to be expanded enables the new optical fiber to focus on the newly emerging areas of geological disasters and the original monitoring blind spots, thereby improving the integrity of the optical fiber monitoring network. Optimizing the layout of the new optical fiber in combination with the geomorphic features makes the actual distribution path more in line with the actual geological conditions. Configuring the new optical fiber based on the quantification result of the geological risk level realizes the scientific planning of the actual distribution path. Accumulating disaster signal characteristic data through virtual disaster scenario tests provides "standard samples" for the prediction model. By comparing the real-time signal data with the characteristic data, automatic identification of disaster signals is achieved. By calculating the loss situation, the influence of the physical characteristics of the optical fiber on the vibration signal is effectively eliminated. By correcting the characteristic data according to the transmission characteristics, it helps to eliminate the vibration signal response deviation caused by the difference in the laying environment of the new optical fiber and unify the quantization benchmark of the vibration signal. The combination of environmental information and the prediction model can effectively avoid misjudgment of a single signal and enhance the environmental adaptability of the prediction system.

[0008] In an embodiment of the present invention, obtaining the monitoring requirements in the target area and determining the area to be expanded according to the monitoring requirements and the system distribution path of the original optical fiber in the distributed optical fiber vibration sensing system specifically includes: clarifying the monitoring requirements according to the geological exploration data and historical disaster records of the target area; constructing a three-dimensional monitoring coverage model of the original optical fiber according to the monitoring performance indicators and terrain shielding effect of the original optical fiber; determining the new risk areas according to the three-dimensional monitoring coverage model and the monitoring requirements; screening out the monitoring blind spots and low-efficiency areas according to the three-dimensional monitoring coverage model; and determining the area to be expanded according to the new risk areas, monitoring blind spots and low-efficiency areas.

[0009] Compared with the prior art, the technical effects achieved by adopting this technical solution are as follows: By means of geological exploration and historical disaster data, the potential disaster types and high-risk areas in the target area are identified, the monitoring requirements are reasonably defined, newly added risk areas are dynamically identified and incorporated into the monitoring, the response lag during geological disasters is reduced, and the screening and coverage of monitoring blind spots and inefficient areas are carried out, which helps to ensure that the accuracy and reliability of the entire monitoring system meet the monitoring requirements, and comprehensively improve the integrity and early warning efficiency of the optical fiber monitoring network.

[0010] In an embodiment of the present invention, the actual distribution path of the newly added optical fiber is determined according to the geomorphic features and geological risk levels of the area to be expanded, which specifically includes: determining the distribution density of the newly added optical fiber according to the geological risk level and the disaster occurrence frequency; determining the theoretical distribution path of the newly added optical fiber according to the geomorphic features and the distribution density of the area to be expanded; conducting virtual disaster scenario tests on the three-dimensional model of the theoretical distribution path, and adjusting the theoretical distribution path according to the rehearsal results to determine the actual distribution path.

[0011] Compared with the prior art, the technical effects achieved by adopting this technical solution are as follows: The distribution density of the newly added optical fiber is determined by the geological risk level and the disaster occurrence frequency, which enhances the timeliness of early warning while ensuring the monitoring accuracy of the area to be expanded. The theoretical distribution path is planned by combining the geomorphic features and the distribution density to ensure that the layout of the newly added optical fiber conforms to the terrain conditions and maximally covers the potential disaster signal propagation path. By simulating the impact of disasters in the three-dimensional model of the theoretical distribution path, potential problems in the theoretical distribution path of the newly added optical fiber can be identified in advance and optimized and adjusted, further improving the accuracy and adaptability of the optical fiber sensing system.

[0012] In an embodiment of the present invention, after the newly added optical fiber is installed, the characteristic data is corrected according to the loss situation of the original optical fiber and the transmission characteristics of the newly added optical fiber, and a prediction model is constructed based on the corrected data, which specifically includes: dividing the original optical fiber into multiple loss sections according to the number of turning points; calculating the attenuation coefficient of each loss section according to the turning degree and the optical fiber length of the loss section; calculating the loss coefficient of the original optical fiber according to the attenuation coefficient of each loss section and the service life; correcting the characteristic data according to the loss coefficient and the transmission characteristics of the newly added optical fiber, and constructing a prediction model based on the corrected data.

[0013] Compared with the prior art, the technical effects achieved by adopting this technical solution are as follows: By accurately dividing the "loss homogeneous sections" through the turning points, independent analysis of different physical state sections is realized, avoiding errors caused by global averaging. The accurate attenuation coefficient of each loss section is calculated through the turning degree and the optical fiber length, providing data support for subsequent correction of characteristic data. The loss coefficient is calculated through the attenuation coefficient and the service life, thereby realizing loss compensation for old optical fibers and improving the monitoring accuracy of the optical fiber sensing system.

