A method and system for noise reduction of seismic signals during mining operations in complex geological environments

Abstract

This invention discloses a method and system for noise reduction of seismic signals during mining operations in complex geological environments, relating to the field of mineral geological exploration technology. The method includes: acquiring seismic waveforms from a seismic wave detection device during mining operations as the signal to be processed; establishing a device response degradation model and obtaining current response distortion parameters; acquiring on-site environmental monitoring data and determining the device noise coupling coefficient using an environmental noise coupling analyzer in conjunction with the response distortion parameters; and performing adaptive noise reduction processing on the signal to be processed based on this coefficient, outputting a noise-reduced seismic signal. This invention achieves the synergistic removal of both device degradation noise and environmentally coupled noise by quantifying the device performance degradation law and the environmental noise coupling effect. It solves the problem of noise residue or signal distortion caused by neglecting dynamic changes in device performance in traditional methods, thereby improving the signal-to-noise ratio and geological interpretation reliability of seismic signals in complex geological environments.

Description

Technical Field

[0001] This invention relates to the field of mineral geological exploration technology, specifically to a method and system for noise reduction of seismic signals during mining operations in complex geological environments. Background Technology

[0002] In seismic exploration operations in complex geological environments, seismic wave detection equipment needs to operate continuously for extended periods during mining operations. It collects weak seismic reflection signals in harsh field environments such as high temperature, high humidity, and strong vibration. Inevitably, performance degradation occurs during long-term use, leading to distortion of response characteristics. Simultaneously, the complex environmental factors on-site are coupled with the equipment's degradation status, resulting in a large amount of complex noise related to both equipment condition and environmental factors being mixed into the acquired signals.

[0003] Existing noise reduction technologies are mainly based on fixed noise models and preset filtering parameters, which are difficult to adapt to the dynamic changes in equipment performance and the interaction of environmental factors. They cannot distinguish the differences in noise response of equipment in different states under the same environmental conditions, resulting in problems such as effective signal loss or insufficient noise suppression during noise reduction processing, which seriously affects the quality of seismic data and the reliability of geological interpretation. Summary of the Invention

[0004] This invention addresses the technical problem of effectively handling mixed noise caused by the coupling of equipment performance degradation and environmental noise in existing technologies, and provides a method and system for noise reduction of seismic signals during mining in complex geological environments.

[0005] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: In a first aspect, the present invention provides a method for noise reduction of seismic signals during mining operations in complex geological environments, comprising: Collect seismic waveforms from seismic wave detection equipment within the target exploration area as seismic signals to be processed; Establish a device response degradation model for the seismic wave detection equipment, and obtain the current response distortion parameters of the seismic wave detection equipment based on the device response degradation model; Acquire on-site environmental monitoring data of the target exploration area, and determine the equipment noise coupling coefficient based on the on-site environmental monitoring data and the current response distortion parameters; The seismic signal to be processed is denoised based on the noise coupling coefficient of the equipment, and the denoised seismic signal of the target exploration area is output.

[0006] Secondly, the present invention provides a seismic signal noise reduction system for mining operations in complex geological environments, comprising: The signal acquisition module is used to acquire seismic waveforms from seismic wave detection equipment within the target exploration area as seismic signals to be processed. The equipment response analysis module is used to establish an equipment response degradation model of the seismic wave detection equipment and obtain the current response distortion parameters of the seismic wave detection equipment based on the equipment response degradation model. The noise coupling analysis module is used to acquire on-site environmental monitoring data of the target exploration area and determine the equipment noise coupling coefficient based on the on-site environmental monitoring data and the current response distortion parameters. The signal noise reduction processing module is used to perform noise reduction processing on the seismic signal to be processed according to the noise coupling coefficient of the equipment, and output the noise-reduced seismic signal of the target exploration area.

[0007] The beneficial effects of this invention are: Compared to existing technologies, this invention first establishes an equipment response degradation model to accurately quantify the performance degradation of seismic wave detection equipment during long-term service, enabling precise acquisition of the equipment's current response distortion parameters. Secondly, by combining real-time acquired field environmental monitoring data, it dynamically analyzes the coupling relationship between environmental factors and equipment performance degradation, thereby determining an equipment noise coupling coefficient that better reflects actual working conditions. Thirdly, based on this noise coupling coefficient, adaptive noise reduction processing is applied to the acquired seismic signals, achieving synergistic removal of both equipment performance degradation noise and environmental coupling noise. Finally, through the effective implementation of the above technical path, the signal-to-noise ratio and fidelity of acquired seismic signals in complex geological environments are significantly improved, providing a more reliable data foundation for subsequent seismic data processing and geological interpretation. Attached Figure Description

[0008] Figure 1 A flowchart illustrating the method for noise reduction of seismic signals during mining in complex geological environments provided by this invention; Figure 2 This is a schematic diagram of the structure of the seismic signal noise reduction system for complex geological environments provided by the present invention.

[0009] In the attached diagram, the components represented by each number are as follows: Signal acquisition module 11, equipment response analysis module 12, noise coupling analysis module 13, signal noise reduction processing module 14. Detailed Implementation

[0010] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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.

