Rockburst prediction method, device and computer equipment

Abstract

The present invention discloses a rockburst prediction method, device and computer equipment. The method includes: obtaining construction data and microseismic signals of a construction tunnel within a first preset time period, the construction data including first construction data within the first preset time period and second construction data within a second preset time period; predicting the total microseismic energy within the second preset time period based on the microseismic signals, the second preset time period being the next time period of the first preset time period; predicting the location information of a microseismic event occurring within the second preset time period based on the first construction data and the microseismic signals; obtaining the probability of rockburst occurrence and the size of a blast pit based on the total microseismic energy, the location information and the second construction data; and determining whether a rockburst occurs within the second preset time period based on the probability of rockburst occurrence and the size of the blast pit.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel rockburst prediction, and in particular to a rockburst prediction method, device and computer equipment. Background Art

[0002] As underground projects expand in number and depth, geological problems caused by high ground stresses are becoming increasingly severe. Underground excavation is highly susceptible to rockbursts, posing a significant threat to equipment and personnel safety. This has led to new requirements for rockburst early warning and prevention in construction projects. However, existing rockburst early warning technologies are unable to accurately predict the timing of a rockburst, making it difficult to identify and warn of rockburst risks. Current prediction models only consider the mechanical characteristics of the rock mass and fail to account for the tunnel construction process. Summary of the Invention

[0003] Therefore, in order to address the deficiencies of the prior art, embodiments of the present invention provide a rockburst prediction method, apparatus, and computer equipment.

[0004] According to a first aspect, an embodiment of the present invention discloses a resource evaluation method, comprising:

[0005] Acquire construction data and a microseismic signal of a tunnel under construction within a first preset time period, wherein the construction data includes first construction data within the first preset time period and second construction data within a second preset time period;

[0006] Predicting the total energy of the microseismic event within a second preset time period based on the microseismic signal, where the second preset time period is a time period after the first preset time period;

[0007] Predicting location information of a microseismic event occurring within a second preset time period based on the first construction data and the microseismic signal;

[0008] According to the total microseismic energy, location information and the second construction data, the probability of rock burst and the size of the blast crater are obtained;

[0009] Whether a rockburst occurs within a second preset time period is determined based on the rockburst occurrence probability and the size of the blast crater.

[0010] Optionally, the construction data further includes a first excavation speed. When it is determined based on the rockburst probability and the blast pit size that a rockburst will occur within a second preset time, the method further includes:

[0011] Divide the first excavation speed to generate i second excavation speeds;

[0012] Input the j-th second excavation speed, the data in the second construction data excluding the first excavation speed, and the total microseismic energy and location information into a preset rockburst prediction model to predict the j-th rockburst probability and the j-th blast pit size;

[0013] If it is determined that no rockburst will occur within the second preset time period based on the j-th rockburst probability and the j-th blast pit size, the j-th second excavation speed will be used as the new excavation speed for construction, where i is a positive integer greater than or equal to 2, and j is a positive integer less than or equal to i.

[0014] Optionally, predicting the total microseismic energy within a second preset time period based on the microseismic signal specifically includes:

[0015] determining characteristic data of the microseismic signal according to the microseismic signal;

[0016] After the characteristic data is input into a preset energy prediction model, the total energy of the microseismic event within a second preset time period is predicted.

[0017] Optionally, after inputting the characteristic data into a preset energy prediction model, the total microseismic energy within the second preset time period is predicted, specifically including:

[0018] When the second preset time period includes only one preset unit time, the characteristic data in the first preset time period is input into a preset energy prediction model to predict the microseismic energy in the second preset time period;

[0019] or,

[0020] When the second preset time period includes at least two unit times, the microseismic energy corresponding to the next unit time in the second preset time period is predicted based on the characteristic data in the first preset time period, the microseismic energy corresponding to the current unit time in the second preset time period, and the preset energy prediction model, wherein, when the current unit time is the first unit time in the second preset time period, the microseismic energy corresponding to the current unit time is the characteristic data in the first preset time period, which is input into the preset energy prediction model and predicted;

[0021] The total microseismic energy in the second preset time period is obtained according to the microseismic energies corresponding to all unit times in the second preset time period.

[0022] Optionally, the preset rockburst prediction model includes a first rockburst prediction model and a second rockburst prediction model.

[0023] Based on the total microseismic energy, location information, and secondary construction data, the probability of rockburst and crater size are obtained, including:

[0024] Inputting the total microseismic energy, location information, and the second construction parameter into a first rockburst prediction model to obtain a first probability of rockburst occurrence;

[0025] Inputting the total microseismic energy, location information, and second construction data into a second rockburst prediction model to obtain a second probability of rockburst occurrence and a crater size;

[0026] The probability of rockburst occurrence is determined based on the first probability, the second probability and a preset weight coefficient.

