Electromagnetic detection signal extraction method, device, equipment and storage medium

Abstract

The application provides an electromagnetic detection signal extraction method, device and equipment and a storage medium, and belongs to the technical field of electromagnetic detection. The method comprises the following steps: obtaining a target signal, wherein the target signal is an original geological electromagnetic detection signal of a target geological region; calculating the similarity between the target signal and a plurality of standard signals, determining a standard signal with a similarity greater than a first preset similarity threshold as a target standard signal, wherein the plurality of standard signals are geological electromagnetic detection signals of a plurality of standard geological regions with a pre-determined denoising coefficient; constructing a denoising coefficient matrix of the target signal based on the denoising coefficient corresponding to the target standard signal, constructing a denoised signal based on the denoising coefficient matrix; and performing denoising processing on the target signal based on the denoised signal, and extracting a target geological signal from the target signal. The application can improve the reliability of electromagnetic detection signal extraction.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of electromagnetic detection, and more particularly relates to an electromagnetic detection signal extraction method, device, equipment and storage medium. BACKGROUND

[0002] The electromagnetic detection method can be widely applied in police security and exploration. The electromagnetic detection method can accurately capture geological signals at different depths due to its high signal-to-noise ratio, strong anti-interference ability and wide frequency coverage range, thereby providing rich data support for geological exploration.

[0003] The prior art generally needs to reconstruct and denoise the detection signal, and then screen out the corresponding geological signal representing the current geological region. However, when this method is used, most of the signal reconstruction is directly performed, and for some geological regions that do not require high accuracy, a large amount of computing resources need to be called, and the computational complexity is high. SUMMARY

[0004] The application aims to provide an electromagnetic detection signal extraction method, device, equipment and storage medium to solve the problem that most of the prior art needs to reconstruct and denoise the electromagnetic detection signal, needs to call a large amount of computing resources, has high computational complexity, and results in low detection reliability.

[0005] The first aspect of the embodiment of the application provides an electromagnetic detection signal extraction method, comprising:

[0006] obtaining a target signal, the target signal being an original geological electromagnetic detection signal of a target geological region;

[0007] calculating the similarity between the target signal and a plurality of standard signals, determining the standard signal with a similarity greater than a first preset similarity threshold as a target standard signal, the plurality of standard signals being geological electromagnetic detection signals of a plurality of standard geological regions with a pre-determined denoising coefficient;

[0008] constructing a denoising coefficient matrix of the target signal based on the denoising coefficient corresponding to the target standard signal, and constructing a denoised signal based on the denoising coefficient matrix;

[0009] performing denoising processing on the target signal based on the denoised signal, and extracting a target geological signal from the target signal.

[0010] The second aspect of the embodiment of the application provides an electromagnetic detection signal extraction device, comprising:

[0011] a signal acquisition module configured to obtain a target signal, the target signal being an original geological electromagnetic detection signal of a target geological region;

[0012] The similarity calculation module is configured to calculate similarities between the target signal and a plurality of standard signals, determine a standard signal with a similarity greater than a first preset similarity threshold as a target standard signal, and the plurality of standard signals are geological electromagnetic detection signals of a plurality of standard geological regions with pre-determined de-noising coefficients.

[0013] The matrix construction module is configured to construct a de-noising coefficient matrix of the target signal based on the de-noising coefficient corresponding to the target standard signal, and construct a de-noising signal based on the de-noising coefficient matrix.

[0014] The signal processing module is configured to perform de-noising processing on the target signal based on the de-noising signal, and extract a target geological signal from the target signal.

[0015] In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the electromagnetic detection signal extraction method when executing the computer program.

[0016] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program implements the steps of the electromagnetic detection signal extraction method when executed by a processor.

[0017] The electromagnetic detection signal extraction method, device, equipment and storage medium provided by the embodiments of the present application have the following advantages: the embodiments of the present application first acquire the original geological electromagnetic signal of the target region, without complex reconstruction of the signal, but directly calling a plurality of standard geological signals with pre-determined de-noising coefficients as a reference. By calculating the similarities between the target signal and these standard signals, the target standard signal with a similarity greater than a threshold is selected, and a de-noising coefficient matrix is quickly constructed using the known de-noising coefficient, and then a de-noising signal is generated. The entire process does not require a large amount of calculation of signal reconstruction, and the de-noising coefficient of the standard signal is pre-determined, without real-time analysis of noise characteristics, greatly reducing the consumption of computing resources. At the same time, the de-noising matrix is constructed based on the standard signal with known noise characteristics, which can accurately match the noise mode of the target signal, ensuring the stability of the de-noising processing, and finally efficiently extracting a reliable target geological signal from the target signal, realizing high-reliability detection. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0019] Figure 1A flowchart of an electromagnetic detection signal extraction method provided by an embodiment of the present application is shown in FIG. 1.

[0020] Figure 2 A structural block diagram of an electromagnetic detection signal extraction device provided by an embodiment of the present application is shown in FIG. 2.