[0011] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0012] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0013] Example 1, as Figure 1 As shown, embodiments of the present invention provide a method for noise reduction of seismic signals during mining operations in complex geological environments, including: S10: Collect seismic waveforms from seismic wave detection equipment within the target exploration area as seismic signals to be processed; First, raw seismic monitoring data is acquired. During seismic exploration operations in complex geological environments, seismic wave detection equipment is deployed within the target exploration area to continuously receive seismic wave signals from the strata. The equipment performs continuous data acquisition in the on-demand mode, recording raw seismic waveforms containing effective reflected waves and various noise components. During acquisition, it is crucial to ensure the equipment operates according to preset sampling frequencies and gain parameters to guarantee data integrity and accuracy. The preset sampling frequency is set based on the minimum effective wave period of the target geological body and the sampling theorem requirements. For example, if the minimum effective wave period of the target layer is 10 milliseconds, the sampling frequency is set to 1000 Hz to meet the sampling theorem requirements. The gain parameter is set based on the exploration depth and expected signal strength. For example, for shallow exploration below 1000 meters, the gain is set to 60 dB to ensure effective acquisition of weak signals.

[0014] A standardized data acquisition process can preserve the effective components of the original signal to the greatest extent possible while ensuring the integrity of noise characteristics. The acquired seismic waveforms serve as input data for subsequent processing, i.e., the seismic signal to be processed. This seismic signal contains valuable geological information, but also includes noise from equipment performance degradation and environmental interference, providing a high-quality data foundation for subsequent processing stages.

[0015] S20: Establish the device response degradation model of the seismic wave detection equipment, and obtain the current response distortion parameters of the seismic wave detection equipment based on the device response degradation model; After acquiring the seismic signals to be processed, a device response degradation model for the seismic wave detection equipment is further established. This device response degradation model is a mathematical model that describes the change in equipment performance over service time. It is established based on historical performance test data of multiple devices of the same model and is used to quantitatively evaluate the degree of performance degradation of the equipment under the current service state, and to obtain the current response distortion parameters that can accurately reflect the degree of distortion of the equipment response characteristics.

[0016] Specifically, a device response degradation model for the seismic wave detection equipment is established, and the current response distortion parameters of the seismic wave detection equipment are obtained based on the device response degradation model, including: Obtain the device model of the seismic wave detection device, and collect device performance test records of multiple devices of the same model based on the device model; Based on the equipment performance test records of the multiple devices of the same model, an equipment response degradation model of the seismic wave detection device is established. The current service duration of the seismic wave detection equipment is obtained, and the current response distortion parameters of the seismic wave detection equipment are determined in the equipment response degradation model based on the current service duration.

[0017] First, it is necessary to obtain the equipment model information of the currently used seismic wave detection equipment. Based on this model, historical performance test records of multiple devices of the same model are collected from the equipment management database. These historical performance test records contain standard test data of the equipment at different stages of service, reflecting the performance change trend of the equipment over time.

[0018] Secondly, based on the performance test records of multiple devices of the same model collected, a response degradation model for this model of device was established using data modeling methods.

[0019] Specifically, based on the equipment performance test records of the multiple devices of the same model, an equipment response degradation model for the seismic wave detection equipment is established, including: Iterate through the multiple devices of the same model and extract the first device of the same model; Retrieve the first equipment performance test record of the first equipment of the same model. The first equipment performance test record includes multiple service duration points, and each service duration point has acquired seismic waveforms and standard seismic waveforms. Based on the collected seismic waveforms and standard seismic waveforms at each service duration point, the response distortion parameters of the first equipment of the same model at each service duration point are calculated, and the response degradation sub-model of the first equipment is constructed. Following the method of constructing the first device response degradation sub-model for the first device of the same model, device response degradation sub-models for the remaining devices of the same model are constructed to obtain multiple device response degradation sub-models; The device response degradation model of the seismic wave detection device is obtained by fitting the multiple device response degradation sub-models.

[0020] First, multiple devices of the same model are traversed, and the first device of the same model is selected as the modeling sample. The first device of the same model refers to any device selected from multiple seismic wave detection devices of the same model as the first sample. The performance test record of the first device of the same model is retrieved. This first device performance test record contains test data collected by the first device of the same model at multiple different service durations. Each service duration contains two sets of key waveform data: one set is the seismic waveform actually collected at that service duration, and the other set is the standard seismic waveform obtained under the same test conditions. By comparing and analyzing the differences between the actual collected waveform and the standard waveform, the response distortion parameters of the device at each service stage can be calculated, thereby establishing a performance degradation trajectory model for a single device.

[0021] Secondly, based on the acquired seismic waveforms and standard seismic waveforms at each service duration point, the response distortion parameters of the first device of the same model are calculated at each service duration point through waveform comparison analysis. The response distortion parameter is a numerical indicator that quantifies the degree of performance degradation of the device, used to accurately characterize the degree of deviation of the device's signal acquisition capability from the standard state at different service stages. This calculation process essentially quantifies the degree of difference between the actual acquired waveform and the standard waveform. By correlating the calculated service duration points with the corresponding response distortion parameters, a first device response degradation sub-model is constructed, which can reflect the performance degradation trajectory of a single device.

