Oil gas microwave electric pulse resonance impact synergistic production increasing control system

Abstract

The invention discloses an oil gas microwave electric pulse resonance impact collaborative production increase control system, which comprises a vibration response acquisition module and a vibration response input module, which are used for inputting a vibration response sequence into a pre-trained resonance frequency extraction model; the main resonance frequency determination module is used for performing main resonance frequency identification on the vibration response sequence through a resonance frequency extraction model and determining the main resonance frequency of the target shale bed; the electric pulse adjusting module is used for adjusting the output frequency of the electric pulse excitation device according to the determined main resonant frequency until the output frequency is consistent with the main resonant frequency; according to the method, the main resonant frequency extracted from the frequency amplitude distribution diagram is used as a pseudo label, the multi-layer perceptron model is used for training, the main resonant frequency of the stratum is automatically learned under the condition that manual labeling or external experience input is not needed, the fitting capability of a nonlinear response mode of the complex stratum is effectively improved, and the accuracy of the model is improved. And the identification accuracy of the main resonance frequency is enhanced.

Description

Technical Field

[0001] The invention relates to an oil and gas production increase control system, in particular to an oil and gas microwave electric pulse resonance shock coordinated production increase control system. Background Art

[0002] For the effective development of tight oil and gas reservoirs such as shale, physical production enhancement technologies such as electric pulse excitation and microwave heating are often used. Electric pulse excitation technology induces stress waves and electromagnetic interference in the formation by applying high-frequency and high-voltage electric pulses, thereby enhancing the expansion of primary fractures and promoting the flow of oil and gas; while microwave heating technology uses electromagnetic energy to convert into thermal energy, so that the temperature of the oil layer increases and the viscosity of crude oil decreases, thereby improving the permeability. Studies have shown that the combination of the two can significantly improve the production efficiency under the synergistic effect of force and heat. However, the effect of electric pulse excitation is highly dependent on the consistency of the excitation frequency and the natural resonance frequency of the formation. Only when the excitation frequency accurately matches the main resonance frequency can the maximum vibration coupling and fracture resonance expansion be induced inside the shale. Patent document with patent publication number CN110485959B discloses a shale oil and gas microwave resonance shock synergistic production enhancement technology method, which combines the advantages of electromagnetic wave heating production enhancement technology and spectrum resonance shock production enhancement technology, superimposes high-energy shock waves with the inherent frequency of the target reservoir on the basis of electromagnetic wave heating, and has the characteristics of low pollution and low energy consumption.

[0003] However, in the above patented technology and the prior art, fixed frequency excitation or frequency scanning based on manual experience is usually used to find the main resonance frequency. Such methods are not only inefficient and computationally intensive, but also easily interfered by complex geological conditions, resulting in inaccurate identification of the main resonance frequency, which in turn affects the coupling strength and resonance efficiency of the electric pulse excitation. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides an oil and gas microwave electric pulse resonance shock collaborative production increase control system, which learns the main resonance frequency through self-supervised training to solve the technical problems raised in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an oil and gas microwave electric pulse resonance shock coordinated production increase control system, comprising: The vibration response acquisition module is used to acquire the vibration response sequence fed back by the target shale layer within the time window.

[0006] The vibration response input module is used to input the vibration response sequence into a pre-trained resonance frequency extraction model.

[0007] The main resonance frequency determination module is used to identify the main resonance frequency of the vibration response sequence using the resonance frequency extraction model to determine the main resonance frequency of the target shale layer.

[0008] The electric pulse regulating module is used to regulate the output frequency of the electric pulse excitation device according to the determined main resonance frequency until the output frequency is consistent with the main resonance frequency.

[0009] In some embodiments, the pre-training step of the resonance frequency extraction model includes: A1. Obtain a pseudo-label training set containing N two-tuple sample pairs; the target labels of the two-tuple sample pairs are pseudo-labels extracted from the frequency-amplitude distribution diagram.

[0010] A2. Extract the binary sample pairs of the current batch from the pseudo-label training set, input them into the multi-layer perceptron model for self-supervised training, and output the predicted frequency of the current batch.

[0011] A3. Based on the set self-supervised training loss function, calculate the error loss between the predicted frequency and pseudo-label of the current batch, and perform backpropagation to update the model parameters.

