Earthquake forecasting method and system based on optical fiber micro-vibration monitoring

Abstract

The invention discloses an earthquake forecasting method and system based on optical fiber micro-vibration monitoring, and the method comprises the steps: S1, collecting a micro-vibration signal through employing a dynamic adaptive collection frequency adjustment mechanism, carrying out the data collection at a frequency of 1kHz in a distributed optical fiber sensing network, obtaining a data fluctuation condition, setting a fluctuation threshold value, and carrying out the calculation of the fluctuation threshold value; when the fluctuation condition of the micro-vibration signals in m continuous time windows continuously exceeds a fluctuation threshold value, increasing the acquisition frequency to 10kHz for data acquisition, and counting all micro-vibration signal data; s2, constructing a cross correlation coefficient matrix of the micro-vibration signal data among different acquisition frequencies through all the micro-vibration signal data, obtaining direction information and propagation speed information among different monitoring points based on corresponding values in the cross correlation coefficient matrix to form spatial characteristic parameters, and comprehensively capturing spatial propagation characteristics of the signals, and the one-sidedness problem of a traditional method is effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of earthquake prediction, and in particular to an earthquake prediction method and system based on optical fiber micro-vibration monitoring. Background Art

[0002] Traditional earthquake monitoring sensors, such as seismographs, play an important role in monitoring earthquake activities, but they are usually discretely distributed, making it difficult to achieve continuous monitoring of large areas. This means that earthquake information may not be obtained in a timely manner in areas outside the coverage of the sensor. At the same time, the micro-vibration signals before an earthquake are often very weak. Due to the limitation of sensitivity, traditional monitoring equipment finds it difficult to effectively capture these weak signals, which may contain important information about an impending earthquake. The emergence of fiber optic sensing technology has brought new hope for earthquake monitoring. Optical fiber has extremely high sensitivity and can sense extremely small vibrations. At the same time, distributed fiber optic sensing technology can achieve continuous monitoring of areas along the optical fiber, effectively making up for the limited coverage of traditional sensors, and can monitor the micro-vibration conditions in the area in real time and comprehensively, providing rich data support for earthquake prediction.

[0003] At present, the micro-vibration signals before an earthquake are often very weak and complex. These micro-vibration signals cover a variety of frequency components and spatial propagation characteristics from extremely low frequencies (such as 0.01Hz-1Hz) to high frequencies (10Hz). The traditional method only extracts features from a single perspective in the time domain or frequency domain. This one-sidedness makes it impossible to fully present the full picture of the signal and it is difficult to capture the characteristic patterns of abnormal signals before an earthquake. According to relevant research statistics, in actual earthquake monitoring, due to the limitations of traditional methods, about 60% of the weak abnormal signal characteristics before an earthquake have not been effectively identified, and the traditional earthquake prediction model lacks effective correlation processing and analysis capabilities when facing high-dimensional and complex earthquake-related data. Therefore, an earthquake prediction method and system based on optical fiber micro-vibration monitoring is proposed. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention proposes the following technical solutions:

[0005] An earthquake prediction method based on optical fiber micro-vibration monitoring, comprising:

[0006] S1: A dynamic adaptive acquisition frequency adjustment mechanism is used to collect micro-vibration signals. Data is collected at a frequency of 1kHz in a distributed optical fiber sensor network. Data fluctuations are obtained at the same time. A fluctuation threshold is set. When the fluctuation of the micro-vibration signal exceeds the fluctuation threshold for m consecutive time windows, the acquisition frequency is increased to 10kHz for data collection, and all micro-vibration signal data are counted.

[0007] S2: Construct the mutual correlation coefficient matrix of micro-vibration signal data between different acquisition frequencies through all micro-vibration signal data, and obtain the direction information and propagation speed information between different monitoring points based on the corresponding values ​​in the mutual correlation coefficient matrix to form spatial characteristic parameters;

[0008] S3: Determine the analysis window length according to the frequency range of the seismic wave through time-frequency domain representation, convert the microvibration signal in the time domain into the time-frequency domain representation based on the determined window length by using short-time Fourier transform, and determine the time-frequency characteristic parameters through the time-frequency domain representation of the microvibration signal;

[0009] S4: Perform quantum bit encoding on the collected spatial characteristic parameters and time-frequency characteristic parameters to obtain a quantum bit sequence, build an earthquake prediction model based on quantum neural network, input the quantum bit sequence into the earthquake prediction model, and output the earthquake prediction result.

[0010] The acquisition mode of the dynamic adaptive acquisition frequency adjustment mechanism includes a normal acquisition mechanism and an acquisition frequency enhancement mechanism.