[0022] Specifically, based on the acquired seismic waveforms and standard seismic waveforms at each service duration point, the response distortion parameters of the first equipment of the same model at each service duration point are calculated, and a response degradation sub-model of the first equipment is constructed, including: Select a first service duration point from the plurality of service duration points, and obtain the first acquired seismic waveform and the first standard seismic waveform corresponding to the first service duration point; A waveform similarity analysis is performed on the first acquired seismic waveform and the first standard seismic waveform to calculate the first waveform matching degree; Based on the first waveform matching degree and the preset benchmark matching degree, the first response distortion parameter corresponding to the first service duration point is calculated, where the preset benchmark matching degree is 100%. The response distortion parameters for the remaining service durations are calculated using the same method as the first response distortion parameter for the first service duration point, thus obtaining the response distortion parameters for each service duration point of the first equipment of the same model. Using multiple service duration points as the horizontal axis and the response distortion parameters at each service duration point as the vertical axis, a first equipment response degradation curve is constructed, which serves as the first equipment response degradation sub-model.

[0023] First, from multiple service duration points, the first service duration point is selected as the starting point for analysis, and the first acquired seismic waveform and the first standard seismic waveform corresponding to this service duration point are obtained. The acquired seismic waveform is the seismic signal actually recorded by the equipment at this service duration point, while the standard seismic waveform is the standard signal that the equipment should acquire under the same excitation conditions and ideal state.

[0024] Secondly, waveform similarity analysis was performed on the first acquired seismic waveform and the first standard seismic waveform. Specifically, the time-domain and frequency-domain features of the two waveform signals were extracted, including the amplitude envelope shape, main phase sequence, and spectral energy distribution. The consistency of the two waveforms in amplitude variation trends was quantified by calculating the amplitude correlation coefficient, which was obtained by the ratio of the product of the covariance and standard deviation of the sampling point values ​​within the sliding window. The phase matching degree was evaluated by calculating the time alignment error of the main in-phase axes of the two waveforms, and the phase deviation was determined by the extreme point location method of the cross-correlation function. The frequency feature similarity was quantified by comparing the power spectral density distribution of the two waveforms using the spectral similarity coefficient. Finally, the amplitude correlation coefficient, phase matching degree, and spectral similarity coefficient were linearly combined according to preset weights. Each weight was set based on the prior analysis results of the sensitivity of different features in the seismic signal to equipment performance degradation. The weight of amplitude feature was set to 0.5, the weight of phase feature was set to 0.3, and the weight of frequency feature was set to 0.2. After weighted summation and normalization to the 0 to 100% range, the final first waveform matching degree was obtained. The higher the first waveform matching degree value, the better the device performance is maintained; the lower the value, the more obvious the performance degradation.

[0025] Furthermore, based on the calculated first waveform matching degree and the preset benchmark matching degree, the first response distortion parameter corresponding to the first service duration point is obtained through the difference calculation method. The preset benchmark matching degree is set to 100%, representing the perfect matching level that the first device of the same model should achieve under ideal conditions. The response distortion parameter is the deviation between the actual matching degree and the benchmark matching degree; this parameter objectively reflects the degree of performance degradation of the first device of the same model.

[0026] Using the same calculation method, the collected seismic waveforms and standard seismic waveforms at each of the remaining service durations were compared and analyzed sequentially to obtain the response distortion parameters of the first equipment of the same model at all service durations, thus fully recording the performance changes of the equipment throughout its entire service life.

[0027] Finally, using multiple service duration points as the x-axis and the corresponding response distortion parameters as the y-axis, data points are plotted in a two-dimensional coordinate system and connected to form the first equipment response degradation curve. This first equipment response degradation curve visually demonstrates the decay trajectory of the first equipment's performance over service time, serving as a first equipment response degradation sub-model characterizing the performance degradation features of a single piece of equipment.

[0028] Similarly, following the same modeling process used to construct the first equipment response degradation sub-model for the first piece of equipment of the same model, the same modeling procedure is performed on each of the remaining pieces of equipment of the same model. For each piece of equipment, its complete equipment performance test records are obtained, and the acquired seismic waveforms and standard seismic waveforms corresponding to each service duration are extracted. The response distortion parameters at each point are calculated through waveform similarity analysis, and finally, the response degradation curve of the equipment is plotted with the service duration as the horizontal axis and the response distortion parameters as the vertical axis. After this process is completed, multiple equipment response degradation sub-models equal in number to the number of equipment of the same model are obtained, and each sub-model represents the performance degradation trajectory of a specific piece of equipment.

[0029] Subsequently, the obtained sub-models of equipment response degradation were fitted, and the degradation data of all individual equipment were integrated to extract the common and universal performance degradation patterns of this type of equipment. The fitting process typically employs curve regression analysis, superimposing and comparing the curves of multiple sub-models in the same coordinate system. Through mathematical methods such as least squares, an average curve that best represents the degradation trend of all these individuals is found. This final composite curve is the equipment response degradation model of the seismic wave detection equipment. This model can describe the statistically most probable performance degradation path of this type of equipment over time, providing a reliable basis for accurately assessing the current state of any single piece of equipment.