[0012] A4. After the model parameters are updated, determine whether the current model meets the preset convergence conditions.

[0013] A5. If satisfied, terminate the self-supervised training. Otherwise, repeat A2 to A4 until the current model meets the convergence conditions.

[0014] A4. If the model convergence condition is reached, stop minimizing the error loss between the prediction frequency and pseudo-label of the current batch; otherwise, update the model parameters with the preset learning rate to generate updated parameters.

[0015] A5. Repeat A2 to A3 according to the updated parameters until the model converges.

[0016] In some of the embodiments, obtaining a pseudo-label training set containing N bigram sample pairs includes: A1-1. Obtain the vibration response sequence fed back by the target shale layer in N time windows.

[0017] A1-2. According to the vibration response sequence fed back in each time window, a time-frequency diagram in the time window is constructed.

[0018] A1-3. Construct a frequency amplitude distribution diagram based on the time-frequency diagram within the time window.

[0019] A1-4. Select the main resonance frequency in the frequency amplitude distribution diagram.

[0020] A1-5. Define the vibration response sequence as an input vector, define the main resonance frequency as a pseudo label, and generate the binary sample pair.

[0021] A1-6. Repeat A1-2 to A1-5 until a pseudo-label training set containing N two-tuple sample pairs is obtained.

[0022] In some of the embodiments, obtaining a vibration response sequence fed back by a target shale layer in N time windows includes: A1-1-1. Anchor the target shale layer and its N excitation frequencies.

[0023] A1-1-2. According to the excitation frequency, preset the output frequency of the electric pulse excitation device.

[0024] A1-1-3. Use an electric pulse excitation device with a preset output frequency to transmit the excitation frequency to the target shale layer.

[0025] A1-1-4. Collect several vibrations of the target shale layer corresponding to the excitation frequency and arrange them in chronological order as a vibration response sequence.

[0026] A1-1-5. Repeat A1-1-2 to A-1-4 to obtain N groups of vibration response sequences with different excitation frequencies.

[0027] In some of the embodiments, constructing a time-frequency diagram within a time window according to the vibration response sequence fed back within each time window includes: A1-2-1. Divide the time window covered by each vibration response sequence into several time sub-windows.

[0028] A1-2-2. Perform short-time Fourier transform on the vibration response of each time sub-window to obtain the frequency energy distribution of the time sub-window.

[0029] The frequency energy distribution is characterized as follows: within a given time subwindow, a set of frequency components are obtained after short-time Fourier transform, and the amplitude of each frequency component within the time subwindow; the amplitude is used to represent the response intensity of the corresponding frequency component within the time subwindow.

[0030] A1-2-3. Splice the frequency energy distribution of each time sub-window in chronological order to construct a time-frequency diagram within the time window.

[0031] The horizontal axis of the time-frequency diagram is the time sub-window, and the vertical axis is the frequency energy distribution corresponding to the time sub-window. The frequency energy distribution is the distribution of several frequency components in the time sub-window.

[0032] In some of the embodiments, constructing a frequency amplitude distribution diagram according to the time-frequency diagram within the time window includes: A1-3-1. In the time-frequency diagram, extract the amplitude sequence of each frequency component in all time sub-windows.

[0033] A1-3-2. Perform mean calculation on the amplitude sequence of each frequency component in all time sub-windows to obtain the average amplitude of each frequency component.

[0034] A1-3-3. Obtain the average amplitude of all frequency components.

[0035] A1-3-4. With the frequency component as the horizontal axis and the average amplitude of each frequency component as the vertical axis, determine several frequency amplitude points.

[0036] A1-3-5. Connect several frequency amplitude points to generate a frequency amplitude curve to construct a frequency amplitude distribution diagram.

[0037] The frequency amplitude distribution diagram is used to characterize the energy concentration degree of each frequency component during the vibration response process.

[0038] In some of the embodiments, selecting a main resonant frequency in the frequency amplitude distribution diagram comprises: A1-4-1. Mark all amplitude peaks of the frequency amplitude curve in the frequency amplitude distribution diagram .

[0039] A1-4-2. Starting from the marked amplitude peak, search along the left and right sides of the frequency-amplitude curve for the left half frequency point and the right half frequency point that are lower than half of the amplitude peak for the first time.

