Mine filling body top contact quality intelligent detection method and device

Abstract

The application discloses a mine filling body top-joining quality intelligent detection method and device, and relates to the technical field of mine engineering safety. The application comprises the following steps: obtaining and preprocessing an original pressure signal to obtain preprocessed pressure data; generating a weighted pressure gradient through a nonlinear fitting function model with time weighting based on the preprocessed pressure data; simultaneously obtaining an original sound wave signal and performing correction processing to obtain a corrected sound wave energy response; constructing a spatial function field based on the weighted pressure gradient and the corrected sound wave energy response to obtain a spatial boundary indication function value; generating a score result based on the weighted pressure gradient, the corrected sound wave energy response and the spatial boundary indication function value; and obtaining a mine filling body top-joining quality detection result based on the score result. The application solves the problems of low detection precision, poor spatial recognition capability, non-quantized data, fuzzy boundary, judgment relying on artificial experience and high safety risk of the existing filling body top-joining detection method.

Description

Technical Field

[0001] This invention relates to the field of mine engineering safety technology, and in particular to an intelligent detection method and device for the roof contact quality of mine backfill bodies. Background Technology

[0002] In mining operations, backfilling is widely used as an important green mining technology to ensure the stability of the roof in goaf areas and prevent surface subsidence. By backfilling the goaf with cementing materials to form a support structure, not only can resource recovery rates be improved, but ground pressure hazards can also be effectively controlled. However, achieving good contact between the backfill and the roof, i.e., a "roof connection," is crucial to ensuring the backfill plays a stable supporting role. Poor roof connection will prevent the roof load from being effectively transferred to the backfill, leading to a series of safety problems such as backfill voids, roof subsidence, and structural instability, endangering the lives of workers and the stable operation of the production system. Therefore, conducting inspection and evaluation of the roof connection quality of the backfill has become a key technical means in mine safety management.

[0003] Existing methods for detecting the connection of mine backfill bodies primarily rely on sensing single physical quantities, such as single-point pressure sensors, manual tapping echo methods, penetrometer tests, or borehole visual inspection. These methods have significant shortcomings in practical applications. Firstly, single-point sensing methods have limited spatial coverage and cannot comprehensively perceive the overall state of the backfill body. Secondly, these methods largely depend on the operator's experience and judgment, lacking quantitative analysis standards and failing to achieve structural-level connection identification and dynamic monitoring. Furthermore, due to the complex physical properties and nonlinear mechanical behavior of backfill bodies, acoustic or pressure signals are often affected by noise interference and structural reflection distortion, leading to a significant decrease in the accuracy of traditional backfill connection detection methods under actual working conditions where the backfill body is heterogeneous and has irregular interfaces. Therefore, there is an urgent need to provide an intelligent detection method for the quality of mine backfill connections to solve these problems. Summary of the Invention

[0004] This invention provides an intelligent detection method and device for the roof connection quality of mine backfill bodies, which solves the problems of low detection accuracy, poor spatial recognition ability, non-quantitative data, blurred boundaries, reliance on human experience for judgment, and high safety risks in existing backfill body roof connection detection methods.

[0005] The present invention provides an intelligent detection method and device for the roof contact quality of mine backfill bodies, specifically comprising the following technical solutions:

[0006] A method for intelligent detection of the roof contact quality of mine backfill bodies includes the following steps:

[0007] S1. Acquire and preprocess the raw pressure signal to obtain preprocessed pressure data; based on the preprocessed pressure data, generate a weighted pressure gradient through a time-weighted nonlinear fitting function model; simultaneously acquire the raw sound wave signal and perform correction processing to obtain the corrected sound wave energy response.

[0008] S2. Based on the weighted pressure gradient and the corrected acoustic energy response, a spatial function field is constructed to obtain the spatial boundary indicator function value; the quality of the roof connection is quantitatively evaluated based on the weighted pressure gradient, the corrected acoustic energy response, and the spatial boundary indicator function value, and a scoring result is generated; based on the scoring result, the roof connection quality test result of the mine backfill body is obtained.

[0009] Preferably, S1 specifically includes:

[0010] A time-weighted nonlinear fitting function model is constructed based on the contribution term of the instantaneous pressure change rate and the pressure gradient moving average term.

