Deep well multi-parameter integrated monitoring method, system, device and medium

Abstract

The present invention belongs to the technical field of deep well engineering safety monitoring, and specifically provides a deep well multi-parameter integrated monitoring method, system, device and medium. The method mainly includes: obtaining deep well parameters, fusing deep well parameters to generate a spatiotemporal coupling tensor; performing three-dimensional decoupling of the spatiotemporal coupling tensor to generate a dynamic risk hologram containing an interference gradient; performing phase conjugate matching based on the dynamic risk hologram to identify circularly closed co-evolution units; performing manifold expansion of the co-evolution units along the energy path to generate entropy ratio-weighted spatial folding coordinates; based on the spatial folding coordinates, triggering a disaster coordinate warning through the exponential relationship between the phase tearing index and the entropy ratio. The present application realizes the spatiotemporal correlation analysis of deep well parameters and the three-dimensional presentation of risk patterns. Through the manifold expansion of the energy path and the weighted calculation of the entropy ratio, the disaster coordinates can be accurately located and the warning can be triggered in advance, thereby improving the timeliness and accuracy of deep well engineering safety monitoring.

Description

Technical Field

[0001] The present invention belongs to the technical field of deep well engineering safety monitoring, and in particular relates to a deep well multi-parameter integrated monitoring method, system, device and medium. Background Art

[0002] Deep well monitoring aims to provide real-time insights into the underground environment and equipment status, promptly identifying potential safety hazards such as excessive gas concentrations and abnormal roof pressure, and safeguarding miners' lives. Traditional deep well parameter monitoring uses independent sensors to capture different well parameters, such as pressure, temperature, and displacement. The data collected by these sensors is often processed and analyzed independently.

[0003] As the depth and scale of deep well mining and construction continue to increase, the underground environment is becoming increasingly complex and changeable. Since the monitoring data of various parameters are not effectively integrated, it is difficult to reflect the overall status of the deep well system. When facing potential risks, it is difficult to timely and accurately identify the complex risk patterns formed by the interaction of different factors, resulting in delayed early warning of deep well risks, which seriously affects the safety and stability of deep well projects. Summary of the Invention

[0004] This application provides a deep well multi-parameter integrated monitoring method, system, device and medium, which effectively solves the problem in the existing technology that the monitoring data of various parameters of deep well monitoring are not effectively integrated, resulting in delayed early warning of deep well risks. It realizes the spatiotemporal correlation analysis of deep well parameters and the three-dimensional presentation of risk patterns. Through the energy path manifold expansion and entropy ratio weighted calculation, the disaster coordinates can be accurately located and the early warning can be triggered, thereby improving the timeliness and accuracy of deep well engineering safety monitoring.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] In a first aspect, the present application provides a deep well multi-parameter integrated monitoring method, comprising:

[0007] Obtain deep well parameters and fuse them to generate a spatiotemporal coupling tensor.

[0008] The space-time coupling tensor is three-dimensionally decoupled to generate a dynamic risk hologram containing interference gradients.

[0009] Phase conjugate matching is performed based on the dynamic risk hologram to identify the co-evolution units of the ring closure.

[0010] The co-evolution unit is expanded along the energy path to generate entropy-ratio-weighted spatial folding coordinates.

[0011] Based on the space folding coordinates, the catastrophe coordinate warning is triggered through the exponential relationship between the phase tearing index and the entropy ratio.

[0012] Furthermore, the deep well parameters include well wall strain time series data, wellbore vibration spectrum data, fluid pressure fluctuation data, and gas temperature diffusion data.

[0013] Fusion of deep well parameters generates a spatiotemporal coupling tensor, including:

[0014] Perform time base calibration on the vibration spectrum data to match the time axis of the strain time series data.

[0015] Calculate the dynamic entropy ratio coefficient of the pressure fluctuation data and the temperature diffusion data.

[0016] The time-base calibrated vibration data, strain time series data and dynamic entropy ratio coefficient are integrated to construct a four-dimensional space-time coupling tensor.

[0017] Furthermore, the space-time coupling tensor is subjected to three-dimensional decoupling to generate a dynamic risk hologram containing an interference gradient, including:

[0018] The space-time coupling tensor is divided along the time frame dimension to generate a transient stress distribution cloud map; the space-time coupling tensor is sliced ​​along the depth layer dimension to extract the energy conduction path topology; the space-time coupling tensor is projected along the parameter domain dimension to calculate the field interference intensity gradient.