[0040] A1-4-3. Calculate the distance between the left half frequency point and the right half frequency point, and define the distance as the half-height width of the amplitude peak. .

[0041] A1-4-4. Traverse the entire frequency-amplitude curve to obtain the half-widths corresponding to K corresponding amplitude peaks.

[0042] A1-4-5. Calculate the energy concentration of each frequency component according to the half-widths of the K corresponding amplitude peaks to obtain K energy concentrations.

[0043] The calculation expression of the energy concentration is: .

[0044] in, represents the energy concentration of the i-th frequency component, represents the half-height width of the ith frequency component, represents the peak amplitude of the i-th frequency component, The normalized amplitude weight of the i-th peak is used to dynamically balance the influence weights of the half-width and amplitude; represents the regularization constant to prevent the denominator from dividing by zero. represents the slope smoothing term.

[0045] A1-4-6. Select the frequency component corresponding to the minimum concentration from the K energy concentrations, and define the frequency component as the main resonant frequency.

[0046] In some of the embodiments, the target loss of the self-supervised training loss function is mean square error loss or Huber loss.

[0047] In some embodiments, the convergence condition is: when the model satisfies any of the following conditions in several consecutive rounds of training, it is determined to be converged, including:

[0048] The error loss of the current batch is lower than the preset error threshold.

[0049] The error loss change of the model within M consecutive training cycles is less than the set change threshold ε.

[0050] The number of training rounds reaches the preset maximum number of iterations.

[0051] In some of the embodiments, the control system also includes: a microwave adjustment module for adjusting the output frequency of the microwave emitting device so that the adjusted output frequency is within the shale layer absorption frequency band; and a module for adjusting the microwave action duration and penetration depth of the wave emitting device.

[0052] The present invention provides an oil and gas microwave electric pulse resonance shock coordinated production increase control system, which has the following beneficial effects: The present invention uses self-supervised training constructed by vibration response sequence and pseudo-label frequency, uses the main resonance frequency extracted from the frequency amplitude distribution diagram as the pseudo-label, and performs training with a multi-layer perceptron model, thereby automatically learning the main resonance frequency of the formation without manual labeling or external experience input, effectively improving the fitting ability of the nonlinear response mode of complex formations and enhancing the accuracy of main resonance frequency recognition.

[0053] Furthermore, by integrating the half-width with the peak amplitude and the energy concentration of the frequency slope, the main resonant frequency can be accurately screened from the frequency amplitude distribution diagram. This energy concentration quantifies the concentration of frequency components and the sharpness of the response, avoiding the misidentification problem caused by unstable response amplitude or noise interference in traditional methods, and can more effectively distinguish the main resonant frequency from the non-main frequency response, thereby improving the reliability of frequency extraction. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a structural block diagram of an oil and gas microwave electric pulse resonance shock coordinated production increase control system of the present invention.

[0055] Figure 2The present invention is a control flow chart of an oil and gas microwave electric pulse resonance shock coordinated production increase control system.

[0056] Figure 3 It is a schematic diagram of the process of defining the main resonance frequency of the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] Example 1: Please refer to Figure 1 to Figure 2 The present invention provides an oil and gas microwave electric pulse resonance shock coordinated production increase control system, the control system includes: a vibration response acquisition module, which is used to collect the vibration response sequence fed back by the target shale layer within a time window.

[0059] Exemplarily, the vibration response sequence is collected by a three-axis vibration sensor deployed underground under tentative electrical pulse excitation conditions to record the formation response of the target shale layer in three directions of X, Y, and Z, with each direction corresponding to an independent time series.

[0060] In one embodiment of the present invention, the vibration response sequence refers to the three-axis acceleration continuously acquired at a fixed sampling frequency within a set time window, forming a three-channel time series matrix with a structure of three rows and N columns, which is used to characterize the dynamic response behavior of the target shale layer under electric pulse excitation.

[0061] The vibration response input module is used to input the vibration response sequence into a pre-trained resonance frequency extraction model.

[0062] The main resonance frequency determination module is used to identify the main resonance frequency of the vibration response sequence using the resonance frequency extraction model to determine the main resonance frequency of the target shale layer.