[0011] The specific implementation process of the dynamic adaptive acquisition frequency adjustment mechanism is as follows:

[0012] Using distributed optical fiber sensing networks for micro-vibration monitoring, the acquisition equipment converts continuous micro-vibration signals into electrical signals;

[0013] The micro-vibration signal data under normal conditions is collected at a frequency of 1 kHz through the normal acquisition mechanism, expressed as V = (v1, v2, v3, .., v n1 ), where n1 is the number of signal data points collected at a frequency of 1 kHz;

[0014] Calculate the fluctuation of the micro-vibration signal at each monitoring point in the signal data collected by the normal collection mechanism;

[0015] A fluctuation threshold γ is set based on the fluctuation situation, and the real-time monitored fluctuation situation is compared with the fluctuation threshold. The time window of the micro-vibration signal when the amplitude frequency A is greater than the fluctuation threshold γ is counted. When the amplitude frequency A of the micro-vibration signal is greater than the fluctuation threshold γ in m consecutive time windows, it is determined that the current signal fluctuation is abnormal, and the acquisition frequency increase mechanism is triggered;

[0016] The acquisition frequency is increased to 10kHz for data acquisition. The micro-vibration signal data acquired at a frequency of 10kHz is expressed as S = (s1, s2, s3, .., s n2 ), where n2 is the number of signal data points collected at a frequency of 10 kHz.

[0017] The determination process of the fluctuation situation is:

[0018] A time window length T is set, and the time variation of the micro-vibration signal collected by the distributed optical fiber sensor network in each time window is plotted into a waveform diagram;

[0019] The amplitude frequency A of the waveform of each time window length is continuously recorded. The amplitude frequency A within each time window length T reflects the fluctuation of the micro-vibration signal at each monitoring point.

[0020] The construction process of the mutual correlation coefficient matrix is:

[0021] The micro-vibration signal data collected at different acquisition frequencies at the same monitoring point are discretized to obtain discrete signals V[δ] and S[δ], where [δ] is the sampling point number;

[0022] The mutual correlation coefficients of the discrete signals collected at different monitoring points are calculated by computer programs. For the spatial discrete signals V[δ] and S[δ], their mutual correlation coefficients are calculated using the formula

[0023]

[0024] Where N is the total number of sampling points of the signal;

[0025] As the m consecutive time windows change, a series of mutual correlation values ​​are obtained, and all the obtained mutual correlation values ​​are arranged in order to form a correlation coefficient matrix R.

[0026] The process of obtaining the spatial characteristic parameters is as follows:

[0027] Observe the corresponding values ​​in the cross-correlation coefficient matrix;

[0028] Determine the signal propagation delay τ according to the peak position of the mutual correlation coefficient matrix;

[0029] Obtain the signal propagation direction by comparing the signal propagation delay between multiple monitoring points;

[0030] By combining the actual distance between the two points, the formula Calculate the signal propagation speed u and compare the signal propagation speeds in different directions;

[0031] The direction information and propagation speed information between different monitoring points are counted. The data composed of these information constitutes the spatial characteristic parameters. For the set of spatial characteristic parameters of monitoring point i, it is expressed as K = [u i1 , τ i1 ,u i2 , τ i2 ....].

[0032] The process of obtaining the time-frequency characteristic parameters is as follows:

[0033] Determine the window function length M;

[0034] Determine the window function length in the short-time Fourier transform based on the window length M;

[0035] The micro-vibration signal in the time domain is converted into a time-frequency domain representation, specifically a discretized time domain signal, by using short-time Fourier transform. A continuous micro-vibration signal in the time domain is determined and sampled to obtain a time-domain discrete signal G[δ], where [δ] is the sampling point number.

[0036] The short-time Fourier transform of the time domain discrete signal G[δ] is expressed as:

[0037]

[0038] Where t is the time index, f is the frequency index, M is the window function length, w[tm] is the window function, is the Fourier transform process parameter;

[0039] As the time index t changes, the above calculation is performed on the signal segments at different positions to obtain a series of Values, these values ​​constitute a two-dimensional array, this two-dimensional array is the micro-vibration signal converted into time-frequency domain representation, one dimension corresponds to time t, and the other dimension corresponds to frequency f;

[0040] The time-frequency characteristic parameters are determined by the time-frequency domain representation of the micro-vibration signal, and the time-frequency characteristic parameters include the time-domain frequency peak f, the energy center frequency and the energy proportion E of a specific frequency band;

[0041] The time-frequency characteristic parameters of monitoring point i are expressed as:

[0042] The process of obtaining the quantum bit sequence is as follows:

[0043] Perform normalization preprocessing on spatial feature parameters and time-frequency feature parameters;

[0044] Determine the accuracy of quantum bit encoding based on the preprocessed characteristic parameters;

[0045] The principle of quantum state superposition is used for encoding, and each characteristic parameter is mapped to a different state of the quantum bit. For characteristic parameters with values ​​in the interval [0,1], they are represented as the probability superposition of the quantum bit being in the |0> state and the |1> state. Each parameter is encoded in turn to form a quantum bit sequence.

