A mine microseismic signal intelligent identification method and system

Abstract

The application discloses a kind of mine microseismic signal intelligent identification method and system, belong to data processing technical field, this mine microseismic signal intelligent identification method includes: obtaining the microseismic monitoring signal to be identified, as signal to be analyzed;Using preset algorithm, signal to be analyzed is decomposed into several single type signals;Single type signal extracted from decomposition is carried out feature, and the characteristic data of signal to be analyzed is obtained;The characteristic data of signal to be analyzed is input into preset identification model, realizes microseismic signal intelligent identification.Using the mine microseismic signal intelligent identification method and system of the application can provide guidance for mine microseismic intelligent identification, to ensure mine safety production.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a mine microseismic signal intelligent identification method and system. BACKGROUND

[0002] In recent years, with the development of mining industry and the increase of mining depth, mine safety problems have become increasingly prominent. As an important earthquake prediction and safety protection method, microseismic signal monitoring has been widely used in mine safety management. Rapid, accurate and intelligent identification of mine microseismic signals is of great significance to ensure mine safety production. However, due to the complexity of mining environment, the signals collected by microseismic monitoring system often contain a large amount of interference signals, which makes it very difficult to intelligently identify microseismic signals. Therefore, it is particularly important to develop an efficient and accurate microseismic signal intelligent identification method.

[0003] Microseismic signals usually have nonlinear and non-stationary characteristics, which makes it difficult for traditional linear analysis methods to effectively process them. Traditional methods assume that signals are stationary and linear, but actual microseismic signals often contain complex transient characteristics and nonlinear components. In addition, due to the great differences in geological conditions and mining environments of different mines, a single and unchanging microseismic signal intelligent identification method may not be able to adapt to the geological conditions and mining environments of different mines, thus failing to maintain high-precision intelligent identification of microseismic signals in different mine environments.

[0004] Therefore, how to make the microseismic intelligent identification method have high intelligent identification accuracy and gradually adapt to the geological conditions and mining environments of different mines through continuous learning and optimization is crucial for geological research and mine safety production during mining. SUMMARY

[0005] The present application provides a mine microseismic signal intelligent identification method and system to solve the technical problem that existing technologies cannot maintain high-precision intelligent identification of microseismic signals in different mine environments.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] On the one hand, the present application provides a mine microseismic signal intelligent identification method, comprising:

[0008] Obtaining a microseismic monitoring signal to be identified as an analysis signal;

[0009] Decomposing the analysis signal into a plurality of single type signals;

[0010] Extracting features from the decomposed single type signals to obtain feature data of the analysis signal;

[0011] The feature data of the signal to be analyzed is input into a preset recognition model to realize intelligent recognition of the microseismic signal.

[0012] Further, the decomposition of the signal to be analyzed into several single-type signals includes:

[0013] Step 1, performing discrete Fourier transform on the signal to obtain a frequency domain representation S[k] as a residual spectrum;

[0014] Step 2, finding a frequency f corresponding to the maximum amplitude in the residual spectrum max ;

[0015] Step 3, setting a harmonic number m = 1, 2,..., M max , for each possible m, calculating a candidate fundamental frequency f m = f max / m and solving a harmonic energy function value E(f m ); wherein the expression of the harmonic energy function is:

[0016]

[0017] wherein M is the maximum harmonic number; round() represents rounding by rounding; R[] represents the residual spectrum; f s is a sampling frequency; and N is the total number of sampling points of the signal;

[0018] Step 4, determining a candidate fundamental frequency f c-max corresponding to the maximum harmonic energy function value, constructing an optimization function, and obtaining a final fundamental frequency f0 by solving the optimization function; wherein the expression of the optimization function is:

[0019]

[0020] wherein E(f c-max ) represents the harmonic energy function value corresponding to f c-max ;

[0021] Step 5, determining a harmonic m = 1, 2,..., M corresponding to f0, and calculating a frequency k m corresponding to each harmonic:

[0022]

[0023] Step 6, constructing a frequency spectrum S i [k] of a single signal, and removing S i [k] from the residual spectrum to update the residual spectrum; wherein the process of constructing the frequency spectrum S i [k] of the single signal is as follows:

[0024] First, a spectrum S is created which has the same length as S[k]i [k], and initializing all values of S[k] to 0; for each frequency index of the harmonics, extracting the corresponding value from S[k] and assigning it to S i [k] ; then, let S i [N-k m ] = S[N-k m ], except for S i [k m ] and S i [N-k m ], S i [k] at all other positions takes 0;

[0025] Step 7, based on the constructed spectrum of the signal, reconstructing the single signal by inverse discrete Fourier transform;

[0026] Step 8, repeating steps 1 to 7 several times to obtain a plurality of reconstructed signals of a single type;

[0027] Step 9, returning to step 2 until the maximum amplitude of the residual spectrum is lower than a preset threshold, or the expected number of signals is extracted, the iteration is stopped.

