Microseismic event identification method, device and equipment and readable storage medium

Abstract

The invention relates to the technical field of signal processing, and discloses a micro-seismic event identification method, device and equipment and a readable storage medium, and the method comprises the steps: obtaining multi-channel signal data of a target micro-seismic event synchronously collected by a plurality of sensors; aligning the multi-channel signal data to obtain an aligned data set representing the same event stage; performing similarity feature extraction processing on the aligned data set to generate a similarity feature set; and performing discrimination matching processing on the similarity feature set and a preset classification discrimination rule, and determining type information of the target micro-seismic event according to a matching result. According to the micro-seismic event identification method, the accuracy and robustness of micro-seismic event identification are improved, and the method has relatively high anti-interference capability and scene adaptability.

Description

Technical Field

[0001] This application relates to the field of signal processing technology, and in particular to a method, apparatus, device and readable storage medium for identifying microseismic events. Background Technology

[0002] With the increasing demand for mine safety monitoring, microseismic event identification has become an important technical means to ensure operational safety. Currently, for the automatic classification and identification of rock fracture events and electromagnetic noise events, the industry has formed two mainstream technical paths: one is a threshold judgment method based on key spectral indicators. Its basic process is to extract spectral features (such as dominant frequency and peak frequency) from the original waveform and compare them with a preset threshold to complete the event type determination. The core of this method lies in utilizing the difference in frequency domain characteristics between rock fracture signals (usually with lower frequencies) and electromagnetic noise signals (with higher frequencies). The other path is based on traditional feature engineering and machine learning models. This method involves manually constructing multi-dimensional feature sets in the time domain, frequency domain, and other dimensions. After feature selection and dimensionality reduction, these features are input into a machine learning classifier (such as SVM, random forest, etc.) for training and discrimination to achieve the classification output of microseismic events.

[0003] While the two methods mentioned above can achieve certain recognition results in specific scenarios, they still face several key technical bottlenecks. On the one hand, threshold-based judgment methods based on spectral features suffer from oversimplification. Relying solely on a single indicator (such as the dominant frequency) is insufficient to fully characterize complex microseismic signals, easily leading to false alarms and missed alarms in situations such as high-frequency rock breaking or low-frequency noise, severely impacting classification accuracy and environmental adaptability. Furthermore, this type of method highly depends on experience in specific scenarios for threshold selection, exhibiting weak generalization ability and difficulty in deployment across mining areas. On the other hand, while traditional machine learning methods possess stronger fitting capabilities, they rely on extensive expert knowledge to construct feature libraries, resulting in long development cycles, high engineering complexity, and a lack of physical interpretability in classification criteria, leading to insufficient reliability in high-reliability applications such as engineering safety monitoring. Summary of the Invention

[0004] In view of this, embodiments of this application provide a method, apparatus, device, and readable storage medium for identifying microseismic events, which can effectively solve the problems of poor synchronization of multi-channel microseismic signal acquisition, inaccurate estimation of seismic phase arrival time, and low accuracy of event type identification in the prior art.

[0005] In a first aspect, embodiments of this application provide a method for identifying microseismic events, including: Acquire multi-channel signal data of target microseismic events simultaneously collected by multiple sensors; The multi-channel signal data is aligned to obtain an aligned data set representing the same event stage; The alignment dataset is subjected to similarity feature extraction processing to generate a similarity feature set; The similarity feature set is matched with a preset classification rule, and the type information of the target microseismic event is determined based on the matching result.

[0006] In some embodiments, acquiring multi-channel signal data of the target microseismic event simultaneously collected by multiple sensors includes: Receive the raw waveform signals output by each sensor; The original waveform signal is subjected to time synchronization verification; Waveform segments with the same event trigger markers are extracted from the original waveform signals that have passed time synchronization verification and used as the multi-channel signal data.

