A method for monitoring geological disasters along a railway
By laying fiber optic sensors along the railway line and combining them with image comparison technology, the problems of accuracy and sensitivity in monitoring geological disasters along the railway line have been solved, enabling timely early warning and efficient detection of geological disasters and ensuring the safe operation of the railway.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ANHUI HUIYI COMMUNICATION SCIENCE CO LTD
- Filing Date
- 2023-07-07
- Publication Date
- 2026-05-12
AI Technical Summary
Existing technologies are insufficient for effectively monitoring and providing early warning of geological disasters along railway lines, which affects the safe operation of railways.
Fiber optic sensors are laid along the railway line to monitor surface deformation through actual measurement signals. Combined with image comparison technology, alarm signals of varying severity are issued to improve monitoring accuracy and sensitivity.
It has achieved high-precision and high-sensitivity detection of geological disasters along railway lines, timely early warning, reduced false alarms, and improved railway operation safety and detection efficiency.
Smart Images

Figure CN117037423B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of geological disaster monitoring technology, specifically to a method for monitoring geological disasters along railway lines. Background Technology
[0002] China's terrain slopes from west to east, with mountains, plateaus, and hills accounting for approximately 67% of its land area. During railway design and construction, large areas of plains and basins were avoided as much as possible to ensure the integrity of farmland and protect natural environmental resources.
[0003] Therefore, slopes are present in over 70% of the mileage of China's high-speed railways and urban rail transit lines. The slope gradient is influenced by the natural environment, and when it exceeds a certain standard value, specific detection and protection measures are required. Geological hazards are a type of hazardous material movement occurring in the shallow surface layer of the Earth's lithosphere, typically manifesting as landslides, collapses, debris flows, ground subsidence, ground fissures, etc. Geological hazards can damage railways and affect their safe operation; therefore, it is necessary to monitor geological hazards along railway lines. This paper proposes a monitoring method for geological hazards along railway lines to detect and issue early warnings. Summary of the Invention
[0004] The purpose of this invention is to solve the above-mentioned technical problems and provide a method for monitoring geological disasters along railway lines.
[0005] To achieve the above objectives, the present invention employs the following technical solution:
[0006] A method for monitoring geological hazards along railway lines, as follows:
[0007] Acquire the measured signals from the fiber optic sensors, where the measured signals are obtained from the fiber optic sensors laid along the railway line;
[0008] The surface deformation value S at the corresponding location is obtained based on the measured signal. The deformation rate V is calculated based on the time of deformation. When the rate of change V is greater than the first threshold, a first alarm signal is issued. When the rate of change V is greater than the second threshold, a second alarm signal is issued.
[0009] The first threshold is less than the second threshold, and the severity of the first alarm signal is less than that of the second alarm signal.
[0010] Furthermore, when the first alarm signal is issued, the abnormal deformation location corresponding to the measured signal is obtained. Based on the obtained abnormal deformation location, the remote video of that location is activated. Real-time images of that location are captured at each first time interval. The current first real-time image is compared with the second real-time image obtained at the previous first time interval. Based on the comparison result, an early warning confirmation message is issued.
[0011] Furthermore, when comparing the first real-time image with the second real-time image, the obtained first real-time image and the second real-time image are divided into multiple partitions. The first real-time image and the second real-time image are divided into different comparison sub-regions according to the same partitioning method. The image pixels in each comparison sub-region of the obtained first real-time image are compared with the comparison sub-region of the second real-time image. When the comparison difference is greater than the third threshold, the first warning confirmation information is issued.
[0012] Furthermore, the location of the first alarm signal in the first real-time image is obtained as the image anomaly location within the first real-time image. Based on the image anomaly location, the sub-regions within the first real-time image segmentation that include the image anomaly location are further subdivided to obtain a subdivided region of the image anomaly location. The subdivided region of the first real-time image is compared with the image pixels within the subdivided region of the second real-time image. When the difference between the comparison points is greater than a fourth threshold, a second warning confirmation signal is issued; wherein the fourth threshold is less than a third threshold. This ensures that an alarm is issued when the image change value obtained at the anomaly location is less than a specified threshold, thereby improving alarm sensitivity.