[0046] The construction process of the earthquake prediction model is as follows:

[0047] Determine the number of quantum bits based on the length of the encoded quantum bit sequence and the structural requirements of the quantum neural network;

[0048] The earthquake prediction model consists of an input layer, a hidden layer, and an output layer;

[0049] The number of qubits in the input layer is consistent with the total number of qubits of the encoded characteristic parameters;

[0050] The hidden layer uses quantum gate operations to perform quantum computing;

[0051] The qubits in the output layer correspond to the results of earthquake prediction. One qubit is used to indicate whether an earthquake occurs, and the obtained qubit state is mapped to the probability of an earthquake occurring.

[0052] The input layer result of the earthquake prediction model is: the quantum bit is in the superposition state of |ψ>=α|0>+β|1>, where α represents the probability amplitude of the probability that an earthquake will not occur, β represents the probability amplitude of the probability that an earthquake will occur, and |α| 2 represents the probability that an earthquake will not occur, |β| 2 Represents the probability of an earthquake occurring.

[0053] An earthquake prediction system based on optical fiber micro-vibration monitoring, comprising:

[0054] Dynamic signal acquisition module: It uses a dynamic adaptive acquisition frequency adjustment mechanism to collect micro-vibration signals, collects data at a frequency of 1kHz in the distributed optical fiber sensor network, obtains data fluctuations at the same time, sets a fluctuation threshold, and when the fluctuation of the micro-vibration signal continues to exceed the fluctuation threshold within m consecutive time windows, the acquisition frequency is increased to 10kHz for data collection, and all micro-vibration signal data are counted;

[0055] Spatial feature weighting module: construct the mutual correlation coefficient matrix of micro-vibration signal data between different acquisition frequencies through all micro-vibration signal data, and obtain the direction information and propagation speed information between different monitoring points based on the corresponding values ​​in the mutual correlation coefficient matrix to form spatial feature parameters;

[0056] Time-frequency feature weighting module: Determine the analysis window length according to the frequency range of the seismic wave through time-frequency domain representation, use short-time Fourier transform to convert the microvibration signal in the time domain into time-frequency domain representation based on the determined window length, and determine the time-frequency feature parameters through the time-frequency domain representation of the microvibration signal;

[0057] Fusion prediction module: The collected spatial characteristic parameters and time-frequency characteristic parameters are quantum bit encoded to obtain a quantum bit sequence, an earthquake prediction model based on a quantum neural network is constructed, the quantum bit sequence is input into the earthquake prediction model, and the earthquake prediction results are output.

[0058] The present invention has the following beneficial effects:

[0059] In the present invention, firstly, by adopting a dynamic adaptive acquisition frequency adjustment mechanism, micro-vibration signals are collected at two frequencies of 1kHz and 10kHz under different signal fluctuation conditions, so as to obtain richer data, and by using the mutual correlation coefficient matrix construction and short-time Fourier transform, characteristic parameters are extracted from the two dimensions of space and time-frequency, and the spatial propagation characteristics of the signal (such as the direction information and propagation speed information between different monitoring points) and multiple frequency components (time domain frequency peak, energy center frequency and energy proportion of a specific frequency segment, etc.) are fully captured, and the overall picture of the signal is fully presented, which effectively solves the one-sidedness problem of the traditional method;

[0060] Secondly, an earthquake prediction model based on quantum neural network was constructed. The spatial characteristic parameters and time-frequency characteristic parameters were converted into quantum bit sequence input models using quantum bit encoding. The hidden layer of the quantum neural network uses quantum gate operations for quantum computing, which can simultaneously process information of multiple states, mine complex correlations between data, and effectively process high-dimensional and complex data.

[0061] Finally, by extracting the characteristic parameters of the micro-vibration signal from the two dimensions of space and time-frequency, the full picture of the signal is presented. At the same time, the quantum state superposition and entanglement characteristics of the quantum neural network model are used to further analyze the correlation between these multi-dimensional characteristic parameters, and the spatial propagation characteristics of the signal and the comprehensive parameters of the multiple frequency components of the seismic signal are interacted with the quantum neural network to improve the accuracy of earthquake prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A method and step diagram of an earthquake prediction method and system based on optical fiber micro-vibration monitoring proposed by the present invention;

[0063] Figure 2 This is a system block diagram of an earthquake prediction method and system based on optical fiber micro-vibration monitoring proposed by the present invention. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] Embodiment 1

[0066] like Figure 1As shown, the present invention proposes an earthquake prediction method based on optical fiber micro-vibration monitoring, comprising:

[0067] S1: A dynamic adaptive acquisition frequency adjustment mechanism is used to collect micro-vibration signals. Data is collected at a frequency of 1kHz in a distributed optical fiber sensor network. Data fluctuations are obtained at the same time. A fluctuation threshold is set. When the fluctuation of the micro-vibration signal exceeds the fluctuation threshold for m consecutive time windows, the acquisition frequency is increased to 10kHz for data collection, and all micro-vibration signal data are counted.