[0007] In some embodiments, the alignment processing of the multi-channel signal data to obtain an aligned data set representing the same event stage includes: For each channel signal data with the same event trigger marker, extract the event trigger time corresponding to each channel signal data; Among all the extracted event trigger times, the minimum value is determined as a unified time reference; Based on the unified time reference, waveform segments with a start time of the time reference and a duration of a preset duration are extracted from the signal data of each channel and used as the alignment data set.

[0008] In some embodiments, the step of performing similarity feature extraction processing on the aligned data set to generate a similarity feature set includes: For any two channels in the aligned data set, perform normalized cross-correlation calculation to obtain the cross-correlation coefficient between each channel pair; Based on all cross-correlation coefficients, the average similarity index is calculated, and the similarity distribution statistics are constructed. The average similarity index and the statistical results of the similarity distribution are used as the similarity feature set.

[0009] In some embodiments, the step of performing discrimination and matching processing between the similarity feature set and a preset classification discrimination rule includes: Extract the average similarity index and similarity distribution statistics from the set of similarity features; The average similarity index is compared with a first preset threshold to obtain a first comparison result; The proportion parameter in the similarity distribution statistics is compared with the second preset threshold to obtain the second comparison result; Based on the combination of the first comparison result and the second comparison result, the event type information of the target microseismic event is determined.

[0010] In some embodiments, determining the event type information of the target microseismic event based on the combination of the first comparison result and the second comparison result includes: When the average similarity index is lower than the first preset similarity threshold, and the proportion of low similarity channel pairs in the similarity distribution statistics is lower than the second preset proportion threshold, the target microseismic event is determined to be a rock fracture event. When the average similarity index is higher than the third preset similarity threshold, and the proportion of high similarity channel pairs in the similarity distribution statistics is higher than the fourth preset proportion threshold, the target micro-seismic event is determined to be an electromagnetic noise event.

[0011] In some embodiments, after determining the event type information of the target microseismic event, the method further includes: The event type information and event identification information are associated and stored to generate event record data for statistical analysis or early warning management.

[0012] Secondly, embodiments of this application provide a microseismic event identification device, comprising: The data acquisition module is used to acquire multi-channel signal data of target microseismic events collected synchronously by multiple sensors; An alignment processing module is used to perform alignment processing on the multi-channel signal data to obtain an aligned data set representing the same event stage; The extraction and processing module is used to perform similarity feature extraction processing on the aligned data set to generate a similarity feature set; The discrimination module is used to perform discrimination matching processing between the similarity feature set and the preset classification discrimination rules, and determine the type information of the target microseismic event based on the matching result.

[0013] Thirdly, embodiments of this application provide a terminal device, the terminal device including a processor and a memory, the memory storing a computer program, and the processor executing the computer program to implement the microseismic event identification method of the first aspect described above.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium, wherein when the computer program is executed on a processor, it implements the microseismic event identification method of the first aspect described above.

[0015] The embodiments of this application have the following beneficial effects: By acquiring multi-channel signal data of a target microseismic event simultaneously collected by multiple sensors, and aligning the multi-channel signals based on the event trigger time, an aligned data set representing the same event stage is constructed. Based on this, similarity features between the waveforms of each channel are extracted to form a similarity feature set, which is then matched with preset classification rules to achieve intelligent identification of the target microseismic event type.

[0016] The embodiments of this application enhance the temporal consistency of event signals through multi-channel data alignment, improve the accuracy of classification and identification by leveraging similarity features, and achieve efficient discrimination of microseismic event types by combining preset rules, which can significantly improve the automated processing capability of microseismic data and the reliability of event identification. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart of a microseismic event identification method according to an embodiment of this application is shown; Figure 2 Another flowchart of the microseismic event identification method according to an embodiment of this application is shown; Figure 3 This paper illustrates yet another flowchart of the microseismic event identification method according to an embodiment of this application; Figure 4 A schematic diagram illustrating the statistical distribution characteristics of rock fracture signals in the microseismic event identification method of this application is shown. Figure 5 A schematic diagram illustrating the statistical distribution characteristics of electromagnetic shock signals in the microseismic event identification method of this application is shown. Figure 6 A schematic diagram of a microseismic event identification method according to an embodiment of this application is shown. Detailed Implementation

[0019] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0020] The components of the embodiments of this application described and illustrated in the accompanying drawings can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0021] In the following text, the terms "comprising," "having," and their cognates, which may be used in various embodiments of this application, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more combinations thereof. Furthermore, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0022] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be construed as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.