[0027] Optionally, when the second preset time period is n time periods after the first preset time period, where n is greater than or equal to 2, the method further includes:

[0028] According to the prediction results in n-1 preset time periods and Bayesian theory, the probability of rock burst occurring in the nth preset time period is determined.

[0029] According to a second aspect, an embodiment of the present invention further discloses a rockburst prediction device, comprising:

[0030] an acquisition module, configured to acquire construction data and a microseismic signal of a tunnel under construction within a first preset time period, wherein the construction data includes first construction data within the first preset time period and second construction data within a second preset time period;

[0031] A first prediction module is configured to predict the total microseismic energy within a second preset time period based on the microseismic signal, where the second preset time period is a time period subsequent to the first preset time period;

[0032] A second prediction module is used to predict location information of a microseismic event occurring within a second preset time period based on the first construction data and the microseismic signal;

[0033] The third prediction module is used to obtain the probability of rock burst and the size of the blast crater based on the total microseismic energy, location information, and the second construction data;

[0034] The judgment module is used to determine whether a rock burst occurs within a second preset time period based on the rock burst occurrence probability and the size of the blast pit.

[0035] Optionally, the construction data further includes a first excavation speed, and the device further includes:

[0036] a division module, configured to divide the first excavation speed into i second excavation speeds;

[0037] a fourth prediction module, configured to input the j-th second excavation speed, data other than the first excavation speed in the second construction data, and the total microseismic energy and location information into a preset rockburst prediction model to predict the j-th rockburst probability and the j-th blast pit size;

[0038] A determination module is used to use the jth second excavation speed as the new excavation speed for construction if it is determined that no rockburst will occur within a second preset time period based on the jth rockburst probability and the jth blast pit size, where i is a positive integer greater than or equal to 2 and j is a positive integer less than or equal to i.

[0039] According to a third aspect, an embodiment of the present invention further discloses a computer device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the rockburst prediction method as described in the first aspect or any optional embodiment of the first aspect.

[0040] According to a fourth aspect, an embodiment of the present invention further discloses a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the rockburst prediction method according to the first aspect or any optional embodiment of the first aspect are implemented.

[0041] The technical solution of the present invention has the following advantages:

[0042] The rockburst prediction method, device, and computer equipment provided by the present invention include: obtaining construction data and microseismic signals of the construction tunnel within a first preset time period in this way, and combining the construction data and microseismic signals in the process of predicting rockburst, thereby making the rockburst prediction result more accurate. Furthermore, based on the microseismic signals within the first preset time period, the total microseismic energy within the second preset time period is predicted; based on the first construction data and microseismic signals within the first preset time period, the location information of the time when the microseismic occurred within the second preset time period is predicted, and based on the actual data collected within the first preset time period, the data within the second preset time period can be truly and effectively predicted. Finally, after the total microseismic energy and location information within the second preset time period are predicted, the probability of rockburst occurrence within the second preset time period is predicted based on the construction data, total microseismic energy, and location information within the second preset time period, and the probability of rockburst occurrence within the second preset time period can be accurately obtained. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1This is a flowchart of a specific example of a rockburst prediction method according to an embodiment of the present invention;

[0045] Figure 2 This is a flowchart of a specific example of a rockburst prediction method according to an embodiment of the present invention;

[0046] Figure 3a A schematic diagram of a specific example of a rockburst prediction method according to an embodiment of the present invention;

[0047] Figure 3b A schematic diagram of a specific example of a rockburst prediction method according to an embodiment of the present invention;

[0048] Figure 4 A schematic diagram of a specific example of a rockburst prediction method according to an embodiment of the present invention;

[0049] Figure 5 A schematic diagram of a specific example of a rockburst prediction method according to an embodiment of the present invention;

[0050] Figure 6 This is a flowchart of a specific example of a rockburst prediction method according to an embodiment of the present invention;

[0051] Figure 7 A schematic diagram of a specific example of a rockburst prediction method according to an embodiment of the present invention;

[0052] Figure 8 A schematic diagram of a specific example of a rockburst prediction method according to an embodiment of the present invention;

[0053] Figure 9 is a principle block diagram of a specific example of a rockburst prediction device in an embodiment of the present invention;

[0054] Figure 10 FIG. 4 is a diagram showing a specific example of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0056] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0057] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "installed," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; internal connections between two components; wireless connections or wired connections. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0058] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0059] In response to the technical problems mentioned in the background technology, the present application embodiment provides a rockburst prediction method, see Figure 1 As shown, the method includes the following steps:

[0060] Step 101: Acquire construction data and microseismic signals of a tunnel under construction within a first preset time period.

[0061] The construction data includes first construction data within a first preset time period and second construction data within a second preset time period.