[0011] Preferably, S1 specifically includes:

[0012] The corrected acoustic energy response is calculated by combining directional weighting and multipath time inversion with a directional time weighting function, a distance attenuation compensation term, and a nonlinear reflection enhancement term.

[0013] Preferably, S2 specifically includes:

[0014] Based on the weighted pressure gradient and the corrected acoustic energy response, a spatial boundary indicator function is constructed through a nonlinear deformation function.

[0015] Preferably, S2 specifically includes:

[0016] In the spatial boundary indicator function, a boundary scale factor is introduced, and the spatial boundary indicator function value is generated based on the pressure gradient and the sound wave energy gradient.

[0017] Preferably, S2 specifically includes:

[0018] Based on the weighted pressure gradient, the corrected acoustic energy response, and the spatial boundary indicator function value, a unified index evaluation formula is constructed to obtain the scoring results.

[0019] Preferably, S2 specifically includes:

[0020] The evaluation area is divided, and a unified index evaluation formula is constructed based on the degree of contact between the sampling points within the evaluation area and the top under pressure and sound wave energy intensity, combined with the combined criteria of geometric consistency and spatial fit integrity.

[0021] Preferably, S2 specifically includes:

[0022] The scoring results are compared with the preset threshold to obtain the quality test results of the mine backfill body.

[0023] A smart detection device for the roof contact quality of mine backfill bodies includes the following components:

[0024] Pressure data acquisition component, weighted pressure gradient fitting component, acoustic signal acquisition and correction component, spatial function field construction component, and top-end quality quantitative evaluation component.

[0025] The pressure data acquisition component acquires the raw pressure signal and sends it to the weighted pressure gradient fitting component.

[0026] The weighted pressure gradient fitting component preprocesses the original pressure signal, generates a weighted pressure gradient by constructing a time-weighted nonlinear fitting function model, and sends the weighted pressure gradient to the spatial function field construction component and the top-end quality quantification evaluation component.

[0027] The acoustic signal acquisition and correction component acquires the original acoustic signal and performs correction processing to obtain the corrected acoustic energy response, and sends the corrected acoustic energy response to the spatial function field construction component and the top-end quality quantification evaluation component.

[0028] The spatial function field construction component constructs a spatial function field based on the weighted pressure gradient and the corrected acoustic energy response, obtains the spatial boundary indicator function value, and sends the spatial boundary indicator function value to the top-end quality quantification evaluation component;

[0029] The component for quantitatively evaluating the quality of roof support is based on the spatial boundary indicator function value, combined with the weighted pressure gradient and the corrected acoustic energy response, to obtain a unified index that can quantitatively evaluate the quality of roof support. The results of the roof support quality test of the mine backfill body are obtained based on the unified index.

[0030] The beneficial effects of the technical solution of the present invention are:

[0031] 1. By constructing a time-weighted nonlinear fitting function model, it can identify non-abrupt contact behavior caused by packing deformation and slow compaction during the top connection process, avoiding false omissions when instantaneous signals are not significant. Compared with the traditional difference method, which only identifies abrupt change points, this model achieves higher time resolution and trend recognition capability through sliding weighted fitting.

[0032] 2. In acoustic signal processing, an acoustic echo correction based on angle and time delay weighting is introduced. Combined with path distance compensation and reflection enhancement mechanisms, it can effectively handle problems such as complex acoustic propagation paths and echo reverberation under heterogeneous media. Even when the material transition at the top surface is discontinuous or tilted, the main reflection path can still be accurately extracted.

[0033] 3. The spatial boundary indicator function constructed through a nonlinear deformation function enables structural judgment to be independent of regular meshes, avoiding the "step-like" boundary and structural discontinuity problems that occur in traditional voxel modeling. Its construction method integrates multiple factors such as Euclidean distance attenuation, pressure gradient, and acoustic energy gradient, and has good structural smoothness, geometric consistency, and spatial continuity, providing a reliable spatial basis for subsequent evaluation. Attached Figure Description

[0034] Figure 1 This is a structural diagram of an intelligent detection device for the roof contact quality of mine backfill bodies according to the present invention.