[0030] Furthermore, the current service life of the seismic wave detection equipment is obtained, which refers to the total working time of the equipment since it was put into operation. Based on this current service life, a query is performed in the established equipment response degradation model. Specifically, on the curve characterizing the equipment performance degradation law, the horizontal axis point corresponding to the current service life is located, and the corresponding response distortion parameter value on the vertical axis is read.

[0031] The parameters determined in this way are the response distortion parameters of the device under its current operating state. These response distortion parameters quantify the degree of performance degradation caused by long-term operation of the device, providing key state input for subsequent noise analysis.

[0032] S30: Obtain on-site environmental monitoring data of the target exploration area, and determine the equipment noise coupling coefficient based on the on-site environmental monitoring data and the current response distortion parameter; After obtaining the response distortion parameters, the noise impact caused by equipment performance degradation will vary significantly with changes in the environmental conditions at the exploration site. Therefore, it is also necessary to obtain the on-site environmental monitoring data of the target exploration area. Based on the on-site environmental monitoring data and the current response distortion parameters, the equipment noise coupling coefficient is determined. This equipment noise coupling coefficient is a comprehensive index characterizing the noise interference intensity under the combined effect of environmental factors and equipment performance degradation. It is used to accurately quantify the noise level generated by the coupling between the equipment and the environment under the current operating conditions, and to provide a precise correction basis for subsequent targeted noise reduction processing.

[0033] Specifically, acquiring on-site environmental monitoring data of the target exploration area, and determining the equipment noise coupling coefficient based on the on-site environmental monitoring data and the current response distortion parameters, including: Obtain on-site environmental monitoring data of the target exploration area, normalize the on-site environmental monitoring data, and construct an environmental monitoring data vector; Obtain the equipment model of the seismic wave detection equipment, and extract the environmental noise coupling analyzer associated with the equipment model; The environmental monitoring data vector and the current response distortion parameter are input into the environmental noise coupling analyzer to obtain the equipment noise coupling coefficient.

[0034] First, it is necessary to acquire on-site environmental monitoring data of the target exploration area, including parameters such as ambient temperature, humidity, ground vibration intensity, and electromagnetic field intensity. These multi-source, heterogeneous environmental monitoring data are then normalized to eliminate differences in dimensions and numerical ranges among the parameters, converting them into dimensionless values ​​at a standard scale, thereby constructing a unified environmental monitoring data vector.

[0035] Simultaneously, the system acquires the equipment model information of the current seismic wave detection equipment and extracts the environmental noise coupling analyzer associated with that model from the equipment model database. This environmental noise coupling analyzer is a dedicated computational model trained using a large amount of historical data, capable of accurately characterizing the noise response characteristics of a specific equipment model under different environmental conditions and performance states.

[0036] Specifically, the construction steps of the environmental noise coupling analyzer include: Data retrieval is performed based on the device model to obtain multiple seismic waveform acquisition records. Each seismic waveform acquisition record includes sample seismic waveforms acquired during sampling, sample environmental monitoring data, sample actual seismic waveforms, and sample response distortion parameters. Based on the multiple seismic waveform acquisition records, multiple environmental noise coupling sub-analyzers are constructed, and the multiple environmental noise coupling sub-analyzers are integrated to generate the environmental noise coupling analyzer.

[0037] First, multiple seismic waveform acquisition records are retrieved from the historical database based on specific equipment models. The historical database is a data warehouse storing complete operational records accumulated by various seismic exploration equipment over long-term operation. Data is organized and managed based on multi-dimensional indexing information such as equipment model, acquisition time, and operating environment. Each seismic waveform acquisition record contains four key data elements: the sample acquired seismic waveform is the raw signal actually acquired by the equipment under specific environmental conditions; the sample environmental monitoring data records the environmental parameters at the time of acquisition, including temperature, humidity, vibration, and other indicators; the sample actual seismic waveform is the real seismic signal obtained through independent measurement; and the sample response distortion parameters characterize the performance status of the equipment at that acquisition moment.

[0038] Secondly, based on the data records, multiple environmental noise coupling sub-analyzers are constructed. Each environmental noise coupling sub-analyzer establishes a mapping relationship between environmental monitoring data, equipment response distortion parameters, and noise characteristics to form a specific analysis model. It can capture the coupling law between environmental factors and equipment status from different dimensions, and together they constitute an analyzer set.

[0039] Specifically, based on the multiple seismic waveform acquisition records, multiple environmental noise coupling sub-analyzers are constructed, including: Multiple sample environmental monitoring data are extracted from the multiple seismic waveform acquisition records to construct a sample environmental monitoring data vector set; Multiple sample response distortion parameters are extracted from the multiple seismic waveform acquisition records to construct a sample response distortion parameter set; Multiple sample seismic waveforms acquired during seismic acquisition and multiple sample actual seismic waveforms are extracted from the multiple seismic waveform acquisition records. A set of sample noise coupling coefficients is constructed based on the multiple sample seismic waveforms acquired during seismic acquisition and multiple sample actual seismic waveforms. Set up multiple environmental noise coupler analysis networks; Using the sample environmental monitoring data vector set and the sample response distortion parameter set as inputs, and the sample noise coupling coefficient set as supervision labels, the multiple environmental noise coupler analysis networks are trained respectively to obtain multiple environmental noise coupler analyzers.