[0021] Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 3. DETAILED DESCRIPTION

[0022] In the following description, specific details are set forth in order to provide a thorough understanding of embodiments of the present application. However, persons having ordinary skill in the art will appreciate that embodiments of the present application can be practiced without the specific details, and that the present application is not limited to the specific details or the particular order in which matters are presented herein. In some instances, descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as to not unnecessarily obscure the description of the present application.

[0023] In order to make the objectives, technical solutions, and advantages of the present application clearer, the following will be described in detail with reference to the accompanying drawings.

[0024] Reference will be made to Figure 1 , Figure 1 A flowchart of an electromagnetic detection signal extraction method provided by an embodiment of the present application can be executed by an electronic device, and the method can include S101-S104.

[0025] S101, obtaining a target signal, the target signal being an original geologic electromagnetic detection signal of a target geologic region.

[0026] In this embodiment, the target signal can be an original geologic electromagnetic detection signal of a target geologic region that needs to be detected, and can be collected by at least one electromagnetic detection sensor. A plurality of collection points can be provided in the target geologic region, and at least one electromagnetic detection sensor is provided at each collection point. The electromagnetic sensors at the collection points can upload the collected original geologic electromagnetic detection signal to an electronic device, and the electronic device can analyze the signal and extract useful geologic signals therefrom, which can be marked as target geologic signals. The target geologic signals can be used to analyze the situation of the target geologic region.

[0027] Generally, the target signal can be a multi-source signal. The original geologic electromagnetic detection signal can include a large amount of noise, and the noise signal in the original geologic electromagnetic detection signal needs to be filtered out to obtain useful geologic signals that can be used to indicate the characteristics of the target geologic region, and then the geologic analysis can be performed according to the useful geologic signals.

[0028] For example, the target geological region can include a plurality of monitoring regions, each monitoring region is provided with at least one collection point, and each collection point is provided with an electromagnetic detection sensor which can collect electromagnetic detection signals of the region.

[0029] In S102, similarity between the target signal and a plurality of standard signals is calculated, and a standard signal with a similarity greater than a first preset similarity threshold is determined as a target standard signal, the plurality of standard signals being geological electromagnetic detection signals of a plurality of standard geological regions with pre-determined denoising coefficients.

[0030] In the embodiments of the present application, the standard geological region can be a geological region with pre-defined noise categories and pre-determined denoising coefficients of different noise categories. In the field of police security exploration, the standard geological region and the denoising coefficients of the standard geological region can be obtained by processing signals of existing or screened geological regions. That is, a database of standard geological regions can be pre-constructed.

[0031] Generally, a geological electromagnetic detection signal is superimposed by a target geological signal and a noise signal, and the noise signal in the geological electromagnetic detection signal can be filtered to obtain the target geological signal. The denoising coefficient is used to generate a denoising signal opposite to the noise signal, and then the denoising signal is multiplied by the original geological electromagnetic detection signal to filter the noise signal.

[0032] Optionally, the similarity between the target signal and the plurality of standard signals can be calculated by a Pearson correlation coefficient, a cross-correlation coefficient, an Euclidean distance, a cosine similarity, or a pre-trained signal similarity calculation model, to obtain a plurality of similarities. The way of calculating the similarity between the target signal and the plurality of standard signals is consistent.

[0033] After obtaining the plurality of similarities, a standard signal with a similarity greater than a first preset similarity threshold is screened out. If there is at least one standard signal with a similarity greater than the first preset similarity threshold, the at least one standard signal is marked as a target standard signal. If there is no standard signal with a similarity greater than the first preset similarity threshold, a denoising signal of the target signal can be determined by signal reconstruction.

[0034] The first preset similarity threshold can be determined in combination with a detection level of the target geological region, and the detection level is used to represent the importance of the geological region. The detection level can be increased as the importance increases.

[0035] For example, the detection levels can be marked as a first detection level, a second detection level, a third detection level, a fourth detection level, and a fifth detection level, and the corresponding first similarity threshold, the second similarity threshold, the third similarity threshold, the fourth similarity threshold, and the fifth similarity threshold can be 0.6, 0.65, 0.7, 0.75, and 0.8 respectively. The actual situation can be set according to the actual situation.

[0036] In the embodiment of the present application, the determination process of the de-noising coefficient corresponding to the standard signal includes: obtaining an original signal, the original signal being an original geology electromagnetic detection signal of a standard geology region; performing feature extraction on the original signal to obtain a noise signal and a key geology signal corresponding to the original signal; determining a de-noising coefficient of the noise signal based on a linear relationship between the original signal, the noise signal, and the key geology signal.

[0037] In the embodiment of the present application, after obtaining the target standard signal, a de-noising coefficient matrix of the target signal can be constructed based on the de-noising coefficient corresponding to the target standard signal.

[0038] In the embodiment of the present application, after obtaining the target standard signal, a de-noising coefficient matrix of the target signal can be constructed based on the de-noising coefficient corresponding to the target standard signal.