[0035] Figure 2 This is a flowchart of an intelligent detection method for the roof connection quality of mine backfill bodies according to the present invention. Detailed Implementation

[0036] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0038] The following description, in conjunction with the accompanying drawings, details the specific scheme of the intelligent detection method and device for the roof contact quality of mine backfill provided by the present invention.

[0039] See attached document Figure 1 The diagram illustrates a structural diagram of an intelligent detection device for the roof contact quality of mine backfill bodies according to an embodiment of the present invention. The device includes the following parts:

[0040] Pressure data acquisition component, weighted pressure gradient fitting component, acoustic signal acquisition and correction component, spatial function field construction component, and top-end quality quantitative evaluation component.

[0041] The pressure data acquisition component acquires raw pressure signals through a flexible distributed pressure sensor array preset according to expert experience, and sends the raw pressure signals to the weighted pressure gradient fitting component.

[0042] The weighted pressure gradient fitting component preprocesses the original pressure signal, generates a weighted pressure gradient by constructing a time-weighted nonlinear fitting function model, and sends the weighted pressure gradient to the spatial function field construction component and the top-end quality quantification evaluation component.

[0043] The acoustic signal acquisition and correction component uses a low-frequency controllable acoustic transducer array to acquire the original acoustic signal and perform correction processing to obtain the corrected acoustic energy response. The corrected acoustic energy response is then sent to the spatial function field construction component and the top-end quality quantification evaluation component.

[0044] The spatial function field construction component constructs a spatial function field based on the weighted pressure gradient and the corrected acoustic energy response. It models complex boundary structures through nonlinear deformation functions, obtains spatial boundary indicator function values, and sends the spatial boundary indicator function values ​​to the top-end quality quantification evaluation component.

[0045] The component for quantitatively evaluating the quality of roof support is based on the spatial boundary indicator function value, combined with the weighted pressure gradient and the corrected acoustic energy response. Through a unified index evaluation formula, a unified index is obtained that can quantitatively evaluate the quality of roof support. The results of the roof support quality test of the mine backfill body are obtained based on the unified index.

[0046] See attached document Figure 2 The diagram illustrates a flowchart of an intelligent detection method for the roof contact quality of mine backfill bodies according to an embodiment of the present invention. The method includes the following steps:

[0047] S1. Acquire and preprocess the original pressure signal to obtain preprocessed pressure data; based on the preprocessed pressure data, generate a weighted pressure gradient through a time-weighted nonlinear fitting function model; simultaneously acquire the original sound wave signal and perform correction processing to obtain the corrected sound wave energy response.

[0048] In order to perceive the local pressure evolution of the filling body at different spatial locations during the connection process in real time, and thus determine the density change trend and initial contact state, a flexible distributed pressure sensor array is used to collect the original pressure signal based on the expert experience method. The original pressure signal is preprocessed by means such as noise reduction, cleaning, standardization and normalization to obtain preprocessed pressure data. The preprocessing process is a technical means well known to those skilled in the art and will not be described in detail here.

[0049] Furthermore, to avoid nonlinear dynamic changes during the sampling process due to factors such as sampling time, filler rheology, and sensor drift, a time-weighted nonlinear fitting function model is constructed to generate a weighted pressure gradient. The specific implementation formula is as follows:

[0050]

[0051] in, It is a weighted pressure gradient, representing The intensity of pressure change at any given moment, i.e., the gradient index, is used to determine the trend of reaching the top. This is the current item weight fusion factor, determined based on expert experience, with a reference value range of [value missing]. ; yes The pressure value at any given time is taken from the preprocessed pressure data; yes The pressure value at any given time is taken from the preprocessed pressure data; It is the sampling time interval of the sliding window, preset according to the application scenario; This is the number of sampling points in the sliding window, representing the number of historical samples counted backward from the current time point, which is determined according to specific application requirements; It is an index variable, representing the sample index in the sliding window; It is the time decay exponential factor, used to control the historical pressure change term. The effect of changes over time was determined based on expert experience, with a reference range of values. ; yes The pressure value at any given time is taken from the preprocessed pressure data; yes The pressure value at any given time is taken from the preprocessed pressure data; It is the contribution of the instantaneous rate of change of pressure (instantaneous derivative) at the current moment; It is the time weighting factor of the historical pressure change term, which is essentially an exponential decay function that simulates the phenomenon of time memory decay. It is the pressure gradient moving average term in the sliding window, used for trend judgment and stability compensation.