[0019] The transient stress distribution cloud map, energy conduction path topology and field interference intensity gradient are integrated to generate a dynamic risk hologram containing interference gradient.

[0020] Furthermore, phase conjugate matching is performed based on the dynamic risk hologram to identify the circularly closed co-evolutionary units, including:

[0021] Identify the core nodes in the dynamic risk hologram where the peak value of the field interference intensity gradient exceeds a threshold.

[0022] The energy conduction path segments of the core nodes are extracted, and the phase conjugate matching is performed on the path segments of adjacent nodes to obtain matching results.

[0023] When the matching results form a closed-loop topology, it is marked as a coevolutionary unit with closed loop.

[0024] Furthermore, the co-evolution unit is expanded along the energy path to generate entropy-ratio-weighted spatial folding coordinates, including:

[0025] The co-evolution unit is topologically expanded along the energy conduction path to obtain an expanded manifold.

[0026] The curvature gradient of the unfolded manifold is calculated, and when the curvature gradient exceeds a critical value, it is marked as an abnormal cell body.

[0027] Correlate the abnormal cell bodies with the dynamic entropy ratio coefficient to generate the entropy ratio-weighted spatial folding coordinates.

[0028] Furthermore, based on the space folding coordinates, the exponential relationship between the phase tearing index and the entropy ratio is used to trigger a disaster coordinate warning, including:

[0029] Trace back the core nodes corresponding to the spatial folding coordinates.

[0030] The phase tear index is calculated based on the time-base calibrated vibration data and strain time series data.

[0031] When the phase tearing index forms an exponential relationship with the dynamic entropy ratio coefficient, a catastrophe coordinate warning is triggered.

[0032] Furthermore, the deep well multi-parameter integrated monitoring method also includes:

[0033] Taking the disaster coordinate warning as the center point, a three-dimensional resonance cavity is delineated in the dynamic risk hologram.

[0034] The topological fragments of the energy conduction path in the resonant cavity are extracted and the path inverse convolution is performed.

[0035] The convolution result is superimposed with the entropy ratio coefficient of the spatial folding coordinate to generate a focused energy flow density map.

[0036] When the focused energy flow density exceeds the bearing threshold of the resonance cavity, a structural instability enhancement warning is output.

[0037] In a second aspect, the present application provides a deep well multi-parameter integrated monitoring system, characterized in that a deep well parameter spatiotemporal fusion module: obtains deep well parameters, and fuses the deep well parameters to generate a spatiotemporal coupling tensor.

[0038] Three-dimensional decoupled risk hologram generation module: performs three-dimensional decoupling on the space-time coupling tensor to generate a dynamic risk hologram containing interference gradients.

[0039] Phase conjugate collaborative unit identification module: performs phase conjugate matching based on the dynamic risk hologram to identify the circularly closed collaborative evolution unit.

[0040] Energy manifold folding coordinate generation module: performs manifold expansion on the co-evolution unit along the energy path to generate entropy ratio-weighted spatial folding coordinates.

[0041] Phase entropy ratio catastrophe warning module: Based on the space folding coordinates, the catastrophe coordinate warning is triggered through the exponential relationship between the phase tearing index and the entropy ratio.

[0042] In a third aspect, the present application provides a deep well multi-parameter integrated monitoring device, which includes a memory and a processor; the memory is used to store computer programs; the processor is used to implement the steps of the deep well multi-parameter integrated monitoring method described in the first aspect when executing the computer program.

[0043] In a fourth aspect, the present application provides a readable storage medium, which includes: computer program instructions are stored in the readable storage medium, and when the computer program instructions are read and run by a processor, the steps of the deep well multi-parameter integrated monitoring method described in the first aspect are executed.

[0044] Beneficial effects of the present invention:

[0045] This application obtains deep well parameters and fuses them to generate a spatiotemporal coupling tensor, obtains a dynamic risk hologram through three-dimensional decoupling, identifies co-evolution units through phase conjugate matching, and triggers disaster warnings after manifold expansion to generate spatial folding coordinates. It effectively solves the problem in the existing technology that the monitoring data of various parameters of deep well monitoring are not effectively integrated, resulting in delayed warnings of deep well risks, and realizes the spatiotemporal correlation analysis of deep well parameters and the three-dimensional presentation of risk patterns. Through the energy path manifold expansion and entropy ratio weighted calculation, the disaster coordinates can be accurately located and warnings can be triggered in advance, thereby improving the timeliness and accuracy of deep well engineering safety monitoring.