[0063] The electric pulse regulating module is used to regulate the output frequency of the electric pulse excitation device according to the determined main resonance frequency until the output frequency is consistent with the main resonance frequency.

[0064] The control system further comprises: The microwave adjustment module is used to adjust the output frequency of the microwave launch device so that the adjusted output frequency is within the absorption frequency band of the shale layer, so as to enhance the energy deposition efficiency of microwaves in the formation. It is also used to adjust the microwave action duration and penetration depth of the microwave launch device so that the microwave energy fully covers the target reservoir area in the shale layer and the oil layer temperature reaches the viscosity reduction threshold, thereby synergistically improving the fluidity of oil and gas and the ability of fracture expansion, enhancing the resonance fracture effect of electric pulse excitation, and realizing the synergistic production increase effect of microwave heating and electric pulse shock.

[0065] In this embodiment, by inputting the three-axis vibration response sequence of the target shale layer under the tentative electric pulse excitation into the pre-trained resonance frequency extraction model, the optimal main resonance frequency can be quickly identified, so that the output frequency of the electric pulse excitation device is accurately matched with the natural resonance frequency of the shale layer, thereby improving the effectiveness of the resonance excitation. After the matching is completed, by adjusting the output frequency of the microwave transmitting device to the absorption band of the shale layer, and combining the control of the microwave action time and penetration depth, the microwave thermal effect is fully covered in the shale reservoir, prompting the oil layer temperature to reach the critical point of viscosity reduction, which helps to improve the fluidity of crude oil and reduce the toughness of the reservoir, thereby enhancing the fracture triggering strength of the electric pulse excitation, and finally achieving the goal of coordinated production control.

[0066] Embodiment 2: The technical solution of Embodiment 2 is different from that of Embodiment 1 in that a pre-training step of the resonance frequency extraction model in Embodiment 1 is disclosed, and the pre-training step includes: A1. Obtain a pseudo-label training set containing N two-tuple sample pairs; the target labels of the two-tuple sample pairs are pseudo-labels extracted from the frequency-amplitude distribution diagram.

[0067] A2. Extract the binary sample pairs of the current batch from the pseudo-label training set, input them into the multi-layer perceptron model for self-supervised training, and output the predicted frequency of the current batch.

[0068] A3. Based on the set self-supervised training loss function, calculate the error loss between the predicted frequency and pseudo-label of the current batch, and perform backpropagation to update the model parameters.

[0069] A4. After the model parameters are updated, determine whether the current model meets the preset convergence conditions.

[0070] A5. If satisfied, terminate the self-supervised training. Otherwise, repeat A2 to A4 until the current model meets the convergence conditions.

[0071] A4. If the model convergence condition is reached, stop minimizing the error loss between the prediction frequency and pseudo-label of the current batch; otherwise, update the model parameters with the preset learning rate to generate updated parameters.

[0072] A5. Repeat A2 to A3 according to the updated parameters until the model converges.

[0073] In this embodiment, a binary pseudo-label training set consisting of a vibration response sequence and a main resonance frequency is constructed for the main resonance frequency identification task, and self-supervised training is carried out based on a multi-layer perceptron (MLP) model. This training mechanism can efficiently fit the nonlinear mapping relationship between the shale layer response sequence and the main frequency in the absence of manual labeling.

[0074] Exemplarily, in step A1, the step of obtaining the pseudo-label training set is: A1-1. Obtain the vibration response sequence fed back by the target shale layer in N time windows.

[0075] For example, in the data construction stage of model pre-training, the system controls the electric pulse excitation device to sequentially excite the target shale layer at a set frequency, and the three-axis vibration sensor deployed downhole synchronously collects the response signal. The sensor continuously records the vibration acceleration data in the three directions of X, Y, and Z within the set time window at a fixed sampling frequency to form a three-channel time series sample. Each group of samples is associated with its corresponding excitation frequency.

[0076] A1-2. According to the vibration response sequence fed back in each time window, a time-frequency diagram in the time window is constructed.

[0077] A1-3. Construct a frequency amplitude distribution diagram based on the time-frequency diagram within the time window.

[0078] A1-4. Select the main resonance frequency in the frequency amplitude distribution diagram.

[0079] A1-5. Define the vibration response sequence as an input vector, define the main resonance frequency as a pseudo label, and generate the binary sample pair.