[0013] Furthermore, the subdivided region is obtained in the following way: the sub-region including the abnormal position of the image is divided into rectangular partitions. Specifically, the sub-region is wrapped with a square, and the square is divided into 4 smaller squares from the middle of the horizontal and vertical directions. Similarly, the smaller squares are divided into 4 squares from the center of the horizontal and vertical directions. When the number of pixels in the square is less than the fifth threshold, the separation is stopped. The final segmented region is the subdivided region.
[0014] Furthermore, based on the obtained second alarm signal, first warning confirmation signal, and third warning confirmation signal, a fourth warning signal is issued, wherein the severity of the fourth warning signal is higher than that of the second alarm signal, the first warning confirmation signal, and the third warning confirmation signal.
[0015] The present invention provides a method for monitoring geological hazards along railway lines, which has the following beneficial effects:
[0016] By laying fiber optic sensors along railway lines and collecting and analyzing their signals, alarm signals can be issued based on the analysis results. This allows for timely detection of geological hazards along the railway, enabling proactive responses and preventing railway operational accidents. Fiber optic sensors also provide high-precision, high-sensitivity detection of pipelines, detecting even minute anomalies. Furthermore, fiber optic sensors are highly resistant to interference and corrosion, maintaining stable detection performance even in complex railway environments. The sensors and equipment in the fiber optic detection system are characterized by long lifespan and low maintenance, allowing for stable operation over extended periods and reducing detection costs and risks. In data analysis, monitoring the rate of deformation change allows for a more accurate reflection of geological disaster occurrences. Furthermore, issuing different alarm signals based on monitoring data enables a more accurate assessment of the degree of danger. After the first alarm signal is issued, images of anomaly points are collected, and image comparison is used to reconfirm the alarm signal, making it more accurate and preventing false alarms. In image comparison, zoning processing is employed, with detailed zoning of key anomaly locations and coarse zoning of other areas. This allocates resources to alarm areas, improving accuracy while reducing computational resources, analysis time, and response speed. Attached Figure Description
[0017] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings:
[0018] Figure 1 This is a flowchart illustrating a method for monitoring geological hazards along railway lines, as provided by the present invention. Detailed Implementation
[0019] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0021] like Figure 1 As shown, a method for monitoring geological hazards along railway lines is as follows:
[0022] Acquire the measured signals from the fiber optic sensors, where the measured signals are obtained from the fiber optic sensors laid along the railway line;
[0023] The surface deformation value S at the corresponding location is obtained based on the measured signal. The deformation rate V is calculated based on the time t that the deformation occurs, where V = S / t. When the deformation rate V is greater than the first threshold, a first alarm signal is issued. When the deformation rate V is greater than the second threshold, a second alarm signal is issued.
[0024] The first threshold is lower than the second threshold, and the severity of the first alarm signal is lower than that of the second alarm signal. By issuing first and second alarm signals of different severity, the severity of the current anomaly can be understood, thereby facilitating appropriate handling decisions.
[0025] When the first alarm signal is issued, the location of the abnormal deformation corresponding to the measured signal is obtained. Based on the obtained abnormal deformation location, a remote video of that location is activated. Real-time images of that location are captured at first time intervals. The current first real-time image is compared with the second real-time image obtained at the previous first time interval. Based on the comparison result, an early warning confirmation message is issued. The first real-time image is the image obtained at the current time, and the second real-time image is the image obtained at the previous first time interval, i.e., the previously obtained image. Differences are identified by comparing the current image with the previous image.
[0026] When comparing the first real-time image with the second real-time image, the obtained first and second real-time images are divided into multiple partitions. Each of the first and second real-time images is divided into different comparison sub-regions using the same partitioning method. The image pixels within each comparison sub-region of the first real-time image are compared with those within the comparison sub-region of the second real-time image. When the difference in the comparison points exceeds a third threshold, a first warning confirmation message is issued. Based on the image comparison results, a second warning message is issued, thereby confirming the previous warning information and improving the accuracy of the warning information.
[0027] Specifically, the location of the first alarm signal in the first real-time image is obtained as the image anomaly location within the first real-time image. Based on the image anomaly location, the sub-regions within the first real-time image that include the image anomaly location are further subdivided to obtain a subdivided region of the image anomaly location. The subdivided region of the first real-time image is compared with the image pixels within the subdivided region of the second real-time image. When the difference between the comparison points exceeds a fourth threshold, a second warning confirmation signal is issued; where the fourth threshold is less than a third threshold. This ensures that an alarm is triggered when the image change value obtained at the anomaly location is less than a specified threshold, thereby improving alarm sensitivity.
