Blasting vibration monitoring data processing method and device based on edge calculation

Abstract

The invention discloses a blasting vibration monitoring data processing method and device based on edge calculation, and relates to the technical field of blasting vibration monitoring, a blasting point monitoring range of a blasting site is divided into a plurality of edge monitoring units, and a plurality of edge data analysis units are deployed at geometric centers of the plurality of edge monitoring units; and a plurality of vibration sensors in the edge monitoring unit are respectively in communication connection with the edge data analysis unit at the geometric center. According to the invention, the edge data analysis unit realizes the localization processing of data, reduces the delay of data transmission, and improves the real-time monitoring and quick response capabilities. The localization processing of the edge calculation unit enables mutation analysis to be carried out in real time, and once mutation is detected, corresponding measures can be taken immediately, so that the quick response capability is improved. Through step-by-step feature extraction and comparison, the algorithm process is clear, and optimization and adjustment are facilitated to adapt to different monitoring environments and requirements.

Description

Technical Field

[0001] The present invention relates to the technical field of blasting vibration monitoring, and particularly to a method and device for processing blasting vibration monitoring data based on edge computing. Background Art

[0002] Blasting operations are widely used in many engineering fields such as mine exploitation, tunnel construction, and road construction. However, the vibration generated by blasting may cause serious impacts on surrounding buildings, infrastructure, and the ecological environment. To effectively control the hazards of blasting vibration, accurate blasting vibration monitoring is crucial. With the continuous development of technology, blasting vibration monitoring technology is also continuously evolving; Sensor technology: Commonly used sensors include piezoelectric acceleration sensors, strain gauges, etc. Piezoelectric acceleration sensors reflect the vibration situation by detecting the acceleration of the mass point, with high sensitivity and a wide frequency response range. Strain gauges are mainly used to measure the strain of structures caused by blasting, and the impact of blasting vibration on the structure can be indirectly evaluated by measuring the strain value. For example, in the blasting demolition projects of some large bridges, strain gauges will be arranged at key positions to monitor the strain changes of the structure.

[0003] Data acquisition system: The data acquisition system is responsible for converting the analog signals collected by the sensors into digital signals, and performing preliminary data storage and transmission. Common data acquisition devices include data acquisition cards, portable data acquisition instruments, etc. They have multi-channel acquisition functions and can collect data from multiple sensors simultaneously. Some advanced data acquisition instruments also support wireless transmission functions, facilitating remote acquisition of data.

[0004] The main methods for analyzing blasting monitoring data are as follows: Fourier transform, which converts the vibration signal in the time domain to the frequency domain, analyzes the frequency components of the signal, and determines parameters such as the main vibration frequency. For example, through Fourier transform, the energy distribution of different frequency components in the blasting vibration signal can be analyzed to judge the frequency range that may have an impact on different structures.

[0005] Wavelet transform, which can perform multi-resolution analysis on the signal, has good localization characteristics in both the time-frequency domain, and is suitable for analyzing non-stationary blasting vibration signals. For example, wavelet transform can be used to extract the mutation characteristics in the blasting vibration signal and identify the starting and ending moments of the blasting vibration.

[0006] Peak value analysis method, by calculating parameters such as the peak particle vibration velocity of the vibration signal and comparing with the safety allowable standard, to evaluate the hazard degree of the blasting vibration. In actual engineering, according to the relevant regulations in the "Blasting Safety Regulations", the peak particle vibration velocity is used as an important indicator to judge whether the blasting vibration is safe.

[0007] Data transmission and storage pressure: In large-scale blasting monitoring scenarios, the amount of data generated by a large number of sensors is huge. Transmitting all data to a remote server for centralized processing and storage will result in excessive network bandwidth occupancy, large data transmission delays, and even possible data loss. For example, in the blasting operations of large open-pit coal mines, hundreds of sensors collect data simultaneously, and the data transmission pressure is extremely prominent.

[0008] Insufficient real-time performance: Due to the process of data transmission and centralized processing, there is often a long time delay from when the sensors collect data to when the analysis results are obtained, making it difficult to meet the requirements of real-time monitoring of blasting vibrations and taking timely control measures. For some structures that are sensitive to vibration responses, such as ancient buildings and precision equipment in operation, this lack of real-time performance may lead to the inability to avoid vibration hazards in a timely manner.

[0009] Limited data analysis accuracy: In complex blasting environments, noise interference is severe, and traditional data analysis methods have certain limitations in removing noise and accurately extracting signal features. For example, in blasting operations in urban environments, there are a large number of noise sources such as electromagnetic interference, which will affect the accurate analysis of blasting vibration signals and lead to inaccurate assessment of blasting vibration hazards.