[0040] First, sample environmental monitoring data, including parameters such as temperature, humidity, and vibration, are extracted from seismic waveform acquisition records. After normalization, a standardized sample environmental monitoring data vector set is constructed. Simultaneously, sample response distortion parameters are extracted from the seismic waveform acquisition records to form a sample response distortion parameter set, which together serve as the input features for the environmental noise coupling sub-analyzer.

[0041] Secondly, waveform data is processed by extracting sample seismic waveforms and actual sample seismic waveforms from seismic waveform acquisition records. By calculating the degree of difference between the two waveforms, the coupling effect of environmental noise and equipment distortion is quantified, and a sample noise coupling coefficient set is constructed. This calculation process can be achieved through signal-to-noise ratio estimation, waveform residual energy ratio, or specialized noise assessment algorithms. The obtained sample noise coupling coefficient set serves as a supervision label for the training process, reflecting the true situation of noise coupling under specific environmental conditions and equipment states.

[0042] Furthermore, multiple environmental noise coupling sub-analysis networks are set up. These multiple environmental noise coupling sub-analysis networks adopt different internal architectures and parameter initialization strategies to obtain diverse feature representation capabilities. For example, machine learning models based on different principles, such as multilayer perceptrons, support vector regression, and gradient boosting decision trees, can be used to construct a heterogeneous set of environmental noise coupling sub-analyzers.

[0043] For example, due to the highly nonlinear and complex correlation between environmental monitoring data, equipment response distortion parameters and noise coupling coefficients, and the significant advantages of neural network models in multi-level feature abstraction and complex pattern recognition, a neural network model is selected to construct one of its environmental noise coupling sub-analyzers.

[0044] Specifically, this environmental noise coupler analysis network mainly consists of an input layer, a feature fusion layer, and a coefficient output layer. The input layer receives standardized environmental monitoring data vectors and device response distortion parameters to form joint input features. The feature fusion layer employs a three-layer fully connected neural network structure. The number of hidden layer neurons is configured at a ratio of 1.5 times the dimension of the input features. Each neural network layer uses the ReLU activation function to introduce nonlinear transformation capabilities, and Dropout layers are embedded between network layers with a dropout rate of 0.3 to effectively suppress model overfitting and improve its generalization performance. The output layer uses the Sigmoid activation function to map the final abstract features to continuous values ​​between 0 and 1, serving as the device noise coupling coefficients.

[0045] During training, key hyperparameters included a learning rate of 0.0005, a training epoch count of 200, and a batch size of 32. The learning rate was set to balance training stability and convergence accuracy. The number of training epochs ensured the model fully learned the coupling relationship between environmental factors and equipment status on noise. The batch size balanced training efficiency and gradient stability. Specifically, a supervised learning approach was adopted. Sample environmental monitoring data vectors and sample response distortion parameters were extracted from historical seismic waveform acquisition records as the input sample set. Simultaneously, a sample label set was formed based on the noise coupling coefficient calculated from the sampled seismic waveform and the actual seismic waveform. The input sample set and the corresponding label sample set were divided into training, validation, and test sets in a 7:2:1 ratio.

[0046] Furthermore, the sample feature vectors in the training set are used as input, and the corresponding noise coupling coefficients are used as supervision signals. The network weight parameters are iteratively optimized using the backpropagation algorithm and the Adam optimizer. The mean squared error loss function is used to measure the deviation between the predicted and actual noise coupling coefficients. The training process is monitored using a validation set. Training is terminated when the validation set loss function value no longer decreases for 10 consecutive rounds and the model prediction error is below a predetermined threshold, such as 5%, resulting in a converged environmental noise coupling sub-analyzer. This environmental noise coupling sub-analyzer can effectively capture the complex nonlinear effects of environmental factors and equipment status on noise coupling, achieving accurate prediction of the noise coupling coefficient.

[0047] Similarly, the training set data is input into environmental noise coupler analysis networks with different structures, and each network is trained independently using its own adapted optimization algorithm. Finally, a set of environmental noise coupler analyzers with different principles and complementary advantages are obtained, which can capture the coupling mechanism between the environment and equipment status from multiple dimensions and provide a diverse decision basis for subsequent integrated analysis.

[0048] Finally, an ensemble learning approach is employed to effectively integrate multiple environmental noise coupling sub-analyzers, generating the final environmental noise coupling analyzer through a weighted fusion strategy. Specifically, the prediction accuracy of each environmental noise coupling sub-analyzer is evaluated on the retained test dataset, with the reciprocal of the root mean square error (RMSE) serving as the primary basis for weight allocation. Environmental noise coupling sub-analyzers with smaller RMSEs on the test set are assigned higher weight coefficients, allowing them to play a larger role in the final decision; while those with relatively weaker performance are assigned lower weight coefficients. All weight coefficients are normalized to ensure that the sum of all weights equals 1.

[0049] After obtaining the weighting coefficients of each sub-analyzer, the final environmental noise coupling analyzer generates the prediction result through a weighted average. When new environmental monitoring data vectors and equipment response distortion parameters are received, each environmental noise coupling sub-analyzer outputs its own predicted noise coupling coefficient value. These values ​​are then weighted and summed according to preset weighting coefficients to obtain the final equipment noise coupling coefficient. This integrated environmental noise coupling analyzer combines the advantages of each environmental noise coupling sub-analyzer, significantly improving the accuracy of noise coupling coefficient prediction under different environmental conditions and equipment states.