[0014] In one embodiment of the present invention, the characteristic data is corrected according to the loss coefficient and the transmission characteristics of the newly added optical fiber, and a prediction model is constructed based on the corrected data, which specifically includes: determining the installation location according to the actual distribution path of the newly added optical fiber, and dividing the sub-installation modules according to the geomorphic characteristics of the installation location; calculating the actual transmission efficiency of the vibration signal according to the transmission characteristics in the sub-installation modules; obtaining the standard transmission efficiency of the newly added optical fiber under the standard state, and calculating the deviation coefficient of the newly added optical fiber according to the actual transmission efficiency and the standard transmission efficiency; calculating the corrected data according to the deviation coefficient, the loss coefficient and the characteristic data, and constructing a prediction model according to the corrected data.

[0015] Compared with the prior art, the technical effects achieved by adopting this technical solution are as follows: by analyzing the geomorphic characteristics, the area to be expanded can be divided into multiple homogeneous sub-installation modules, so as to more accurately obtain the transmission characteristics of the newly added optical fiber in each sub-installation module, which helps to accurately evaluate the transmission performance of the optical fiber in different modules. By calculating the deviation coefficient, the influence of the installation environment factors on the transmission performance of the newly added optical fiber can be identified and compensated, so as to eliminate the signal transmission deviation between different sub-modules. Constructing a prediction model according to the corrected data can improve the adaptability of the prediction model to complex geological environments, thereby improving the accuracy and reliability of the prediction results.

[0016] In one embodiment of the present invention, the prediction model is combined with environmental information to determine the type of disaster that occurs in the target area, which specifically includes: when the environmental information remains unchanged, inputting the real-time signal data monitored by the newly added optical fiber and the original optical fiber into the prediction model to determine the type of geological disaster; when the environmental information changes, obtaining the interference signal generated by the change of the environmental information, adjusting the prediction model according to the interference signal to obtain an adjusted model; determining the abnormal parameter set according to the adjusted model and the real-time signal data, and determining the type of geological disaster according to the abnormal parameter set.

[0017] Compared with the prior art, the technical effects achieved by adopting this technical solution are as follows: when the environmental parameters remain unchanged, the real-time signal data can be directly input into the prediction model, avoiding the complex interference identification and model adjustment processes, shortening the disaster determination time, accurately extracting the interference signal according to the environmental change and dynamically adjusting the prediction model to avoid the model failure caused by sudden environmental changes and reducing the missed detection risk of geological disasters. Determining the abnormal parameters according to the adjusted model and the real-time signal data helps to accurately capture and reliably classify the geological disaster signals.

[0018] In one embodiment of the present invention, when environmental information changes, an interference signal generated by the change in environmental information is obtained, and the prediction model is adjusted according to the interference signal to obtain an adjusted model, which specifically includes: obtaining monitoring performance indicators affected by the interference signal, and marking the monitoring performance indicators as indicators to be adjusted; updating the indicators to be adjusted by the signal type and trigger frequency of the interference signal, which are recorded as corrected performance indicators; obtaining geological disaster scenarios affected by the corrected performance indicators, which are recorded as corrected scenarios, and updating the correction data corresponding to the corrected scenarios in the prediction model; adjusting the prediction model according to the updated corrected data to obtain an adjusted model.

[0019] Compared with the existing technology, the technical effect achieved by adopting this technical solution is as follows: by extracting the monitoring performance indicators affected by interference and converting the interference impact into quantifiable indicators to be adjusted, it is helpful to accurately locate the adjustment target of the prediction model, thereby avoiding blindly adjusting irrelevant parameters and making the optimization direction of the prediction model more targeted. The correction performance indicators are dynamically generated by combining the signal type and trigger frequency of the interference signal, which can effectively capture the impact of external environmental changes on the performance of the prediction model. This precise parameter adjustment based on the characteristics of the interference signal ensures that the prediction model can still maintain the accuracy and timeliness of the prediction in a complex environment. By mapping the correction performance indicators to specific correction scenarios, the correction data of the corresponding scenarios in the prediction model can be updated in a targeted manner, ensuring that the prediction model adapts to the new environment while avoiding the problem of over-correction that may be caused by global parameter adjustment, thereby maintaining the stability and adaptability of the prediction model and improving the prediction accuracy.

[0020] In one embodiment of the present invention, an abnormal parameter set is determined based on an adjustment model and real-time signal data, and the disaster type of the geological disaster is determined based on the abnormal parameter set, specifically including: determining the type of disaster that may occur in the target area based on each abnormal data in the abnormal parameter set, recorded as a theoretical type; obtaining the fluctuation range of the abnormal data when all theoretical types occur from a historical disaster database; when the abnormal data does not exceed the fluctuation range, determining the disaster type in the target area as a single type, and determining the disaster type based on the degree of fit between the abnormal data and the fluctuation ranges of different disaster types; when the abnormal data exceeds the fluctuation range, recording the abnormal data that exceeds the fluctuation range as combined data, matching according to the disaster type corresponding to the combined data, and determining the combination method of multiple disaster types.

[0021] Compared with the prior art, the technical effects achieved by adopting this technical solution are as follows: Abnormal data, as the core element for identifying geological disaster risks, can capture the characteristic parameters deviating from the normal state in real-time signal data, providing real-time information for disaster prediction. Combining the theoretical types with the historical disaster database provides support of historical data for the prediction of disaster types, helping to reduce the prediction error of the adjustment model. The fluctuation range provides a determination boundary for abnormal data, and the determination mechanism of single type and degree of fit ensures the high efficiency and accuracy of the adjustment model in most conventional scenarios. The determination of the combination data and combination method takes into account the complex scenarios of multiple concurrent disaster types, making the adjustment model more adaptable and better able to handle complex geological disaster situations.