[0062] For example, during tunnel construction, the construction site collects real-time microseismic signals from microseismic events occurring during the construction process. This construction data can be pre-construction plans or actual construction data recorded during the actual construction process. Specifically, this actual construction data can be data recorded by TBM (Tunnel Boring Machine) equipment during the construction process. This detailed construction data can include information such as face position, torque, burial depth, axial force, and tunneling speed at each moment.

[0063] The first preset time period is a historical time period that has actually occurred. The microseismic signals and the first construction data within the first preset time period are actually collected data. Since the second preset time period is in the future and no data has occurred yet, the second construction data is the planned construction data within the second preset time period and can be obtained according to the construction plan.

[0064] Step 102: predict the total energy of microseismic events within a second preset time period based on the microseismic signals.

[0065] The second preset time period is a time period after the first preset time period.

[0066] For example, after obtaining the microseismic signal in the first time period, the total microseismic energy in the second preset time period is predicted based on the microseismic energy in the first preset time period, wherein the prediction of the total microseismic energy is performed using a neural network model. The specific neural network model can use an LSTM (Long Short-Term Memory, LSTM for short) neural network for prediction, and the LSTM neural network consists of 2 layers of LSTM nodes and 1 fully connected layer.

[0067] When using an LSTM neural network for prediction, the LSTM must first be trained. During training, the source energy in the microseismic signal within a first preset time period is used as input data, and the total energy of the microseismic signals within a second preset time period is used as output data. During training, the LSTM parameters are adjusted until the accuracy reaches a certain level. The source energy can be calculated by extracting characteristic parameters from the microseismic signal.

[0068] In an optional embodiment, if Figure 2 As shown, the process of extracting characteristic parameters of microseismic signals and the process of predicting the total microseismic energy in step 102 may include, but are not limited to, the following method steps:

[0069] Step 1021: Determine characteristic data of the microseismic signal based on the microseismic signal.

[0070] For example, the characteristic data of the collected microseismic signals include the occurrence time, energy, magnitude, and location of the microseismic signals, etc. The method for determining the above characteristic data based on the microseismic signals is described below.

[0071] The occurrence time is the acquisition time of the microseismic signal; the occurrence position is determined by the time difference of the elastic waves of the microseismic signal obtained by different sensors.

[0072] The energy of microseismic is calculated by the following formula:

[0073]

[0074] Where, F c is the radiation pattern coefficient of the radiation wave in the microseismic signal, where the radiation wave includes P wave and S wave. When the radiation wave is P wave, F c Take 0.52, when the radiation wave is S wave, F c Take 0.63; is the square of the mean value of the radiation pattern coefficient; ρ is the average density of the rock mass; c is the velocity of the P wave or S wave; R is the spatial distance between the source and the sensor; J c is the energy flux, which can be obtained by integrating the particle velocity spectrum in the frequency domain. It can be calculated using the following formula:

[0075]

[0076] Where V(f) is the velocity spectrum; f1 is the Nyquist frequency, which is half the sensor sampling frequency. The energy of the microseismic event is the average of the energies obtained by each sensor.

[0077] The earthquake source magnitude can be calculated using the following formula:

[0078]

[0079] Where M0 is the moment magnitude scale and is defined as the earthquake moment. It can be calculated using the following formula:

[0080]

[0081] Where Ω0 is the low-frequency spectrum level of the P wave or S wave in the microseismic signal, which is roughly equal to the amplitude of the zero frequency after Fourier transform.

[0082]

[0083] Where t1 is the total time of the signal; S(t) is the displacement function of the signal in the time domain.

[0084] Step 1022: After inputting the characteristic data into a preset energy prediction model, the total energy of the microseismic event within a second preset time period is predicted.

[0085] Exemplarily, all characteristic data of the microseismic signal are obtained in the above steps. In the process of predicting the total energy of the microseismic signal in this step, it is only necessary to input the energy of the microseismic signal within the first preset time period into the preset energy prediction model, and then predict the total energy of the microseismic signal within the second preset time period.

[0086] In a specific embodiment, considering that the total microseismic energy within the second preset time period is obtained, in order to more accurately control the microseismic energy at each moment within the second preset time period, it is necessary to further refine the microseismic energy within the second preset time period. The process of achieving the total microseismic energy specifically includes:

[0087] In an optional embodiment, when the second preset time period includes only one preset unit time, characteristic data within the first preset time period is input into a preset energy prediction model to predict the microseismic energy of the second preset time period.

[0088] Illustratively, the first preset time period includes n preset unit times, where n is greater than or equal to 1. In the process of predicting the total microseismic energy in the second preset time period based on the microseismic energy in the first preset time period, each preset time period is divided into n sub-time periods of preset unit times, wherein the size of each preset step size is the same.

[0089] For example, Figure 3a As shown, the first preset time period is 0-5 o'clock, the second preset time period is 5-6 o'clock, and the preset unit time is one hour. Therefore, the first preset time period includes 5 unit times, and the second preset time period includes one unit time.