[0050] Finally, the constructed environmental monitoring data vector and the current equipment response distortion parameters are input into the environmental noise coupling analyzer. This analyzer calculates the final equipment noise coupling coefficient using an internally established mapping relationship. This coefficient comprehensively reflects the noise interference intensity caused by equipment performance degradation under current environmental conditions, providing crucial parameter data for subsequent precise noise reduction processing.

[0051] S40: Perform noise reduction processing on the seismic signal to be processed according to the noise coupling coefficient of the equipment, and output the noise-reduced seismic signal of the target exploration area.

[0052] Furthermore, based on the aforementioned equipment noise coupling coefficient, precise noise reduction processing is implemented on the seismic signal to be processed. The equipment noise coupling coefficient, as a key parameter, directly determines the coefficient configuration of the filter bank and the noise suppression strength in the noise reduction algorithm. In specific implementation, the corresponding adaptive filtering algorithm architecture is first selected according to the numerical range of the equipment noise coupling coefficient. For example, a threshold range is set: when the equipment noise coupling coefficient is greater than 0.7, it is considered high noise coupling; between 0.3 and 0.7, it is considered medium; and below 0.3, it is considered low. When the noise coupling degree is high, a Wiener filter combination with deep noise analysis capabilities is used; when the coefficient indicates a medium noise coupling degree, a wavelet threshold denoising method is selected; and when the coefficient indicates a low noise coupling degree, an improved Kalman filter algorithm is applied.

[0053] Furthermore, after determining the basic algorithm architecture, the equipment noise coupling coefficient is input as a core parameter into the selected denoising algorithm, dynamically adjusting key threshold settings: controlling the width and depth of the band-stop filter in frequency domain filtering, adjusting the size and update frequency of the sliding window in time domain processing, and influencing the selection of wavelet basis functions and the form of the threshold function in time-frequency joint analysis. This parameterized adaptive mechanism ensures that the denoising intensity precisely matches the actual noise interference level. Simultaneously, changes in the statistical characteristics of the signal are continuously monitored during processing, and denoising parameters are dynamically fine-tuned to ensure signal fidelity. The final denoised seismic signal output significantly suppresses various types of noise generated by equipment performance degradation and environmental factors while effectively preserving the original geological information, providing a high-quality data foundation for subsequent seismic data interpretation and geological structural analysis.

[0054] In summary, the embodiments of this application have at least the following technical effects: Compared to existing technologies, this invention firstly constructs a device response degradation model, enabling a quantitative description of the performance degradation law of seismic wave detection equipment and accurately assessing the degree of response distortion under current service conditions. Secondly, by combining real-time environmental monitoring data with equipment distortion parameters, a dual sensing mechanism of environmental factors and equipment status is established, thereby accurately calculating the noise coupling coefficient reflecting the actual operating conditions. Thirdly, based on this noise coupling coefficient, targeted noise reduction processing is carried out, effectively solving the problems of noise residue or signal distortion caused by neglecting equipment performance degradation in traditional methods.

[0055] Finally, this processing method, which combines device state awareness with environmental adaptation, significantly improves the accuracy and reliability of seismic signal noise reduction in complex geological environments, providing high-quality data support for subsequent geological interpretation.

[0056] Example 2, as Figure 2 As shown, based on the same inventive concept as the mining-in-process seismic signal denoising method for complex geological environments provided in Embodiment 1, this embodiment of the invention also provides a mining-in-process seismic signal denoising system for complex geological environments, comprising: Signal acquisition module 11 is used to acquire seismic waveforms from seismic wave detection equipment within the target exploration area as seismic signals to be processed; The equipment response analysis module 12 is used to establish an equipment response degradation model of the seismic wave detection equipment and obtain the current response distortion parameters of the seismic wave detection equipment based on the equipment response degradation model. The noise coupling analysis module 13 is used to acquire on-site environmental monitoring data of the target exploration area and determine the equipment noise coupling coefficient based on the on-site environmental monitoring data and the current response distortion parameters. The signal noise reduction processing module 14 is used to perform noise reduction processing on the seismic signal to be processed according to the noise coupling coefficient of the equipment, and output the noise-reduced seismic signal of the target exploration area.

[0057] The signal acquisition module 11 is specifically used for: Seismic waveforms collected by seismic wave detection equipment within the target exploration area are used as seismic signals to be processed.

[0058] The device response analysis module 12 is specifically used for: Establish a device response degradation model for the seismic wave detection equipment, and obtain the current response distortion parameters of the seismic wave detection equipment based on the device response degradation model, including: Obtain the device model of the seismic wave detection device, and collect device performance test records of multiple devices of the same model based on the device model; Based on the equipment performance test records of the multiple devices of the same model, an equipment response degradation model of the seismic wave detection device is established. The current service duration of the seismic wave detection equipment is obtained, and the current response distortion parameters of the seismic wave detection equipment are determined in the equipment response degradation model based on the current service duration.