[0023] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features described herein can be combined with each other.

[0024] Considering the problems of poor synchronization in multi-channel microseismic signal acquisition, inaccurate phase arrival time estimation, and low accuracy in event type identification in existing technologies, a microseismic event identification method is proposed. This method constructs high-quality time-aligned signal segments, introduces a dual-channel feature fusion coding network, performs joint training by combining phase supervision signals and event label information, and integrates phase classification and event identification results during the inference stage. This significantly improves the accuracy and stability of microseismic event identification and is applicable to various engineering application scenarios such as rock mass fracture monitoring and mine earthquake early warning.

[0025] The following examples illustrate the microseismic event identification method.

[0026] Figure 1 A flowchart of a microseismic event identification method according to an embodiment of this application is shown. Exemplarily, the microseismic event identification method includes the following steps: Step S100: Acquire multi-channel signal data of the target microseismic event simultaneously collected by multiple sensors.

[0027] Multi-channel signal data refers to the set of raw signals from multiple waveform channels synchronously acquired by multiple sensor nodes deployed in the microseismic monitoring system, used to describe a specific microseismic event. Each channel corresponds to an independent sensor node, and the recorded waveform reflects the time-series changes of the source signal at that node. The main purpose of this step is to provide a unified and comparable data foundation for subsequent time-series alignment and similarity calculation.

[0028] In an optional embodiment, step S100 includes the following sub-steps: S101 receives the raw waveform signals output by each sensor.

[0029] Here, the original waveform signal refers to the continuous time-series data recorded by each sensor when a microseismic event is triggered, denoted as Where i = 1, 2, ..., N represents the channel number, and t is the sampling time. Each sensor independently records the seismic waveform received at its location, with a uniform signal format and consistent sampling rate, ensuring comparability.

[0030] As an example, after a target event is triggered, the system automatically receives the raw waveform signals from each sensor channel and temporarily caches them in the signal processing module of the acquisition server for subsequent unified processing and retrieval.

[0031] S102 performs time synchronization verification on the original waveform signal.

[0032] Time synchronization verification refers to using the timestamps attached to the waveforms of each channel to determine whether all acquisition channels have completed synchronous acquisition based on a unified clock system. If clock offset or sampling drift exists, the signal time axis is corrected to ensure that all waveform signals have a comparable time reference system.

[0033] As an example, the system adds a trigger timestamp to all channel signals. Compare the data to confirm that the time difference is within the tolerance range (e.g., ±1 ms), and stretch or truncate the time axis of channels that do not meet the synchronization conditions to ensure that all channel data points to a unified vibration response window.

[0034] S103 extracts waveform segments with the same event trigger markers from the original waveform signals that have passed time synchronization verification, and uses them as multi-channel signal data.

[0035] Among them, the event trigger mark refers to the unified event number or identification label assigned to all channels by the system after detecting the micro-vibration event trigger signal, which is used to identify that the waveform segment belongs to the same vibration event.

[0036] As an example, suppose an event is simultaneously triggered and recorded by N sensors, and its corresponding event number is Event_ID_001. The system extracts the waveform data with this number from all channels to form a set of "raw multi-channel waveform data".