[0028] Further, the single type of signal decomposed is subjected to feature extraction to obtain feature data of the signal to be analyzed, comprising:

[0029] Dividing the signal into a plurality of time windows according to a fixed time length, and calculating the statistical quantity of the signal in each time window; wherein the statistical quantity includes the mean, variance, skewness and kurtosis of the signal in the corresponding time window;

[0030] Calculating the difference value of the statistical quantity between adjacent time windows;

[0031] Combining the difference value of the statistical quantity between each two adjacent time windows into a feature vector, and taking all the obtained feature vectors as the feature data of the signal to be analyzed.

[0032] Further, the preset recognition model is a BP neural network model optimized by a genetic algorithm.

[0033] Further, the training process of the preset recognition model comprises:

[0034] Obtaining historical microseismic monitoring signals as sample signals, and classifying them;

[0035] Decomposing the sample signals into a plurality of single type signals, and extracting features of the single type signals decomposed to obtain feature data of the sample signals;

[0036] Using the feature data and label data of the sample signals to construct a feature database;

[0037] The preset recognition model is trained by using the feature database, and the weight and threshold parameters of the BP neural network are optimized by using the genetic algorithm, so that the learning ability and generalization ability of the neural network are enhanced.

[0038] In another aspect, the present application also provides a mine microseismic signal intelligent identification system, comprising:

[0039] A data acquisition module is configured to acquire a microseismic monitoring signal to be identified as a signal to be analyzed.

[0040] A data processing module is configured to decompose the signal to be analyzed into a plurality of single-type signals, and extract features from the decomposed single-type signals to obtain feature data of the signal to be analyzed.

[0041] An intelligent identification module is configured to input the feature data of the signal to be analyzed obtained by the data processing module into a preset recognition model to realize intelligent identification of the microseismic signal.

[0042] Further, the decomposition of the signal to be analyzed into a plurality of single-type signals comprises:

[0043] Step 1: Discrete Fourier transform is performed on the signal to obtain a frequency domain representation S[k] as a residual spectrum;

[0044] Step 2: Find the frequency f corresponding to the maximum amplitude in the residual spectrum max ;

[0045] Step 3: Set the harmonic number m = 1, 2, …, M max , for each possible m, calculate its candidate fundamental frequency f m = f max / m, and solve its harmonic energy function value E(f m ); wherein the expression of the harmonic energy function is:

[0046]

[0047] wherein M is the maximum harmonic number; round() represents rounding by rounding; R[] represents the residual spectrum; f s is the sampling frequency; and N is the total number of sampling points of the signal.

[0048] Step 4: Determine the candidate fundamental frequency f c-max corresponding to the maximum harmonic energy function value, construct an optimization function, and obtain the final fundamental frequency f0 by solving the optimization function; wherein the expression of the optimization function is:

[0049]

[0050] wherein E(f c-max) represents f c-max corresponding to the harmonic energy function value;

[0051] Step 5, determine the corresponding harmonic f0m = 1, 2, …, M, calculate the corresponding frequency of each harmonic k m :

[0052]

[0053] Step 6, construct the frequency spectrum S i [k] of a single signal, while removing S i [k] from the residual spectrum; wherein the frequency spectrum S i [k] of a single signal is constructed as follows:

[0054] First, create a spectrum S i [k] with the same length as S[k], and initialize all its values to 0; for each harmonic frequency index, extract the corresponding value from S[k] and assign it to S i [k]; then, let S i [N-k m ] = S[N-k m ], except for S i [k m ] and S i [N-k m ], all other positions of S i [k] take 0;

[0055] Step 7, based on the constructed frequency spectrum of the signal, reconstruct the single signal by inverse discrete Fourier transform;

[0056] Step 8, repeat steps 1 to 7 several times to obtain multiple single type reconstructed signals;

[0057] Step 9, return to step 2, and stop iteration when the maximum amplitude of the residual spectrum is below a preset threshold, or the expected number of signals is extracted.

[0058] Further, the single type signal decomposed is subjected to feature extraction to obtain feature data of the signal to be analyzed, including:

[0059] Divide the signal into multiple time windows according to a fixed time length, and calculate the statistical quantity of the signal in each time window; wherein the statistical quantity includes the mean, variance, skewness and kurtosis of the signal in the corresponding time window;

[0060] Calculate the difference value of the statistical quantity between adjacent time windows;

[0061] The difference of the statistical quantity between every two adjacent time windows is combined into a feature vector, and all the obtained feature vectors are taken as the feature data of the signal to be analyzed.

[0062] Further, the preset recognition model is a BP neural network model optimized by a genetic algorithm.

[0063] Further, the training process of the preset recognition model comprises:

[0064] A historical microseismic monitoring signal is acquired as a sample signal, and is labeled by category;

[0065] The sample signal is decomposed into a plurality of single-type signals, and the single-type signals decomposed are subjected to feature extraction to obtain feature data of the sample signal.

[0066] The feature database is constructed by using the feature data and label data of the sample signal.

[0067] The preset recognition model is trained by using the feature database, and the weights and threshold parameters of the BP neural network are optimized by using a genetic algorithm to enhance the learning ability and generalization ability of the neural network.