[0090] In a specific embodiment, when predicting the microseismic energy within the second preset time period, assuming a time window based on three hours and moving in steps of unit time, the characteristic data (microseismic energy) within 0-5 hours is input into the preset energy prediction model to obtain the microseismic energy within 3-6 hours. Since the microseismic energy within 3-5 hours is known, the total microseismic energy within the second preset time period can be obtained by subtracting the microseismic energy within 3-5 hours from the microseismic energy within 3-6 hours.

[0091] In another optional embodiment, when the second preset time period includes at least two unit times, the microseismic energy corresponding to the next unit time in the second preset time period is predicted based on the characteristic data in the first preset time period, the microseismic energy corresponding to the current unit time in the second preset time period, and the preset energy prediction model.

[0092] The total microseismic energy in the second preset time period is obtained according to the microseismic energies corresponding to all unit times in the second preset time period.

[0093] Among them, when the current unit time is the first unit time in the second preset time period, the microseismic energy corresponding to the current unit time is the characteristic data in the first preset time period, which is predicted after being input into the preset energy prediction model.

[0094] For example, Figure 3b As shown, the first preset time period is 0-5 o'clock, the second preset time period is 5-8 o'clock, and the preset unit time is one hour. Therefore, the first preset time period includes 5 unit times, and the second preset time period includes 3 unit times.

[0095] First, the characteristic data within 0-5 hours (microseismic energy obtained according to the microseismic signal) is input into the preset energy prediction model to obtain the microseismic energy within 3-6 hours. Since the microseismic energy within 3-5 hours is known, the microseismic energy within 3-5 hours is subtracted from the microseismic energy within 3-6 hours to obtain the microseismic energy within the second preset time period 5-6 hours; secondly, the microseismic energy within 0-6 hours is input into the energy prediction model to obtain the microseismic energy within 4-7 hours. Since the microseismic energy within 4-6 hours is known before, the microseismic energy within 4-7 hours is subtracted from the predicted microseismic energy within 4-6 hours to obtain the microseismic energy within 6-7 hours; finally, the microseismic energy within 0-7 hours is input into the energy prediction model to obtain the microseismic energy within 5-8 hours. Similarly, the microseismic energy within 5-8 hours is subtracted from the known microseismic energy within 5-7 hours to obtain the microseismic energy within 7-8 hours.

[0096] In summary, the microseismic energy in each hour of the second preset time period has been obtained, and the total microseismic energy in the second preset time period can be obtained by adding up the microseismic energy in each hour.

[0097] like Figure 4 As shown, it is a schematic diagram of training and prediction based on the LSTM neural network, wherein the original data is the microseismic energy within the first preset time period. After preprocessing, an energy sequence consisting of microseismic energy corresponding to each preset unit time within the first preset time period is obtained. The energy sequence is trained and predicted separately. During the training process, the loss is calculated based on the predicted energy and the actual energy. The parameters of the network are optimized according to the loss until the calculated loss is minimized. During the prediction process, prediction is performed based on the optimal parameters obtained through training to obtain an energy sequence for each preset step length within the second preset time period.

[0098] Step 103 : predicting location information of a microseismic event occurring within a second preset time period based on the first construction data and the microseismic signal.

[0099] For example, after obtaining the first construction data and microseismic signals within the first preset time period, CNN (Convolutional Neural Networks, CNN for short) is used to predict the location information of the microseismic event occurring within the second preset time period based on the data within the first preset time period.

[0100] Before prediction, the CNN network needs to be trained based on known data. The training process can be to use the microseismic energy and construction data (face position, burial depth, torque, axial force and tunneling speed) within the first preset time period as input data, and the position coordinates and corresponding standard deviations of the microseismic events that actually occurred within the first preset time period as output data. When there is only one microseismic event within the first preset time period, the standard deviation is 0; when there are multiple microseismic events, the standard deviation is the weighted average of the position coordinates according to the microseismic energy, and then the corresponding standard deviation is calculated.

[0101] As shown in the following formula,

[0102]

[0103] Where, is the weighted average of the location coordinates of the microseismic events in the i-th time window, e j is the energy corresponding to the jth microseismic event, x j is the position coordinate corresponding to the jth microseismic event.

[0104] Furthermore, after calculating each possible location coordinate, the polar coordinates with the location coordinate as the origin are normally distributed, and the probability distribution of different location coordinates can be obtained. The probability of occurrence of the corresponding distance around the location coordinate can be further determined, as shown in the following formula:

[0105]

[0106]

[0107] Where x is the spatial coordinate, R is the position relative to the rockburst center. distance, π is the ratio of circumference to circumference, exp() is the exponential function with e as the base, σ i is the weighted standard deviation of the microseismic event coordinates in the i-th time window, which can be calculated based on the 2-norm of the coordinate vector.