[0059] Specifically, based on the equipment performance test records of the multiple devices of the same model, an equipment response degradation model for the seismic wave detection equipment is established, including: Iterate through the multiple devices of the same model and extract the first device of the same model; Retrieve the first equipment performance test record of the first equipment of the same model. The first equipment performance test record includes multiple service duration points, and each service duration point has acquired seismic waveforms and standard seismic waveforms. Based on the collected seismic waveforms and standard seismic waveforms at each service duration point, the response distortion parameters of the first equipment of the same model at each service duration point are calculated, and the response degradation sub-model of the first equipment is constructed. Following the method of constructing the first device response degradation sub-model for the first device of the same model, device response degradation sub-models for the remaining devices of the same model are constructed to obtain multiple device response degradation sub-models; The device response degradation model of the seismic wave detection device is obtained by fitting the multiple device response degradation sub-models.

[0060] Specifically, based on the acquired seismic waveforms and standard seismic waveforms at each service duration point, the response distortion parameters of the first equipment of the same model at each service duration point are calculated, and a response degradation sub-model of the first equipment is constructed, including: Select a first service duration point from the plurality of service duration points, and obtain the first acquired seismic waveform and the first standard seismic waveform corresponding to the first service duration point; A waveform similarity analysis is performed on the first acquired seismic waveform and the first standard seismic waveform to calculate the first waveform matching degree; Based on the first waveform matching degree and the preset benchmark matching degree, the first response distortion parameter corresponding to the first service duration point is calculated, where the preset benchmark matching degree is 100%. The response distortion parameters for the remaining service durations are calculated using the same method as the first response distortion parameter for the first service duration point, thus obtaining the response distortion parameters for each service duration point of the first equipment of the same model. Using multiple service duration points as the horizontal axis and the response distortion parameters at each service duration point as the vertical axis, a first equipment response degradation curve is constructed, which serves as the first equipment response degradation sub-model.

[0061] The noise coupling analysis module 13 is specifically used for: Acquire on-site environmental monitoring data of the target exploration area, and determine the equipment noise coupling coefficient based on the on-site environmental monitoring data and the current response distortion parameters, including: Obtain on-site environmental monitoring data of the target exploration area, normalize the on-site environmental monitoring data, and construct an environmental monitoring data vector; Obtain the equipment model of the seismic wave detection equipment, and extract the environmental noise coupling analyzer associated with the equipment model; The environmental monitoring data vector and the current response distortion parameter are input into the environmental noise coupling analyzer to obtain the equipment noise coupling coefficient; Specifically, the construction steps of the environmental noise coupling analyzer include: Data retrieval is performed based on the device model to obtain multiple seismic waveform acquisition records. Each seismic waveform acquisition record includes sample seismic waveforms acquired during sampling, sample environmental monitoring data, sample actual seismic waveforms, and sample response distortion parameters. Based on the multiple seismic waveform acquisition records, multiple environmental noise coupling sub-analyzers are constructed, and the multiple environmental noise coupling sub-analyzers are integrated to generate the environmental noise coupling analyzer.

[0062] Furthermore, based on the multiple seismic waveform acquisition records, multiple environmental noise coupling sub-analyzers are constructed, including: Multiple sample environmental monitoring data are extracted from the multiple seismic waveform acquisition records to construct a sample environmental monitoring data vector set; Multiple sample response distortion parameters are extracted from the multiple seismic waveform acquisition records to construct a sample response distortion parameter set; Multiple sample seismic waveforms acquired during seismic acquisition and multiple sample actual seismic waveforms are extracted from the multiple seismic waveform acquisition records. A set of sample noise coupling coefficients is constructed based on the multiple sample seismic waveforms acquired during seismic acquisition and multiple sample actual seismic waveforms. Set up multiple environmental noise coupler analysis networks; Using the sample environmental monitoring data vector set and the sample response distortion parameter set as inputs, and the sample noise coupling coefficient set as supervision labels, the multiple environmental noise coupler analysis networks are trained respectively to obtain multiple environmental noise coupler analyzers.

[0063] Specifically, the signal noise reduction processing module 14 is used for: The seismic signal to be processed is denoised based on the noise coupling coefficient of the equipment, and the denoised seismic signal of the target exploration area is output.

[0064] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0065] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0066] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A method for noise reduction of seismic signals during mining operations in complex geological environments, characterized in that, The method includes: Collect seismic waveforms from seismic wave detection equipment within the target exploration area as seismic signals to be processed; Establish a device response degradation model for the seismic wave detection equipment, and obtain the current response distortion parameters of the seismic wave detection equipment based on the device response degradation model; Acquire on-site environmental monitoring data of the target exploration area, and determine the equipment noise coupling coefficient based on the on-site environmental monitoring data and the current response distortion parameters; The seismic signal to be processed is denoised based on the noise coupling coefficient of the equipment, and the denoised seismic signal of the target exploration area is output.

2. The method according to claim 1, characterized in that, Establish a device response degradation model for the seismic wave detection equipment, and obtain the current response distortion parameters of the seismic wave detection equipment based on the device response degradation model, including: Obtain the device model of the seismic wave detection device, and collect device performance test records of multiple devices of the same model based on the device model; Based on the equipment performance test records of the multiple devices of the same model, an equipment response degradation model of the seismic wave detection device is established. The current service duration of the seismic wave detection equipment is obtained, and the current response distortion parameters of the seismic wave detection equipment are determined in the equipment response degradation model based on the current service duration.