[0068] The dynamic adaptive acquisition frequency adjustment mechanism acquisition methods include normal acquisition mechanism and acquisition frequency enhancement mechanism;

[0069] The specific implementation process of the dynamic adaptive acquisition frequency adjustment mechanism is as follows:

[0070] Use distributed optical fiber sensing networks to monitor micro-vibration. Optical fiber is used as a sensing medium. When a small vibration occurs underground or is disturbed by the external environment, the optical fiber will sense the corresponding vibration. The acquisition equipment converts these continuous micro-vibration signals into electrical signals.

[0071] The micro-vibration signal data under normal conditions are collected at a frequency of 1 kHz through a normal acquisition mechanism, and statistical analysis is performed on the micro-vibration signal data under normal conditions. The micro-vibration signal data collected at a frequency of 1 kHz is expressed as V = (v1, v2, v3, .., v n1 ), where n1 is the number of signal data points collected at a frequency of 1 kHz;

[0072] Calculate the fluctuation of the micro-vibration signal at each monitoring point in the signal data collected by the normal collection mechanism;

[0073] The process of obtaining the fluctuation of the micro-vibration signal at the monitoring point is as follows:

[0074] A time window length T (e.g., 10 seconds) is set, and the time variation of the micro-vibration signal collected by the distributed optical fiber sensing network in each time window is plotted into a waveform graph;

[0075] Specifically, the amplitude and frequency of the signal can be observed intuitively through the waveform diagram;

[0076] The amplitude frequency A of the waveform of each time window length is continuously recorded. The amplitude frequency A within each time window length T reflects the fluctuation of the micro-vibration signal at each monitoring point.

[0077] A fluctuation threshold γ is set, and the real-time monitored fluctuation is compared with the fluctuation threshold. The time window of the micro-vibration signal when the amplitude frequency A is greater than the fluctuation threshold γ is counted. When the amplitude frequency A of the micro-vibration signal is greater than the fluctuation threshold γ in m consecutive time windows, it is determined that the current signal fluctuation is abnormal, and the acquisition frequency enhancement mechanism is triggered. The acquisition frequency is increased to 10kHz for data acquisition. The micro-vibration signal data collected at a frequency of 10kHz is expressed as S=(s1, s2, s3, .., s n2 ), where n2 is the number of signal data points collected at a frequency of 10 kHz;

[0078] Specifically, the fluctuation threshold γ is based on the monitoring of the signal under normal conditions, and the amplitude value corresponding to twice the standard deviation of the normal amplitude range is taken as the threshold. The dynamic adaptive acquisition frequency adjustment mechanism dynamically adjusts the data acquisition frequency of the distributed optical fiber sensor network according to the fluctuation of the micro-vibration signal. Under normal conditions, it collects data at a lower frequency (1kHz) to reduce the amount of data. When the signal fluctuates abnormally, it is increased to a higher frequency (10kHz) to capture more details, thereby achieving high efficiency and accuracy in data acquisition.

[0079] S2: Construct the mutual correlation coefficient matrix of micro-vibration signal data between different acquisition frequencies through all micro-vibration signal data, and obtain the direction information and propagation speed information between different monitoring points based on the corresponding values ​​in the mutual correlation coefficient matrix to form spatial characteristic parameters;

[0080] The micro-vibration signal data collected at the same monitoring point with different acquisition frequencies are discretized to obtain discrete signals V[δ] and S[δ] ([δ] is the sampling point number);

[0081] This step is to convert continuous signals into discrete forms that can be processed by computers. When a small vibration occurs underground or is disturbed by the external environment, the optical fiber will sense the corresponding vibration. The acquisition equipment converts these continuous micro-vibration signals into electrical signals and stores them in discrete forms to obtain discrete signal sequences such as V[δ] and S[δ].

[0082] In the data processing center, the discrete signals collected at different monitoring points are calculated through computer programs. For the spatial discrete signals V[δ] and S[δ], their mutual correlation coefficient R is calculated using the formula m VS :

[0083]

[0084] Where N is the total number of sampling points of the signal;

[0085] Through the change of m consecutive time windows, the correlation between the two signals under different delays can be obtained, and then the mutual correlation coefficients between all monitoring points at different acquisition frequencies can be calculated. With the change of m consecutive time windows, a series of mutual correlation values ​​are obtained. All the obtained mutual correlation values ​​are arranged in order to form a correlation coefficient matrix R;

[0086] Observe the corresponding values ​​in the mutual correlation coefficient matrix and analyze the distribution of signal correlation coefficients between different monitoring points. If the correlation coefficients between monitoring points in a certain area are generally high, it means that the signals in this area have strong consistency and come from the same or related vibration sources. For areas with low correlation coefficients, the signal consistency is poor and may be affected by different factors or come from different sources.

[0087] The propagation delay τ of the signal is determined according to the peak position of the mutual correlation coefficient matrix. The propagation delay of the signal between multiple monitoring points is compared using the correlation matrix. For three monitoring points A, B, and C, the propagation delay of the known signal from a certain source point to these three points is τ A , τ B , τ C By comparing the size and difference of these delays, we can preliminarily determine the direction of signal propagation. For example, if τ A >τ B >τ C , then the signal comes from the direction close to A;

[0088] Combined with the actual distance between the two points, the formula Calculate the signal propagation speed u and compare the signal propagation speeds in different directions;

[0089] Specifically, if the propagation speed changes gradually in a certain direction, it means that the properties of the underground medium are different in that direction, or the signal is affected differently during the propagation process. For example, if the propagation speed decreases gradually, it may be because the density or elastic modulus of the underground medium has changed, resulting in the obstruction of signal propagation.