[0068] In still another aspect, the present application further provides an electronic device comprising a processor and a memory; wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the above method.

[0069] In still another aspect, the present application further provides a computer readable storage medium, which stores at least one instruction, which is loaded and executed by a processor to implement the above method.

[0070] The technical solution provided by the present application has at least the following beneficial effects:

[0071] The present application can provide guidance for mine microseismic identification and ensure mine safety production. BRIEF DESCRIPTION OF DRAWINGS

[0072] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative effort.

[0073] Figure 1 is a flow chart of the intelligent recognition method of the mine microseismic signal provided by the embodiments of the present application;

[0074] Figure 2 is a time-domain waveform and a frequency-domain graph of the original signal provided by the embodiments of the present application;

[0075] Figure 3 is a time-domain waveform and a frequency-domain graph of the original signal after the decomposition by the “iterative harmonic extraction method” provided by the embodiments of the present application;

[0076] Figure 4 is a recognition result graph of the training set and the test set after the feature vector is extracted based on the local statistics and the dynamic difference and used as the input of the neural network provided by the embodiments of the present application;

[0077] Figure 5 is a neural network training performance graph provided by the embodiments of the present application;

[0078] Figure 6 is an output microseismic signal graph provided by the embodiments of the present application; wherein (a)-(f) respectively represent different output microseismic signals;

[0079] Figure 7 is a system block diagram of the electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0080] In order to make the objects, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0081] First of all, it should be noted that in the embodiments of the present application, the words “exemplarily”, “for example” and the like are used to represent as an example, illustration or explanation. Any embodiment or design scheme described as “exemplary” in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the word “exemplarily” is intended to present the concept in a specific way. In addition, in the embodiments of the present application, the meaning expressed by “and / or” can be both, or can be one of the two.

[0082] First Embodiment

[0083] The embodiment provides a mine microseismic signal intelligent identification method, the method can be realized by an electronic device, and the electronic device can be a terminal or a server. As shown in the execution flow of the method in Figure 1 FIG. 1, the method comprises the following steps:

[0084] S1, obtaining a microseismic monitoring signal to be identified as an analysis signal;

[0085] S2, decomposing the analysis signal into a plurality of single type signals;

[0086] It should be noted that the composite sound signal s(t) can be regarded as the superposition of a plurality of single sound signals s i (t), that is, s(t) = s1(t) + s2(t) + … + s n (t), assuming that each single sound signal is a harmonic signal, has a fundamental frequency f 0i and its harmonic component kf 0i (wherein, k = 1, 2, 3, …).

[0087] Based on the above, the embodiment adopts an "iterative harmonic extraction method" to decompose the composite sound signal into a plurality of single type sound signals, thereby constructing a sound signal database. Specifically, the method comprises the following steps:

[0088] S21, performing discrete Fourier transform (DFT) on the composite sound signal to obtain a frequency domain representation:

[0089]

[0090] Wherein, S[k] is the complex amplitude of the composite sound signal after the discrete Fourier transform, on the frequency index k, which is the representation of the signal in the frequency domain; s[n] is the sampled composite sound signal, n is the time index, the value range is n = 0, 1, …, N-1, which represents the discrete signal sample in the time domain; N is the total number of sampling points of the signal, that is, the length of the signal; k is the frequency index, the value range is k = 0, 1, …, N-1, which corresponds to a specific frequency component, the actual frequency is f k = kf s / N, wherein f s is the sampling frequency; j is the imaginary unit, defined as for representing the imaginary part in the complex number; e -j2πkn / N is the base function of DFT, which is a complex exponential function, representing the rotation factor on the frequency k, used to project the time domain signal to the frequency domain; is the summation operation for all time indexes n, which calculates the total contribution of the signal on the frequency k.

[0091] S22, set the frequency domain signal as the initial residual spectrum, find the frequency corresponding to the maximum value in the amplitude of the residual spectrum (i.e. the significant frequency), and estimate the possible fundamental frequency based on the frequency; the specific process is as follows:

[0092] First, initialize the residual spectrum R[k]:

[0093] R[k] = S[k]

[0094] In the amplitude |R[k]| of the residual spectrum R[k], find the frequency f corresponding to the maximum value max :

[0095] f max = k max f s / N

[0096] wherein k max is the position of the strongest energy in the spectrum when the amplitude of the residual spectrum reaches the maximum value, and the value range is k = 0, 1,..., N-1; f s is the sampling frequency, with the unit of hertz Hz, representing the number of samples collected per second.

[0097] f max is likely to be a harmonic component of a certain fundamental frequency, so the possible fundamental frequency is estimated based on the frequency.

