All-fiber intelligent rockburst early warning and monitoring system

Abstract

The invention relates to an all-fiber intelligent rockburst early warning and monitoring system, and the system comprises an optical fiber arrangement module which is used for arranging an all-fiber sensing network; the all-optical fiber sensing network comprises a plurality of optical fiber sensors arranged at different positions of the rock mass; the signal acquisition module is used for acquiring a multi-dimensional signal of the optical fiber sensor; the signal conversion module is used for performing time-frequency domain analysis on the collected multi-dimensional signals to obtain time domain signals, and converting the time domain signals into frequency domain signals through Fourier transform; the rockburst prediction module is used for performing mode recognition on the signals after time-frequency analysis through an intelligent algorithm, predicting a probability value of occurrence of a rockburst risk and obtaining a prediction result; the rockburst early warning module is used for setting a rockburst early warning threshold value according to the prediction result and triggering an alarm when the following conditions are met; and the dynamic adjustment module is used for feeding back and dynamically adjusting the position and the monitoring frequency of the optical fiber sensing network in real time. According to the invention, the accuracy and timeliness of rockburst early warning can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an all-optical intelligent rock burst early warning and monitoring system, an electronic device and a non-transient computer-readable storage medium. Background Art

[0002] Existing rockburst warning and monitoring mainly rely on traditional seismic monitoring technology, acoustic emission monitoring technology, stress monitoring technology, etc. These technologies monitor the seismic waves, acoustic emission signals or stress changes of the rock mass by arranging sensor arrays, thereby providing early warning of rockbursts. These methods can provide early information on rock mass changes to a certain extent, helping relevant personnel take preventive measures to avoid disasters. In addition, existing fiber optic sensing technology has also been gradually applied to the field of rockburst monitoring. It provides real-time feedback on the stress state of the rock mass by monitoring changes in the force or deformation of the optical fiber.

[0003] However, existing rockburst early warning and monitoring have certain limitations. First, traditional seismic monitoring and acoustic emission monitoring equipment are easily interfered by environmental noise, which affects the accuracy of the data. Secondly, these methods often rely on point sensor arrangements, which cannot fully capture large-scale changes in rock mass conditions and have monitoring blind spots. At the same time, the installation and maintenance costs of sensors are high, especially in complex geological environments. The durability and performance stability of sensors are poor, which limits their scope of application. Although fiber optic sensing technology has overcome some problems, existing applications are mostly single sensing methods, which cannot achieve multi-dimensional, intelligent comprehensive early warning and monitoring. Summary of the invention

[0004] In view of the technical problems existing in the prior art, the present invention provides an all-optical intelligent rock burst warning and monitoring system, an electronic device and a non-transient computer-readable storage medium capable of improving the accuracy and timeliness of rock burst warning.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: The present invention provides an all-optical intelligent rockburst early warning and monitoring system, the system comprising: An optical fiber arrangement module, used for arranging an all-optical fiber sensing network; the all-optical fiber sensing network comprises a plurality of optical fiber sensors arranged at different positions of the rock mass; A signal acquisition module, used for acquiring multi-dimensional signals of the optical fiber sensor; A signal conversion module, used for performing time-frequency domain analysis on the collected multi-dimensional signal to obtain a time domain signal, and converting the time domain signal into a frequency domain signal through Fourier transform; The rockburst prediction module is used to perform pattern recognition on the signal after time-frequency analysis through intelligent algorithms, predict the probability value of rockburst risk, and obtain the prediction result; The rockburst warning module is used to set the rockburst warning threshold according to the prediction results, and trigger an alarm when the following conditions are met: ; in, is the rockburst warning threshold, To set the threshold, the rockburst warning threshold is expressed as: ; in, is the probability value of rockburst corresponding to the data collected by the i-th optical fiber sensor, and n is the number of optical fiber sensors; The dynamic adjustment module is used for real-time feedback and dynamic adjustment of the position and monitoring frequency of the optical fiber sensor network.