[0052] To identify the true contact boundary profile from the echo signal within the filled area, and to avoid reverberation and interference issues in the original acoustic signal acquired from the low-frequency controllable acoustic transducer array due to multipath reflection, frequency distortion, and directional energy loss caused by the inhomogeneity and density irregularity of the filling material, directional weighting and multipath time inversion are used to eliminate scattering and energy distortion caused by the inhomogeneous structure within the filling body, extracting the optimal acoustic signal representation of the contact boundary. Injection of filling medium, path length is ,exist The energy received at any given time is Based on the acoustic wave propagation model in heterogeneous media and directional beam control theory, the corrected energy response expression is obtained:

[0053]

[0054] in, yes At all times in the direction angle Down-corrected acoustic energy response; It is the angle between the direction of sound wave propagation in space and the perpendicular direction, used to simulate the directional weight of the sound wave propagation path and the change in the directionality of the echo, and is acquired using a low-frequency controllable acoustic transducer array; It is the maximum integral path length, i.e., the maximum depth of echo detection; It is the path length of the sound wave propagation, and it is the integral variable; It is a time window sensitivity factor used to control The weighted response speed is determined based on expert experience, with a reference range of values. ; It is the delay time corresponding to the maximum energy of the main path echo, which is determined by the sampling depth; It is a path compensation term used to avoid The division-by-zero singularity and near-field amplification issues at time t are determined using expert empirical methods, with a reference range of values ​​being [value missing]. ; It is the reflection coefficient, which represents the intensity of sound wave energy reflection at the contact interface. It is calculated based on the energy ratio of the echo to the incident wave. The energy of the echo and the incident wave are acquired by a low-frequency controllable acoustic transducer array. It is the reflection enhancement index, used to improve the nonlinear response of abrupt changes in interface reflection. It is determined based on expert experience, and the reference range is [range missing]. ; It is a directional time weighting function, used to adjust the weight of acoustic echo responses in different directions and at different time points, thereby suppressing interference from non-main directions and non-main paths. It is a distance attenuation compensation term for the original acoustic signal intensity, used to perform "geometric diffusion" correction on the acoustic intensity at each point on the detection path; It is a nonlinear reflection enhancement term used to emphasize the intensity response of sound waves when they are reflected at the material interface, so as to better identify "contact surfaces" or "structural abrupt changes"; It is a multi-weighted signal enhancement core used to determine whether the acoustic signal is sufficient to indicate changes in the contact surface or abnormal structure at a specific direction, time, and path.

[0055] S2. Based on the weighted pressure gradient and the corrected acoustic energy response, a spatial function field is constructed to obtain the spatial boundary indicator function value; the quality of the roof connection is quantitatively evaluated based on the weighted pressure gradient, the corrected acoustic energy response, and the spatial boundary indicator function value, and a scoring result is generated; based on the scoring result, the roof connection quality test result of the mine backfill body is obtained.

[0056] Based on the weighted pressure gradient and corrected acoustic energy response, a spatial function field is constructed. Complex boundary structures are modeled using a nonlinear deformation function, accurately fitting the actual contact interface between the infill and the top plate. Furthermore, to avoid the block effect and boundary fracture caused by voxel meshes, a spatial boundary indicator function is constructed for each point within the entire target area. The spatial boundary indicator function value is calculated, and its specific definition is as follows:

[0057]

[0058] in, It is the spatial boundary indicator function value, which represents the normalized strength of the contact boundary at a point in four-dimensional space. The higher the value, the closer it is to the actual contact surface. This is the boundary scale factor, used to control the overall amplitude variation of the spatial boundary indicator function. It plays a role in adjusting the sensitivity of the final boundary surface extraction. It is determined based on expert experience, with a reference value range of [value missing]. ; This is the distance attenuation factor, used to control the degree of boundary deformation. It is determined based on expert experience, and the reference range is [range missing]. ; It is the Euclidean distance, the average of the Euclidean distances between the current point and the points of maximum pressure and maximum echo energy, used for boundary expansion; It is the pressure gradient, calculated using the first-order difference. It is the sound wave energy gradient, calculated using the first-order difference; It is the ratio of the exponential decay term to the normalized suppression term of the local gradient. It describes the probability trend of whether the current point belongs to the boundary of the top by using the ratio of the exponential decay term to the normalized suppression term of the local gradient at the distance from the principal point (such as the point of maximum pressure or the point of maximum sound energy). It is a coupling term of dynamic response mutation ratio and direction adaptation.