[0108] like Figure 5 Figure 1 shows a schematic diagram of CNN training and prediction. CNNs can accept data of varying lengths as input, but they do not restrict the dimensionality of the input data. Therefore, a CNN approach is used to maintain consistent dimensionality of the output data through global pooling. This is then connected to a fully connected layer for data classification. The model consists of one mask layer, six convolutional layers, two max pooling layers, one global average pooling layer, and one fully connected layer.

[0109] Step 104 : Obtain the probability of rock burst and the size of the blast crater based on the total microseismic energy, the location information, and the second construction data.

[0110] For example, after obtaining the total microseismic energy within the second preset time period, the location information of the rockburst, and the construction data (construction plan) within the second preset time period, the probability of rockburst and the size of the crater can be predicted based on these data within the second preset time period.

[0111] In an optional embodiment, if Figure 6 As shown, the preset rockburst prediction model includes a first rockburst prediction model and a second rockburst prediction model. The implementation process of step 104 may include but is not limited to the following method steps:

[0112] Step 1041 : Input the total microseismic energy, location information, and the second construction parameter into a first rockburst prediction model to obtain a first probability of rockburst occurrence.

[0113] For example, the first rockburst prediction model may be a rockburst prediction network based on a BP neural network, such as Figure 7 Figure 2 shows a schematic diagram of a BP neural network. The input data are the energy of the microseismic event, the coordinates of the microseismic location calculated above, and construction data (burial depth, tunnel face position, and tunneling speed). The output data is the probability of a rockburst occurring. This output data can include either a rockburst occurring or no rockburst occurring, with the probability corresponding to no rockburst occurring being 0. The BP neural network has seven input nodes in the input layer and two hidden layers, each containing 100 nodes and using the sigmoid activation function. The output layer has two nodes and uses the softmax activation function.

[0114] Step 1042 , input the total microseismic energy, location information, and second construction data into a second rockburst prediction model to obtain a second probability of rockburst occurrence and a crater size.

[0115] Exemplarily, the second rockburst prediction model can be a rockburst prediction method based on explosion dynamics theory. Using explosion dynamics theory, the total energy of microseismic events, position information, and the second construction parameter are input into the explosion dynamics theory to obtain the second probability of rockburst occurrence and the size of the crater that will be produced by the rockburst.

[0116] Step 1043: Determine the probability of rockburst occurrence based on the first probability, the second probability and a preset weight coefficient.

[0117] For example, the first probability and the second probability are weighted by performing correlation coefficient calculation to obtain the corresponding rock burst occurrence probability, wherein the correlation coefficient weighted calculation can be performed by averaging or other methods.

[0118] Step 105 : Determine whether a rockburst occurs within a second preset time period based on the rockburst probability and the size of the blast crater.

[0119] For example, after obtaining the rock burst probability and the crater size, the relationship table between the rock burst probability, the crater size, and whether a rock burst occurs is used to determine whether a rock burst occurs. After determining whether a rock burst occurs, the corresponding rock burst level can also be obtained. Details are shown in Table 1.

[0120] Table 1

[0121]

[0122]

[0123] Based on the above embodiment, another embodiment of the present invention provides another rockburst prediction method. In this embodiment, the contents already described in the above embodiment will not be repeated. In this embodiment, considering that when it is determined that a rockburst will occur within the second preset time based on the rockburst probability and the crater size, it is necessary to adjust the construction data before actual construction to avoid the rockburst, the method further includes:

[0124] Divide the first excavation speed to generate i second excavation speeds;

[0125] Input the j-th second excavation speed, the data in the second construction data excluding the first excavation speed, and the total microseismic energy and location information into a preset rockburst prediction model to predict the j-th rockburst probability and the j-th blast pit size;

[0126] If it is determined that no rockburst will occur within the second preset time period based on the j-th rockburst probability and the j-th blast pit size, the j-th second excavation speed will be used as the new excavation speed for construction, where i is a positive integer greater than or equal to 2, and j is a positive integer less than or equal to i.

[0127] For example, when the prediction result is that there is a risk of rock burst, the tunneling speed is the main control parameter. For example, when i is 10, the first tunneling speed is the current tunneling speed v c The second excavation speed is divided into 10 numbers according to the first excavation speed [0,v c / 10,2v c / 10,……,9v c / 10], sequentially replacing the tunneling data in the current input data with the second tunneling speed in the sequence. This data, combined with the other construction data except for the tunneling speed, generates 10 sets of constructed input data. This input data is fed into the rockburst prediction model to determine the probability of rockburst. When the rockburst probability indicates no rockburst, the corresponding second tunneling speed is used as the new tunneling speed for construction. If at least two of the 10 tunneling speeds predict no rockburst, the faster of the two tunneling speeds is selected as the new tunneling speed for construction.