[0080] A1-6. Repeat A1-2 to A1-5 until a pseudo-label training set containing N two-tuple sample pairs is obtained.

[0081] In this embodiment, by systematically collecting the triaxial vibration response sequence of the target shale layer at different excitation frequencies, and combining short-time Fourier transform to construct a time-frequency diagram, and then extracting the main resonance frequency as a pseudo-label based on the frequency amplitude distribution diagram, high-quality training data generation without manual annotation is achieved. This construction process is based on the real response of the shale layer, ensuring that the pseudo-label frequency has formation structure sensitivity, and realizing high-confidence automatic generation of frequency pseudo-labels under unsupervised conditions.

[0082] Furthermore, the A1-1 step specifically includes: A1-1-1. Anchor the target shale layer and its N excitation frequencies.

[0083] A1-1-2. According to the excitation frequency, preset the output frequency of the electric pulse excitation device.

[0084] A1-1-3. Use an electric pulse excitation device with a preset output frequency to transmit the excitation frequency to the target shale layer.

[0085] A1-1-4. Collect several vibrations of the target shale layer corresponding to the excitation frequency and arrange them in chronological order as a vibration response sequence.

[0086] A1-1-5. Repeat A1-1-2 to A-1-4 to obtain N groups of vibration response sequences with different excitation frequencies.

[0087] In this embodiment, by anchoring the target shale layer and applying the set N excitation frequencies in sequence, combined with the frequency preset of the electric pulse excitation device and the dynamic acquisition of the formation response, multiple sets of vibration response sequences corresponding to different excitation conditions can be systematically constructed. This acquisition process ensures the consistency of the sample source and the comprehensiveness of the frequency coverage.

[0088] Furthermore, the A1-2 step specifically includes: A1-2-1. Divide the time window covered by each vibration response sequence into several time sub-windows.

[0089] A1-2-2. Perform short-time Fourier transform on the vibration response of each time sub-window to obtain the frequency energy distribution of the time sub-window.

[0090] The frequency energy distribution is characterized as follows: within a given time subwindow, a set of frequency components are obtained after short-time Fourier transform, and the amplitude of each frequency component within the time subwindow; the amplitude is used to represent the response intensity of the corresponding frequency component within the time subwindow.

[0091] A1-2-3. Splice the frequency energy distribution of each time sub-window in chronological order to construct a time-frequency diagram within the time window.

[0092] The horizontal axis of the time-frequency diagram is the time sub-window, and the vertical axis is the frequency energy distribution corresponding to the time sub-window. The frequency energy distribution is the distribution of several frequency components in the time sub-window.

[0093] In an embodiment of the present invention, the system sets a sliding analysis window for the complete vibration response sequence, and performs a short-time Fourier transform in each window to obtain the frequency energy distribution of the time segment; the spectrum results of all windows are integrated into a complete time-frequency diagram according to the time series, wherein the horizontal axis represents time and the vertical axis represents frequency components. The amplitude of each point in the diagram represents the energy intensity of a certain frequency component in a specific time window, which is used to characterize the multi-frequency response characteristics of the formation.

[0094] Furthermore, the A1-3 step specifically includes: A1-3-1. In the time-frequency diagram, extract the amplitude sequence of each frequency component in all time sub-windows.

[0095] A1-3-2. Perform mean calculation on the amplitude sequence of each frequency component in all time sub-windows to obtain the average amplitude of each frequency component.

[0096] A1-3-3. Obtain the average amplitude of all frequency components.

[0097] A1-3-4. With the frequency component as the horizontal axis and the average amplitude of each frequency component as the vertical axis, determine several frequency amplitude points.

[0098] A1-3-5. Connect several frequency amplitude points to generate a frequency amplitude curve to construct a frequency amplitude distribution diagram.

[0099] The frequency amplitude distribution diagram is used to characterize the energy concentration degree of each frequency component during the vibration response process.

[0100] In this embodiment, by performing statistical mean processing on the amplitude of each frequency component in the time subwindow in the time-frequency diagram and constructing a frequency amplitude distribution diagram, the time disturbance factor in the formation response can be effectively removed, and the steady-state characteristics reflecting the intensity of the formation frequency response can be extracted. The frequency amplitude distribution diagram uses frequency as the horizontal axis and the average amplitude as the vertical axis to intuitively present the energy contribution of each frequency component in the entire response process.