[0090] The direction information and propagation speed information between different monitoring points are counted. The data composed of these information constitutes the spatial characteristic parameters. For the set of spatial characteristic parameters of monitoring point i, it is expressed as K = [u i1 , τ i1 ,u i2 , τ i2 ....];

[0091] These spatial characteristic parameters can help researchers understand the propagation direction and speed of underground vibrations, as well as the degree of correlation between vibrations at different locations, thereby inferring changes in underground geological structures or potential signs of seismic activity.

[0092] S3: Determine the analysis window length according to the frequency range of the seismic wave through time-frequency domain representation, convert the microvibration signal in the time domain into the time-frequency domain representation based on the determined window length by using short-time Fourier transform, and determine the time-frequency characteristic parameters through the time-frequency domain representation of the microvibration signal;

[0093] The process of determining the window function length M is:

[0094] For low-frequency components (such as 1 Hz) in the frequency range of seismic waves, in order to accurately analyze these low-frequency components, a larger analysis window length is required to improve the frequency resolution. For a 1 Hz signal, according to the above frequency resolution formula, if the sampling frequency f s =1000Hz, in order to distinguish at least 1Hz frequency difference, the window length is at least 1000 sampling points. If the sampling interval is 1ms, the corresponding window length is 1s;

[0095] When the seismic wave frequency range contains high-frequency components (such as 10 Hz), in order to capture the rapid changes of high-frequency signals, a shorter analysis window length is required to ensure time resolution. For example, for a 10 Hz signal, if the sampling frequency f s =1000Hz. Considering the time resolution requirement, the window length is set to 100 sampling points, corresponding to 0.1s.

[0096] The window function length in the short-time Fourier transform is determined based on the window length M. The window function length is equal to the analysis window length. This is because the window function is intended to perform weighted processing on the signal within the selected window to ensure that each signal sample within the window is appropriately weighted. For example, if the determined analysis window length is 500 sampling points, then the window function length is also set to 500 sampling points. Let the determined window function length be M.

[0097] The short-time Fourier transform is used to convert the micro-vibration signal in the time domain into a discretized time domain signal in the time-frequency domain. A continuous micro-vibration signal in the time domain is determined and sampled to obtain a time-domain discrete signal G[δ], where [δ] is the sampling point number. The sampling process satisfies the Nyquist sampling theorem, that is, the sampling frequency f s Must be greater than or equal to the highest frequency f of the signal max twice as much;

[0098] The short-time Fourier transform of the time domain discrete signal G[δ] is expressed as:

[0099]

[0100] Where t is the time index, is the frequency index, M is the window function length, w[tm] is the window function, is the Fourier transform process parameter;

[0101] As the time index t changes, the above calculation is performed on the signal segments at different positions to obtain a series of These values ​​form a two-dimensional array, which is the micro-vibration signal converted into the time-frequency domain, where one dimension corresponds to time t and the other dimension corresponds to frequency

[0102] The process of determining the time-frequency characteristic parameters through the time-frequency domain representation of the micro-vibration signal is as follows;

[0103] The time-frequency characteristic parameters include the time-domain frequency peak determined by the time-frequency domain representation The energy center frequency and the energy proportion E of a specific frequency band;

[0104] Time domain frequency peak Acquisition process:

[0105] Obtained by a series of After the two-dimensional array (represented in the time-frequency domain) consisting of values ​​is obtained, at each time point represented in the time-frequency domain, the search column The frequency value with the largest energy is obtained by comparing the sizes corresponding to all frequency indexes f, so that The largest The corresponding actual frequency value is the time domain frequency peak It reflects the most dominant vibration frequency in the signal at that moment;

[0106] The process of obtaining the energy center frequency F:

[0107] Based on the formula Get, where the numerator of the formula is the sum of the product of frequency and energy squared, and the denominator is the sum of energy squared. The energy center frequency is obtained by the ratio of the two, which reflects the concentration of signal energy in frequency;

[0108] The process of obtaining the energy proportion E of a specific frequency band is as follows:

[0109] In a two-dimensional array with time-frequency domain representation After that, for a given frequency band Based on the formula: The numerator is the sum of the energy in a specific frequency band, and the denominator is the sum of the energy of the entire signal at that moment. The ratio of the two is used to obtain the energy proportion of a specific frequency band, which is used to analyze the energy distribution characteristics of the signal within a specific frequency range and helps to identify the frequency components related to earthquakes.