[0128] Based on the above embodiment, another embodiment of the present invention provides another rockburst prediction method. In this embodiment, the contents already described in the above embodiment will not be repeated. In this embodiment, when the second preset time period is not a time period adjacent to the first preset time period, a rockburst situation in a future time period is predicted. When the second preset time period is n time periods after the first preset time period, where n is greater than or equal to 2, the method further includes:

[0129] The probability of rockburst occurrence in the n-th preset time period is determined based on the prediction results in the n-1 preset time periods, where n is a positive integer greater than or equal to 2.

[0130] For example, in the above embodiment, the prediction is always made for the second preset time period adjacent to the first preset time period. When the second preset time period is separated from the first preset time period by n n-th preset time periods, for the n-th preset time period, a total of n-1 prediction results can be obtained from the first preset time period to the n-1-th preset time period. The n-1 prediction results are combined with the Bayesian theory to obtain the probability of rockburst occurrence in the corresponding n-th prediction time period.

[0131] Specifically, let event A = {rock burst occurs}, event B = {prediction result is [0,1]}, event When the prediction result is [0,1], the actual probability of rock burst is,

[0132]

[0133] Where P() represents the event probability; P(B|A) is the probability that a rock burst occurs but the predicted result is [0, 1]; The probability that no rock burst occurs is [0,1]; P(B|A), The performance of the reaction model can be obtained based on the training and testing data of the rockburst possibility judgment model, for example,

[0134]

[0135]

[0136] Among them, N 11 , N 01 , N 10 , N 10 The representative contents are shown in Table 2.

[0137] Table 2

[0138]

[0139] When the prediction result is [1,0], the probability of rock burst is,

[0140]

[0141] in, is the probability of rock burst occurrence, and the prediction result is [0,1]; The probability that no rock burst occurs is [0,1]; The performance of the same reaction model can be derived based on the training and testing data of the rockburst possibility judgment model, as shown in the following formula:

[0142]

[0143]

[0144] As the prediction results are continuously updated, the probability of rock burst within a certain time period and the corresponding energy, location information, and blast pit size can be given in real time, so as to formulate targeted rock burst protection plans.

[0145] like Figure 8 The figure shows an overall schematic diagram of the rockburst prediction method of this application. First, a database of microseismic events and a database of construction parameters are established. Second, based on these two databases, the microseismic energy and location information of the microseismic events within a second preset time period are predicted. Third, based on the microseismic energy and location information and the construction data within the second preset time period, the probability of rockburst and the corresponding crater size are predicted. Finally, the probability of rockburst occurrence and crater size are determined based on the rockburst probability and crater size. Similarly, rockburst prediction within the nth preset time period can be performed using Bayesian theory.

[0146] In this way, the construction data and the microseismic signals of the construction tunnel within the first preset time period are obtained. The construction data and the microseismic signals can be combined in the process of predicting rockburst, thereby making the rockburst prediction result more accurate. Furthermore, based on the microseismic signals within the first preset time period, the total microseismic energy within the second preset time period is predicted; based on the first construction data and microseismic signals within the first preset time period, the location information of the time when the microseism occurred within the second preset time period is predicted. Based on the actual data collected within the first preset time period, the data within the second preset time period can be truly and effectively predicted. Finally, after the total microseismic energy and location information within the second preset time period are predicted, the probability of rockburst occurrence within the second preset time period is predicted based on the construction data, total microseismic energy and location information within the second preset time period, and the probability of rockburst occurrence within the second preset time period can be accurately obtained.

[0147] The above are embodiments of the rockburst prediction method provided in the present application. Other embodiments of the rockburst prediction method provided in the present application are described below. Please refer to the following for details.

[0148] The embodiment of the present invention also discloses a rock burst prediction device, such as Figure 9 As shown, the device includes:

[0149] An acquisition module 901 is configured to acquire construction data and a microseismic signal of a tunnel under construction within a first preset time period, wherein the construction data includes first construction data within the first preset time period and second construction data within a second preset time period;

[0150] A first prediction module 902 is configured to predict the total microseismic energy within a second preset time period based on the microseismic signal, where the second preset time period is a time period subsequent to the first preset time period;

[0151] A second prediction module 903 is configured to predict location information of a microseismic event occurring within a second preset time period based on the first construction data and the microseismic signal;

[0152] The third prediction module 904 is used to obtain the probability of rock burst and the size of the blast crater based on the total microseismic energy, location information, and the second construction data;

[0153] The judgment module 905 is used to determine whether a rock burst occurs within a second preset time period according to the rock burst occurrence probability and the size of the blast crater.