[0101] Further, see Figure 3 , the A1-4 steps specifically also include: A1-4-1. Mark all amplitude peaks of the frequency amplitude curve in the frequency amplitude distribution diagram .

[0102] Exemplarily, a local maximum detection algorithm may be used to determine, in the frequency amplitude curve, a turning point where adjacent frequency points increase on the left and decrease on the right as an amplitude peak.

[0103] A1-4-2. Starting from the marked amplitude peak, search along the left and right sides of the frequency-amplitude curve for the left half frequency point and the right half frequency point that are lower than half of the amplitude peak for the first time.

[0104] A1-4-3. Calculate the distance between the left half frequency point and the right half frequency point, and define the distance as the half-height width of the amplitude peak. .

[0105] A1-4-4. Traverse the entire frequency-amplitude curve to obtain the half-widths corresponding to K corresponding amplitude peaks.

[0106] A1-4-5. Calculate the energy concentration of each frequency component according to the half-widths of the K corresponding amplitude peaks to obtain K energy concentrations.

[0107] The calculation expression of the energy concentration is: .

[0108] in, Indicates the energy concentration of the i-th frequency component, which is used to compare multiple frequency peaks. The smaller the energy concentration, the more likely the frequency component is to be the main resonant frequency. represents the half-height width of the ith frequency component, which indicates the width of the energy distribution of that frequency (the smaller the more concentrated), represents the peak amplitude of the i-th frequency component, indicating the response intensity of the frequency (the larger the more obvious), The normalized amplitude weight of the i-th peak is used to dynamically balance the influence weights of the half-height width and the amplitude. In this embodiment, the normalized amplitude weight can adopt a minimum-maximum scaling method; represents the regularization constant to prevent the denominator from dividing by zero. Represents the slope smoothing term, which is used to prevent the amplitude / width ratio from being 0 and maintain the continuity of concentration.

[0109] Specifically, the calculation expression of energy concentration consists of two parts. The first part is , represents power adaptive weighting. Big means strong peak, emphasizing the importance of amplitude → the denominator becomes larger and the score becomes smaller (tends to retain strong peaks); Small means weak peaks, emphasizing half-width penalty → the numerator becomes larger, the score becomes larger (tends to exclude wide and weak peaks); through power adaptive weighting, dynamically balance "amplitude vs concentration". Part 2 represents the slope penalty factor, where It is the unit width slope of the frequency peak (i.e. "sharpness"), the sharper (larger slope) → large denominator → small score (better), the flatter (smaller slope → small denominator → large score (penalty).

[0110] A1-4-6. Select the frequency component corresponding to the minimum concentration from the K energy concentrations, and define the frequency component as the main resonant frequency.

[0111] In other words, the energy concentration comprehensively considers the frequency amplitude, half-width and sharpness, adaptively adjusts the influence of each parameter through the normalized amplitude weight, and combines the peak slope index to finally select the frequency corresponding to the lowest concentration as the main frequency.

[0112] In this embodiment, by extracting the amplitude peak in the frequency amplitude distribution diagram and calculating its half-height width, combined with energy concentration, a comprehensive quantitative evaluation of multiple frequency components in three dimensions of energy concentration, amplitude intensity and response sharpness is achieved. Compared with the traditional main frequency extraction method that only selects based on peak amplitude, this method balances the influence between width and height through normalized weights, and introduces frequency slope as an auxiliary indicator of distribution sharpness, which can effectively suppress the interference of wide and weak disturbance peaks in the formation response, accurately identify the frequency components that are most concentrated in the resonance response, and provide highly reliable pseudo-labels for self-supervised training.

[0113] In the above embodiment 2, the target loss of the self-supervised training loss function is mean square error loss or Huber loss.

[0114] Specifically, the mean square error loss can square the frequency prediction error, thereby producing a stronger penalty effect on the prediction results with large deviations during the training process; while the Huber loss (smoothed L1 loss) appears in the form of mean square error when the error is small, and degenerates into a linear penalty when the error is large, thereby maintaining error sensitivity while having a stronger ability to resist outliers; compared with the two, the Huber loss is more robust in actual collected data with geological anomalies or sensor interference, while the mean square error can achieve faster convergence and higher accuracy under high-quality pseudo-label training samples, and can be selected according to the quality of training data and model tuning strategy.