[0046] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the 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.

[0048] Figure 1 The figure shows a flow chart of the deep well multi-parameter integrated monitoring method of the present invention. DETAILED DESCRIPTION

[0049] In order to solve the problems raised by the background technology, this application obtains deep well parameters and fuses them to generate a space-time coupling tensor, obtains a dynamic risk hologram through three-dimensional decoupling, identifies co-evolution units through phase conjugate matching, and triggers disaster warnings after manifold expansion to generate spatial folding coordinates. It can accurately locate disaster coordinates and trigger warnings in advance, thereby improving the timeliness and accuracy of deep well engineering safety monitoring.

[0050] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings 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 making creative efforts shall fall within the scope of protection of the present invention.

[0051] In some embodiments, as Figure 1 As shown, the present application provides a deep well multi-parameter integrated monitoring method, comprising:

[0052] S1. Obtain deep well parameters and fuse them to generate a spatiotemporal coupling tensor.

[0053] S2. Perform three-dimensional decoupling of the spatiotemporal coupling tensor to generate a dynamic risk hologram with interference gradients.

[0054] S3. Identify ring-closed coevolution units using phase conjugate matching based on dynamic risk holograms.

[0055] S4. Expand the coevolutionary units along the energy path to generate entropy-weighted spatial folding coordinates.

[0056] S5. Based on the space folding coordinates, the exponential relationship between the phase tearing index and the entropy ratio is used to trigger the disaster coordinate warning.

[0057] In some embodiments, the deep well parameters include wellbore strain time series data, wellbore vibration spectrum data, fluid pressure fluctuation data, and gas temperature diffusion data.

[0058] The wellbore strain time series data is collected by the resistance strain sensor installed on the inner wall of the wellbore, which continuously records the wellbore structure deformation at a fixed sampling frequency and can reflect the roof deformation trend.

[0059] The wellbore vibration spectrum data is obtained through vibration acceleration sensors arranged around the well. The spectrum amplitude distribution generated by fast Fourier transform processing can identify the characteristic frequency of rock fracture.

[0060] Fluid pressure fluctuation data comes from pressure transmitters embedded in the well wall, which monitor drilling fluid or groundwater pressure fluctuations and are strongly correlated with water inrush risk.

[0061] Gas temperature diffusion data is captured by thermocouple sensors deployed in the wellbore annulus, which record the temperature gradient diffusion rate and correlate it with the coal rock oxidation exothermic process.

[0062] The deep well parameters are integrated in S1 to generate the spatiotemporal coupling tensor, including:

[0063] S11. Perform time base calibration on the vibration spectrum data to match the time axis of the strain time series data.

[0064] The time base of the wellbore vibration spectrum data is calibrated so that its sampling time point is strictly aligned with the time axis of the wellbore strain time series data.

[0065] Calibration is achieved using linear interpolation technology. When there is an offset between the sampling time of the vibration data and the sampling time of the strain data, interpolation calculation is performed based on the numerical change rate of adjacent sampling points of the vibration data to generate calibration vibration data that is completely synchronized with the strain data time axis.

[0066] The calibration trigger condition may be: when the time offset of a specified number of consecutive sampling points (such as 5) exceeds a specified multiple (such as one twentieth) of the strain data sampling interval.

[0067] S12. Calculate the dynamic entropy ratio coefficient of the pressure fluctuation data and the temperature diffusion data.

[0068] S121. Within a sliding time window of a specified length (e.g., 30 seconds), calculate the Shannon entropy value of the pressure data and the Shannon entropy value of the temperature data, respectively; wherein the Shannon entropy value of the pressure data represents the disorder of the pressure fluctuation, and the Shannon entropy value of the temperature data represents the disorder of the temperature diffusion.

[0069] S122. Calculate the pressure variation range and temperature variation range within the same time window.

[0070] S123. Calculate the dynamic entropy ratio coefficient according to the entropy calculation formula.

[0071] S13. Fusion of time-base calibrated vibration data, strain time series data, and dynamic entropy ratio coefficient to construct a four-dimensional space-time coupling tensor.

[0072] The strain value of the wellbore strain time series data, the amplitude of the vibration spectrum data after time base calibration, and the real-time calculation results of the state entropy ratio coefficient are integrated to construct a four-dimensional space-time coupling tensor.