[0059] Furthermore, combining the weighted pressure gradient obtained from the above processing, the corrected acoustic energy response, and the spatial boundary indicator function value, a unified index evaluation formula is constructed based on the pressure change mapping model and the acoustic structure energy correction model:

[0060]

[0061] in, It is a unified indicator that can quantify and evaluate the quality of the top-level connection, namely the scoring result; It is the total number of sampling points involved in the calculation, that is, the number of sampling points in the selected evaluation area. The evaluation area can be divided using existing methods such as octree space partitioning, and the specific application scenario needs to be determined. It is the first Sampling point at time The weighted pressure gradient; It is the first Sampling point at time Direction angle The corrected acoustic energy response; It is the first Sampling point at time and corresponding positions The spatial boundary indicates the function value; It is the first Sampling point orientation angle, i.e., the first The angle (in radians) between the sampling point normal vector and the direction perpendicular to the Earth's center; It is the first The spatial vertical offset distance from the sampling point to the theoretical ideal top surface, such as the reconstruction center surface; It is the steepness control coefficient of the Sigmoid function, used to adjust... The degree of influence on the scoring results was determined based on expert experience, with a reference range of values. ; It is a spatial offset penalty function The exponential coefficient, used to control the intensity of the vertical distance penalty, is determined based on expert experience, with a reference range of values. ; It is a non-linear power exponent of the distance offset, used for control. exist The nonlinear increasing rate in; Indicates the first Sampling point at time Direction angle The logarithmic scale response of the corrected acoustic energy response; A reliability index for force-acoustic dual-channel contact is described, where force refers to pressure. It is the denominator form of the Sigmoid function, used to generate nonlinear adjustments to the spatial boundary indicator function, representing the ambiguity of the determination of the contact structure at that point, thus suppressing the ambiguity band of the docking top boundary and avoiding misjudging non-structural contact as a valid docking top. This indicates the degree of contact between the sampling point and the top under pressure and sound wave energy intensity, and is a reliable contact factor after boundary structure adjustment; It is a combined criterion of geometric consistency and spatial fit integrity, which shows that even if the pressure and sound wave energy are high, if the spatial offset is far or the angle is incorrect, the reliability of the sampling point will be reduced.

[0062] Finally, the scoring results will be... Compared with the threshold preset by expert experience method , (Values ​​such as 0.85 and 0.6) were compared to obtain the test results of the mine backfill body roof connection quality:

[0063] when When it is fully connected to the top, a green alert is issued; when When this occurs, it indicates partial top-level contact, and a yellow alert is issued; when When this occurs, it indicates that the connection to the top has failed or the connection has been lost, and a red alert is issued.

[0064] The data, signals, and other parameters involved in steps S1 and S2 above have all undergone standardization processing, such as Z-score.

[0065] In summary, a method and device for intelligent detection of the roof contact quality of mine backfill bodies have been developed.

[0066] The order of the embodiments is for illustrative purposes only and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0067] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0068] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions 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, and should all be included within the protection scope of the present invention.