[0037] For example, in order to uniformly extract the effective portion of the signal from each channel, the system extracts the trigger time from each channel. For the reference waveform segment, the earliest trigger time is uniformly used as the starting point. The cut length is A segment (e.g., 1 second) is used to construct a data set that meets the requirements of subsequent alignment processing:

[0038] In other implementations, an event intensity filtering mechanism can be preset to extract only event waveforms whose maximum amplitude exceeds the background noise threshold, thereby improving the signal-to-noise ratio and recognition accuracy of subsequent processing.

[0039] Step S200: Align the multi-channel signal data to obtain an aligned data set representing the same event stage.

[0040] Alignment processing refers to unifying the waveform data of the same microseismic event recorded in different sensor channels along the time dimension, so that the waveforms of each channel can be compared and analyzed under the same time reference. Due to the different propagation paths of seismic waves in space, the signals recorded by each channel have a certain time offset. Therefore, it is necessary to perform an alignment operation on the signal data to obtain an aligned data set representing the same vibration stage, which provides a basis for subsequent similarity calculations.

[0041] In one alternative embodiment, such as Figure 2 As shown, step S200 includes the following sub-steps: S201, for each channel signal data with the same event trigger marker, extract the event trigger time corresponding to each channel signal data.

[0042] The event trigger time refers to the local trigger time recorded by each sensor when it detects a microseismic event, denoted as . Where i = 1, 2, ..., N represents the channel number. This time point can be extracted from the original waveform signal using automatic or manual picking algorithms, and is usually a characteristic point or initial zero intersection point of the rising segment of the signal amplitude.

[0043] As an example, the system analyzes the waveform signal of each channel. Preliminary analysis was conducted, and the event initiation point was detected using the threshold triggering method or the STA / LTA (short-time energy ratio) method to extract the triggering time of the channel. This serves as the benchmark for subsequent alignment.

[0044] S202, among all the extracted event trigger times, determine the minimum value as a unified time reference.

[0045] The unified time reference refers to the earliest trigger time selected to establish a unified starting point, used to calibrate the start point of waveform segments across all channels. Let the trigger times of all channels be... Then a unified time base Defined as:

[0046] As an example, the system iterates through the set of trigger times for all channels, calculates its minimum value, and uses this value as the starting time for waveform slicing of all channels, so that all waveform segments have consistency from this point in time.

[0047] S203, based on a unified time reference, extracts waveform segments from the waveform signal data of each channel with a start time of the time reference and a duration of a preset duration, as an alignment data set.

[0048] Among them, waveform segments refer to those on a unified time base. Top cut, length is The waveform data within the time window constitutes the representation of each channel signal within the same event phase. The aligned waveform segment is represented as follows:

[0049] in, This represents the waveform segment of channel i aligned to the time coordinates. It is a variable relative to the start time.

[0050] For example, in practical applications, It can be set to 0.5 seconds or 1 second; the specific value should cover the main energy range of the signal. The system operates according to... Cut a segment of length The waveforms constitute the final aligned data set. This is for use in subsequent similarity calculations.

[0051] In other implementations, the system may further perform amplitude normalization on the truncated segments to offset the effects of different channel gain settings, but this step is not mandatory.

[0052] Step S300: Perform similarity feature extraction processing on the aligned data set to generate a similarity feature set.

[0053] The similarity feature extraction process involves calculating the degree of similarity in time series shape among aligned waveform segments across multiple channels, and quantifying this similarity into feature indicators using appropriate statistical methods. This process provides numerical data for subsequent event identification and classification, reflecting the consistency of vibration signal propagation in multi-channel space.

[0054] In one alternative embodiment, such as Figure 3 As shown, step S300 includes the following sub-steps: S301: For any two channels in the aligned dataset, perform normalized cross-correlation calculation to obtain the cross-correlation coefficient between each channel pair.

[0055] Normalized cross-correlation is a mathematical operation used to measure the shape similarity of two waveform sequences at different time offsets. For any two channels i and j, their aligned waveform segments are denoted as follows: and The formula for calculating the maximum cross-correlation coefficient between the two is:

[0056] in, For the allowed time lag window, and These represent the waveform mean values ​​for channels i and j, respectively. This cross-correlation coefficient... The closer the value is to 1, the more consistent the waveforms of the two channels are.