[0022] In an embodiment of the present invention, a geological disaster monitoring system based on a distributed optical fiber vibration sensing system is further provided. The geological disaster monitoring method described in the above embodiment is applied to this geological disaster monitoring system. The geological disaster monitoring system includes: a positioning module, which is used to determine the area to be expanded according to the monitoring requirements and the system distribution path; a testing module, which is used to perform virtual disaster scenario tests on the system distribution path to obtain the characteristic data corresponding to each geological disaster scenario; a correction module, which corrects the characteristic data according to the loss situation of the original optical fiber and the transmission characteristics of the newly added optical fiber; a prediction module, which is used to predict the type of disaster occurring in the target area. This geological disaster monitoring system has all the technical features of the above geological disaster monitoring method, and will not be elaborated here one by one. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is one of the flowcharts of the geological disaster monitoring method; Figure 2 is the second flowchart of the geological disaster monitoring method; Figure 3 is the third flowchart of the geological disaster monitoring method; Figure 4 is the fourth flowchart of the geological disaster monitoring method; Figure 5 is the system schematic diagram of the geological disaster monitoring system; Description of the Reference Numerals: 100 - Geological disaster monitoring system; 110 - Positioning module; 120 - Testing module; 130 - Correction module; 140 - Prediction module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention is provided in conjunction with the accompanying drawings.

[0025]

The First Embodiment

[0026] In steps S100 and S200, the target area refers to a specific geographical range that needs to be monitored for geological disasters, including areas such as mountains, mining areas, slopes, and the peripheries of reservoirs, etc. The monitoring requirements are specific monitoring objectives formulated according to factors such as the types of geological disasters, risk levels, and monitoring accuracies in the target area. The original optical fiber refers to the optical fiber that has been installed and is operating normally in the distributed optical fiber vibration sensing system in the target area. The system distribution path refers to the physical laying route of the original optical fiber in the target area, including the trend, laying method, and key nodes, etc. The area to be expanded refers to the area that needs to be supplemented with newly added optical fibers for monitoring due to changes in monitoring requirements and the increase in geological disaster risks. The geomorphic features refer to the topographic and geomorphic attributes of the area to be expanded, including slope, vegetation coverage rate, hydrological conditions, and rock exposure rate, etc. The geological risk level is the risk level of geological disasters evaluated based on the current environmental inducing factors and historical geological disaster data in the area to be expanded. The newly added optical fiber is the monitoring optical fiber newly laid for the area to be expanded on the basis of the existing distributed optical fiber vibration sensing system according to the monitoring requirements and geological risk levels. The actual distribution path is the specific physical laying route of the newly added optical fiber determined according to the geomorphic features and geological risk levels of the area to be expanded.

[0027] In steps S300 and S400, the virtual disaster scenario test uses typical geological disaster events generated through numerical simulation to test the response ability of the distributed fiber optic vibration sensing system. A geological disaster scenario refers to the specific types of disasters that may occur in the target area and their evolution processes, such as the "creep - acceleration - landslide" process of a landslide. Characteristic data refers to the signal characteristics shown by the disaster events obtained through the virtual disaster scenario test in the fiber optic sensor, including parameters such as vibration frequency, amplitude, phase change rate, and signal propagation speed. The loss situation refers to the degree of optical signal attenuation caused by factors such as the aging, bending, and joint defects of the original optical fiber. The transmission characteristics refer to the propagation law of the vibration signal in the newly added optical fiber, which is usually related to factors such as the laying position, laying method, and burial depth of the newly added optical fiber. The corrected data is the data obtained by correcting the characteristic data based on the loss situation of the original optical fiber and the transmission characteristics of the newly added optical fiber. The prediction model is a machine learning model constructed based on the corrected data, which is used to identify the disaster characteristics in the real - time signal and predict the type of disaster.

[0028] For example, when the area to be expanded is a landslide monitoring area, the burial depth of the newly added optical fiber will affect its transmission characteristics. If the newly added optical fiber is buried at two different depths, shallow - buried and deep - buried, at the sliding surface, the shallow - buried optical fiber is more sensitive to the high - frequency vibration signals generated on the ground surface, and the signal amplitude attenuates with the increase of the burial depth.

[0029] It should be noted that the deployment and installation of the newly added optical fiber require a construction period. Before installing the newly added optical fiber, a virtual disaster scenario test is first carried out on the system distribution path of the original optical fiber to obtain the characteristic data corresponding to each geological disaster scenario, forming an initial signal characteristic library. After the installation of the newly added optical fiber is completed, although it is possible to directly conduct a virtual disaster scenario test on it to obtain more accurate characteristic data, a comprehensive and repeated test needs to simulate a large number of disaster scenarios, and the computational amount increases exponentially, which may lead to data - processing delays and affect the real - time warning efficiency. Moreover, frequent testing may cause physical damage to the optical fiber itself. Therefore, by analyzing the loss situation of the original optical fiber and the transmission characteristics of the newly added optical fiber to make targeted corrections to the initial characteristic data, the operation efficiency of the expanded fiber optic sensing system can be significantly improved while ensuring the monitoring accuracy.