[0073] The tensor structure is defined as: time frame index, depth layer index, parameter channel index and physical quantity value; among them, the time frame index corresponds to the sampling time series, the depth layer index corresponds to the vertical coordinate of the wellbore, channel 1 of the parameter channel index stores the strain value, channel 2 stores the vibration amplitude, channel 3 stores the entropy ratio coefficient, and the physical quantity value corresponds to floating-point data.

[0074] The assignment rule for each data point is as follows: at a specific time point and depth position, the strain value, vibration amplitude, and entropy ratio coefficient are stored in the corresponding parameter channel respectively, and the time offset threshold is dynamically set according to the sampling frequency of the strain sensor.

[0075] In some embodiments, in S2, the spatiotemporal coupling tensor is three-dimensionally decoupled to generate a dynamic risk hologram containing an interference gradient, including:

[0076] S21. Split the space-time coupling tensor along the time frame dimension to generate a transient stress distribution cloud map; slice the space-time coupling tensor along the depth layer dimension to extract the energy conduction path topology; project the space-time coupling tensor along the parameter domain dimension to calculate the field interference intensity gradient.

[0077] The time frame dimension of the space-time coupling tensor is sliced ​​at equal intervals, and each slice generates a transient stress distribution cloud map. Each cloud map shows the strain value distribution at the full depth of the wellbore at a specific moment, and the color gradient corresponds to the strain amplitude.

[0078] A vertical section is made along the depth dimension of the space-time coupling tensor to extract the energy conduction path topology. The sectioning direction is parallel to the wellbore axis. The path topology is stored in a directed graph structure, where the nodes represent the depth position and the edge weights represent the vibration energy transmission intensity.

[0079] The field interference intensity gradient is calculated by projecting along the parameter domain dimension of the space-time coupling tensor. The projection rule is: for each space-time point (time frame + depth layer), the maximum eigenvalue of the covariance matrix of the strain channel value, vibration channel value and entropy ratio channel value is calculated. This eigenvalue is the field interference intensity gradient.

[0080] S22. Generate a dynamic risk hologram containing interference gradient by integrating transient stress distribution cloud map, energy conduction path topology and field interference intensity gradient.

[0081] S22 specifically includes:

[0082] S221. Using the depth layer as the reference coordinate system, render the transient stress distribution cloud map into a two-dimensional thermal layer.

[0083] S222. Directed edges in superimposed energy conduction path topology.

[0084] S223. Superimpose a semi-transparent highlight mark on the area where the field interference intensity gradient is greater than a specified value (such as 0.5).

[0085] The hologram is stored in the form of time series frames, and each frame corresponds to the three-dimensional wellbore risk field visualization result of a time slice.

[0086] The display threshold of the field interference intensity gradient is set based on historical data statistics. When the gradient value exceeds a specified value (such as 2 times the standard deviation of the historical mean) for a specified number of consecutive frames (such as 3 frames), the highlight mark is activated.

[0087] In some embodiments, performing phase conjugate matching based on the dynamic risk hologram in S3 to identify the circularly closed co-evolutionary unit includes:

[0088] S31. Identify the core nodes in the dynamic risk hologram where the peak value of the field interference intensity gradient exceeds the threshold.

[0089] Scan the distribution of the field interference intensity gradient in the dynamic risk hologram, and locate the spatial point where the gradient peak exceeds the preset threshold as the core node.

[0090] The threshold is set based on the physical properties of the surrounding rock of the wellbore. Specifically, the judgment is valid when the gradient peak exceeds the specified value (such as 2 times the standard deviation of the historical mean) for consecutive specified frames (such as 3 frames).

[0091] S32. Extract the energy conduction path segments of the core nodes, perform phase conjugate matching on the path segments of adjacent nodes, and obtain matching results.

[0092] Perform complex conjugate multiplication of the vibration phase spectra of the two path segments and calculate the real part integral value of the product result. When the integral value is greater than the matching threshold (such as 0.8), it is marked as a successful phase matching.

[0093] The matching results are stored as a weighted adjacency matrix, and the weight value is the phase matching integral value.

[0094] S33. When the matching results form a closed-loop topology, the co-evolution unit is marked as a closed-loop co-evolution unit.

[0095] A coevolutionary unit is marked as a loop-closed coevolutionary unit when a closed-loop path that meets the following conditions appears:

[0096] 1. The closed-loop path contains at least 3 core nodes.