[0039] The target signal includes a plurality of original geology detection signals collected by electromagnetic detection sensors, and is a detection signal set. Correspondingly, the target standard signal is also a standard detection signal set, and the number of geology detection signals in the target standard signal is the same as the number of geology detection signals included in the target signal.

[0040] In the embodiment of the present application, when the target standard signal includes one signal, a de-noising coefficient matrix can be constructed based on the de-noising coefficient in the one target standard signal, and a de-noising signal can be constructed based on the de-noising coefficient matrix. Alternatively, when the target standard signal includes a plurality of signals, an average value of the de-noising coefficients in the plurality of target standard signals can be calculated to determine a plurality of average de-noising coefficients, and then a de-noising coefficient matrix can be constructed.

[0041] Optionally, after obtaining the de-noising coefficient matrix, a corresponding de-noising signal can be directly constructed based on the de-noising coefficient matrix. Alternatively, after obtaining the de-noising coefficient matrix, the de-noising coefficient matrix can be modified based on the similarity, and then a corresponding de-noising signal can be constructed in combination with the modified de-noising coefficient matrix. The actual situation can be selected according to the actual situation.

[0042] In the embodiment of the present application, a mapping table can be determined in advance, in which different de-noising coefficients can correspond to different de-noising signals. A plurality of de-noising signals can be pre-stored in the electronic device, and after obtaining the de-noising coefficient matrix, different de-noising signals can be quickly called based on each de-noising coefficient in the de-noising coefficient matrix, without the need for re-construction.

[0043] S104, denoising processing is performed on the target signal based on the denoised signal, and a target geological signal is extracted from the target signal.

[0044] After obtaining the corresponding denoised signal, the denoised signal can be multiplied with the target signal, and the noise signal in the target signal can be inversely eliminated, and the target geological signal can be extracted from the target signal. Finally, the target geological region can be analyzed in combination with the target geological signal, and the corresponding detection result can be obtained.

[0045] In an embodiment of the present application, the target geological signal includes a geological feature signal corresponding to each collection point in the target region. After extracting the target geological signal from the target signal, it further includes: calculating the signal-to-noise ratio between the geological feature signal corresponding to each collection point and the preset geological feature signal to obtain a plurality of signal-to-noise ratios; determining the fusion weight corresponding to each geological feature signal based on the plurality of signal-to-noise ratios; and performing signal fusion on the geological feature signals corresponding to the plurality of collection points based on the respective fusion weights to obtain a geological fusion signal corresponding to the target region. After obtaining the geological fusion signal, the corresponding geological fusion signal can be used for geological monitoring.

[0046] From the above, it can be concluded that the embodiment of the present application first acquires the original geological electromagnetic signal of the target region, without complex reconstruction of the signal, but directly calls a plurality of standard geological signals with pre-determined denoising coefficients as a reference. By calculating the similarity between the target signal and these standard signals, the target standard signal with a similarity exceeding a threshold is selected, and a denoising coefficient matrix is quickly constructed using the known denoising coefficient, and a denoised signal is generated. The entire process does not require a large amount of calculation for signal reconstruction, as the denoising coefficients of the standard signals are pre-determined, without the need for real-time analysis of noise characteristics, greatly reducing the consumption of computing resources. At the same time, the denoising matrix is constructed based on the standard signal with known noise characteristics, which can accurately match the noise mode of the target signal, ensuring the stability of the denoising process, and finally efficiently extracting a reliable target geological signal from the target signal, achieving high-reliability detection.

[0047] In an embodiment of the present application, the target signal includes a plurality of geological signals, and the target standard signal includes a plurality of standard geological signals, each standard geological signal corresponding to a denoising coefficient.

[0048] Constructing a denoising coefficient matrix of the target signal based on the denoising coefficient corresponding to the target standard signal includes:

[0049] For each geologic signal, the similarity of the geologic signal to all standard geologic signals is calculated. If there is a standard geologic signal with a similarity to the geologic signal greater than a second preset similarity threshold, the de-noising coefficient corresponding to the geologic signal is determined based on the de-noising coefficients of all standard geologic signals with a similarity greater than the second preset similarity threshold. If there is no standard geologic signal with a similarity to the geologic signal greater than the second preset similarity threshold, the de-noising coefficient corresponding to the geologic signal is determined based on the de-noising coefficients of all standard geologic signals. The de-noising coefficient matrix is constructed based on the de-noising coefficients corresponding to all geologic signals.

[0050] For example, the de-noising coefficient matrix is [de-noising coefficient 1, de-noising coefficient 2, …]. After obtaining the de-noising coefficient matrix, different de-noising signals can be determined in combination with the de-noising coefficients in the de-noising coefficient matrix to filter out noise signals.

[0051] The embodiments of the present application can calculate the similarity between each geologic signal and all standard geologic signals, find standard geologic signals with high similarity to the geologic signal from all standard geologic signals, so as to determine the de-noising coefficient corresponding to the geologic signal, and finally realize the construction of the de-noising coefficient matrix.