[0006] Optionally, the multi-dimensional signal includes an optical signal, an acoustic signal and a strain signal; The signal acquisition module is also used for: The optical signal, the acoustic signal and the strain signal within the acquisition time are differentiated to obtain a time domain signal of the multi-dimensional signal.

[0007] Optionally, the time domain signal of the multi-dimensional signal is represented as: ; in, is the time domain signal of the multi-dimensional signal, is an optical signal, is the acoustic signal, is the strain signal, and T is the acquisition time.

[0008] Optionally, the signal conversion module is further used for: The time domain signal of the multi-dimensional signal is differentiated according to the angular frequency to obtain the frequency domain signal.

[0009] Optionally, the frequency domain signal is expressed as: ; in, is the frequency domain signal, is the angular frequency, is a time domain signal.

[0010] Optionally, the rockburst prediction module is further used for: Constructing a multi-dimensional feature matrix of the multi-dimensional signal; The multidimensional feature matrix is ​​processed according to the algorithm model to obtain the probability value.

[0011] Optionally, the probability value is expressed as: ; in, is the probability value, X is the multidimensional feature matrix, are algorithm model parameters.

[0012] Optionally, the rockburst warning module is also used for: Obtaining a probability value of rock burst corresponding to the data collected by each optical fiber sensor; The rockburst warning threshold is determined according to each of the probability values.

[0013] Optionally, the rockburst warning threshold is optimized according to real-time monitoring data.

[0014] In addition, to achieve the above-mentioned purpose, the present invention also proposes an electronic device, comprising: a memory for storing a computer software program; a processor for reading and executing the computer software program, thereby implementing the steps performed by the all-optical fiber intelligent rock burst early warning and monitoring system as described above.

[0015] In addition, to achieve the above-mentioned purpose, the present invention also proposes a non-transitory computer-readable storage medium, in which a computer software program is stored. When the computer software program is executed by a processor, the steps performed by the all-optical fiber intelligent rock burst early warning and monitoring system as described above are implemented.

[0016] The beneficial effects of the present invention are: (1) The present invention can collect multi-dimensional data including stress, strain, acoustics, etc. in real time through an all-fiber sensor network, thereby providing a comprehensive perception of the rock mass state. Compared with the traditional point sensor arrangement, the all-fiber sensor network can cover a larger range, avoid monitoring blind spots, and ensure the comprehensiveness and accuracy of monitoring.

[0017] (2) The present invention adopts an all-fiber sensor. The fiber optic sensing technology is less sensitive to external noise interference and can significantly improve the reliability and accuracy of data, which is particularly suitable for complex geological environments.

[0018] (3) The present invention can intelligently analyze the collected multi-dimensional data through deep learning or machine learning algorithms to accurately identify rockburst precursors. Through time-frequency domain analysis, complex rock mass change patterns are converted into interpretable features, and then intelligent algorithms are used to conduct risk assessments, greatly improving the accuracy and timeliness of rockburst warnings.

[0019] In summary, the present invention can significantly improve the accuracy and timeliness of rockburst warning, solve the problems of environmental interference, monitoring blind spots and high maintenance costs in traditional systems, and is suitable for wide application in complex geological environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A scene diagram of an all-fiber intelligent rockburst early warning and monitoring system provided by the present invention; Figure 2 A structural schematic diagram of an all-optical fiber intelligent rockburst early warning and monitoring system provided by the present invention; Figure 3 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention; Figure 4 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0022] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0023] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0024] See also Figure 1 , Figure 1 This is a scene diagram of an all-fiber intelligent rockburst early warning and monitoring system provided by the present invention. Figure 1As shown, the terminal and the server are connected via a network, such as a wired or wireless network connection. The terminal may include but is not limited to portable terminals such as mobile phones and tablets installed with various network platform applications, as well as fixed terminals such as computers, query machines, and advertising machines. The server provides users with various business services, including service push servers, user recommendation servers, etc.