[0030] In step S500, the environmental information refers to the real - time environmental data in the target area, including meteorological data, human activities, animal activities, and geological disaster precursor information, etc. The type of disaster is the specific type of geological disaster determined according to the abnormal parameter set, including earthquakes, landslides, collapses, debris flows, and ground settlement and karst collapses, etc.

[0031] It should be noted that in the geological disaster monitoring method, environmental information refers to all external conditions within the target area that affect the signal interpretation of the distributed optical fiber vibration sensing system. It includes both disaster activity information directly related to the gestation and occurrence of geological disasters and non-disaster external interference factors that may interfere with signal analysis. Although these interference factors do not directly trigger geological disasters, they may interfere with the normal fluctuation of vibration signals and affect the accuracy and reliability of prediction results. Therefore, it is necessary to combine the prediction model with environmental information.

[0032] The clarification of monitoring requirements and the acquisition of the system distribution path of the optical fiber are helpful for guiding the design of the actual distribution path of the newly added optical fiber, ensuring that the extended optical fiber vibration sensing system matches the actual requirements, avoiding redundancy or omission. The accurate identification of the area to be extended enables the newly added optical fiber to focus on the newly emerging areas of geological disasters and the original monitoring blind spots, thereby enhancing the integrity of the optical fiber monitoring network. Optimizing the layout of the newly added optical fiber in combination with the geomorphic features makes the actual distribution path more in line with the actual geological conditions. Configuring the newly added optical fiber based on the quantitative results of the geological risk level realizes the scientific planning of the actual distribution path. By testing virtual disaster scenarios, characteristic data of disaster signals are accumulated to provide "standard samples" for the prediction model. By comparing real-time signal data with characteristic data, automatic identification of disaster signals is achieved. By calculating the loss situation, the influence of the physical properties of the optical fiber on the vibration signal is effectively eliminated. By correcting the characteristic data through transmission characteristics, it helps to eliminate the deviation of the vibration signal response caused by the difference in the laying environment of the newly added optical fiber and unify the quantization benchmark of the vibration signal. The combination of environmental information and the prediction model can effectively avoid misjudgment of a single signal and enhance the environmental adaptability of the prediction system.

[0033]

Second Embodiment

[0034] In steps S110 and S120, the geological exploration data are basic data such as the formation structure, geotechnical mechanical parameters, and hydrogeological characteristics obtained through geophysical exploration, drilling sampling, remote sensing mapping, etc. The historical disaster records refer to the complete archives of geological disasters that occurred in the target area during the historical time period, including data such as the occurrence time, location, scale, and inducing factors. The monitoring performance indicators are technical parameters used to describe the monitoring performance and capabilities of the original optical fiber, usually including parameters such as the attenuation coefficient, signal-to-noise ratio, spatial resolution, and monitoring node density. The terrain shielding effect refers to the blocking or attenuation effect of the geomorphic features in the target area on the propagation of vibration signals in the original optical fiber. The three-dimensional monitoring coverage model is a visualized three-dimensional model constructed based on the spatial coordinates of the original optical fiber, the monitoring performance indicators, and the terrain shielding effect.

[0035] In steps S130 to S150, the newly added risk areas refer to the potential geological disaster areas that were not covered during the deployment of the original optical fiber and those that newly emerged later. The monitoring blind spots refer to the areas that the original optical fiber cannot effectively monitor. Usually, the signal intensity detected by the original optical fiber in the monitoring blind spots is lower than the monitoring threshold. The low-efficiency areas refer to the areas where the resolution of the original optical fiber is lower than the preset accuracy or the node density is insufficient.

[0036] By clarifying the potential disaster types and high-risk sections in the target area through geological exploration and historical disaster data, reasonably defining the monitoring requirements, dynamically identifying and including the newly added risk areas in the monitoring, reducing the response lag when geological disasters occur, and screening and covering the monitoring blind spots and low-efficiency areas, it helps to ensure that the accuracy and reliability of the entire monitoring system meet the monitoring requirements, and comprehensively improve the integrity and early warning efficiency of the optical fiber monitoring network.

[0037]

Third Embodiment

[0038] In steps S210 to S230, the disaster occurrence frequency refers to the number of geological disasters occurring in the area to be expanded per unit time. The distribution density refers to the laying spacing of newly added optical fibers or the number of monitoring nodes per unit area of the area to be expanded. The theoretical distribution path is the preliminary planned route for laying newly added optical fibers based on the distribution density and geomorphic features. The three-dimensional model refers to a three-dimensional digital model that integrates elements such as geomorphic features, optical fiber distribution density, and optical fiber physical parameters. The preview result refers to the monitoring performance indicators of the newly added optical fibers output after virtual disaster scenario testing of the three-dimensional model, usually including indicators such as signal-to-noise ratio, spatial resolution, and false alarm probability. The actual distribution path refers to the final deployment plan of the newly added optical fibers after being optimized through preview verification.