[0052] The embodiments of the present application consider that similar signals are affected by similar rules of noise, and the de-noising coefficient of the geologic signal can be determined by means of the de-noising coefficient of the similar standard geologic signal. Therefore, after calculating the similarity between each geologic signal and all standard geologic signals, if there is a standard geologic signal with a similarity to the geologic signal greater than a second preset similarity threshold, the de-noising coefficient of the geologic signal can be determined by means of the de-noising coefficient of the similar standard geologic signal.

[0053] Optionally, the average of the de-noising coefficients of all standard geologic signals with a similarity greater than the second preset similarity threshold can be calculated as the de-noising coefficient of the geologic signal.

[0054] Alternatively, the de-noising coefficient of the standard geologic signal with the maximum similarity can be selected from all standard geologic signals with a similarity greater than the second preset similarity threshold as the de-noising coefficient of the geologic signal.

[0055] If there is no standard geologic signal with a similarity to the geologic signal greater than the second preset similarity threshold, the de-noising coefficient of the geologic signal can be determined by means of the de-noising coefficients of all standard geologic signals in the target standard geologic signal.

[0056] In an embodiment of the present application, the de-noising coefficient corresponding to the geological signal is determined based on de-noising coefficients of all standard geological signals, including: calculating the average of the de-noising coefficients of all standard geological signals as the de-noising coefficient corresponding to the geological signal. Alternatively, the similarity between each standard geological signal and the geological signal is used as a de-noising coefficient weighting value, and the weighted average of the de-noising coefficients of each standard geological signal is calculated, and the weighted average is used as the de-noising coefficient corresponding to the geological signal.

[0057] Specifically, if there is no standard geological signal with high similarity, but there may be a standard geological signal with a de-noising coefficient higher than the geological signal among all standard geological signals, and there may also be a standard geological signal with a de-noising coefficient lower than the geological signal. At this time, the average of the de-noising coefficients of all standard geological signals in the target standard geological signal can be calculated, and the average is used as the de-noising coefficient of the geological signal.

[0058] Alternatively, the de-noising coefficient of the standard geological signal with the highest similarity to the geological signal is weighted, and the weighted de-noising coefficient is used as the de-noising coefficient of the geological signal.

[0059] Wherein, if the difference between the geological signal and the standard geological signal with the highest similarity is not negative, it indicates that the noise of the geological signal may be greater than the noise of the standard geological signal, at this time, forward weighting can be performed to determine the de-noising coefficient that matches the geological signal better.

[0060] If the difference between the geological signal and the standard geological signal with the highest similarity is negative, it indicates that the noise of the geological signal may be less than the noise of the standard geological signal, at this time, reverse weighting can be performed to determine the de-noising coefficient that matches the geological signal better.

[0061] In an embodiment of the present application, the second preset similarity threshold can be determined by weighting the first preset similarity threshold in combination with the signal-to-noise ratio of the target standard signal, and the second preset similarity threshold is less than the first preset similarity threshold.

[0062] Specifically, if the signal-to-noise ratio of the target standard signal exceeds the preset signal-to-noise ratio threshold, it indicates that the target standard signal is a high-noise signal, and the first preset similarity threshold can be positively adjusted in combination with the similarity between the target signal and the target standard signal to obtain the second preset similarity threshold. At this time, the second preset similarity threshold obtained by positive adjustment = 0.5 × (1 + the similarity) × the first preset similarity threshold, which is closer to the first preset similarity threshold

[0063] If the signal-to-noise ratio of the target standard signal does not exceed the preset signal-to-noise ratio threshold, it indicates that the target standard signal is a non-high-noise signal. The first preset similarity threshold can be inversely adjusted in combination with the similarity of the target signal and the target standard signal to obtain a second preset similarity threshold. At this time, the second preset similarity threshold obtained by inverse adjustment = (1-the similarity) x the first preset similarity threshold, which is further away from the first preset similarity threshold. The preset signal-to-noise ratio threshold can be selected and set in combination with the actual situation.

[0064] After obtaining the denoising coefficients of all the geological signals, a denoising coefficient matrix can be constructed according to the order corresponding to the geological signals in the target signal, so as to facilitate the generation of the corresponding denoising signal subsequently.

[0065] The embodiments of the present application preferentially match each geological signal in the target signal with the most similar standard signal, and reuse the denoising experience thereof. For special geological signals, the experience of all standard geological signals can be comprehensively used for processing. The finally formed denoising coefficient matrix can provide denoising parameters for each sub-signal in the target signal, thereby improving the accuracy and adaptability of the overall denoising effect.