[0025] It should be noted that Figure 1 The scenario diagram of an all-fiber intelligent rock burst warning and monitoring system shown is only an example. The terminal, server, and application scenario described in the embodiment of the present invention are intended to more clearly illustrate the technical solution of the embodiment of the present invention, and do not generate limitations on the technical solution provided by the embodiment of the present invention. Ordinary technicians in this field can know that with the evolution of the system and the emergence of new business scenarios, the technical solution provided by the embodiment of the present invention is also applicable to similar technical problems.

[0026] Among them, the terminal can be used for: Arranging an all-optical fiber sensing network; the all-optical fiber sensing network comprises a plurality of optical fiber sensors arranged at different positions of the rock mass; Collecting multi-dimensional signals of the optical fiber sensor; Performing time-frequency domain analysis on the collected multi-dimensional signal to obtain a time-domain signal, and converting the time-domain signal into a frequency-domain signal by Fourier transform; Through intelligent algorithms, the signal after time-frequency analysis is subjected to pattern recognition, and the probability value of rockburst risk is predicted to obtain the prediction result; According to the prediction results, a rockburst warning threshold is set, and an alarm is triggered when the following conditions are met; Real-time feedback and dynamic adjustment of the location and monitoring frequency of the fiber optic sensor network.

[0027] It should also be noted that the present invention strictly follows the principles of user authorization and legal provisions. For example, before collecting relevant data from users, it is possible to ensure that the user's explicit authorization is obtained, and the data is processed strictly in accordance with the scope and purpose of the user's authorization. At the same time, it also strictly follows applicable privacy laws and regulations, protects the security and privacy of user data by formulating strict data protection policies and security measures, and regularly reviews and updates the data processing process to ensure compliance with the latest legal requirements and best practices.

[0028] See also Figure 2 , Figure 2 A structural schematic diagram of an all-optical fiber intelligent rockburst early warning and monitoring system provided by the present invention.

[0029] like Figure 2As shown, an all-fiber intelligent rockburst early warning and monitoring system proposed in an embodiment of the present invention includes: an optical fiber arrangement module 201, a signal acquisition module 202, a signal conversion module 203, and a rockburst prediction module 204, which are specifically as follows: The optical fiber arrangement module 201 is used to arrange an all-optical fiber sensing network.

[0030] Among them, the all-fiber sensing network includes multiple fiber optic sensors arranged at different positions of the rock mass, which are used to monitor the stress, displacement and other physical parameters of the rock mass in real time.

[0031] The signal acquisition module 202 is used to acquire multi-dimensional signals from the optical fiber sensor.

[0032] In some embodiments, the multi-dimensional signal includes an optical signal, an acoustic signal, and a strain signal. The signal acquisition module 202 is also used to: The optical signal, acoustic signal and strain signal within the acquisition time are differentiated to obtain the time domain signal of the multi-dimensional signal.

[0033] In some embodiments, the time domain signal of the multi-dimensional signal is represented as: ; in, is the time domain signal of the multi-dimensional signal, is an optical signal, is the acoustic signal, is the strain signal, and T is the acquisition time.

[0034] In the specific implementation, It represents the change of the total signal obtained from the system in the time domain. It is a comprehensive signal that reflects the overall state change of the rock mass by integrating data from multiple dimensions. They all represent the total amount of signals detected by the system at that moment, which is obtained by superimposing different types of signals (such as optical, acoustic, and strain signals).

[0035] It refers to the optical signal detected by the fiber optic sensor, which usually reflects the change of optical parameters (such as Brillouin scattering or Rayleigh scattering) caused by stress or deformation of the fiber. Small stress changes in the fiber will cause changes in the phase, frequency or wavelength of the light. Through these optical characteristics, the system can indirectly monitor the stress state of the rock mass.

[0036] The advantage of optical signals is that they are less sensitive to environmental disturbances and can be measured distributed along the entire length of the fiber. It is a very important signal dimension that can provide detailed temporal and spatial variation information for rock stress distribution in the monitoring area.

[0037] It stands for acoustic emission signal, which captures the sound waves generated when the rock mass breaks through acoustic sensors. These acoustic signals originate from activities such as crack expansion or friction sliding inside the rock mass, especially in the early stage of rock burst, which are usually accompanied by acoustic emission caused by micro fractures.