[0039] For example, if a certain hillside in the area to be expanded has experienced multiple landslide disasters with relatively high risk levels in history, the newly added optical fibers will be densely arranged in the valleys or steep slopes where landslides occur frequently, thereby determining the theoretical distribution path of the newly added optical fibers. When simulating a landslide disaster for the three-dimensional model of the theoretical distribution path, if the preview result shows that the signal is attenuated in a certain area due to terrain shielding, it is necessary to adjust the path of the newly added optical fibers to avoid the terrain with strong shielding effects, thereby obtaining the actual distribution path of the newly added optical fibers.

[0040] Determine the distribution density of the newly added optical fibers based on the geological risk level and disaster occurrence frequency, enhance the timeliness of early warning while ensuring the monitoring accuracy of the area to be expanded, plan the theoretical distribution path by combining geomorphic features and distribution density, ensure that the layout of the newly added optical fibers fits the terrain conditions, maximize the coverage of potential disaster signal propagation paths, and by simulating the impact of disasters in the three-dimensional model of the theoretical distribution path, potential problems in the theoretical distribution path of the newly added optical fibers can be identified in advance and optimized and adjusted, further improving the accuracy and adaptability of the fiber optic sensing system.

[0041]

Fourth Embodiment

[0042] In step S410 and step S420, the number of turning points refers to the number of locations where the signal transmission characteristics of the original optical fiber change significantly. The turning points are usually located at locations such as terrain changes, joint connections, and equipment access points in the system distribution path. The loss section refers to a fiber section with relatively uniform signal loss characteristics obtained by dividing adjacent turning points in the laying direction of the original optical fiber. The turning degree refers to the bending angle of the optical fiber at the turning point. The optical fiber length refers to the actual physical length of each loss section. The attenuation coefficient refers to the signal power attenuation per unit length of optical fiber in the loss section. The attenuation coefficient k d The calculation formula is as follows: .

[0043] Among them, p i is the input power of the optical signal, p o is the output power of the optical signal in dBm, L is the fiber length in km, β is the bending loss coefficient, usually between 0.001 and 0.005 dB / °, and θ is the turning degree.

[0044] In step S430 and step S440, the service life refers to the accumulated time after the original optical fiber is put into use, and the loss coefficient is a quantitative parameter of the signal loss of the original optical fiber calculated by combining the attenuation coefficient and the aging factor. The loss coefficient k a The calculation formula is as follows: k a =k d ×(1+c×t).

[0045] Among them, c is the aging coefficient, the value range is usually between 0.005 and 0.03, and t is the service life.

[0046] It should be noted that due to the complexity of the fiber optic laying method and actual environmental conditions, directly measuring the loss of the entire fiber optic section is costly and difficult to implement. Therefore, the fiber optic loss is usually estimated through simulation calculations or theoretical estimation methods. However, due to factors such as changes in the external environment of the optical fiber and hidden engineering defects in the laying, the estimated results may deviate greatly from the actual loss. Therefore, in order to improve the prediction accuracy of the fiber optic sensing system, when installing the new optical fiber, the actual loss of the original optical fiber can be measured simultaneously.

[0047] By accurately dividing the "loss homogeneous section" through turning points, independent analysis of sections with different physical states can be achieved to avoid errors caused by global averaging. The precise attenuation coefficient of each loss section is calculated by the turning degree and fiber length, providing data support for subsequent characteristic data correction. The loss coefficient is calculated by the attenuation coefficient and service life, thereby achieving loss compensation for old optical fibers and improving the monitoring accuracy of the fiber optic sensing system.

[0048]

Fifth Embodiment

[0049] In steps S441 and S442, the installation location refers to the specific coordinates and laying direction of the newly added optical fiber in the area to be expanded. The sub-installation module is an independent analysis unit divided according to the geomorphic features of the installation location. The vibration signal is a waveform signal carrying the physical characteristics of mechanical vibration events monitored by the optical fiber sensing system. The actual transmission efficiency refers to the signal transmission effect of the vibration signal in the sub-installation module. The calculation parameters of the actual transmission efficiency usually include signal-to-noise ratio, polarization stability, and spatial resolution, etc.

[0050] For example, when the area to be expanded is a plain farmland and the newly added optical fiber is buried for monitoring soil settlement disasters, if the plain area includes clay farmland, sandy soil irrigation area, and concrete road crossing area, then at this time, the sub-installation module can be divided into clay farmland buried section, sandy soil irrigation buried section, and road pipe crossing section.

[0051] In steps S443 and S444, the standard state refers to the standard installation conditions that comply with industry installation specifications, have no significant structural defects, and the environmental parameters are within the designed allowable range. Usually, under the standard state, the transmission performance of the optical fiber reaches the design expectation. The standard transmission efficiency refers to the theoretical transmission efficiency of the newly added optical fiber under the standard state. The deviation coefficient represents the degree of deviation of the actual transmission efficiency e a from the standard transmission efficiency e s . The calculation formula of the deviation coefficient k z is as follows: k z = (e a - e s ) ÷ e s .