[0066] In an embodiment of the present application, the denoising coefficient matrix is constructed based on the denoising coefficients corresponding to all the geological signals, including: for each geological signal, calculating a signal difference value between the geological signal and a target standard geological signal, the target standard geological signal being the standard geological signal with the highest similarity to the geological signal; if the signal difference value is not negative, positively weighting the denoising coefficient of the geological signal based on the similarity of the geological signal to all the standard geological signals to obtain a weighted denoising coefficient of the geological signal; if the signal difference value is negative, inversely weighting the denoising coefficient of the geological signal based on the similarity of the geological signal to all the standard geological signals to obtain a weighted denoising coefficient of the geological signal; and constructing the denoising coefficient matrix based on the weighted denoising coefficients of all the geological signals.

[0067] In the present embodiment, the difference value between the geological signal and the target standard geological signal can be an average amplitude difference value, or a highest amplitude difference value.

[0068] In the embodiments of the present application, A represents a geological signal, and Ai represents an i th geological signal. B represents a standard geological signal, and Bj represents a j th standard geological signal. Mij represents the similarity between the i th geological signal and the j th standard geological signal. Pi represents the weighted denoising coefficient of the i th geological signal. Bj = xjXj + yjYj, yj represents the denoising coefficient in the j th standard geological signal, xj represents the coefficient of the target geological signal in the j th standard geological signal, Xj represents the target geological signal in the j th standard geological signal, and Yj represents the noise signal in the j th standard geological signal. Nimax = Ai - Bimax represents the difference between the standard geological signal with the highest similarity to the i th geological signal.

[0069] Optionally, if Nimax≥0, the forward weighting process is: Pi = (1 + the first mean value) × yi. If Nimax<0, the reverse weighting process is: Pi = (1 - the first mean value) × yi. Wherein, the first mean value is the mean value of the similarity of all standard geological signals with a similarity higher than a second preset threshold to the geological signal.

[0070] Alternatively, if Nimax≥0, the forward weighting process is: Pi = (1 + the second mean value) × yi. If Nimax<0, the reverse weighting process is: Pi = (1 - the second mean value) × yi. Wherein, the second mean value is the mean value of the similarity of all standard geological signals with a similarity higher than a first preset threshold (if not, the second mean value is not selected as the calculation method) to the geological signal.

[0071] In the embodiments of the present application, the noise signal can be multiple, and different noise signals can correspond to different denoising coefficients. In order to ensure the reliability of denoising, the embodiments of the present application can select the denoising precision in combination with the detection level of the target geological area, that is, determine the number of denoising coefficients of different noise signals.

[0072] Illustratively, the detection level can be marked as a first detection level, a second detection level, and a third detection level.

[0073] In response to the detection level of the target geological area being a first detection level, the number of geological signals is determined to be a first number, the denoising coefficients corresponding to the first number of noise signals in the geological signals can be determined according to the signal amplitude, and then the corresponding denoising signals are constructed for denoising.

[0074] In response to the detection level of the target geological area being a second detection level, the number of geological signals is determined to be a second number, the denoising coefficients corresponding to the second number of noise signals in the geological signals can be determined according to the signal amplitude, and then the corresponding denoising signals are constructed for denoising.

[0075] In response to the detection level of the target geological area being the third detection level, the number of the geological signals is determined as a third number, the de-noising coefficients corresponding to the third number of noise signals in the geological signals can be determined according to the signal amplitudes, and then the corresponding de-noising signals are constructed for de-noising.

[0076] The first number is less than the second number, and the second number is less than the third number.

[0077] In the embodiments of the present application, after obtaining the weighted de-noising coefficients of all the geological signals, the corresponding de-noising coefficient matrix can be constructed in combination with the weighted de-noising coefficients of all the geological signals.

[0078] The embodiments of the present application can dynamically adjust the weight logic according to the specific situation of the signal deviating from the standard, and then construct the de-noising coefficient matrix. The constructed de-noising coefficient matrix is not a fixed parameter set, but a personalized parameter matrix that can reflect the unique characteristics of each geological signal. When de-noising the overall target signal, the matrix can assign each geological signal the most suitable de-noising strength and method.

[0079] The embodiments of the present application focus more on enhancing de-noising accuracy for signals with clear features and high consistency with standard signals. For signals with fuzzy features and deviating from the standard, the coefficient focuses more on balancing de-noising and feature preservation. This fine processing can significantly reduce the probability of over-de-noising or under-de-noising, improve the de-noising quality of the overall target signal, and help subsequent accurate analysis.

[0080] In an embodiment of the present application, after calculating the similarity between the target signal and the plurality of standard signals, it further includes: if there is no standard signal with a similarity to the target signal greater than a first preset similarity threshold, processing the target signal based on an automatic online multi-source domain adaptive algorithm (Automatic Online Multi-Source Domain Adaptation, AOMSDA) to obtain a target geological signal extracted from the target signal.

[0081] In the embodiments of the present application, before processing the target signal based on AOMSDA, it further includes: processing the target signal based on global positioning system (Global Positioning System, GPS) synchronization technology to ensure time consistency. Subsequently, the same frequency signal of the target geological signal can be generated through synchronization related detection technology, multiplied with the target signal and then integrated to amplify the target geological signal and weaken the interference of other noise signals.