[0038] The strength and frequency of the acoustic emission signal can reflect the potential crack expansion and stress release in the rock mass. By monitoring the changing trend of the acoustic emission signal, the system can identify possible rockburst precursor events. It is an extremely critical dimension in rockburst monitoring.

[0039] It is a strain signal detected by optical fiber or other sensors, which directly reflects the deformation of rock mass under different stresses. Strain is a measure of the deformation of rock mass under stress. By measuring the strain changes in different areas of the rock mass, we can understand the stress concentration of the rock mass and identify potential fracture areas.

[0040] The strain signal is captured by optical fiber sensing technology or traditional strain sensors. This type of signal can continuously monitor the deformation process of the rock mass over a long period of time, thereby providing trend information on long-term stress changes. The system can identify potential rock mass instability early through abnormal changes in strain signals.

[0041] T is the signal acquisition time range. The monitoring system will continuously collect multi-dimensional signals within T time and calculate the total signal volume by integration. T can be a fixed monitoring window or dynamically adjusted to meet different monitoring needs.

[0042] In practical applications, the monitoring time can be real-time or set to a specific time interval, such as seconds, minutes or hours. The multi-dimensional signals collected within time T are integrated and summarized to obtain a comprehensive signal S(t), which is convenient for subsequent analysis and processing.

[0043] The integral symbol in the formula indicates that all signals are accumulated during the period from time 0 to T. This means that the system not only collects optical, acoustic and strain signals at each moment, but also accumulates and analyzes these signals over the entire time period to form an overall trend of change. The integral formula can help the system filter out noise signals, highlight continuous and significant signal changes, and thus better identify rockburst precursors.

[0044] The significance of the integral formula is that it can smooth the occasional noise or mutation signal at a single moment, and capture the stable and continuous change trend through long-term accumulation, which is particularly critical for early warning in rock mass monitoring. The formula integrates various signal dimensions to obtain a total signal quantity, which is convenient for the application of subsequent early warning models.

[0045] formula The changes in multiple signals such as optics, acoustics and strain are comprehensively considered and accumulated over a period of time through integration. The purpose of this is to obtain a global, multi-dimensional signal total to help the system better analyze the overall stress state of the rock mass and possible instability. By monitoring and integrating these signals, the system can improve its ability to identify rockburst precursors, thereby achieving earlier and more accurate early warning.

[0046] Assume that in a certain monitoring area, the fiber optic sensor array detects weak stress fluctuations and acoustic emission signals, the acoustic emission frequency gradually increases over time, and the strain signal shows abnormal deformation in the local area. , and The signal is integrated in real time to obtain the total If As time goes by and the preset threshold is exceeded, the system will trigger an alarm to indicate the risk of rock burst.

[0047] The signal conversion module 203 is used to perform time-frequency domain analysis on the collected multi-dimensional signal to obtain a time domain signal, and convert the time domain signal into a frequency domain signal through Fourier transform.

[0048] In some embodiments, the signal conversion module 203 is further used to perform differentiation processing on the time domain signal of the multi-dimensional signal according to the angular frequency to obtain a frequency domain signal.

[0049] In some embodiments, the frequency domain signal is represented as: ; in, is the frequency domain signal, is the angular frequency, is a time domain signal.

[0050] In the specific implementation, It represents the performance of the signal in the frequency domain, usually called spectrum or frequency component. It is obtained through Fourier transform and represents the time domain signal For rockburst early warning and monitoring methods, frequency domain signals can reveal the frequency distribution of rock mass vibration and help identify key seismic waves, acoustic emissions or strain change patterns.

[0051] Shows the signal at different frequencies The energy distribution on the rock mass, such as which frequency components (low frequency, high frequency) are dominant. This is very important for identifying precursor signals of potential rock bursts, because there are usually significant changes in a specific frequency range before the rock mass cracks or breaks.

[0052] Represents angular frequency, in radians per second (rad / s), which is a way of expressing frequency f. Angular frequency is an important parameter for describing the periodicity of signal vibration. In Fourier transform, Represents the different frequency components in the signal. The purpose of the calculation is to identify the changes in the signal at different frequencies.