[0052] By analyzing the geomorphic features, the area to be expanded can be divided into multiple homogeneous sub-installation modules, so as to more accurately obtain the transmission characteristics of the newly added optical fibers in each sub-installation module, which helps to accurately evaluate the transmission performance of the optical fibers in different modules. Through the calculation of the deviation coefficient, the influence of the installation environment factors on the transmission performance of the newly added optical fibers can be identified and compensated, so as to eliminate the signal transmission deviation between different sub-modules. By constructing a prediction model based on the corrected data, the adaptability of the prediction model to complex geological environments can be improved, thus enhancing the accuracy and reliability of the prediction results.

[0053]

Sixth Embodiment

[0054] In steps S510 and S520, the real-time signal data refers to the vibration signal sequence collected from the newly added optical fiber and the original optical fiber sensor, which reflects the current environmental state of the target area. The interference signal refers to the non-disaster vibration signal that will affect the accuracy of the expanded optical fiber sensing system and interfere with the disaster warning. The interference signal is usually caused by the change of environmental information, such as human engineering activities. The adjusted model refers to the corrected model that can adapt to the changed environment after integrating the interference signal characteristics on the basis of the original prediction model when the environmental information changes.

[0055] It should be noted that environmental changes can cause the characteristic distribution of real-time signal data to shift by changing the physical properties of geological bodies or introducing external disturbances. This shift may manifest as a structural change in the signal components, such as the addition of periodic interference or the disappearance of the original background noise. When there is a long-term stable interference source in the environment, its interference signal will form a specific time-frequency-amplitude distribution pattern. The prediction model has learned and adapted to this normal working condition with interference during construction to ensure the accurate extraction of geological disaster signals. However, if this interference source temporarily disappears, the specific frequency components generated by the interference signal will suddenly decrease, resulting in a significant change in the frequency distribution in the real-time signal. If the prediction model does not synchronously update the characteristic shift brought about by this environmental change, it may mistake the frequency characteristics of the disaster signal for the normal working condition, thus missing the opportunity for early warning and resulting in missed detections. Therefore, environmental changes will affect the prediction results of the prediction model by influencing the real-time signal data.

[0056] For example, when there is a high-speed railway section in the target area, there are regular pulsed vibration signals in the 20 - 80 Hz frequency band during the daily period from 6:00 to 23:00. The prediction model has set an interference tolerance window for this period during construction, allowing periodic signals with an amplitude within 20 dB in this frequency band not to trigger an alarm. When the high-speed railway is temporarily out of service for maintenance, the energy in the 10 - 50 Hz frequency band decreases significantly, but the prediction model still uses the interference tolerance threshold set when the high-speed railway is operating normally. At this time, if the amplitude of the geological disaster signal falls within the 20 - 80 Hz frequency band and the amplitude is less than 20 dB, the prediction model will mistakenly determine it as a normal signal within the interference range of the high-speed railway, thus ignoring its disaster warning significance and ultimately resulting in missed detections.

[0057] In step S530, the abnormal parameter set refers to the set of parameters extracted from the real-time signal that significantly deviates from the normal data pattern. The normal data pattern refers to the normal behavior pattern of the signal data obtained through long-term monitoring in the target area when there is no geological disaster after the environmental information changes.

[0058] When the environmental parameters do not change, the real-time signal data can be directly input into the prediction model, avoiding complex interference identification and model adjustment processes, shortening the disaster determination time, accurately extracting interference signals according to environmental changes and dynamically adjusting the prediction model, avoiding model failure caused by sudden environmental changes, reducing the risk of missed detections of geological disasters, and determining abnormal parameters by adjusting the model and real-time signal data, which helps to accurately capture and reliably classify geological disaster signals.

[0059]

Seventh Embodiment

[0060] In steps S521 to S524, the indicators to be adjusted refer to those monitoring performance parameters affected by the interference signal, usually including attenuation coefficient, signal-to-noise ratio, and spatial resolution, etc. The signal type refers to the physical attribute classification of the interference signal, and the trigger frequency refers to the number of times the interference signal appears per unit time and the time law. The corrected performance indicators are the real-time performance parameters obtained by updating the interfered indicators to be adjusted according to the signal type and trigger frequency. The corrected scenario refers to the specific geological disaster monitoring scenario affected by the corrected performance indicators.

[0061] It should be noted that according to the spatio-temporal regularity characteristics of the interference signal, the interference signal is divided into two signal types: fixed signal and random signal. A fixed signal refers to an interference with clear periodic, repetitive, or stable frequency characteristics. A random signal refers to an interference with no fixed period, frequency, or randomly changing amplitude. The trigger frequency of the fixed signal is usually obtained through historical data, and the trigger frequency of the random signal is usually obtained through real-time signal monitoring data. The corrected performance indicators reflect the impact of environmental information changes on specific geological disasters. By analyzing historical disaster data and the corrected performance indicators, the corrected scenarios that need to be adjusted can be determined.

[0062] For example, when there was no high-speed rail passing through the target area originally, then after the high-speed rail passes through, the signal type of the interference signal is a fixed signal, while the interference signal generated by the occasional animal group activities in the target area is a random signal.