[0082] AOMSDA generally includes four execution steps, namely: a generation stage, a discrimination stage, an intelligent tracing stage, and a dynamic adaptation stage.

[0083] Generation stage: extract the key features of the target geological signal in the target signal to ensure that useful information is obtained.

[0084] Discrimination stage: label the extracted key features to distinguish which ones may be useful signals, and make the signal features of the detection target approach the known useful signal template to reduce deviation.

[0085] Intelligent source selection stage: based on the similarity between each detection source and the target signal, irrelevant signal sources can be automatically filtered out, and only relevant ones are retained to avoid interference.

[0086] Dynamic adaptation stage: considering that the detection environment is constantly changing, the number of calculation nodes in the model can be automatically increased or decreased, and the importance of each node can be adjusted to quickly adapt to new changes and obtain the target geological signal.

[0087] For example, the working process is as follows:

[0088] First, synchronize the 12 detection sensors through GPS to ensure consistent collection time.

[0089] During detection, the useful signal reflected underground is 5Hz (very weak), but mixed with 50Hz power grid interference and 20-200Hz vehicle vibration noise.

[0090] AOMSDA first locks the 5Hz signal through "synchronous correlation detection", generates a reference signal of the same frequency, and generates an inverted 50Hz signal to cancel the power grid interference.

[0091] Finally, fuse the data of the 12 sensors, automatically give high weight to the 3 sensors with the clearest signal, and finally raise the useful signal from "submerged in noise" (-120dB) to a clear detection level (-80dB), and finally obtain the target geological signal.

[0092] The embodiments of the present application can more accurately and in real time extract weak useful signals in strong interference and changing environment police security scenes, and can adapt to various complex situations to greatly improve detection efficiency and accuracy.

[0093] Corresponding to the electromagnetic detection signal extraction method of the above embodiment, Figure 2 The structural block diagram of the electromagnetic detection signal extraction device provided by an embodiment of the present application is shown. For ease of illustration, only parts related to the embodiments of the present application are shown. For reference Figure 2 The electromagnetic detection signal extraction device 20 includes a signal acquisition module 201, a similarity calculation module 202, a matrix construction module 203, and a signal processing module 204.

[0094] The signal obtaining module 201 is configured to obtain a target signal, the target signal being an original geologic electromagnetic exploration signal of a target geologic region.

[0095] The similarity calculating module 202 is configured to calculate similarities between the target signal and a plurality of standard signals, determine a standard signal with a similarity greater than a first preset similarity threshold as a target standard signal, and the plurality of standard signals being geologic electromagnetic exploration signals of a plurality of standard geologic regions with pre-determined denoising coefficients.

[0096] The matrix constructing module 203 is configured to construct a denoising coefficient matrix of the target signal based on a denoising coefficient corresponding to the target standard signal, and construct a denoised signal based on the denoising coefficient matrix.

[0097] The signal processing module 204 is configured to perform denoising processing on the target signal based on the denoised signal, and extract a target geologic signal from the target signal.

[0098] In an embodiment of the present application, the target signal includes a plurality of geologic signals, the target standard signal includes a plurality of standard geologic signals, and each standard geologic signal corresponds to a denoising coefficient. The matrix constructing module 203 is specifically configured to calculate, for each geologic signal, a similarity between the geologic signal and all standard geologic signals, determine a denoising coefficient corresponding to the geologic signal based on denoising coefficients of all standard geologic signals with similarities greater than a second preset similarity threshold if there is a standard geologic signal with a similarity greater than the second preset similarity threshold to the geologic signal, determine the denoising coefficient corresponding to the geologic signal based on denoising coefficients of all standard geologic signals if there is no standard geologic signal with a similarity greater than the second preset similarity threshold to the geologic signal, and construct the denoising coefficient matrix based on denoising coefficients corresponding to all geologic signals.

[0099] In an embodiment of the present application, the matrix constructing module 203 is further specifically configured to calculate an average value of the denoising coefficients of all standard geologic signals as the denoising coefficient corresponding to the geologic signal, or take the similarity between each standard geologic signal and the geologic signal as a denoising coefficient weighting value, calculate a weighted average value of the denoising coefficients of all standard geologic signals, and take the weighted average value as the denoising coefficient corresponding to the geologic signal.

[0100] In an embodiment of the present application, the matrix construction module 203 is further specifically configured to, for each geological signal, calculate a signal difference between the geological signal and a target standard geological signal, the target standard geological signal being a standard geological signal with the highest similarity to the geological signal; if the signal difference is not negative, positively weight the de-noising coefficient of the geological signal based on the similarity between the geological signal and all the standard geological signals to obtain a weighted de-noising coefficient of the geological signal; if the signal difference is negative, inversely weight the de-noising coefficient of the geological signal based on the similarity between the geological signal and all the standard geological signals to obtain the weighted de-noising coefficient of the geological signal; and construct a de-noising coefficient matrix based on the weighted de-noising coefficients of all the geological signals.