[0098] S23, estimate the fundamental frequency and calculate the harmonic energy: assume f max = mf0, wherein m is the harmonic order, m = 1, 2,..., M max , M max is the maximum possible value of the harmonic order, and M max = 5 is often taken empirically; for each possible m, calculate its candidate fundamental frequency f m = f max / m, and solve its harmonic energy function value E(f m ), calculate the total energy of the first several harmonics in the residual spectrum; wherein the expression of the harmonic energy function is:

[0099]

[0100] wherein E(f m ) is the harmonic energy function value corresponding to f m , representing the total energy of the harmonic components of the corresponding fundamental frequency in the residual spectrum, which is used to evaluate the significance of a certain fundamental frequency; f mis the candidate fundamental frequency, i.e. the assumed signal fundamental frequency, in Hz; M is the maximum number of harmonics considered, for example: M=5 means the energy of the first 5 harmonics is calculated; m is the harmonic number, m=1,2,...,M, which means the m-th harmonic (for example, m=1 is the fundamental frequency, m=2 is the second harmonic); R[] represents the residual spectrum, which is equal to S[k] (DFT result) at the beginning and will be updated in each iteration, which represents the remaining unextracted spectral components; round(x) is the rounding function, which takes the input value x to the nearest integer, used to find the frequency index closest to the harmonic frequency; represents the approximate position of the frequency index corresponding to the m-th harmonic frequency, where N / f s is the time length; |R[k]| 2 is the energy of the residual spectrum at frequency index k, which is calculated by squaring the complex amplitude.

[0101] The harmonic energy function value corresponding to each k can be calculated by the above formula;

[0102] S24, determine the k and candidate fundamental frequency f corresponding to the maximum harmonic energy function value c-max , construct an optimization function, and obtain the final fundamental frequency f0 by solving the optimization function; wherein the optimization function expression is:

[0103]

[0104] wherein, represents finding the f c-max that maximizes E(f fc-max ) among all possible f c-max .

[0105] wherein, in this embodiment, the above optimization function is solved as follows:

[0106] Take f c-max as the starting point, and use numerical optimization methods such as gradient ascent or grid search in a small range near f c-max to solve the harmonic energy equation to maximize the harmonic energy. Wherein, since the harmonic energy function is a function of discrete spectrum, its gradient can be approximated by numerical difference.

[0107] After obtaining the final fundamental frequency, the frequency index corresponding to the first several harmonics is calculated, the spectrum of a single signal is constructed, and then the spectrum is converted back to the time domain through inverse discrete Fourier transform (IDFT) to reconstruct the single signal. The extracted harmonic components are removed from the residual spectrum, completing the separation of an independent signal, and updating the residual for the next iteration. The specific implementation process is as follows:

[0108] S25, after determining f0, extract its harmonic set. For each harmonic m = 1, 2,..., M, calculate the corresponding frequency k m :

[0109]

[0110] where k m is the frequency index corresponding to the mth harmonic, used to locate the harmonic position in the spectrum; is the accurate frequency index position corresponding to the mth harmonic, usually a decimal, rounded to an integer.

[0111] S26, construct the spectrum S i [k] of the individual signal.

[0112] First create a spectrum S i [k] with the same length as S[k] and initialize all values to 0. For each harmonic frequency index k m (m = 1, 2,..., M) extract the corresponding value from the original spectrum S[k] and assign it to S i [k]: S i [k m ] = S[k m ]; considering the conjugate symmetry of the Fourier transform spectrum, let S i [N-k m ] = S[N-k m ], in addition to the above S i [k m ] and S i [N-k m ], all other positions of S i [k] take 0.

[0113] S27, based on the spectrum of the signal, reconstruct the individual signal s i [n] by inverse discrete Fourier transform:

[0114]

[0115] where s i [n] is the ith extracted individual sound signal, n is the time index, taking values n = 0, 1,..., N-1, representing the reconstructed time-domain signal; s i [k] is the spectrum of the ith signal, usually only at the harmonic frequency index, and 0 at other positions; e j2πkn / N is the basis function of inverse discrete Fourier transform (IDFT), which is a complex exponential function, used to convert the frequency domain signal back to the time domain; sum over all frequency indices k to complete the reconstruction from the frequency domain to the time domain; is a normalization factor to ensure the correct amplitude of the inverse transform.

[0116] S28, repeating S21 to S27 several times, gradually extracting all main sound components in the composite signal through multiple iterations, completing the separation of each sound signal.

[0117] S29, returning to S22, using the updated residual spectrum R[k], continuing to find the next significant frequency, repeating steps S23 and S28. When the maximum amplitude of the residual spectrum is below a preset threshold, or the expected number of signals is extracted, the iteration stops. The iteration process ensures that the method can adaptively decompose composite signals of different complexity, and finally complete the separation of single sound signals, and build a single sound signal database.

[0118] S3, extracting features from the decomposed single type signal to obtain feature data of the signal to be analyzed;

[0119] Specifically, in this embodiment, the feature database is extracted from the sound signal database obtained in S2 by extracting feature vectors based on local statistics and dynamic differences, as the input of the neural network, to improve the recognition ability of the neural network to data. The specific steps are as follows:

[0120] S31, divide the sound signal into multiple time windows (for example, each window contains 100 sampling points) according to a fixed time length. In each time window, the following statistics are calculated: mean (reflecting the average intensity of the signal in the window), variance (reflecting the fluctuation degree of the signal), skewness (reflecting the symmetry of the signal distribution), kurtosis (reflecting the sharpness of the signal peak). Then calculate the difference of the statistics between adjacent time windows, for example: mean difference (reflecting the change of the mean of adjacent windows); variance difference (reflecting the change of the variance of adjacent windows);

[0121] S32, combine the statistics (mean, variance, skewness, kurtosis) of each window and the difference between adjacent windows into a feature vector, obtain the feature database corresponding to the corresponding signal to be analyzed as the input of the network.