[0097] 2. The weight values ​​of the matching results between adjacent nodes are all greater than 0.7.

[0098] 3. The total length of the path is within the range of 50-200 meters.

[0099] The coevolution unit of loop closure includes the spatial coordinates and matching weights of the closed loop topology.

[0100] In some embodiments, S4 performs manifold expansion on the co-evolution unit along the energy path to generate entropy-ratio-weighted spatial folding coordinates, including:

[0101] S41. Expand the co-evolutionary unit along the energy conduction path topology to obtain the expanded manifold.

[0102] Based on differential geometry parameterization, the ring-closed coevolutionary unit is expanded along the energy conduction path topology. Using the energy conduction path as a reference curve, the expansion process maps the three-dimensional spatial structure onto a two-dimensional parametric plane, generating an expanded manifold that preserves the original topological relationships.

[0103] For example, when the co-evolution unit is a ring structure with a diameter of 20 meters, it forms a rectangular strip structure with a length of 62.8 meters and a width of 5 meters after unfolding.

[0104] S42. Calculate the curvature gradient of the unfolded manifold. When the curvature gradient exceeds a critical value, mark it as an abnormal cell body.

[0105] Calculate the curvature gradient of the unfolded manifold, which is obtained by taking the directional derivative of Gaussian curvature along the arc length using differential geometry methods.

[0106] When the curvature gradient exceeds a specified critical value (e.g., 0.35 rad / m), the corresponding area is marked as an abnormal cell. The critical value is calibrated based on the uniaxial compressive strength test of the wellbore surrounding rock.

[0107] S43. Associate abnormal cell bodies with dynamic entropy ratio coefficients to generate entropy ratio-weighted spatial folding coordinates.

[0108] The coordinate point of the abnormal cell body in the original three-dimensional space is located, the dynamic entropy ratio coefficient value corresponding to the point is read, and the original depth coordinate is multiplied by the dynamic entropy ratio coefficient to generate the entropy ratio-weighted spatial folding coordinate.

[0109] For example, when the abnormal cell body is located at a well depth of 300 meters and the dynamic entropy ratio coefficient is 1.6, the depth value of the output space folding coordinate is 300×1.6=480 meters.

[0110] In some embodiments, in S5, based on the space folding coordinates, the exponential relationship between the phase tearing index and the entropy ratio is used to trigger a disaster coordinate warning, including:

[0111] S51. Trace the core nodes corresponding to the spatial folding coordinates.

[0112] According to the depth value of the spatial folding coordinate, it is reversely mapped to the corresponding core node in the dynamic risk hologram. The mapping rule is: ;in, Represents the original core node depth coordinate, Represents the depth value of the space folding coordinate, Represents the dynamic entropy ratio coefficient corresponding to the space folding coordinate.

[0113] S52. Calculate the phase tear index based on the time-base calibrated vibration data and strain time series data.

[0114] Extracting phase spectrum from vibration data and strain data phase spectrum .

[0115] Calculate the frequency domain phase difference , .

[0116] Calculating the Phase Tearing Index , ;in, represents the angular frequency, 、 Represents the lower and upper limits of the integral, and needs to cover the characteristic frequency band of rock mass fracture, such as 0-100Hz, represents the phase difference exponential function, Represents the angular frequency differential element.

[0117] S53. When the phase tearing index and the dynamic entropy ratio coefficient form an exponential relationship, the catastrophe coordinate warning is triggered.

[0118] For example, when When the disaster coordinate warning is triggered; where k represents the base coefficient, such as 0.8, Represents growth factors, such as 0.5, k and Both can be calibrated through regression of historical disaster data.

[0119] In some embodiments, the deep well multi-parameter integrated monitoring method further includes:

[0120] S6. Perform entropy field tracing based on disaster coordinate warning, dynamic risk hologram, and space folding coordinates, and output enhanced warning.

[0121] S6 specifically includes:

[0122] S61. With the disaster coordinate warning as the center point, define the three-dimensional resonance cavity in the dynamic risk hologram.

[0123] Taking the spatial position of the disaster coordinate warning as the center point, a three-dimensional rectangular resonance cavity is delineated in the dynamic risk hologram.

[0124] The cavity size is dynamically adjusted by the entropy ratio coefficient of the space folding coordinate. For example, the product of the reference length and the dynamic entropy ratio coefficient is used as the cavity side length.