[0110] Specifically, the time-frequency characteristic parameters of monitoring point i are expressed as:

[0111]

[0112] S4: Perform quantum bit encoding on the collected spatial characteristic parameters and time-frequency characteristic parameters to obtain a quantum bit sequence, construct an earthquake prediction model based on a quantum neural network, input the quantum bit sequence into the earthquake prediction model, and output the earthquake prediction result;

[0113] The process of obtaining the quantum bit sequence is:

[0114] Before quantum bit encoding, the spatial characteristic parameters and the time-frequency characteristic parameters are normalized and preprocessed to obtain characteristic parameters that combine the spatial characteristic parameters and the time-frequency characteristic parameters;

[0115] Determine the accuracy of quantum bit encoding based on the preprocessed characteristic parameters;

[0116] The quantum state superposition principle is used for encoding, and each characteristic parameter is mapped to a different state of the quantum bit. For characteristic parameters with values ​​in the interval [0,1], they are represented as the probability superposition of the quantum bit being in the |0> state and the |1> state. Each parameter is encoded in turn to form a quantum bit sequence.

[0117] Construct an earthquake prediction model based on quantum neural network;

[0118] Determine the number of quantum bits based on the length of the encoded quantum bit sequence and the structural requirements of the quantum neural network;

[0119] Specifically, if the input layer of the quantum neural network needs to receive all the encoded characteristic parameter information, then the number of qubits must be at least equal to the length of the encoded qubit sequence. Considering the complexity and resource consumption of quantum computing, the number of qubits is optimized through experiments and theoretical analysis, and the number of qubits is gradually increased to observe the training effect and computing efficiency of the model. The number of qubits that minimizes computing resource consumption while ensuring the accuracy of the model is selected.

[0120] The process of building an earthquake prediction model is:

[0121] The earthquake prediction model consists of an input layer, a hidden layer, and an output layer;

[0122] The number of quantum bits in the input layer is consistent with the total number of quantum bits of the encoded characteristic parameters, which is used to receive the encoded characteristic information. The hidden layer uses quantum gate operations to perform quantum calculations.

[0123] Specifically, the hidden layer of the earthquake prediction module performs quantum calculations through quantum gate operations. These quantum gates transform and entangle the input quantum bit states to achieve feature extraction and information processing. The quantum gates can transform the input quantum bit states. Through a series of quantum gate combinations and operations, the hidden layer transforms and extracts features from the input quantum bit sequence layer by layer. When processing earthquake-related characteristic parameters, the hidden layer may extract characteristic patterns related to the probability and magnitude of earthquakes. These characteristic patterns are directly obtained by performing quantum calculations on the original spatial and time-frequency characteristic parameters.

[0124] The quantum bits of the output layer correspond to the results of earthquake prediction. One quantum bit is used to indicate whether an earthquake occurs (0 means no earthquake occurs, 1 means earthquake occurs). The quantum bit state obtained will be mapped to the probability of earthquake occurrence.

[0125] For example:

[0126] The result of the input layer of the earthquake prediction model is: finally the quantum bit is in the superposition state of |ψ>=α|0>+β|1>, where |α| 2 represents the probability that an earthquake will not occur, |β| 2 represents the probability of an earthquake, then |β| 2 It represents the probability of an earthquake. For example, the quantum bit is in the range of 0.2|0>+0.8|1>, 0.8 2 =0.64, the model outputs that the probability of an earthquake occurring is 64%;

[0127] Furthermore, when the probability of the model output result is lower than 30%, it is a low risk level; when the probability is between 30%-70%, it is a medium risk level; and when the probability is higher than 70%, it is a high risk level. If the model outputs that the probability of an earthquake is 64%, the corresponding earthquake prediction level is "medium risk level", prompting relevant departments and personnel to activate emergency plans.

[0128] Embodiment 2

[0129] like Figure 2 As shown, the present invention proposes an earthquake prediction system based on optical fiber micro-vibration monitoring, comprising:

[0130] Dynamic signal acquisition module: It uses a dynamic adaptive acquisition frequency adjustment mechanism to collect micro-vibration signals, collects data at a frequency of 1kHz in the distributed optical fiber sensor network, obtains data fluctuations at the same time, sets a fluctuation threshold, and when the fluctuation of the micro-vibration signal continues to exceed the fluctuation threshold within m consecutive time windows, the acquisition frequency is increased to 10kHz for data collection, and all micro-vibration signal data are counted;

[0131] Spatial feature weighting module: construct the mutual correlation coefficient matrix of micro-vibration signal data between different acquisition frequencies through all micro-vibration signal data, and obtain the direction information and propagation speed information between different monitoring points based on the corresponding values ​​in the mutual correlation coefficient matrix to form spatial feature parameters;

[0132] Time-frequency feature weighting module: Determine the analysis window length according to the frequency range of the seismic wave through time-frequency domain representation, use short-time Fourier transform to convert the microvibration signal in the time domain into time-frequency domain representation based on the determined window length, and determine the time-frequency feature parameters through the time-frequency domain representation of the microvibration signal;

[0133] Fusion prediction module: The collected spatial characteristic parameters and time-frequency characteristic parameters are quantum bit encoded to obtain a quantum bit sequence, an earthquake prediction model based on a quantum neural network is constructed, the quantum bit sequence is input into the earthquake prediction model, and the earthquake prediction results are output.