3. The method according to claim 2, characterized in that, Based on the equipment performance test records of the multiple devices of the same model, an equipment response degradation model for the seismic wave detection equipment is established, including: Iterate through the multiple devices of the same model and extract the first device of the same model; Retrieve the first equipment performance test record of the first equipment of the same model. The first equipment performance test record includes multiple service duration points, and each service duration point has acquired seismic waveforms and standard seismic waveforms. Based on the collected seismic waveforms and standard seismic waveforms at each service duration point, the response distortion parameters of the first equipment of the same model at each service duration point are calculated, and the response degradation sub-model of the first equipment is constructed. Following the method of constructing the first device response degradation sub-model for the first device of the same model, device response degradation sub-models for the remaining devices of the same model are constructed to obtain multiple device response degradation sub-models; The device response degradation model of the seismic wave detection device is obtained by fitting the multiple device response degradation sub-models.

4. The method according to claim 3, characterized in that, Based on the acquired seismic waveforms and standard seismic waveforms at each service duration point, the response distortion parameters of the first equipment of the same model at each service duration point are calculated, and a response degradation sub-model of the first equipment is constructed, including: Select a first service duration point from the plurality of service duration points, and obtain the first acquired seismic waveform and the first standard seismic waveform corresponding to the first service duration point; A waveform similarity analysis is performed on the first acquired seismic waveform and the first standard seismic waveform to calculate the first waveform matching degree; Based on the first waveform matching degree and the preset benchmark matching degree, the first response distortion parameter corresponding to the first service duration point is calculated, where the preset benchmark matching degree is 100%. The response distortion parameters for the remaining service durations are calculated using the same method as the first response distortion parameter for the first service duration point, thus obtaining the response distortion parameters for each service duration point of the first equipment of the same model. Using multiple service duration points as the horizontal axis and the response distortion parameters at each service duration point as the vertical axis, a first equipment response degradation curve is constructed, which serves as the first equipment response degradation sub-model.

5. The method according to claim 1, characterized in that, Acquire on-site environmental monitoring data of the target exploration area, and determine the equipment noise coupling coefficient based on the on-site environmental monitoring data and the current response distortion parameters, including: Obtain on-site environmental monitoring data of the target exploration area, normalize the on-site environmental monitoring data, and construct an environmental monitoring data vector; Obtain the equipment model of the seismic wave detection equipment, and extract the environmental noise coupling analyzer associated with the equipment model; The environmental monitoring data vector and the current response distortion parameter are input into the environmental noise coupling analyzer to obtain the equipment noise coupling coefficient.

6. The method according to claim 5, characterized in that, The construction steps of the environmental noise coupling analyzer include: Data retrieval is performed based on the device model to obtain multiple seismic waveform acquisition records. Each seismic waveform acquisition record includes sample seismic waveforms acquired during sampling, sample environmental monitoring data, sample actual seismic waveforms, and sample response distortion parameters. Based on the multiple seismic waveform acquisition records, multiple environmental noise coupling sub-analyzers are constructed, and the multiple environmental noise coupling sub-analyzers are integrated to generate the environmental noise coupling analyzer.

7. The method according to claim 6, characterized in that, Based on the multiple seismic waveform acquisition records, multiple environmental noise coupling sub-analyzers are constructed, including: Multiple sample environmental monitoring data are extracted from the multiple seismic waveform acquisition records to construct a sample environmental monitoring data vector set; Multiple sample response distortion parameters are extracted from the multiple seismic waveform acquisition records to construct a sample response distortion parameter set; Multiple sample seismic waveforms acquired during seismic acquisition and multiple sample actual seismic waveforms are extracted from the multiple seismic waveform acquisition records. A set of sample noise coupling coefficients is constructed based on the multiple sample seismic waveforms acquired during seismic acquisition and multiple sample actual seismic waveforms. Set up multiple environmental noise coupler analysis networks; Using the sample environmental monitoring data vector set and the sample response distortion parameter set as inputs, and the sample noise coupling coefficient set as supervision labels, the multiple environmental noise coupler analysis networks are trained respectively to obtain multiple environmental noise coupler analyzers.

8. A seismic signal noise reduction system for mining operations in complex geological environments, characterized in that, For performing the method according to any one of claims 1-7, comprising: The signal acquisition module is used to acquire seismic waveforms from seismic wave detection equipment within the target exploration area as seismic signals to be processed. The equipment response analysis module is used to establish an equipment response degradation model of the seismic wave detection equipment and obtain the current response distortion parameters of the seismic wave detection equipment based on the equipment response degradation model. The noise coupling analysis module is used to acquire on-site environmental monitoring data of the target exploration area and determine the equipment noise coupling coefficient based on the on-site environmental monitoring data and the current response distortion parameters. The signal noise reduction processing module is used to perform noise reduction processing on the seismic signal to be processed according to the noise coupling coefficient of the equipment, and output the noise-reduced seismic signal of the target exploration area.

Images