[0122] S4, input the feature data of the signal to be analyzed into a preset recognition model to realize intelligent recognition of microseismic signals.

[0123] The preset recognition model used in the embodiment is a BP neural network model GA-BP optimized by using a genetic algorithm. The BP neural network is composed of an input layer, a hidden layer (also referred to as an intermediate layer), and an output layer, wherein the hidden layer has one or more layers. Each layer can have several nodes. The connection state of the nodes between layers is embodied by weights. First, forward propagation is performed: after data is input from the input end, the data is multiplied by the corresponding weights, summed, and then the result is calculated in an activation function as input, and the calculated result is passed to the next node as input; calculation is performed in sequence until the final result is obtained. Then, backward propagation is performed: the output result is compared with the expected output result, the error generated by the comparison is propagated backward using the network, and the weights between the nodes on the network are adjusted (updated) through multiple iterations.

[0124] The activation function can be selected from a sigmoid function, a Tanh function, a ReLU function, and the like. If the sigmoid function is selected, the expression is as follows:

[0125]

[0126] In the formula, x represents a linear combination of input features, and the specific form is x = w·z + b, wherein w is a weight vector, z is an input feature vector, and b is a bias term.

[0127] There is often an error between the output result after forward propagation and the expected output result, and a loss function is used to measure the size of the error:

[0128]

[0129] In the formula, y i is the expected output result of the i-th item; is the actual output result of the i-th item; and n is the total number of samples in the training data set.

[0130] The adjustment (update) of the weights can be performed by using the gradient descent method for iteration to make the loss function as small as possible. Other algorithms, such as mini-batch gradient descent, Adam, and the like, can also be used to update the weights. If the gradient descent method is used, the algorithm expression is as follows:

[0131]

[0132] In the formula, W (t) is the parameter after the t-th update; η is a learning rate, which controls the step size of each parameter update; is the gradient of the loss function with respect to the parameter w; and α[W (t) -W (t-1) ] is a smoothing term.

[0133] The training process of the recognition model comprises:

[0134] A historical microseismic monitoring signal is acquired as a sample signal, and is labeled by category;

[0135] The sample signal is decomposed into a plurality of single type sound signals by using an "iterative harmonic extraction method", and a feature vector is extracted based on "local statistics and dynamic difference", so as to form feature data of the sample signal;

[0136] The feature data and label data of the sample signal are used to construct a feature database;

[0137] The feature database is used to train a preset recognition model, and a genetic algorithm is used to optimize weight and threshold parameters of a BP neural network, so as to enhance learning ability and generalization ability of the neural network and improve accuracy.

[0138] The genetic algorithm optimizes the BP neural network, and the basic idea is that an individual represents initial weight and threshold values of the network, a norm of a test error of the BP neural network of the prediction sample is taken as an output of an objective function, and then an adaptability value of the individual is calculated, and an optimal individual, that is, optimal initial weight and threshold values of the BP neural network, is found through selection, crossover and mutation operations. In addition to the genetic algorithm, a particle swarm algorithm, an ant colony algorithm and the like can also be used to optimize the initial weight and threshold values of the BP neural network.

[0139] An example of intelligent recognition of microseismic signals by using the method of the present application is provided as follows:

[0140] Randomly selected data of two days of a mine are taken as a composite sound signal set, and the data set contains 18 rock mass microseismic signals, 34 electric noise signals, 28 blasting signals and 14 other types of signals after complex artificial recognition. Figure 2 The original signal is a time domain waveform and a frequency domain image. After the BP neural network model is trained by using the previously mined microseismic data marked by artificial labeling, the mine data is subjected to intelligent recognition of microseismic signals according to the above steps S1 to S3. Figure 3 The original signal is a time domain waveform and a frequency domain image. After the BP neural network model is trained by using the previously mined microseismic data marked by artificial labeling, the mine data is subjected to intelligent recognition of microseismic signals according to the above steps S1 to S3. Figure 4 The original signal is a time domain waveform and a frequency domain image. After the BP neural network model is trained by using the previously mined microseismic data marked by artificial labeling, the mine data is subjected to intelligent recognition of microseismic signals according to the above steps S1 to S3. Figure 5 The original signal is a time domain waveform and a frequency domain image. After the BP neural network model is trained by using the previously mined microseismic data marked by artificial labeling, the mine data is subjected to intelligent recognition of microseismic signals according to the above steps S1 to S3. Figure 6The output is the microseismic signal after processing by the method of this invention. Analysis of the output results shows that the intelligent identification output a total of 21 signals, including 18 rock mass microseismic signals, with an accuracy rate of 85.7%. This indicates that the intelligent microseismic signal identification model has high reliability and practicality. In practical applications, this intelligent identification rate can effectively help staff quickly and intelligently identify and analyze microseismic signals, thereby making timely decisions and responses.