[0053] It is a signal in the time domain, indicating the intensity of the signal changing over time. The time domain signal is the raw data collected directly from the sensor, reflecting the physical changes of the monitoring point at different times. The time domain signal can be a combination of optical signals, acoustic signals or strain signals.

[0054] In rockburst monitoring, time domain signals often contain a lot of information, but the key patterns (such as stress release or crack expansion before rockburst) may be hidden in complex time changes. Through Fourier transform, these time domain signals can be converted into frequency domain, which is convenient for extracting meaningful frequency features.

[0055] Through Fourier transform, we can Mapping to the frequency domain generates , to indicate that the signal has different frequencies The result of Fourier transform is usually a complex number, and the real and imaginary parts represent the amplitude and phase information of the signal respectively.

[0056] It is a complex exponential function, which represents a complex sine wave. Its real part and imaginary part represent different phases of the signal. Through this complex exponential function, the time domain signal can be decomposed into sine waves of different frequencies, and then the information of the signal on each frequency component can be obtained.

[0057] In rockburst monitoring, time domain signals usually contain multiple frequency components, which may correspond to different types of geological activities. For example, low-frequency components may reflect slow stress accumulation, while high-frequency components may be associated with sudden rupture of rock microcracks. By performing Fourier transform on the time domain signal, these key frequency components can be identified, thereby better predicting the occurrence of rockburst. Frequency domain signal obtained by Fourier transform , it is possible to analyze the vibration or stress release of the rock mass at different angular frequencies, thereby extracting characteristic signals before rockburst, such as frequency anomaly, energy accumulation, etc. In addition, frequency domain analysis can also effectively reduce the noise in the time domain signal and improve the accuracy of the analysis.

[0058] Assume that the fiber optic sensor array detects the vibration signal inside the rock mass , which contains high-frequency acoustic emission signals and low-frequency stress waves during the rock mass stress release process. Through Fourier transform, the system Decompose into frequency components , it was found that the energy of some high-frequency components suddenly increased, indicating that the crack expansion accelerated, and the system issued a rockburst warning signal based on this.

[0059] In summary, the present invention can transform complex time domain signals Decompose into different frequencies The frequency domain signal In the rockburst early warning system, this transformation can be used to extract the frequency characteristics of the signal to help identify the potential fracture risk inside the rock mass. This frequency domain analysis can not only reveal the stress state of the rock mass, but also filter out noise signals, improving monitoring accuracy and timeliness.

[0060] The rockburst prediction module 204 is used to perform pattern recognition on the signal after time-frequency analysis through an intelligent algorithm, predict the probability value of the rockburst risk, and obtain a prediction result.

[0061] In some embodiments, the rockburst prediction module 204 is further configured to: Construct a multi-dimensional feature matrix of multi-dimensional signals; The multi-dimensional feature matrix is ​​processed according to the algorithm model to obtain the probability value.

[0062] In some embodiments, the probability value is expressed as: ; in, is the probability value, X is the multidimensional feature matrix, are algorithm model parameters.

[0063] In the specific implementation, Represents the probability of rockburst, with a value range of 0 to 1. When the probability is close to 1, it means that the possibility of rockburst is high; when the probability is close to 0, it means that the possibility of rockburst is low. This probability value is calculated by the system based on the input monitoring data and historical data, and is the core output of the rockburst warning model.

[0064] X is a multidimensional feature matrix collected from the fiber optic sensor network, which represents the physical state of the rock mass at different times and different monitoring points. The matrix contains features of multiple dimensions, which are used to characterize the stress, displacement, acoustic signal, temperature change, etc. of the rock mass. Specifically, each column of the matrix represents a different physical quantity, and each row represents the measurement value at a different time point or spatial position.

[0065] For example, assuming there are three key features: stress signal, strain signal, and acoustic emission signal, X can be expressed as: ; in, is the stress signal, is the strain signal, is the acoustic emission signal, and t is the time point. The matrix can continuously add new monitoring data and update in real time.