Claims

1. A mine filling roof contact quality intelligent detection method, characterized in that, The method comprises the following steps: S1. Obtain and preprocess the original pressure signal to obtain preprocessed pressure data; Based on the preprocessed pressure data, a time-weighted nonlinear fitting function model is constructed based on the contribution term of the instantaneous pressure change rate and the pressure gradient moving average term to generate a weighted pressure gradient, and the specific implementation formula is as follows: ； wherein, is a weighted pressure gradient, representing the pressure change intensity at the moment, i.e. the gradient index, for determining the docking trend; is a current item weight fusion factor; is the pressure value at the moment, taken from the pre-processed pressure data; is the pressure value at the moment, taken from the pre-processed pressure data; is the sampling time interval of the sliding window, pre-set according to the application scenario; is the number of sampling points of the sliding window, representing the number of historical samples counted forward from the current time point, determined according to the specific application requirement; is an index variable, representing the sample index in the sliding window; is a time decay exponential factor, for controlling the influence of the historical pressure change item on the change over time near and far; is the pressure value at the moment, taken from the pre-processed pressure data; is the pressure value at the moment, taken from the pre-processed pressure data; is the contribution item of the instantaneous pressure change rate at the current moment; is the time weight factor of the historical pressure change item, which is essentially an exponential decay function, simulating the time memory decay phenomenon; is the sliding average item of the pressure gradient in the sliding window, for trend judgment and stability compensation; At the same time, the original acoustic wave signal is obtained and corrected to obtain a corrected acoustic energy response; S2. Construct a spatial function field based on the weighted pressure gradient and the corrected acoustic energy response; introduce a boundary scale factor in a way of constructing a spatial boundary indicator function through a nonlinear deformation function, and based on the pressure gradient and the acoustic energy gradient, calculate the spatial boundary indicator function value of each point in the whole target region The spatial boundary indicator function value is calculated, and is specifically defined as follows: ； wherein, is a spatial boundary indicator function value, representing the normalized intensity of the contact boundary at a certain point in four-dimensional space, the higher the value, the closer to the actual contact surface; is a boundary scale factor, used to control the overall amplitude variation of the spatial boundary indicator function, and adjusts the sensitivity of the final boundary surface extraction; is a distance attenuation factor, used to control the degree of boundary deformation; is the Euclidean distance, the average of the Euclidean distance between the current point and the point with the maximum pressure and the maximum echo energy, used for boundary expansion; is the pressure gradient, calculated by first-order difference; is the sound energy gradient, calculated by first-order difference; is the ratio of the exponential decay term to the normalized suppression term of the local gradient, which describes the probability trend of whether the current point belongs to the contact boundary by the ratio of the exponential decay term to the normalized suppression term of the local gradient from the main point; is the dynamic response mutation ratio and direction adaptation coupling term; is is the sound wave energy response corrected at the direction angle at the moment; is the angle between the direction of sound wave propagation in space and the vertical direction, used to simulate the directivity weight of sound wave propagation path and the change of echo directivity, obtained by using a low-frequency controllable acoustic transducer array. Based on the weighted pressure gradient, the corrected acoustic energy response and the spatial boundary indicator function value, the quality of the mine filling body is evaluated, and a score result is generated; based on the score result, a mine filling body roof contact quality detection result is obtained.

2. The intelligent detection method for the roof contact quality of the mine filling body according to claim 1, characterized in that, The S1 specifically comprises: By directional weighting and multi-path time reversal, the scattering and energy distortion caused by the inhomogeneous structure inside the filling body are eliminated, and the optimal acoustic signal expression of the contact boundary is extracted; considering the directional angle of the sound wave , the path length of the filling medium is , and the energy received at the moment is , combined with the directional time weighting function, the distance attenuation compensation term and the nonlinear reflection enhancement term, the corrected energy response expression is obtained: ； wherein, is the corrected acoustic energy response at the direction angle ; is the angle between the direction of acoustic wave propagation in space and the vertical direction, used to simulate the directivity weight of acoustic wave propagation path and the change of echo directivity, acquired by low-frequency controllable acoustic transducer array; is the maximum integral path length, i.e. the maximum depth of echo detection; is the acoustic wave propagation path length, which is the integral variable; is the time window sensitive factor, used to control the weight response speed of ; is the delay time corresponding to the maximum energy of the main path echo, determined according to the sampling depth; is the path compensation term, used to avoid the zero-division singularity and near-field amplification problem at ; is the reflection coefficient, representing the energy reflection intensity of acoustic wave on the contact interface, calculated based on the energy ratio of echo and incident wave, and the echo and incident wave energy are acquired by low-frequency controllable acoustic transducer array; is the reflection enhancement index, used to enhance the nonlinear response of interface reflection mutation; is the directivity time weighting function, used to weight and adjust the acoustic wave echo response at different directions and different time points, and plays a role in suppressing non-main direction and non-main path interference; is the distance attenuation compensation term of original acoustic wave signal intensity, used to correct the acoustic wave intensity at each point on the detection path; is the nonlinear reflection enhancement term, used to emphasize the intensity response of acoustic wave reflection at the material interface, so as to better identify the "contact surface" or "structural mutation"; is the multi-weighted signal enhancement kernel, used to determine whether the acoustic wave signal at a specific direction, a specific time and a specific path is sufficient to represent the contact surface or abnormal structural change.