[0101] In an embodiment of the present application, the device 20 further comprises a signal construction module. The signal construction module is configured to, before calculating the similarity between the target signal and the plurality of standard signals, acquire an original signal, the original signal being an original geological electromagnetic detection signal of a standard geological region; perform feature extraction on the original signal to obtain a noise signal and a key geological signal corresponding to the original signal; determine a de-noising coefficient of the noise signal based on a linear relationship among the original signal, the noise signal and the key geological signal; and take the original signal with the determined de-noising coefficient as a standard signal.

[0102] In an embodiment of the present application, the device 20 further comprises a model signal extraction module. The model signal extraction module is configured to, after calculating the similarity between the target signal and the plurality of standard signals, if there is no standard signal with a similarity to the target signal greater than a first preset similarity threshold, process the target signal based on AOMSDA to obtain a target geological signal extracted from the target signal.

[0103] In an embodiment of the present application, the target geological signal comprises geological feature signals corresponding to a plurality of collection points in a target region. The device 20 further comprises a signal fusion module. The signal fusion module is configured to, after extracting the target geological signal from the target signal, calculate a signal-to-noise ratio between each collection point corresponding geological feature signal and a preset geological feature signal to obtain a plurality of signal-to-noise ratios; determine a fusion weight corresponding to each geological feature signal based on the plurality of signal-to-noise ratios; and perform signal fusion on the geological feature signals corresponding to the plurality of collection points based on the respective fusion weights to obtain a geological fusion signal corresponding to the target region.

[0104] Referring to Figure 3 , Figure 3 A schematic block diagram of an electronic device according to an embodiment of the present application is shown in FIG. 1. As shown in FIG. 1, the electronic device comprises a processor 10, a memory 20 and a communication interface 30. Figure 3The electronic device 300 in the embodiment shown can include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processor 301, the input device 302, the output device 303, and the memory 304 can communicate with each other through a communication bus 305. The memory 304 is configured to store a computer program including program instructions. The processor 301 is configured to execute the program instructions stored in the memory 304. For example, the processor 301 is configured to invoke the program instructions to implement the functions of the modules in the above-described device embodiments. Figure 2 The signal acquisition module 201, the similarity calculation module 202, the matrix construction module 203, and the signal processing module 204 are configured to perform the functions described above.

[0105] It should be understood that, in the embodiments of the present application, the processor 301 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, or the like. The general-purpose processor can be a microprocessor, or the processor can also be any conventional processor.

[0106] The input device 302 can include a touchpad, a fingerprint acquisition sensor (for acquiring fingerprint information and direction information of a fingerprint of a user), a microphone, and the like, and the output device 303 can include a display (LCD, etc.), a speaker, and the like.

[0107] The memory 304 can include read-only memory and random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 can also include non-volatile random access memory.

[0108] In specific implementations, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present application can perform the implementation manners described in the electromagnetic detection signal extraction method provided by the embodiments of the present application, and can also perform the implementation manners of the electronic device described in the embodiments of the present application, which will not be described here.

[0109] In another embodiment of the present application, a computer readable storage medium is provided, which stores a computer program. The computer program includes program instructions, which, when executed by a processor, implement all or part of the processes of the above-mentioned embodiment methods. The computer program can also instruct related hardware to complete the implementation. The computer program can be stored in a computer readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0110] The computer readable storage medium can be an internal storage unit of the electronic device of any of the preceding embodiments, such as a hard disk or a memory of the electronic device. The computer readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer readable storage medium can include both the internal storage unit and the external storage device of the electronic device. The computer readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0111] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in general terms in the above description. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0112] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic device and the units described above can refer to the corresponding processes in the above-mentioned method embodiments, which will not be described here.

[0113] In several embodiments provided in the present application, it should be understood that the disclosed electronic device and method can be implemented in other manners. For example, the division of the units is only a logical function division, and there can be another division manner in actual implementation. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, or can be in electrical, mechanical or other forms of connection.

[0114] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments of the present application.

[0115] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any skilled person in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for extracting electromagnetic detection signals, characterized in that: include: Acquiring a target signal, wherein the target signal is an original geological electromagnetic detection signal of a target geological area; Calculating the similarity between the target signal and a plurality of standard signals, and determining a standard signal having a similarity greater than a first preset similarity threshold as a target standard signal, wherein the plurality of standard signals are geological electromagnetic detection signals of a plurality of standard geological regions with predetermined denoising coefficients; Constructing a denoising coefficient matrix of the target signal based on the denoising coefficients corresponding to the target standard signal, and constructing a denoised signal based on the denoising coefficient matrix; performing denoising processing on the target signal based on the denoised signal, and extracting a target geological signal from the target signal; The target signal includes a plurality of geological signals, the target standard signal includes a plurality of standard geological signals, and each standard geological signal corresponds to a denoising coefficient; The constructing the denoising coefficient matrix of the target signal based on the denoising coefficient corresponding to the target standard signal includes: For each geological signal, the similarity between the geological signal and all standard geological signals is calculated; if there is a standard geological signal whose similarity to the geological signal is greater than a second preset similarity threshold, the denoising coefficient corresponding to the geological signal is determined based on the denoising coefficients of all standard geological signals whose similarities are greater than the second preset similarity threshold; if there is no standard geological signal whose similarity to the geological signal is greater than the second preset similarity threshold, the denoising coefficient corresponding to the geological signal is determined based on the denoising coefficients of all standard geological signals; Constructing the denoising coefficient matrix based on the denoising coefficients corresponding to all geological signals; The process of determining the denoising coefficient corresponding to the standard signal includes: Acquiring an original signal, where the original signal is an original geological electromagnetic detection signal of a standard geological area; Performing feature extraction on the original signal to obtain a noise signal and a key geological signal corresponding to the original signal; A denoising coefficient of the noise signal is determined based on a linear relationship among the original signal, the noise signal and the key geological signal.