[0066] It is the parameter set of the model, which contains information such as model weights and biases used for rockburst prediction. These parameters are obtained by training with historical data. During the training phase, the model uses a large amount of historical data to optimize In order to achieve the best prediction effect for the input feature X.

[0067] The adjustment can be done through a variety of machine learning methods, such as linear regression, logistic regression, neural network, etc. The specific model selected depends on the complexity and scale of the rockburst data. The process of training the model is actually to find the optimal parameter set. , to minimize the predicted value The error between the predicted rock burst and the actual rock burst situation.

[0068] It is a nonlinear mapping used to transform the input multidimensional feature matrix X through the parameters Mapped to an output probability value . This function can be a simple linear model or a complex neural network. In complex models (such as deep neural networks), It contains multiple layers of neurons and activation functions. Each layer further performs nonlinear transformation based on the output of the previous layer and finally outputs a probability value.

[0069] By taking the multi-dimensional sensor data matrix X as input and combining it with the pre-trained model parameters ,function Able to analyze the changing trends of rock stress, strain, and acoustic signals, and derive the probability of rock burst When the probability exceeds a certain threshold, the system will trigger an early warning, thereby helping mine or other engineering managers take timely measures to reduce disaster risks.

[0070] By introducing new sensor data and feedback information from historical rockburst events, the parameters can be further trained and optimized. , so that the model can better adapt to the prediction tasks under different geological conditions. The model can also gradually improve the prediction accuracy in long-term monitoring through self-learning function, forming a more intelligent early warning mechanism.

[0071] In summary, the formula It is a prediction model that integrates multi-dimensional data, machine learning algorithms and self-optimization to calculate the probability of rock burst and support real-time warning and risk prevention and control of the system.

[0072] The rockburst warning module 205 is used to set the rockburst warning threshold according to the prediction results, and trigger an alarm when the following conditions are met.

[0073] In some embodiments, the rockburst warning module 205 is further used to: Obtain the probability value of rock burst corresponding to the data collected by each optical fiber sensor; According to each probability value, the rockburst warning threshold is determined.

[0074] In some embodiments, the rockburst warning threshold 205 is expressed as: ; in, is the rockburst warning threshold, is the probability value of rock burst corresponding to the data collected by the i-th optical fiber sensor. It should be noted that the rock burst warning threshold can be optimized according to the real-time monitoring data.

[0075] In the specific implementation, It is the rockburst warning threshold calculated by the system based on the data from different sensors. It is the average value of the rockburst probability given by multiple sensors and is used to assess whether there is a rockburst risk in the entire monitoring area. When a certain preset critical value is exceeded, the system will trigger an alarm, indicating that a rockburst may be imminent. The role of this threshold is to aggregate the local detection results of each sensor into a comprehensive evaluation value to reflect the overall rock mass status in the monitored area. If the probability of rockburst detected by most sensors is high, the comprehensive threshold It will also increase accordingly, thereby improving the sensitivity of the early warning.

[0076] is the probability of rockburst detected by the ith fiber optic sensor at its monitoring point. Each sensor will calculate a probability value through the model based on the monitoring data at its location (such as fiber stress, acoustic emission signal, strain, etc.), which ranges from 0 to 1: When it is close to 1, it means that the risk of rock burst near the sensor is high; When it is close to 0, it means that the risk of rock burst in the area is relatively small.

[0077] The calculation relies on the real-time analysis of the monitoring data such as stress, displacement, acoustic signals, etc. in the area by sensors, combined with the output results of the model (such as deep learning or statistical analysis).

[0078] n represents the total number of fiber optic sensors. The sum in the formula means that the system will sum the output results of all n sensors. By integrating the data from multiple monitoring points, a more stable and reliable estimate of the probability of rockburst can be obtained.

[0079] In practical applications, multiple sensors can be deployed in the monitoring area, especially in complex geological environments. These sensors are distributed in different key locations, such as near cracks in the rock mass, where stress is concentrated, or in areas with rock burst records. Each sensor monitoring different areas can provide a more comprehensive risk assessment and reduce monitoring blind spots.