[0028] The subdivided regions are obtained as follows: Sub-regions including image anomaly locations are rectangularly partitioned. Specifically, each sub-region is enclosed in a square. This square is then divided into four smaller squares from its horizontal and vertical center. This process is repeated, dividing each smaller square into four smaller squares from its horizontal and vertical center. Separation stops when the number of pixels within a square is less than a fifth threshold. The resulting subdivided regions are then used as the subdivided regions. In image comparison, this partitioning process refines the subdivisions of key anomaly locations while coarsely partitioning other areas. This allows resources to be allocated to alarm areas, improving accuracy while reducing computational resources, analysis time, and response speed.
[0029] Based on the obtained second alarm signal, first warning confirmation signal, and third warning confirmation signal, a fourth warning signal is issued. This fourth warning signal has a higher severity than the second, first, and third alarm confirmation signals. When all different alarm signals are triggered, a fourth warning signal with a higher severity of geological disaster is issued to alert staff to the severity level so that timely action can be taken, thereby improving railway operation safety.
[0030] The parts not covered in this technical solution can be implemented using existing technologies.
[0031] The foregoing has shown and described the basic principles, main features, and characteristics of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.
Claims
1. A method for monitoring geological hazards along railway lines, characterized in that: In the following way: Acquire the measured signals from the fiber optic sensors, where the measured signals are obtained by the fiber optic sensors laid along the railway line; The surface deformation value S at the corresponding location is obtained based on the measured signal. The deformation rate V is calculated based on the time of deformation. When the rate of change V is greater than the first threshold, a first alarm signal is issued. When the rate of change V is greater than the second threshold, a second alarm signal is issued. The first threshold is less than the second threshold, and the severity of the first alarm signal is less than that of the second alarm signal; When the first alarm signal is issued, the abnormal deformation location corresponding to the measured signal is obtained. Based on the obtained abnormal deformation location, the remote video of that location is activated. The real-time image of that location is captured at each first time interval. The current first real-time image is compared with the second real-time image obtained at the previous first time interval. Based on the comparison result, an early warning confirmation message is issued. When comparing the first real-time image with the second real-time image, the obtained first real-time image and the second real-time image are divided into multiple partitions. The first real-time image and the second real-time image are divided into different comparison sub-regions according to the same partitioning method. The image pixels in each comparison sub-region of the obtained first real-time image are compared with the comparison sub-region of the second real-time image. When the comparison difference is greater than the third threshold, the first warning confirmation information is issued.
2. The method for monitoring geological hazards along railway lines according to claim 1, characterized in that: The location of the first alarm signal in the first real-time image is obtained as the image anomaly location in the first real-time image. Based on the image anomaly location, the sub-regions of the first real-time image that include the image anomaly location are further subdivided to obtain a subdivided region of the image anomaly location. The subdivided region of the first real-time image is compared with the image pixels in the subdivided region of the second real-time image. When the difference between the comparison points is greater than a fourth threshold, a second warning confirmation signal is issued. The fourth threshold is less than a third threshold. This ensures that if the image change value obtained at the anomaly location is less than a specified threshold, an alarm is issued, thereby improving alarm sensitivity.
3. The method for monitoring geological hazards along railway lines according to claim 2, characterized in that: The subdivided regions are obtained as follows: the sub-regions including the abnormal locations in the image are divided into rectangular partitions. Specifically, the sub-regions are enclosed by squares, and the squares are divided into four smaller squares from the center in the horizontal and vertical directions. This process is repeated to divide the smaller squares into four smaller squares from the center in the horizontal and vertical directions. The division stops when the number of pixels in a square is less than a fifth threshold. The final subdivided regions are then obtained as the subdivided regions.
4. The method for monitoring geological hazards along railway lines according to claim 3, characterized in that: Based on the obtained second alarm signal, first warning confirmation signal, and third warning confirmation signal, a fourth warning signal is issued, wherein the severity of the fourth warning signal is higher than that of the second alarm signal, the first warning confirmation signal, and the third warning confirmation signal.