[0057] As an example, the system iterates through all channels for each pair of channel combinations (i,j). The maximum cross-correlation value is calculated and recorded within the range of values ​​(e.g., ±5 sampling points) to obtain the set of cross-correlation coefficients between all channel pairs.

[0058] S302, based on all cross-correlation coefficients, calculate the average similarity index and construct the similarity distribution statistics.

[0059] The average similarity index describes the consistency trend of event waveforms across all channels and is defined as the arithmetic mean of all cross-correlation coefficients. Its calculation formula is:

[0060] Furthermore, the similarity distribution statistics result refers to all cross-correlation numbers By value range (e.g. from) Divide the data into multiple intervals (Bins) from 1 to 1, and count the number of channel pairs falling into each interval to construct a frequency histogram.

[0061] For example, to further establish classification criteria, the system can calculate the following two derived statistics: Low similarity channel pairs proportion Cross-correlation coefficients less than a set low threshold The proportion of channel pairs to the total number of channel pairs:

[0062] High similarity channel pairs proportion Cross-correlation coefficients greater than a set high threshold The proportion of channels:

[0063] S303 uses the average similarity index and the statistical results of similarity distribution as the set of similarity features.

[0064] The similarity feature set refers to a structured data set that numerically represents the waveform consistency of microseismic events, typically including an average similarity index. Low similarity ratio High similarity ratio Distribution histograms, etc.

[0065] As an example, the system encapsulates this feature set into a unified feature vector structure:

[0066] Where H represents the multidimensional vector form of the similarity distribution histogram.

[0067] This feature set serves as the input to subsequent classification models and forms the core data foundation for identifying microseismic event types.

[0068] Step S400: Perform discrimination matching processing between the similarity feature set and the preset classification discrimination rules, and determine the type information of the target microseismic event based on the matching results.

[0069] The classification and discrimination rules refer to a set of multidimensional judgment conditions set based on statistical modeling or empirical analysis to determine the type of an event. These rules take numerical features contained in the similarity feature set as input, set multiple judgment thresholds, and identify the event type through comparison operations. The similarity feature set generally includes multiple quantitative indicators such as: average similarity index, similarity distribution histogram, and the proportion of low / high similarity.

[0070] In an optional embodiment, step S400 includes the following sub-steps: S401, extract the average similarity index and similarity distribution statistics from the similarity feature set.

[0071] The average similarity index represents the overall consistency trend of the cross-correlation coefficients among all channel pairs, denoted as . Similarity distribution statistics represent the proportion of channel pairs within different threshold intervals, and typically include the following two derived indicators: Low similarity channel pairs proportion ; High similarity channel pairs proportion .

[0072] Exemplary, the system can extract features from the set of features The three values ​​mentioned above are extracted for subsequent comparison.

[0073] S402, compare the average similarity index with the first preset similarity threshold to obtain the first comparison result.

[0074] Among them, the first preset similarity threshold (denoted as) Used to determine whether the average similarity is below the consistency lower bound. For example, if: The first comparison result is "low consistency". Conversely, it is judged as "high consistency" or "intermediate region" for subsequent joint judgment with other indicators.

[0075] In other implementations, the threshold may be set to an empirical value such as 0.2, 0.3, or determined based on historical data clustering analysis.

[0076] S403, compare the proportion parameter in the similarity distribution statistics with the second preset proportion threshold to obtain the second comparison result.

[0077] Among them, the second preset percentage threshold (denoted as) Used to determine whether the proportion of low-similarity or high-similarity channel pairs exceeds the judgment boundary.

[0078] For example: like This indicates that the proportion of low-consistency channels in the event is relatively low, and that the event has a certain degree of structure. like This indicates that the overall waveform of the event is highly consistent.

[0079] The system outputs a second comparison status based on this result.