[0141] In summary, this embodiment provides an intelligent identification method for mine microseismic signals. This method can intelligently identify microseismic signals with high precision while gradually adapting to different mining environments through continuous learning and optimization. It can provide guidance for intelligent identification of mine microseismic signals and ensure safe production in mines. It also has the advantage of wide applicability.

[0142] Second Embodiment

[0143] This embodiment provides an intelligent identification system for microseismic signals in mines, including the following modules:

[0144] The data acquisition module is used to acquire the microseismic monitoring signals to be identified, as the signals to be analyzed.

[0145] The data processing module is used to decompose the signal to be analyzed into several single-type signals; and to extract features from the decomposed single-type signals to obtain the feature data of the signal to be analyzed.

[0146] The intelligent recognition module is used to input the feature data of the signal to be analyzed obtained by the data processing module into a preset recognition model to realize intelligent recognition of microseismic signals.

[0147] It should be noted that, for ease of explanation, the intelligent identification system for mine microseismic signals in this embodiment corresponds to the intelligent identification method for mine microseismic signals in the first embodiment described above; the functions implemented by each functional module in the intelligent identification system for mine microseismic signals in this embodiment correspond one-to-one with the process steps in the intelligent identification method for mine microseismic signals in the first embodiment described above; therefore, they will not be repeated here.

[0148] Third Embodiment

[0149] This embodiment provides an electronic device, such as... Figure 3 As shown, the electronic device includes at least one processor 71, at least one memory 72, at least one network interface 74, and other user interfaces 73. The various components in the evaluation device are coupled together via a bus system 75. It is understood that the bus system 75 is used to implement communication between these components. In addition to a data bus, the bus system 75 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 7The various buses are shown as bus system 75.

[0150] The user interface 73 can include a display, a keyboard, or a pointing device, such as a mouse, trackball, or touchpad, among others.

[0151] It is to be understood that the memory 72 shown in the figure can be a volatile memory or a nonvolatile memory, or can include both volatile and nonvolatile memory. The nonvolatile memory can be a Read Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM), which is used as the external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), Synch Link DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 72 described herein is intended to include, among others, these and any other suitable types of memory.

[0152] In some embodiments, the memory 72 stores the following elements, executable units or data structures, or a subset of them, or an extended set of them: an operating system 721 and an application program 722.

[0153] The operating system 721 contains various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application program 722 contains various application programs, such as an industrial control device operation management system, for implementing various application services. The program for implementing the method of the embodiments of the present application can be included in the application program 722.

[0154] In the embodiments of the present application, the processor 71 executes the method steps provided by the first embodiment by invoking the programs or instructions stored in the memory 72, specifically, the programs or instructions stored in the application program 722.

[0155] The method disclosed in the above embodiments of the present application can be applied to or implemented by the processor 71. The processor 71 can be an integrated circuit chip with a signal processing capability. In the implementation process, the steps of the above method can be completed by hardware integrated logic circuit or software form of instructions in the processor 71. The processor 71 described above can be a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The disclosed methods, steps and logic block diagrams in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware coding processor for execution, or a combination of hardware and software units in the coding processor for execution. The software unit can be located in a random access memory, a flash memory, a read only memory, a programmable read only memory or an electrically erasable programmable memory, a register, or other mature storage media in the art. The storage medium is located in the memory 72, and the processor 71 reads the information in the memory 72 and combines the hardware to complete the steps of the above method.

[0156] In addition, it should be noted that, Figure 7 The structure of the electronic device shown in the fourth embodiment does not constitute a limitation on the device, and the actual device can include more or fewer components than shown, or combine certain components, or different component arrangements. In addition, the technical effects achieved by the electronic device when executing the method of the first embodiment can refer to the technical effects described in the first embodiment, and therefore will not be described here.

[0157] Fourth embodiment

[0158] The present embodiment provides a computer readable storage medium, the storage medium stores at least one instruction, the instruction is loaded and executed by the processor to realize the method of the first embodiment. Wherein, the computer readable storage medium can be ROM, random access memory, CD-ROM, magnetic tape, floppy disk and optical data storage device, etc. The instructions stored therein can be loaded and executed by the processor in the terminal to execute the above method.

[0159] Moreover, it should be noted that the present application can be provided as a method, an apparatus, or a computer program product. Therefore, the embodiments of the present application can take the form of an entirely or partially hardware embodiment, an entirely or partially software embodiment, or an embodiment combining software and hardware aspects. Furthermore, when implemented in software, the embodiments of the present application can take the form of a computer program product including one or more computer program instructions embodied in a computer-usable storage medium. The computer program instructions can be stored in a computer-usable storage medium, or transmitted from one computer-usable storage medium to another, for example, from a website site, a computer, a server, or a data center to another website site, a computer, a server, or a data center through a wired (for example, infrared, wireless, microwave, or the like) manner. The computer-usable storage medium can be any available medium or a collection of medium accessible by a computer or a data storage device such as a server, a data center, or the like, including one or more of a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0160] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the method, terminal device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate a device for implementing the flow Figure 1 The flow or the plurality of flows and / or blocks Figure 1 The apparatus for implementing the functions specified in the flow or the plurality of flows and / or blocks.