[0080] It means that by taking the average of the rockburst probability of each sensor, a comprehensive warning threshold is obtained. This threshold not only takes into account the individual output of each sensor, but also reflects the overall rockburst risk of the entire monitoring area.

[0081] The core of this early warning mechanism is to combine the information of multiple sensors to improve the accuracy of prediction. Since rock bursts are often the result of stress concentration at multiple points, the data of a single sensor may be affected by local conditions, and the joint analysis of multiple sensors can provide more stable results. For example, if some sensors in a certain area detect high-risk signals, but the sensors in the entire area detect low risks, the system may not trigger an alarm immediately. On the contrary, if multiple sensors detect high-risk signals, the system may not trigger an alarm immediately. The system will combine these results and raise the warning threshold. , thereby sounding the alarm earlier.

[0082] In some embodiments, an alarm is triggered when the following conditions are met: (set value), a rock burst warning is issued for prevention. Assumption: , are 0.7, 0.6, 0.8 and 0.9 respectively, and finally calculated If the alarm trigger threshold is set to 0.75, the system will trigger an alarm to indicate that a rockburst is about to occur.

[0083] In summary, by analyzing the outputs of multiple sensors, the system can dynamically adjust the sensor layout, monitoring frequency, and warning threshold. For example, when certain sensors continue to show a high risk of rock burst, the system can increase the monitoring frequency of the area or adjust the position of the sensor to more accurately capture abnormal signals before rock burst. In addition, through real-time monitoring and feedback, the system can also continuously optimize model parameters to improve the accuracy and reliability of predictions.

[0084] The dynamic adjustment module 206 is used for real-time feedback and dynamic adjustment of the position and monitoring frequency of the optical fiber sensor network.

[0085] Among them, real-time feedback refers to the system's continuous monitoring and analysis of the data collected by the sensors, and rapid response to rock changes or abnormal signals found during the monitoring process. The system can instantly process and analyze the information fed back by each sensor, and make decisions based on the latest monitoring data. The core of this function lies in the instant processing and dynamic response of data, ensuring that the system can detect potential dangers in real time and issue early warning signals in time before disasters occur.

[0086] Dynamically adjusting the position of the sensor network means that the system intelligently adjusts the placement of sensors in the monitoring area based on real-time feedback information. Different geological conditions and rock mass movement states will cause changes in the monitoring requirements of certain areas. The flexibility of the fiber optic sensor network can improve the monitoring efficiency and accuracy of the system.

[0087] The monitoring frequency refers to the time interval at which the system collects data. Dynamic adjustment of the monitoring frequency means that the system flexibly adjusts the frequency of data collection based on the feedback of real-time data to adapt to changes in rock mass conditions.

[0088] In summary, the present invention ensures that the system can flexibly adapt to rock mass changes and dynamically adjust the sensor position and data acquisition frequency when necessary through intelligent data analysis and feedback mechanisms. This dynamic response mechanism improves the accuracy and efficiency of monitoring, allowing the system to detect rockburst precursors faster and more accurately, thereby reducing the possibility of disasters and improving the timeliness and accuracy of early warnings.

[0089] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented: Arranging an all-optical fiber sensing network; the all-optical fiber sensing network comprises a plurality of optical fiber sensors arranged at different positions of the rock mass; Collecting multi-dimensional signals of the optical fiber sensor; Performing time-frequency domain analysis on the collected multi-dimensional signal to obtain a time-domain signal, and converting the time-domain signal into a frequency-domain signal by Fourier transform; Through intelligent algorithms, the signal after time-frequency analysis is subjected to pattern recognition, and the probability value of rockburst risk is predicted to obtain the prediction result; According to the prediction results, a rockburst warning threshold is set, and an alarm is triggered when the following conditions are met; The dynamic adjustment module is used for real-time feedback and dynamic adjustment of the position and monitoring frequency of the optical fiber sensor network.