[0115] The model convergence condition in Example 2 is: when the model meets any of the following conditions in several consecutive rounds of training, it is determined to be converged, including:

[0116] The error loss of the current batch is lower than the preset error threshold.

[0117] The error loss change of the model in several consecutive training cycles is less than the set change threshold ε.

[0118] The number of training rounds reaches the preset maximum number of iterations.

[0119] The model convergence condition of this embodiment is set based on three criteria: error threshold, change rate limit and maximum number of iterations, to ensure the stability and controllability of the self-supervised training process. The convergence condition provides flexible termination criteria at different training stages to avoid overfitting or invalid iterations.

[0120] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means.

[0121] The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0122] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division of a waterway underwater terrain change analysis system and method. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0123] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An oil and gas microwave electric pulse resonance shock coordinated production increase control system, characterized in that: include: A vibration response acquisition module is used to acquire the vibration response sequence fed back by the target shale layer within a time window; A vibration response input module, used for inputting the vibration response sequence into a pre-trained resonance frequency extraction model; A main resonance frequency determination module, used to identify the main resonance frequency of the vibration response sequence by the resonance frequency extraction model, and determine the main resonance frequency of the target shale layer; The electric pulse regulating module is used to regulate the output frequency of the electric pulse excitation device according to the determined main resonance frequency until the output frequency is consistent with the main resonance frequency.

2. The oil and gas microwave electric pulse resonance shock coordinated production increase control system according to claim 1 is characterized in that: The pre-training step of the resonance frequency extraction model includes: A1. Obtain a pseudo-label training set containing N binary sample pairs; the target labels of the binary sample pairs are pseudo-labels extracted from the frequency amplitude distribution diagram; A2, extracting the binary sample pairs of the current batch from the pseudo-label training set, inputting them into the multi-layer perceptron model for self-supervised training, and outputting the predicted frequency of the current batch; A3. Based on the set self-supervised training loss function, calculate the error loss between the predicted frequency and pseudo-label of the current batch, and perform back propagation to update the model parameters. A4. After the model parameters are updated, determine whether the current model meets the preset convergence conditions; A5. If satisfied, terminate the self-supervised training. Otherwise, repeat A2 to A4 until the current model meets the convergence conditions. A4. If the model convergence condition is reached, stop minimizing the error loss between the prediction frequency and pseudo-label of the current batch; otherwise, update the model parameters with the preset learning rate to generate updated parameters; A5. Repeat A2 to A3 according to the updated parameters until the model converges.

3. The oil and gas microwave electric pulse resonance shock coordinated production increase control system according to claim 2 is characterized in that: Get a pseudo-label training set containing N two-tuple sample pairs, including: A1-1. Obtain the vibration response sequence fed back by the target shale layer in N time windows; A1-2. Construct a time-frequency diagram within each time window according to the vibration response sequence fed back within each time window; A1-3, constructing a frequency amplitude distribution diagram according to the time-frequency diagram within the time window; A1-4, selecting a main resonant frequency in the frequency amplitude distribution diagram; A1-5, defining the vibration response sequence as an input vector, defining the main resonance frequency as a pseudo label, and generating the binary sample pair; A1-6. Repeat A1-2 to A1-5 until a pseudo-label training set containing N two-tuple sample pairs is obtained.

4. The oil and gas microwave electric pulse resonance shock coordinated production increase control system according to claim 3 is characterized in that: Obtain the vibration response sequence of the target shale layer in N time windows, including: A1-1-1, anchoring the target shale layer and its N excitation frequencies; A1-1-2. According to the excitation frequency, preset the output frequency of the electric pulse excitation device; A1-1-3, using an electric pulse excitation device with a preset output frequency to emit an excitation frequency to the target shale layer; A1-1-4. Collect several vibrations of the target shale layer corresponding to the excitation frequency and arrange them in chronological order as a vibration response sequence; A1-1-5. Repeat A1-1-2 to A-1-4 to obtain N groups of vibration response sequences with different excitation frequencies.