[0063] By extracting the monitoring performance indicators affected by interference and converting the interference impact into quantifiable indicators to be adjusted, it helps to accurately locate the adjustment targets of the prediction model, thereby avoiding blindly adjusting irrelevant parameters and making the optimization direction of the prediction model more targeted. Dynamically generating corrected performance indicators by combining the signal type and trigger frequency of the interference signal can effectively capture the impact of changes in the external environment on the performance of the prediction model. This precise parameter adjustment based on the characteristics of the interference signal ensures that the prediction model can still maintain the accuracy and timeliness of predictions in a complex environment. By mapping the corrected performance indicators to specific correction scenarios, it is possible to directionally update the correction data corresponding to the scenarios in the prediction model, while ensuring that the prediction model adapts to the new environment and avoiding the overcorrection problem that may be caused by global parameter adjustment, thereby maintaining the stability and adaptability of the prediction model and improving the prediction accuracy.

[0064]

Eighth Embodiment

[0065] In steps S531 to S533, the abnormal data is the basic unit constituting the abnormal parameter set, the theoretical type is the potential disaster type initially speculated based on the abnormal data, the historical disaster database refers to the archive that stores the complete parameters of various geological disaster events in history, usually including parameters such as the influence radius, signal characteristics, and signal fluctuation range of the disaster, the fluctuation range refers to the change interval of the abnormal data corresponding to each geological disaster occurrence in the historical disaster database, the single type means that when the abnormal data does not exceed the fluctuation range, the possible disaster type in the target area is unique, and the degree of fit refers to the matching degree between the abnormal data and the fluctuation ranges of various geological disaster signals.

[0066] It should be noted that in geological disaster monitoring, different types of disasters often have corresponding abnormal data. For example, the abnormal data corresponding to earthquakes usually includes data such as the amplitude, frequency, duration of seismic waves, and the displacement of the ground during an earthquake. By collecting various types of abnormal data during past geological disasters to construct a historical disaster database, the current set of abnormal parameters can be obtained through real-time signal data, and multiple theoretical types of geological disasters can be preliminarily screened. When the abnormal data corresponding to multiple theoretical types does not exceed the fluctuation range, it is determined that the disaster type in the target area is a single type, and the degree of fit between the abnormal data and multiple theoretical types is calculated. The theoretical type with the highest degree of fit is the disaster type finally predicted by the adjustment model.

[0067] In step S534, the combined data refers to the abnormal data that exceeds the fluctuation range of a single disaster, and the combination method refers to the associated combination mode between multiple disaster types.

[0068] It should be noted that when the abnormal data exceeds the fluctuation range defined in the historical disaster database, it is determined that the disaster type in the target area is a combination of multiple types. The combination of potential disaster types is determined through the combined data, the degree of fit between the combined data and the combined disaster types is calculated, and the most likely combination of disaster types and the corresponding combination method are determined according to the fit result.

[0069] For example, when the abnormal data exceeds the fluctuation range and the combined data is amplitude, frequency, ground deformation, and soil moisture, it is speculated that the possible disaster types are earthquake and landslide. The combination methods of disaster types can be divided into two types: concurrent type and induced type. When the degree of fit of the induced type is higher than that of the concurrent type, it is determined that the disaster type and combination method finally predicted by the adjustment model are "earthquake-induced landslide".

[0070] As the core element for identifying geological disaster risks, abnormal data can capture the characteristic parameters that deviate from the normal state in real-time signal data, providing real-time information for disaster prediction. Combining the theoretical types with the historical disaster database provides support for historical data for the prediction of disaster types, helping to reduce the prediction error of the adjustment model. The fluctuation range provides a judgment boundary for abnormal data. The judgment mechanism of single type and degree of fit ensures the efficiency and accuracy of the adjustment model in most conventional scenarios. The determination of combined data and combination method takes into account the complex scenarios of multiple concurrent disaster types, making the adjustment model more adaptable and better able to handle complex geological disaster situations.

[0071]

Ninth Embodiment

[0072] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention should be subject to the scope defined by the claims.

Claims

1. A method for monitoring geological disasters based on a distributed optical fiber vibration sensing system, characterized in that: The geological disaster monitoring method comprises: Acquire monitoring requirements in the target area, and determine the area to be expanded according to the monitoring requirements and the system distribution path of the original optical fiber in the distributed optical fiber vibration sensing system; Determine the actual distribution path of the newly added optical fiber according to the geomorphic features and geological risk level of the area to be expanded; Conducting virtual disaster scenario tests on the system distribution path to obtain characteristic data corresponding to each geological disaster scenario; After the newly added optical fiber is installed, the characteristic data is corrected according to the loss of the original optical fiber and the transmission characteristics of the newly added optical fiber, and a prediction model is constructed according to the corrected data; The prediction model is combined with environmental information to determine the type of disaster occurring in the target area.

2. The method for monitoring geological disasters according to claim 1, characterized in that: The obtaining of monitoring requirements in the target area and determining the area to be expanded according to the monitoring requirements and the system distribution path of the original optical fiber in the distributed optical fiber vibration sensing system specifically includes: Determine the monitoring requirements based on the geological exploration data and historical disaster records of the target area; Constructing a three-dimensional monitoring coverage model of the original optical fiber according to the monitoring performance index of the original optical fiber and the terrain shielding effect; Determine a new risk area based on the three-dimensional monitoring coverage model and the monitoring requirements; Screening out monitoring blind spots and inefficient areas according to the three-dimensional monitoring coverage model; The area to be expanded is determined according to the newly added risk area, the monitoring blind area and the inefficient area.