[0125] S62. Extract the topological fragments of the energy conduction path in the resonant cavity and perform path inverse convolution.

[0126] Extract the topological fragment of the energy conduction path in the resonant cavity and perform a convolution operation along the reverse direction of the path: ;in, represents the inverse convolution energy value at position s, L represents the total length of the energy conduction path segment, u represents the path integral variable, that is, the distance from the current position to the starting point, K represents the decay kernel function, , β represents the rock mass energy attenuation coefficient, represents the path distance, Represents the original energy value at the path position u, and du represents the tiny length unit of path u.

[0127] S63. Superimpose the convolution result with the entropy ratio coefficient of the spatial folding coordinate to generate a focused energy flow density map.

[0128] The inverse convolution result Multiplying the dynamic entropy ratio coefficient corresponding to the spatial folding coordinate generates the focused energy flow density value, and the Φ value distribution of the entire cavity constitutes the focused energy flow density map.

[0129] S64. When the focused energy flux density exceeds the bearing threshold of the resonance cavity, a structural instability enhancement warning is output.

[0130] When the maximum value of the focused energy flux density diagram exceeds the bearing threshold of the resonance cavity, a structural instability reinforcement warning is output; wherein the bearing threshold is calibrated according to the uniaxial compressive strength of the rock mass within the cavity range.

[0131] In some embodiments, the present application provides a deep well multi-parameter integrated monitoring system, a deep well parameter spatiotemporal fusion module: obtains deep well parameters, and fuses the deep well parameters to generate a spatiotemporal coupling tensor.

[0132] Three-dimensional decoupled risk hologram generation module: performs three-dimensional decoupling of the space-time coupling tensor to generate a dynamic risk hologram with interference gradient.

[0133] Phase conjugate collaborative unit identification module: Phase conjugate matching is performed based on the dynamic risk hologram to identify the ring-closed collaborative evolution units.

[0134] Energy manifold folding coordinate generation module: The co-evolution unit is expanded along the energy path to generate entropy ratio-weighted spatial folding coordinates.

[0135] Phase entropy ratio catastrophe warning module: Based on the space folding coordinates, the exponential relationship between the phase tearing index and the entropy ratio is used to trigger the catastrophe coordinate warning.

[0136] In some embodiments, the present application provides a deep well multi-parameter integrated monitoring device, which includes a memory and a processor; the memory is used to store computer programs; the processor is used to implement the steps of a deep well multi-parameter integrated monitoring method when executing the computer program.

[0137] In some embodiments, the present application provides a readable storage medium, which includes: computer program instructions stored in the readable storage medium, and when the computer program instructions are read and executed by a processor, the steps of a deep well multi-parameter integrated monitoring method are executed.

[0138] Any reference to memory, storage, database, or other media used in the embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory.

[0139] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or elements that are inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device that includes the element.

[0140] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A deep well multi-parameter integrated monitoring method, characterized in that: include: Obtain deep well parameters and fuse them to generate space-time coupling tensor; The space-time coupling tensor is subjected to three-dimensional decoupling to generate a dynamic risk hologram containing an interference gradient, including: dividing the space-time coupling tensor along the time frame dimension to generate a transient stress distribution cloud map; sectioning the space-time coupling tensor along the depth layer dimension to extract the energy conduction path topology; projecting the space-time coupling tensor along the parameter domain dimension to calculate the field interference intensity gradient; and fusing the transient stress distribution cloud map, the energy conduction path topology, and the field interference intensity gradient to generate a dynamic risk hologram containing an interference gradient. Performing phase conjugate matching based on the dynamic risk hologram to identify loop-closed co-evolution units includes: identifying core nodes in the dynamic risk hologram where the peak value of the field interference intensity gradient exceeds a threshold; extracting energy conduction path segments of the core nodes, performing phase conjugate matching on the path segments of adjacent nodes to obtain matching results; and marking the matching results as loop-closed co-evolution units when a closed-loop topology is formed. The co-evolution unit is subjected to manifold expansion along the energy path to generate entropy ratio-weighted spatial folding coordinates, including: performing manifold expansion on the co-evolution unit along the energy conduction path topology to obtain an expanded manifold; calculating the curvature gradient of the expanded manifold, and marking it as an abnormal cell body when the curvature gradient exceeds a critical value; associating the abnormal cell body with a dynamic entropy ratio coefficient to generate entropy ratio-weighted spatial folding coordinates; Based on the space folding coordinates, the catastrophe coordinate warning is triggered through the exponential relationship between the phase tearing index and the entropy ratio, including: tracing the core nodes corresponding to the space folding coordinates; calculating the phase tearing index based on the time base calibration vibration data and strain time series data; when the phase tearing index forms an exponential relationship with the dynamic entropy ratio coefficient, the catastrophe coordinate warning is triggered.