[0134] In the application, several formulas involved are calculated by removing dimensions and taking their numerical values. The formulas are established by collecting a large amount of data and performing software simulation to obtain a formula for the most recent actual situation. Some coefficients or weights in the formulas are set by technicians in this field according to actual conditions, so they will not be elaborated here.

[0135] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0136] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An earthquake prediction method based on optical fiber micro-vibration monitoring, characterized in that: include: S1: A dynamic adaptive acquisition frequency adjustment mechanism is used to collect micro-vibration signals. Data is collected at a frequency of 1kHz in a distributed optical fiber sensor network. Data fluctuations are obtained at the same time. A fluctuation threshold is set. When the fluctuation of the micro-vibration signal exceeds the fluctuation threshold for m consecutive time windows, the acquisition frequency is increased to 10kHz for data collection, and all micro-vibration signal data are counted. S2: Construct the mutual correlation coefficient matrix of micro-vibration signal data between different acquisition frequencies through all micro-vibration signal data, and obtain the direction information and propagation speed information between different monitoring points based on the corresponding values ​​in the mutual correlation coefficient matrix to form spatial characteristic parameters; S3: Determine the analysis window length according to the frequency range of the seismic wave through time-frequency domain representation, convert the microvibration signal in the time domain into the time-frequency domain representation based on the determined window length by using short-time Fourier transform, and determine the time-frequency characteristic parameters through the time-frequency domain representation of the microvibration signal; S4: Perform quantum bit encoding on the collected spatial characteristic parameters and time-frequency characteristic parameters to obtain a quantum bit sequence, build an earthquake prediction model based on quantum neural network, input the quantum bit sequence into the earthquake prediction model, and output the earthquake prediction result.

2. The earthquake prediction method based on optical fiber micro-vibration monitoring according to claim 1, characterized in that: The acquisition mode of the dynamic adaptive acquisition frequency adjustment mechanism includes a normal acquisition mechanism and an acquisition frequency enhancement mechanism.

3. The earthquake prediction method based on optical fiber micro-vibration monitoring according to claim 2 is characterized in that: The specific implementation process of the dynamic adaptive acquisition frequency adjustment mechanism is as follows: Using distributed optical fiber sensing networks for micro-vibration monitoring, the acquisition equipment converts continuous micro-vibration signals into electrical signals; The micro-vibration signal data under normal conditions is collected at a frequency of 1 kHz through the normal acquisition mechanism, expressed as V = (v1, v2, v3, .., v n1 ), where n1 is the number of signal data points collected at a frequency of 1 kHz; Calculate the fluctuation of the micro-vibration signal at each monitoring point in the signal data collected by the normal collection mechanism; A fluctuation threshold γ is set based on the fluctuation situation, and the real-time monitored fluctuation situation is compared with the fluctuation threshold. The time window of the micro-vibration signal when the amplitude frequency A is greater than the fluctuation threshold γ is counted. When the amplitude frequency A of the micro-vibration signal is greater than the fluctuation threshold γ in m consecutive time windows, it is determined that the current signal fluctuation is abnormal, and the acquisition frequency increase mechanism is triggered; The acquisition frequency is increased to 10kHz for data acquisition. The micro-vibration signal data acquired at a frequency of 10kHz is expressed as S = (s1, s2, s3, .., s n2 ), where n2 is the number of signal data points collected at a frequency of 10 kHz.

4. The earthquake prediction method based on optical fiber micro-vibration monitoring according to claim 3 is characterized in that: The determination process of the fluctuation situation is: A time window length T is set, and the time variation of the micro-vibration signal collected by the distributed optical fiber sensor network in each time window is plotted into a waveform diagram; The amplitude frequency A of the waveform of each time window length is continuously recorded. The amplitude frequency A within each time window length T reflects the fluctuation of the micro-vibration signal at each monitoring point.

5. The earthquake prediction method based on optical fiber micro-vibration monitoring according to claim 1, characterized in that: The construction process of the mutual correlation coefficient matrix is: The micro-vibration signal data collected at the same monitoring point with different acquisition frequencies are discretized to obtain discrete signals V[δ] and S[δ], where [δ] is the sampling point number; The mutual correlation coefficients of the discrete signals collected at different monitoring points are calculated by computer programs. For the spatial discrete signals V[δ] and S[δ], their mutual correlation coefficients R are calculated using the formula m VS : Where N is the total number of sampling points of the signal; As the m consecutive time windows change, a series of mutual correlation values ​​are obtained, and all the obtained mutual correlation values ​​are arranged in order to form a correlation coefficient matrix R.