[0080] S404. Based on the combination of the first comparison result and the second comparison result, determine the event type information of the target microseismic event.

[0081] The event type information refers to the classification results of microseismic events, such as "rock fracture event" or "electromagnetic noise event". This type is determined jointly by the comparison results of the first two steps, without relying on a single indicator, ensuring the stability and robustness of the judgment.

[0082] In an optional implementation, step S404 further includes: When the average similarity index is lower than the first preset similarity threshold, and the proportion of low similarity channel pairs in the similarity distribution statistics is lower than the second preset proportion threshold, the target microseismic event is determined to be a rock fracture event; when the average similarity index is higher than the third preset similarity threshold, and the proportion of high similarity channel pairs in the similarity distribution statistics is higher than the fourth preset proportion threshold, the target microseismic event is determined to be an electromagnetic noise event.

[0083] When the average similarity index Below the first preset similarity threshold Furthermore, the proportion of low similarity channels Below the second preset percentage threshold At that time, the system determines the target event to be a rock fracture event; When the average similarity index Higher than the third preset similarity threshold Furthermore, the proportion of high similarity channels Higher than the fourth preset percentage threshold When this occurs, the system determines that the target event is an electromagnetic noise event.

[0084] In other implementations, the event type can be associated with and stored with the event number, acquisition time, waveform number, etc., to form a structured event database for subsequent statistical analysis, evolution modeling, or automatic early warning invocation.

[0085] In an optional embodiment, step S400 includes the following sub-steps: Event type information is associated with event identification information and stored together to generate event record data for statistical analysis or early warning management.

[0086] Among them, event identification information refers to information such as number, timestamp, and sensor trigger record used to uniquely identify target microseismic events, and is used to build a traceable event index structure in the system; event record data refers to structured data composed of event identification information and event type information, which is used for subsequent data statistics, trend modeling, and automatic alarm logic triggering in the safety monitoring system.

[0087] As an example, after determining the event type, the system packages the unique identifier Event_ID of the current event, the trigger time T0, and the identification result "rock fracture" or "electromagnetic noise" into a structured record item and writes it into the event database.

[0088] Understandably, in order to verify the effectiveness of the method described in this embodiment in the identification of microseismic events, an experimental dataset containing multiple types of microseismic samples was constructed, and microseismic signals and electromagnetic shock responses during the rock fracturing process were collected respectively. Figure 4 The statistical distribution characteristics of rock fracture signals are shown. Figure 5 The statistical differences of electromagnetic shock signals under different identification results are shown, and the results indicate that the proposed method has significant advantages in the consistency mining of multi-source signals.

[0089] Figure 6 A schematic diagram of a microseismic event identification device according to an embodiment of this application is shown. Exemplarily, the device 100 includes: Data acquisition module 110 is used to acquire multi-channel signal data of target microseismic events synchronously collected by multiple sensors; Alignment processing module 120 is used to perform alignment processing on the multi-channel signal data to obtain an aligned data set representing the same event stage; Extraction and processing module 130 is used to perform similarity feature extraction processing on the aligned data set to generate a similarity feature set; The discrimination module 140 is used to perform discrimination matching processing on the similarity feature set and the preset classification discrimination rules, and determine the type information of the target microseismic event based on the matching result.

[0090] It is understood that the apparatus of this embodiment corresponds to the method of the above embodiments, and the options in the above embodiments are also applicable to this embodiment, so they will not be described again here.

[0091] This application also provides a terminal device, exemplary of which includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to enable the terminal device to perform the functions of the various modules in the above-described method or apparatus.

[0092] The processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a Central Processing Unit (CPU), Graphics Processing Unit (GPU), Network Processor (NP), Digital Signal Processor (DSP), Application-Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0093] The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory is used to store computer programs, and the processor can execute the computer programs accordingly after receiving execution instructions.