2. The deep well multi-parameter integrated monitoring method according to claim 1, characterized in that: The deep well parameters include well wall strain time series data, wellbore vibration spectrum data, fluid pressure fluctuation data, and gas temperature diffusion data; Fusion of deep well parameters generates a spatiotemporal coupling tensor, including: Perform time base calibration on vibration spectrum data to match the time axis of strain time series data; Calculate the dynamic entropy ratio coefficient of pressure fluctuation data and temperature diffusion data; The time-base calibrated vibration data, strain time series data and dynamic entropy ratio coefficient are integrated to construct a four-dimensional space-time coupling tensor.

3. The deep well multi-parameter integrated monitoring method according to claim 1, characterized in that: Also includes: With the disaster coordinate warning as the center point, a three-dimensional resonance cavity is delineated in the dynamic risk hologram; Extract the topological fragments of the energy conduction path in the resonant cavity and perform path inverse convolution; The convolution result is superimposed with the entropy ratio coefficient of the spatial folding coordinate to generate a focused energy flow density map; When the focused energy flow density exceeds the bearing threshold of the resonance cavity, a structural instability enhancement warning is output.

4. A deep well multi-parameter integrated monitoring system, characterized in that: Deep well parameter spatiotemporal fusion module: obtains deep well parameters and fuses them to generate spatiotemporal coupling tensors; 3D decoupled risk hologram generation module: performs 3D decoupling on the spatiotemporal coupling tensor to generate a dynamic risk hologram containing interference gradients, including: segmenting the spatiotemporal coupling tensor along the time frame dimension to generate a transient stress distribution cloud map; slicing the spatiotemporal coupling tensor along the depth layer dimension to extract the energy conduction path topology; projecting the spatiotemporal coupling tensor along the parameter domain dimension to calculate the field interference intensity gradient; and fusing the transient stress distribution cloud map, energy conduction path topology, and field interference intensity gradient to generate a dynamic risk hologram containing interference gradients. Phase conjugate collaborative unit identification module: performs phase conjugate matching based on the dynamic risk hologram to identify loop-closed collaborative evolution units, including: identifying core nodes in the dynamic risk hologram where the peak value of the field interference intensity gradient exceeds a threshold; extracting energy conduction path segments of the core nodes, performing phase conjugate matching on the path segments of adjacent nodes to obtain matching results; when the matching results form a closed-loop topology, it is marked as a loop-closed collaborative evolution unit; Energy manifold folding coordinate generation module: performs manifold expansion on the co-evolution unit along the energy path to generate entropy ratio-weighted spatial folding coordinates, including: performing manifold expansion on the co-evolution unit along the energy conduction path topology to obtain an expanded manifold; calculating the curvature gradient of the expanded manifold, and when the curvature gradient exceeds a critical value, marking it as an abnormal cell body; associating the abnormal cell body with the dynamic entropy ratio coefficient to generate entropy ratio-weighted spatial folding coordinates; Phase entropy ratio catastrophe warning module: Based on the space folding coordinates, the exponential relationship between the phase tearing index and the entropy ratio is used to trigger the catastrophe coordinate warning, including: tracing the core nodes corresponding to the space folding coordinates; calculating the phase tearing index based on the time base calibration vibration data and strain time series data; when the phase tearing index forms an exponential relationship with the dynamic entropy ratio coefficient, the catastrophe coordinate warning is triggered.

5. A deep well multi-parameter integrated monitoring device, characterized in that: It includes a memory and a processor; the memory is used to store a computer program; the processor is used to implement the steps of the deep well multi-parameter integrated monitoring method according to any one of claims 1 to 3 when executing the computer program.

6. A readable storage medium, characterized in that: The method comprises: a computer program instruction is stored in a readable storage medium, and when the computer program instruction is read and executed by a processor, the steps of the deep well multi-parameter integrated monitoring method according to any one of claims 1 to 3 are executed.

Images