6. The earthquake prediction method based on optical fiber micro-vibration monitoring according to claim 1, characterized in that: The process of obtaining the spatial characteristic parameters is as follows: Observe the corresponding values ​​in the cross-correlation coefficient matrix; Determine the signal propagation delay τ according to the peak position of the mutual correlation coefficient matrix; Obtain the signal propagation direction by comparing the signal propagation delay between multiple monitoring points; By combining the actual distance between the two points, the formula Calculate the signal propagation speed u and compare the signal propagation speeds in different directions; The direction information and propagation speed information between different monitoring points are counted. The data composed of these information constitutes the spatial characteristic parameters. For the set of spatial characteristic parameters of monitoring point i, it is expressed as K = [u i1 , τ i1 ,u i2 , τ i2 ....].

7. The earthquake prediction method based on optical fiber micro-vibration monitoring according to claim 1, characterized in that: The process of obtaining the time-frequency characteristic parameters is as follows: Determine the window function length M; Determine the window function length in the short-time Fourier transform based on the window length M; The micro-vibration signal in the time domain is converted into a time-frequency domain representation, specifically a discretized time domain signal, by using short-time Fourier transform. A continuous micro-vibration signal in the time domain is determined and sampled to obtain a time-domain discrete signal G[δ], where [δ] is the sampling point number. The short-time Fourier transform of the time domain discrete signal G[δ] is expressed as: Where t is the time index, f is the frequency index, M is the window function length, w[tm] is the window function, is the Fourier transform process parameter; As the time index t changes, the above calculation is performed on the signal segments at different positions to obtain a series of Values, these values ​​constitute a two-dimensional array, this two-dimensional array is the micro-vibration signal converted into time-frequency domain representation, one dimension corresponds to time t, and the other dimension corresponds to frequency f; The time-frequency characteristic parameters are determined by the time-frequency domain representation of the micro-vibration signal. The time-frequency characteristic parameters include the time domain frequency peak The energy center frequency and the energy proportion E of a specific frequency band; The time-frequency characteristic parameters of monitoring point i are expressed as:

8. The earthquake prediction method based on optical fiber micro-vibration monitoring according to claim 1, characterized in that: The process of obtaining the quantum bit sequence is as follows: Perform normalization preprocessing on spatial feature parameters and time-frequency feature parameters; Determine the accuracy of quantum bit encoding based on the preprocessed characteristic parameters; The principle of quantum state superposition is used for encoding, and each characteristic parameter is mapped to a different state of the quantum bit. For characteristic parameters with values ​​in the interval [0,1], they are represented as the probability superposition of the quantum bit being in the |0> state and the |1> state. Each parameter is encoded in turn to form a quantum bit sequence.

9. The earthquake prediction method based on optical fiber micro-vibration monitoring according to claim 1, characterized in that: The construction process of the earthquake prediction model is as follows: Determine the number of quantum bits based on the length of the encoded quantum bit sequence and the structural requirements of the quantum neural network; The earthquake prediction model consists of an input layer, a hidden layer, and an output layer; The number of qubits in the input layer is consistent with the total number of qubits of the encoded characteristic parameters; The hidden layer uses quantum gate operations to perform quantum computing; The qubits in the output layer correspond to the results of earthquake prediction. One qubit is used to indicate whether an earthquake occurs, and the obtained qubit state is mapped to the probability of an earthquake occurring. The input layer result of the earthquake prediction model is: the quantum bit is in the superposition state of |Ψ>=α|0>+β|1>, where α represents the probability amplitude of the probability of earthquake not occurring, β represents the probability amplitude of the probability of earthquake occurring, and |α| 2 represents the probability that an earthquake will not occur, |β| 2 Represents the probability of an earthquake occurring.

10. An earthquake prediction system based on optical fiber micro-vibration monitoring, using any method described in claims 1 to 9, characterized in that: include: Dynamic signal acquisition module: It uses a dynamic adaptive acquisition frequency adjustment mechanism to collect micro-vibration signals, collects data at a frequency of 1kHz in the distributed optical fiber sensor network, obtains data fluctuations at the same time, sets a fluctuation threshold, and when the fluctuation of the micro-vibration signal continues to exceed the fluctuation threshold within m consecutive time windows, the acquisition frequency is increased to 10kHz for data collection, and all micro-vibration signal data are counted; Spatial feature weighting module: construct the mutual correlation coefficient matrix of micro-vibration signal data between different acquisition frequencies through all micro-vibration signal data, and obtain the direction information and propagation speed information between different monitoring points based on the corresponding values ​​in the mutual correlation coefficient matrix to form spatial feature parameters; Time-frequency feature weighting module: Determine the analysis window length according to the frequency range of the seismic wave through time-frequency domain representation, use short-time Fourier transform to convert the microvibration signal in the time domain into time-frequency domain representation based on the determined window length, and determine the time-frequency feature parameters through the time-frequency domain representation of the microvibration signal; Fusion prediction module: The collected spatial characteristic parameters and time-frequency characteristic parameters are quantum bit encoded to obtain a quantum bit sequence, an earthquake prediction model based on a quantum neural network is constructed, the quantum bit sequence is input into the earthquake prediction model, and the earthquake prediction results are output.

Images