[0090] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 500, on which a computer program 411 is stored. When the computer program 411 is executed by a processor, the following steps are implemented: Arranging an all-optical fiber sensing network; the all-optical fiber sensing network comprises a plurality of optical fiber sensors arranged at different positions of the rock mass; Collecting multi-dimensional signals of the optical fiber sensor; Performing time-frequency domain analysis on the collected multi-dimensional signal to obtain a time-domain signal, and converting the time-domain signal into a frequency-domain signal by Fourier transform; Through intelligent algorithms, the signal after time-frequency analysis is subjected to pattern recognition, and the probability value of rockburst risk is predicted to obtain the prediction result; According to the prediction results, a rockburst warning threshold is set, and an alarm is triggered when the following conditions are met; Real-time feedback and dynamic adjustment of the location and monitoring frequency of the fiber optic sensor network.

[0091] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0092] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0093] The present invention is described with reference to the flowcharts and / or block diagrams of the devices (systems) and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or boxes.

[0094] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0096] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0097] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An all-fiber intelligent rockburst early warning and monitoring system, characterized in that: The system comprises: An optical fiber arrangement module, used for arranging an all-optical fiber sensing network; the all-optical fiber sensing network comprises a plurality of optical fiber sensors arranged at different positions of the rock mass; A signal acquisition module, used for acquiring multi-dimensional signals of the optical fiber sensor; A signal conversion module, used for performing time-frequency domain analysis on the collected multi-dimensional signal to obtain a time domain signal, and converting the time domain signal into a frequency domain signal through Fourier transform; The rockburst prediction module is used to perform pattern recognition on the signal after time-frequency analysis through intelligent algorithms, predict the probability value of rockburst risk, and obtain the prediction result; The rockburst warning module is used to set the rockburst warning threshold according to the prediction results, and trigger an alarm when the following conditions are met: ； in, is the rockburst warning threshold, To set the threshold, the rockburst warning threshold is expressed as: ； in, is the probability value of rockburst corresponding to the data collected by the i-th optical fiber sensor, and n is the number of optical fiber sensors; The dynamic adjustment module is used for real-time feedback and dynamic adjustment of the position and monitoring frequency of the optical fiber sensor network.

2. The all-fiber intelligent rockburst early warning and monitoring system according to claim 1 is characterized in that: The multi-dimensional signal includes an optical signal, an acoustic signal and a strain signal; The signal acquisition module is also used for: The optical signal, the acoustic signal and the strain signal within the acquisition time are differentiated to obtain a time domain signal of the multi-dimensional signal.

3. The all-fiber intelligent rockburst early warning and monitoring system according to claim 2 is characterized in that: The time domain signal of the multi-dimensional signal is expressed as: ； in, is the time domain signal of the multi-dimensional signal, is an optical signal, is the acoustic signal, is the strain signal, and T is the acquisition time.

4. The all-fiber intelligent rockburst early warning and monitoring system according to claim 3 is characterized in that: The signal conversion module is also used for: The time domain signal of the multi-dimensional signal is differentiated according to the angular frequency to obtain the frequency domain signal.

5. The all-optical intelligent rockburst early warning and monitoring system according to claim 4 is characterized in that: The frequency domain signal is expressed as: ； in, is the frequency domain signal, is the angular frequency, is a time domain signal.

6. The all-fiber intelligent rockburst early warning and monitoring system according to claim 5 is characterized in that: The rockburst prediction module is also used for: Constructing a multi-dimensional feature matrix of the multi-dimensional signal; The multidimensional feature matrix is ​​processed according to the algorithm model to obtain the probability value.

7. The all-optical intelligent rockburst early warning and monitoring system according to claim 6 is characterized in that: The probability value is expressed as: ； in, is the probability value, X is the multidimensional feature matrix, are algorithm model parameters.

8. The all-fiber intelligent rockburst early warning and monitoring system according to claim 7 is characterized in that: The rockburst warning module is also used for: Obtaining a probability value of rock burst corresponding to the data collected by each optical fiber sensor; The rockburst warning threshold is determined according to each of the probability values.

9. The all-fiber intelligent rockburst early warning and monitoring system according to any one of claims 1 to 8, characterized in that: The rockburst warning threshold is optimized based on real-time monitoring data.

Images