3. The geological disaster monitoring method according to claim 2, characterized in that: Determining the actual distribution path of the newly added optical fiber according to the geomorphic features and geological risk level of the area to be expanded specifically includes: Determining the distribution density of the newly added optical fibers according to the geological risk level and the frequency of disaster occurrence; Determining a theoretical distribution path of the newly added optical fiber according to the topographical features and the distribution density of the area to be expanded; The virtual disaster scenario test is performed on the three-dimensional model of the theoretical distribution path, and the theoretical distribution path is adjusted according to the preview result to determine the actual distribution path.

4. The geological disaster monitoring method according to claim 3, characterized in that: After the newly added optical fiber is installed, the characteristic data is corrected according to the loss of the original optical fiber and the transmission characteristics of the newly added optical fiber, and a prediction model is constructed according to the corrected data, specifically including: Dividing the original optical fiber into a plurality of loss sections according to the number of turning points; Calculating the attenuation coefficient of each loss section according to the turning degree of the loss section and the length of the optical fiber; Calculating the loss coefficient of the original optical fiber according to the attenuation coefficient and service life of each loss section; The characteristic data is corrected according to the loss coefficient and the transmission characteristics of the newly added optical fiber, and the prediction model is constructed according to the corrected data.

5. The geological disaster monitoring method according to claim 4, characterized in that: The step of correcting the characteristic data according to the loss coefficient and the transmission characteristics of the newly added optical fiber, and constructing the prediction model according to the corrected data, specifically includes: Determine an installation location according to the actual distribution path of the newly added optical fiber, and divide sub-installation modules according to the topographical features of the installation location; Calculating the actual transmission efficiency of the vibration signal according to the transmission characteristics in the sub-mounting module; Obtaining a standard transmission efficiency of the newly added optical fiber under a standard state, and calculating a deviation coefficient of the newly added optical fiber according to the actual transmission efficiency and the standard transmission efficiency; The correction data is calculated according to the deviation coefficient, the loss coefficient and the characteristic data, and the prediction model is constructed according to the correction data.

6. The method for monitoring geological disasters according to claim 5, characterized in that: Combining the prediction model with environmental information to determine the type of disaster occurring in the target area specifically includes: When the environmental information has not changed, the real-time signal data monitored by the newly added optical fiber and the original optical fiber are input into the prediction model to determine the disaster type of the geological disaster; When the environmental information changes, an interference signal generated by the change in the environmental information is acquired, and the prediction model is adjusted according to the interference signal to obtain an adjusted model; An abnormal parameter set is determined according to the adjustment model and the real-time signal data, and the disaster type of the geological disaster is determined according to the abnormal parameter set.

7. The method for monitoring geological disasters according to claim 6, characterized in that: When the environmental information changes, obtaining an interference signal generated by the change in the environmental information, and adjusting the prediction model according to the interference signal to obtain an adjustment model specifically includes: Acquire the monitoring performance index affected by the interference signal, and mark the monitoring performance index as an index to be adjusted; The indicator to be adjusted is updated according to the signal type and trigger frequency of the interference signal, and recorded as a modified performance indicator; The geological disaster scenario affected by the correction performance index is obtained and recorded as a correction scenario, and the correction data corresponding to the correction scenario in the prediction model is updated; The prediction model is adjusted according to the updated correction data to obtain the adjusted model.

8. The method for monitoring geological disasters according to claim 7, characterized in that: Determining an abnormal parameter set according to the adjustment model and the real-time signal data, and determining the disaster type of the geological disaster according to the abnormal parameter set specifically includes: Determine the type of disaster that may occur in the target area according to each abnormal data in the abnormal parameter set, and record it as a theoretical type; Obtaining the fluctuation range of the abnormal data when all the theoretical types occur from the historical disaster database; When the abnormal data does not exceed the fluctuation range, the disaster type in the target area is determined to be a single type, and the disaster type is determined according to the degree of fit between the abnormal data and the fluctuation ranges of different disaster types; When the abnormal data exceeds the fluctuation range, the abnormal data exceeding the fluctuation range is recorded as combined data, and the disaster type corresponding to the combined data is matched to determine the combination method of multiple disaster types.

9. A geological disaster monitoring system based on a distributed optical fiber vibration sensing system, characterized in that: The geological disaster monitoring method according to any one of claims 1 to 8 is applied to the geological disaster monitoring system, and the geological disaster monitoring system comprises: A positioning module, the positioning module is used to determine the area to be expanded according to the monitoring requirements and the system distribution path; A testing module, the testing module is used to perform the virtual disaster scenario test on the system distribution path to obtain the characteristic data corresponding to each geological disaster scenario; A correction module, wherein the correction module corrects the characteristic data according to the loss of the original optical fiber and the transmission characteristics of the newly added optical fiber; A prediction module is used to predict the type of disaster occurring in the target area.

Images