5. The oil and gas microwave electric pulse resonance shock coordinated production increase control system according to claim 3 is characterized in that: According to the vibration response sequence fed back in each time window, a time-frequency diagram in the time window is constructed, including: A1-2-1. Divide the time window covered by each vibration response sequence into several time sub-windows; A1-2-2. Perform short-time Fourier transform on the vibration response of each time sub-window to obtain the frequency energy distribution of the time sub-window; The frequency energy distribution is characterized as follows: within a given time sub-window, a set of frequency components is obtained after short-time Fourier transform, and the amplitude of each frequency component within the time sub-window; the amplitude is used to represent the response intensity of the corresponding frequency component within the time sub-window; A1-2-3, splicing the frequency energy distribution of each time sub-window in chronological order to construct a time-frequency diagram within the time window; The horizontal axis of the time-frequency diagram is the time sub-window, and the vertical axis is the frequency energy distribution corresponding to the time sub-window. The frequency energy distribution is the distribution of several frequency components in the time sub-window.

6. The oil and gas microwave electric pulse resonance shock coordinated production increase control system according to claim 3 is characterized in that: According to the time-frequency diagram in the time window, a frequency amplitude distribution diagram is constructed, including: A1-3-1. In the time-frequency diagram, extract the amplitude sequence of each frequency component in all time sub-windows; A1-3-2. Perform mean calculation on the amplitude sequence of each frequency component in all time sub-windows to obtain the average amplitude of each frequency component; A1-3-3. Obtain the average amplitude of all frequency components; A1-3-4. With the frequency component as the horizontal axis and the average amplitude of each frequency component as the vertical axis, determine several frequency amplitude points; A1-3-5. Connect several frequency amplitude points to generate a frequency amplitude curve to construct a frequency amplitude distribution diagram; The frequency amplitude distribution diagram is used to characterize the energy concentration degree of each frequency component during the vibration response process.

7. The oil and gas microwave electric pulse resonance shock coordinated production increase control system according to claim 3 is characterized in that: Selecting a main resonant frequency in the frequency amplitude distribution diagram comprises: A1-4-1. Mark all amplitude peaks of the frequency amplitude curve in the frequency amplitude distribution diagram ; A1-4-2. Starting from the marked amplitude peak, search along the left and right sides of the frequency amplitude curve for the left half frequency point and the right half frequency point that are lower than half of the amplitude peak for the first time; A1-4-3. Calculate the distance between the left half frequency point and the right half frequency point, and define the distance as the half-height width of the amplitude peak. ; A1-4-4, traverse the entire frequency amplitude curve to obtain the half-height width corresponding to K corresponding amplitude peaks; A1-4-5. Calculate the energy concentration of each frequency component according to the half-widths of the K corresponding amplitude peaks to obtain K energy concentrations; The calculation expression of the energy concentration is: ； in, represents the energy concentration of the i-th frequency component, represents the half-height width of the ith frequency component, represents the peak amplitude of the i-th frequency component, The normalized amplitude weight of the i-th peak is used to dynamically balance the influence weights of the half-width and amplitude; represents the regularization constant to prevent the denominator from dividing by zero. represents the slope smoothing term; A1-4-6. Select the frequency component corresponding to the minimum concentration from the K energy concentrations, and define the frequency component as the main resonant frequency.

8. The oil and gas microwave electric pulse resonance shock coordinated production increase control system according to claim 2 is characterized in that: The target loss of the self-supervised training loss function is mean square error loss or Huber loss.

9. The oil and gas microwave electric pulse resonance shock coordinated production increase control system according to claim 2 is characterized in that: The convergence condition is: The model is considered to have converged when it meets any of the following conditions in several consecutive rounds of training, including: The error loss of the current batch is lower than the preset error threshold; The error loss change of the model in M ​​consecutive training cycles is less than the set change threshold ε; The number of training rounds reaches the preset maximum number of iterations.

10. The oil and gas microwave electric pulse resonance shock coordinated production increase control system according to claim 1, characterized in that: The control system further comprises: The microwave adjustment module is used to adjust the output frequency of the microwave transmitting device so that the adjusted output frequency is within the shale layer absorption frequency band; and is used to adjust the microwave action time and penetration depth of the wave transmitting device.

Images