[0094] This application also provides a computer-readable storage medium for storing the computer program used in the aforementioned terminal device. For example, the computer-readable storage medium may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that, in alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0096] In addition, the functional modules or units in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0097] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0098] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for identifying microseismic events, characterized in that, The method includes: Acquire multi-channel signal data of target microseismic events simultaneously collected by multiple sensors; The multi-channel signal data is aligned to obtain an aligned data set representing the same event stage; The alignment dataset is subjected to similarity feature extraction processing to generate a similarity feature set; The similarity feature set is matched with a preset classification rule, and the type information of the target microseismic event is determined based on the matching result.

2. The microseismic event identification method according to claim 1, characterized in that, The acquisition of multi-channel signal data of the target microseismic event simultaneously collected by multiple sensors includes: Receive the raw waveform signals output by each sensor; The original waveform signal is subjected to time synchronization verification; Waveform segments with the same event trigger markers are extracted from the original waveform signals that have passed time synchronization verification and used as the multi-channel signal data.

3. The microseismic event identification method according to claim 2, characterized in that, The alignment process of the multi-channel signal data to obtain an aligned data set representing the same event stage includes: For each channel signal data with the same event trigger marker, extract the event trigger time corresponding to each channel signal data; Among all the extracted event trigger times, the minimum value is determined as a unified time reference; Based on the unified time reference, waveform segments with a start time of the time reference and a duration of a preset duration are extracted from the signal data of each channel and used as the alignment data set.

4. The microseismic event identification method according to claim 1, characterized in that, The step of extracting similarity features from the aligned data set to generate a similarity feature set includes: For any two channels in the aligned data set, perform normalized cross-correlation calculation to obtain the cross-correlation coefficient between each channel pair; Based on all cross-correlation coefficients, the average similarity index is calculated, and the similarity distribution statistics are constructed. The average similarity index and the statistical results of the similarity distribution are used as the similarity feature set.

5. The microseismic event identification method according to claim 1, characterized in that, The step of performing discrimination and matching processing between the similarity feature set and the preset classification discrimination rules includes: Extract the average similarity index and similarity distribution statistics from the set of similarity features; The average similarity index is compared with a first preset threshold to obtain a first comparison result; The proportion parameter in the similarity distribution statistics is compared with the second preset threshold to obtain the second comparison result; Based on the combination of the first comparison result and the second comparison result, the event type information of the target microseismic event is determined.

6. The microseismic event identification method according to claim 5, characterized in that, The step of determining the event type information of the target microseismic event based on the combination of the first comparison result and the second comparison result includes: When the average similarity index is lower than the first preset similarity threshold, and the proportion of low similarity channel pairs in the similarity distribution statistics is lower than the second preset proportion threshold, the target microseismic event is determined to be a rock fracture event. When the average similarity index is higher than the third preset similarity threshold, and the proportion of high similarity channel pairs in the similarity distribution statistics is higher than the fourth preset proportion threshold, the target micro-seismic event is determined to be an electromagnetic noise event.

7. The microseismic event identification method according to claim 1, characterized in that, After determining the event type information of the target microseismic event, the method further includes: The event type information and event identification information are associated and stored to generate event record data for statistical analysis or early warning management.

8. A microseismic event identification device, characterized in that, include: The data acquisition module is used to acquire multi-channel signal data of target microseismic events collected synchronously by multiple sensors; An alignment processing module is used to perform alignment processing on the multi-channel signal data to obtain an aligned data set representing the same event stage; The extraction and processing module is used to perform similarity feature extraction processing on the aligned data set to generate a similarity feature set; The discrimination module is used to perform discrimination matching processing between the similarity feature set and the preset classification discrimination rules, and determine the type information of the target microseismic event based on the matching result.

9. A terminal device, characterized in that, The terminal device includes a processor and a memory, the memory storing a computer program, and the processor executing the computer program to implement the microseismic event identification method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed on a processor, implements the microseismic event identification method according to any one of claims 1-7.

Images