[0161] These computer program instructions can also be stored in a computer-readable memory capable of directing the computer or other programmable data processing terminal device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including instruction apparatus, which implements the flow Figure 1 The flow or the plurality of flows and / or blocks Figure 1the functions specified in the individual block or blocks. Such computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable devices to generate a computer-implemented process, thus the instructions executed on the computer or other programmable devices provide a process for implementing the functions specified in the flowchart block(s) or block(s). Figure 1 the functions specified in the individual block or blocks. Such computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable devices to generate a computer-implemented process, thus the instructions executed on the computer or other programmable devices provide a process for implementing the functions specified in the flowchart block(s) or block(s). Figure 1 the functions specified in the individual block or blocks. Such computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable devices to generate a computer-implemented process, thus the instructions executed on the computer or other programmable devices provide a process for implementing the functions specified in the flowchart block(s) or block(s).

[0162] It should also be noted that, in the present document, the terms such as first and second, and the like, are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between such entities or operations. The terms "comprising", "containing", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal device including a list of elements does not only include those elements, but also includes other elements not explicitly listed, or further includes elements inherent in such process, method, article, or terminal device. Without more limitations, an element defined by the statement "including a..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device including the element. In addition, the term "and / or" is only a description of the associated relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which means that A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In addition, the character " / " in the present document generally represents an "or" relationship between the front and rear associated objects, but can also represent an "and / or" relationship, which can be understood in the context of the front and rear text. "One or more" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c, can mean a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0163] In addition, it can be understood that in various embodiments of the present application, the size of the sequence number of the above processes does not mean the order of execution, and the execution order of the processes should be determined by their functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0164] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized in electronic hardware or in a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solutions. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0165] In several embodiments provided by the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic, for example, the division of functional modules / units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another device, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms. The units described as separate components can be or can not be physically separated, and the components displayed as units can be or can not be physical units, that is, can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment. In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present, or two or more units can be integrated in one unit.

[0166] If the method is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in the embodiments of the present application. The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0167] Finally, it should be noted that the above description is only the preferred embodiment of the application, it should be pointed out that although the preferred embodiment of the application has been described, for those skilled in the art, once the basic creative concept of the application is known, several improvements and refinements can be made without departing from the principles of the application, and these improvements and refinements should also be considered as the protection scope of the application. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the application.

Claims

1. A method for intelligent identification of microseismic signals in mining, characterized in that, include: Acquire the microseismic monitoring signal to be identified as the signal to be analyzed; The signal to be analyzed is decomposed into several single-type signals; Feature extraction is performed on the decomposed single-type signals to obtain the feature data of the signal to be analyzed. Input the characteristic data of the signal to be analyzed into a preset recognition model to achieve intelligent recognition of microseismic signals; The process of decomposing the signal to be analyzed into several single-type signals includes: Step 1: Perform a discrete Fourier transform on the signal to obtain the frequency domain representation S[k], which serves as the residual spectrum; Step 2: Find the frequency f corresponding to the largest amplitude in the residual spectrum. max ; Step 3, set the harmonic order m = 1, 2, ..., M max For each possible m, calculate its candidate fundamental frequency f. m =f max / m, and solve for its harmonic energy function value E(f m The expression for the harmonic energy function is: Where M is the maximum harmonic number; round() indicates rounding to the nearest integer; R[] represents the residual spectrum; f s It is the sampling frequency; N is the total number of sampling points for the signal; Step 4: Determine the candidate fundamental frequency f corresponding to the maximum harmonic energy function value. c-max An optimization function is constructed, and the final fundamental frequency f0 is obtained by solving the optimization function; the expression of the optimization function is: Among them, E(f) c-max ) represents f c-max The corresponding harmonic energy function value; Step 5: Determine the harmonics m = 1, 2, ..., M corresponding to f0, and calculate the frequency k corresponding to each harmonic. m : Step 6, construct the spectrum S of a single signal i [k], while removing S from the residual spectrum i [k], update the residual spectrum; where, construct the spectrum S of a single signal. i The process for [k] is as follows: First, create a spectrum S with the same length as S[k]. i [k], and initialize all its values ​​to 0; for each harmonic frequency index, extract the corresponding value from S[k] and assign it to S. i [k]; then, let S i [Nk m ]=S[Nk m ], except S i [k m ] and S i [Nk m Except for [ ], S in all other positions i [k] is 0; Step 7: Based on the spectrum of the constructed signal, reconstruct the individual signal using the inverse discrete Fourier transform; Step 8: Repeat steps 1 to 7 several times to obtain multiple single-type reconstructed signals; Step 9: Return to Step 2 until the maximum amplitude of the residual spectrum is lower than the preset threshold, or the expected number of signals have been extracted, then stop the iteration. The step of extracting features from the decomposed single-type signals to obtain feature data of the signal to be analyzed includes: The signal is divided into multiple time windows of fixed length, and the statistics of the signal are calculated in each time window; the statistics include the mean, variance, skewness and kurtosis of the signal in the corresponding time window. Calculate the difference in statistics between adjacent time windows; The differences in statistics between any two adjacent time windows are combined into a feature vector, and all the resulting feature vectors are used as the feature data of the signal to be analyzed.