[0154] In an optional embodiment, the construction data further includes a first excavation speed. When the judgment module determines that a rock burst will occur within the second preset time, the device is further configured to perform the following steps:

[0155] Divide the first excavation speed to generate i second excavation speeds;

[0156] Input the j-th second excavation speed, the data in the second construction data excluding the first excavation speed, and the total microseismic energy and location information into a preset rockburst prediction model to predict the j-th rockburst probability and the j-th blast pit size;

[0157] If it is determined that no rockburst will occur within the second preset time period based on the j-th rockburst probability and the j-th blast pit size, the j-th second excavation speed will be used as the new excavation speed for construction, where i is a positive integer greater than or equal to 2, and j is a positive integer less than or equal to i.

[0158] As an optional embodiment of the present invention, the first prediction module is specifically configured to perform:

[0159] determining characteristic data of the microseismic signal according to the microseismic signal;

[0160] After the characteristic data is input into a preset energy prediction model, the total energy of the microseismic event within a second preset time period is predicted.

[0161] As an optional embodiment of the present invention, the first prediction module is further configured to execute:

[0162] After the characteristic data is input into a preset energy prediction model, the total microseismic energy within the second preset time period is predicted, specifically including:

[0163] When the second preset time period includes only one preset unit time, the characteristic data in the first preset time period is input into a preset energy prediction model to predict the microseismic energy in the second preset time period;

[0164] or,

[0165] When the second preset time period includes at least two unit times, the microseismic energy corresponding to the next unit time in the second preset time period is predicted based on the characteristic data in the first preset time period, the microseismic energy corresponding to the current unit time in the second preset time period, and the preset energy prediction model, wherein, when the current unit time is the first unit time in the second preset time period, the microseismic energy corresponding to the current unit time is the characteristic data in the first preset time period, which is input into the preset energy prediction model and predicted;

[0166] The total microseismic energy in the second preset time period is obtained according to the microseismic energies corresponding to all unit times in the second preset time period.

[0167] As an optional embodiment of the present invention, the preset rockburst prediction model includes a first rockburst prediction model and a second rockburst prediction model, and a judgment module, specifically configured to execute:

[0168] Inputting the total microseismic energy, location information, and the second construction parameter into a first rockburst prediction model to obtain a first probability of rockburst occurrence;

[0169] Inputting the total microseismic energy, location information, and second construction data into a second rockburst prediction model to obtain a second probability of rockburst occurrence and a crater size;

[0170] The probability of rockburst occurrence is determined based on the first probability, the second probability and a preset weight coefficient.

[0171] As an optional embodiment of the present invention, when the second preset time period is n time periods after the first preset time period, where n is greater than or equal to 2, the apparatus is further configured to perform:

[0172] According to the prediction results in n-1 preset time periods and Bayesian theory, the probability of rock burst occurring in the nth preset time period is determined.

[0173] The functions performed by the various components in the rockburst prediction device provided by the embodiment of the present invention have been described in detail in any of the above method embodiments, and therefore will not be repeated here.

[0174] By executing this device, construction data and microseismic signals of the construction tunnel within the first preset time period are obtained. The construction data and microseismic signals can be combined in the process of predicting rockburst, thereby making the rockburst prediction result more accurate. Furthermore, based on the microseismic signals within the first preset time period, the total microseismic energy within the second preset time period is predicted; based on the first construction data and microseismic signals within the first preset time period, the location information of the time when the microseism occurred within the second preset time period is predicted. Based on the actual data collected within the first preset time period, the data within the second preset time period can be truly and effectively predicted. Finally, after predicting the total microseismic energy and location information within the second preset time period, the probability of rockburst occurrence within the second preset time period is predicted based on the construction data, total microseismic energy and location information within the second preset time period, and the probability of rockburst occurrence within the second preset time period can be accurately obtained.

[0175] The embodiment of the present invention also provides a computer device, such as Figure 10 As shown, the computer device may include a processor 1001 and a memory 1002, wherein the processor 1001 and the memory 1002 may be connected via a bus or other means. Figure 10 The bus connection is taken as an example.

[0176] The processor 1001 may be a central processing unit (CPU). The processor 1001 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0177] Memory 1002, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the rockburst prediction method in the embodiments of the present invention. Processor 1001 executes the non-transitory software programs, instructions, and modules stored in memory 1002 to perform various processor functions and data processing, thereby implementing the rockburst prediction method in the above-mentioned method embodiments.

[0178] The memory 1002 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created by the processor 1001, etc. In addition, the memory 1002 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 1002 may optionally include a memory remotely located relative to the processor 1001, and these remote memories may be connected to the processor 1001 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0179] One or more modules are stored in the memory 1002 and when executed by the processor 1001, the execution is as follows: Figure 1 The rockburst prediction method in the illustrated embodiment.

[0180] For details of the above computer equipment, please refer to Figure 1 The corresponding descriptions and effects in the embodiments shown can be understood and will not be repeated here.

[0181] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD). The storage medium can also include a combination of the above-mentioned types of memory.