2. The method according to claim 1, wherein The step of determining the denoising coefficient corresponding to the geological signal based on the denoising coefficients of all standard geological signals includes: Calculate the average value of the denoising coefficients of all standard geological signals as the denoising coefficient corresponding to the geological signal; or use the similarity between each standard geological signal and the geological signal as the weighted value of the denoising coefficient, calculate the weighted average value of the denoising coefficients of each standard geological signal, and use the weighted average value as the denoising coefficient corresponding to the geological signal.

3. The method according to claim 1, wherein The denoising coefficient matrix is ​​constructed based on the denoising coefficients corresponding to all geological signals, including: For each geological signal, the difference between the geological signal and the target standard geological signal is calculated, and the target standard geological signal is the standard geological signal with the highest similarity to the geological signal; if the signal difference is not negative, the denoising coefficient of the geological signal is positively weighted based on the similarity between the geological signal and all the standard geological signals to obtain the weighted denoising coefficient of the geological signal; if the signal difference is negative, the denoising coefficient of the geological signal is reversely weighted based on the similarity between the geological signal and all the standard geological signals to obtain the weighted denoising coefficient of the geological signal; The denoising coefficient matrix is ​​constructed based on the weighted denoising coefficients of all geological signals.

4. The method according to claim 1, wherein After calculating the similarity between the target signal and the plurality of standard signals, the method further includes: If there is no standard signal whose similarity with the target signal is greater than a first preset similarity threshold, the target signal is processed based on AOMSDA to obtain a target geological signal extracted from the target signal.

5. The method according to any one of claims 1 to 4, characterized in that The target geological signal includes geological characteristic signals corresponding to multiple acquisition points in the target area; After extracting the target geological signal from the target signal, the method further includes: Calculating the signal-to-noise ratio between the geological characteristic signal corresponding to each acquisition point and the preset geological characteristic signal to obtain multiple signal-to-noise ratios; Determining fusion weights corresponding to the respective geological characteristic signals based on the multiple signal-to-noise ratios; The geological characteristic signals corresponding to the plurality of acquisition points are fused based on the respective fusion weights to obtain a geological fusion signal corresponding to the target area.

6. An electromagnetic detection signal extraction device, characterized in that: include: A signal acquisition module is used to acquire a target signal, wherein the target signal is an original geological electromagnetic detection signal of a target geological area; a similarity calculation module, configured to calculate the similarity between the target signal and a plurality of standard signals, and determine a standard signal having a similarity greater than a first preset similarity threshold as a target standard signal, wherein the plurality of standard signals are geological electromagnetic detection signals of a plurality of standard geological regions with predetermined denoising coefficients; a matrix construction module, configured to construct a denoising coefficient matrix of the target signal based on the denoising coefficients corresponding to the target standard signal, and to construct a denoised signal based on the denoising coefficient matrix; a signal processing module, configured to perform denoising processing on the target signal based on the denoised signal, and extract a target geological signal from the target signal; The target signal includes a plurality of geological signals, the target standard signal includes a plurality of standard geological signals, and each standard geological signal corresponds to a denoising coefficient; The matrix construction module is specifically used to: calculate, for each geological signal, the similarity between the geological signal and all standard geological signals; if there is a standard geological signal whose similarity to the geological signal is greater than a second preset similarity threshold, determine the denoising coefficient corresponding to the geological signal based on the denoising coefficients of all standard geological signals whose similarities are greater than the second preset similarity threshold; if there is no standard geological signal whose similarity to the geological signal is greater than the second preset similarity threshold, determine the denoising coefficient corresponding to the geological signal based on the denoising coefficients of all standard geological signals; and construct the denoising coefficient matrix based on the denoising coefficients corresponding to all geological signals; The device further comprises: a signal construction module for acquiring an original signal, wherein the original signal is an original geological electromagnetic detection signal of a standard geological area; Feature extraction is performed on the original signal to obtain a noise signal and a key geological signal corresponding to the original signal; and a denoising coefficient of the noise signal is determined based on a linear relationship among the original signal, the noise signal and the key geological signal.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images