3. The intelligent detection method for the roof contact quality of the mine filling body according to claim 2, characterized in that, The S2 specifically comprises: Based on the weighted pressure gradient, the corrected acoustic energy response and the spatial boundary indicator function value, a unified index evaluation formula is constructed to obtain a score result.

4. The intelligent detection method for the roof contact quality of the mine filling body according to claim 3, characterized in that, The S2 specifically comprises: The evaluation area is divided, and based on the roof contact degree of the sampling points in the evaluation area under the pressure and acoustic energy intensity, a unified index evaluation formula is constructed by combining the geometric consistency and spatial fitting integrity combined criterion: ； in, It is a unified indicator that can quantify and evaluate the quality of the top-level connection, namely the scoring result; This is the total number of sampling points involved in the calculation, i.e., the number of sampling points within the selected evaluation area; It is the first Sampling point at time The weighted pressure gradient; It is the first Sampling point at time Direction angle The corrected acoustic energy response; It is the first Sampling point at time and corresponding positions The spatial boundary indicates the function value; It is the first Sampling point orientation angle, i.e., the first The angle between the sampling point normal vector and the direction perpendicular to the Earth's center; It is the first From the sampling point to the theoretical ideal junction surface; It is the steepness control coefficient of the Sigmoid function, used to adjust... The degree of influence on the scoring results; It is a spatial offset penalty function The exponential coefficient is used to control the strength of the vertical distance penalty; It is a non-linear power exponent of the distance offset, used for control. exist The nonlinear increasing rate in; Indicates the first Sampling point at time Direction angle The logarithmic scale response of the corrected acoustic energy response; A reliability index for force-acoustic dual-channel contact is described, where force refers to pressure. It is the denominator form of the Sigmoid function, used to generate nonlinear adjustments to the spatial boundary indicator function, representing the ambiguity of the determination of the contact structure at that point, thus suppressing the ambiguity band of the docking top boundary and avoiding misjudging non-structural contact as a valid docking top. This indicates the degree of contact between the sampling point and the top under pressure and sound wave energy intensity, and is a reliable contact factor after boundary structure adjustment; It is a combined criterion of geometric consistency and spatial fit integrity, which shows that even if the pressure and sound wave energy are high, if the spatial offset is far or the angle is incorrect, the reliability of the sampling point will be reduced.

5. The intelligent detection method for the roof contact quality of the mine filling body according to claim 4, characterized in that, The S2 specifically comprises: The score result is compared with a preset threshold to obtain a mine filling body roof contact quality detection result.

6. A mine filling roof contact quality intelligent detection device applied to the mine filling roof contact quality intelligent detection method of claim 1, characterized in that, The method comprises the following parts: The pressure data acquisition component, the weighted pressure gradient fitting component, the acoustic signal acquisition and correction component, the spatial function field construction component, and the roof contact quality evaluation component; The pressure data acquisition component acquires the original pressure signal and sends the original pressure signal to the weighted pressure gradient fitting component; The weighted pressure gradient fitting component generates a weighted pressure gradient by constructing a time-weighted nonlinear fitting function model after preprocessing the original pressure signal, and sends the weighted pressure gradient to the spatial function field construction component and the roof contact quality evaluation component; The acoustic signal acquisition and correction component acquires the original acoustic wave signal and performs correction processing to obtain a corrected acoustic energy response, and sends the corrected acoustic energy response to the spatial function field construction component and the roof contact quality evaluation component; The spatial function field construction component constructs a spatial function field based on the weighted pressure gradient and the corrected acoustic energy response to obtain a spatial boundary indicator function value, and sends the spatial boundary indicator function value to the roof contact quality evaluation component; The roof contact quality evaluation component obtains a unified index that can quantitatively evaluate the quality of the roof contact based on the spatial boundary indicator function value and the weighted pressure gradient and the corrected acoustic energy response, and obtains a mine filling body roof contact quality detection result according to the unified index.

Images