[0182] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A rockburst prediction method, characterized in that: The method comprises: Acquiring construction data and a microseismic signal of a tunnel under construction within a first preset time period, wherein the construction data includes first construction data within the first preset time period and second construction data within a second preset time period; predicting the total microseismic energy within a second preset time period according to the microseismic signal, where the second preset time period is a time period after the first preset time period; Predicting location information of a microseismic event occurring within the second preset time period based on the first construction data and the microseismic signal; Obtaining a rockburst probability and a blast crater size based on the total microseismic energy, the location information, and the second construction data; Whether a rockburst occurs within the second preset time period is determined according to the rockburst occurrence probability and the blast crater size.

2. The method according to claim 1, characterized in that The construction data further includes a first excavation speed. When it is determined, based on the rockburst probability and the blast pit size, that a rockburst will occur within the second preset time, the method further includes: Dividing the first excavation speed to generate i second excavation speeds; Inputting the jth second excavation speed, data of the second construction data other than the first excavation speed, the total microseismic energy, and the location information into a preset rockburst prediction model to predict the jth rockburst probability and the jth blast crater size; If it is determined that no rockburst occurs within the second preset time period based on the j-th rockburst probability and the j-th blast pit size, the j-th second excavation speed will be used as the new excavation speed for construction, where i is a positive integer greater than or equal to 2, and j is a positive integer less than or equal to i.

3. The method according to claim 1 or 2, characterized in that The predicting of the total microseismic energy within the second preset time period according to the microseismic signal specifically includes: determining characteristic data of the microseismic signal according to the microseismic signal; After the characteristic data is input into a preset energy prediction model, the total energy of the microseismic event within the second preset time period is predicted.

4. The method according to claim 3, characterized in that After inputting the characteristic data into a preset energy prediction model, predicting the total microseismic energy within the second preset time period specifically includes: When the second preset time period includes only one preset unit time, the characteristic data in the first preset time period is input into a preset energy prediction model to predict the microseismic energy in the second preset time period; or, When the second preset time period includes at least two unit times, the microseismic energy corresponding to the next unit time in the second preset time period is predicted based on the characteristic data in the first preset time period, the microseismic energy corresponding to the current unit time in the second preset time period, and the preset energy prediction model, wherein, when the current unit time is the first unit time in the second preset time period, the microseismic energy corresponding to the current unit time is the characteristic data in the first preset time period, which is input into the preset energy prediction model and predicted; The total microseismic energy in the second preset time period is obtained according to the microseismic energies corresponding to all unit times in the second preset time period.

5. The method according to claim 2, characterized in that The preset rockburst prediction model includes a first rockburst prediction model and a second rockburst prediction model. Obtaining the rockburst probability and crater size based on the total microseismic energy, the location information, and the second construction data specifically includes: Inputting the total microseismic energy, the location information, and the second construction data into a first rockburst prediction model to obtain a first probability of the rockburst occurring; Inputting the total microseismic energy, the location information, and the second construction data into a second rockburst prediction model to obtain a second probability of rockburst occurrence and a crater size; The rockburst occurrence probability is determined based on the first probability and the second probability.

6. The method according to claim 5, characterized in that When the second preset time period is the nth time period after the first preset time period, where n is greater than or equal to 2, the method further includes: The probability of rockburst occurrence in the n-th preset time period is determined based on the prediction results in the n-1 preset time periods, where n is a positive integer greater than or equal to 2.

7. A rockburst prediction device, characterized in that: include: an acquisition module, configured to acquire construction data and a microseismic signal of a tunnel under construction within a first preset time period, wherein the construction data includes first construction data within the first preset time period and second construction data within a second preset time period; a first prediction module, configured to predict the total microseismic energy within a second preset time period based on the microseismic signal, where the second preset time period is a time period subsequent to the first preset time period; a second prediction module, configured to predict location information of a microseismic event occurring within the second preset time period based on the first construction data and the microseismic signal; a third prediction module, configured to obtain a rockburst probability and a crater size based on the total microseismic energy, the location information, and the second construction data; The judgment module is used to determine whether a rock burst occurs within the second preset time period according to the rock burst occurrence probability and the size of the blast crater.

8. The device according to claim 7, characterized in that The construction data further includes a first excavation speed, and the device further includes: a division module, configured to divide the first excavation speed to generate i second excavation speeds; a fourth prediction module, configured to input the j-th second excavation speed, data of the second construction data other than the first excavation speed, the total microseismic energy, and the location information into a preset rockburst prediction model to predict the j-th rockburst probability and the j-th blast crater size; A determination module is configured to, if it is determined based on the j-th rockburst probability and the j-th blast pit size that no rockburst occurs within the second preset time period, use the j-th second excavation speed as the new excavation speed for construction, where i is a positive integer greater than or equal to 2, and j is a positive integer less than or equal to i.

9. A computer device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the rockburst prediction method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the rockburst prediction method according to any one of claims 1 to 6 are implemented.

Images