2. The intelligent identification method for mine microseismic signals as described in claim 1, characterized in that, The preset recognition model is a BP neural network model optimized using a genetic algorithm.

3. The intelligent identification method for mine microseismic signals as described in claim 2, characterized in that, The training process of the preset recognition model includes: Historical microseismic monitoring signals were acquired as sample signals and categorized accordingly. The sample signal is decomposed into several single-type signals, and features are extracted from the decomposed single-type signals to obtain the feature data of the sample signal. A feature database is constructed using the feature data and label data of the sample signals; The preset recognition model is trained using the feature database, and the weights and threshold parameters of the BP neural network are optimized using a genetic algorithm to enhance the learning and generalization capabilities of the neural network.

4. A mine micro-seismic signal intelligent identification system, characterized in that, include: The data acquisition module is used to acquire the microseismic monitoring signals to be identified, as the signals to be analyzed. The data processing module is used to decompose the signal to be analyzed into several single-type signals; and to extract features from the decomposed single-type signals to obtain the feature data of the signal to be analyzed. The intelligent recognition module is used to input the feature data of the signal to be analyzed obtained by the data processing module into a preset recognition model to realize intelligent recognition of microseismic signals; The process of decomposing the signal to be analyzed into several single-type signals includes: Step 1: Perform a discrete Fourier transform on the signal to obtain the frequency domain representation S[k], which serves as the residual spectrum; Step 2: Find the frequency f corresponding to the largest amplitude in the residual spectrum. max ; Step 3, set the harmonic order m = 1, 2, ..., M max For each possible m, calculate its candidate fundamental frequency f. m =f max / m, and solve for its harmonic energy function value E(f m The expression for the harmonic energy function is: Where M is the maximum harmonic number; round() indicates rounding to the nearest integer; R[] represents the residual spectrum; f s It is the sampling frequency; N is the total number of sampling points for the signal; Step 4: Determine the candidate fundamental frequency f corresponding to the maximum harmonic energy function value. c-max An optimization function is constructed, and the final fundamental frequency f0 is obtained by solving the optimization function; the expression of the optimization function is: Among them, E(f) c-max ) represents f c-max The corresponding harmonic energy function value; Step 5: Determine the harmonics m = 1, 2, ..., M corresponding to f0, and calculate the frequency k corresponding to each harmonic. m : Step 6, construct the spectrum S of a single signal i [k], while removing S from the residual spectrum i [k], update the residual spectrum; where, construct the spectrum S of a single signal. i The process for [k] is as follows: First, create a spectrum S with the same length as S[k]. i [k], and initialize all its values ​​to 0; for each harmonic frequency index, extract the corresponding value from S[k] and assign it to S. i [k]; then, let S i [Nk m ]=S[Nk m ], except S i [k m ] and S i [Nk m Except for [ ], S in all other positions i [k] is 0; Step 7: Based on the spectrum of the constructed signal, reconstruct the individual signal using the inverse discrete Fourier transform; Step 8: Repeat steps 1 to 7 several times to obtain multiple single-type reconstructed signals; Step 9: Return to Step 2 until the maximum amplitude of the residual spectrum is lower than the preset threshold, or the expected number of signals have been extracted, then stop the iteration. The step of extracting features from the decomposed single-type signals to obtain feature data of the signal to be analyzed includes: The signal is divided into multiple time windows of fixed length, and the statistics of the signal are calculated in each time window; the statistics include the mean, variance, skewness and kurtosis of the signal in the corresponding time window. Calculate the difference in statistics between adjacent time windows; The differences in statistics between any two adjacent time windows are combined into a feature vector, and all the resulting feature vectors are used as the feature data of the signal to be analyzed.

5. The intelligent identification system for mine microseismic signals as described in claim 4, characterized in that, The preset recognition model is a BP neural network model optimized using a genetic algorithm.

6. The intelligent identification system for mine microseismic signals as described in claim 5, characterized in that, The training process of the preset recognition model includes: Historical microseismic monitoring signals were acquired as sample signals and categorized accordingly. The sample signal is decomposed into several single-type signals, and features are extracted from the decomposed single-type signals to obtain the feature data of the sample signal. A feature database is constructed using the feature data and label data of the sample signals; The preset recognition model is trained using the feature database, and the weights and threshold parameters of the BP neural network are optimized using a genetic algorithm to enhance the learning and generalization capabilities of the neural network.

Images