[0010] Poor system scalability: When new monitoring points need to be added or the monitoring scope needs to be expanded, traditional centralized monitoring systems often require large-scale adjustments to the entire data transmission and processing architecture, with high costs and great implementation difficulties. This limits the flexible application of blasting vibration monitoring systems in engineering projects of different scales. Summary of the Invention

[0011] To solve the above technical problems of blasting vibration monitoring, the present invention provides a method and device for processing blasting vibration monitoring data based on edge computing. The following technical solutions are adopted: A method for processing blasting vibration monitoring data based on edge computing includes the following steps: Step 1, divide the monitoring scope of the blasting points at the blasting site into multiple edge monitoring units, and deploy multiple edge data analysis units at the geometric centers of the multiple edge monitoring units respectively; Step 2, respectively communicate and connect multiple vibration sensors in the edge monitoring unit with the edge data analysis unit at the geometric center; Step 3, start the blasting, and all vibration sensors monitor vibration data during the duration of the blasting impact; Step 4, after the duration of the blasting impact ends, multiple edge data analysis units respectively collect the vibration data packets based on time series of multiple vibration sensors in the edge monitoring unit; Step 5, the edge data analysis unit analyzes the vibration data packet based on time series, and performs edge computing analysis on the vibration data of each vibration sensor to obtain vibration waveforms; Step 6, the edge data analysis unit extracts waveform features from the vibration waveforms corresponding to the vibration data of each vibration sensor within the same edge monitoring unit, and performs mutation analysis based on the waveform features; Step 7, if the difference between the eigenvalue and the corresponding feature mean value is greater than the set mutation detection threshold, or the first derivative of the feature waveform is greater than the mutation detection threshold, or the second derivative of the feature waveform is greater than the mutation detection threshold, then it is determined that the eigenvalue is a mutation value; Step 8, the edge data analysis unit marks the identified mutation values and their corresponding waveform features, extracts the key information of the features, and packs the mutation values and key information data into a mutation value data packet; the edge data analysis unit performs data compression and downsampling processing on the ordinary vibration data without mutation to form an ordinary vibration data packet; Step 9, all edge data analysis units first transmit the mutation value data packets to the central server through the wireless communication network. After the central server receives all the mutation value data packets from all edge data analysis units, it respectively sends signals of ordinary vibration data packets to all edge data analysis units, and then all edge data analysis units transmit the ordinary vibration data packets to the central server through the wireless communication network; Step 10, the central server performs global vibration mode recognition and anomaly detection on the received mutation value data packets, and the central server performs statistical analysis on the ordinary vibration data packets to generate a trend chart and a distribution chart of the vibration data.

[0012] By adopting the above technical solution, by deploying the edge data analysis unit in the edge monitoring unit, the localization processing of data is realized, the delay of data transmission is reduced, and the ability of real-time monitoring and rapid response is improved. At the source of data generation, the edge data analysis unit is used for edge computing processing, important information is screened out, key features are extracted and mutation analysis is performed, so that abnormal events in blasting vibration can be more accurately identified, the reliability of data can be improved, the overall data processing efficiency can be greatly improved, and the computing burden on the central server can be reduced.

[0013] The compression and downsampling processing of ordinary vibration data reduces the resource requirements for storage and transmission, and optimizes the resource utilization. The central server performs global vibration mode recognition and anomaly detection, and combines the local detail analysis of the edge unit, so that the vibration data can be more comprehensively understood and more accurate statistical analysis results can be generated.

[0014] This method can flexibly divide the edge monitoring unit and deploy the edge data analysis unit according to the monitoring range and requirements, and is easy to expand to a larger monitoring area or a more complex monitoring scenario.

[0015] The edge computing unit can adapt to various harsh environments. When transmitting data to the central server, it does so after the duration of the blasting impact, so wireless communication is not affected by the explosion.

[0016] Optionally, if the central server analyzes that multiple edge monitoring units with more than a set number threshold simultaneously show mutant values, an alarm mechanism is triggered.

[0017] Optionally, the central server visualizes the analysis results in the form of charts, maps, etc., and visually displays the blasting vibration situation to the user.

[0018] By adopting the above technical solution, the detailed steps for the central server to visualize the analysis results are as follows: Ensure that the mutant value data packets and ordinary vibration data packets received from the edge data analysis unit are complete and accurate. Clean the data to remove invalid or incorrect data points.

[0019] Integrate the mutant value data packets and ordinary vibration data packets uploaded by all edge data analysis units.

[0020] Sort the data according to the timestamp to ensure the correctness of the time-series data.

[0021] Conduct statistical analysis on the integrated data, including calculating the average value, standard deviation, frequency distribution, etc. of the vibration data.

[0022] Trend chart: Use a time-series chart to show the trend of vibration data, such as a line chart or a curve chart.

[0023] X-axis: Time; Y-axis: Vibration intensity or specific vibration characteristics; Distribution chart: Use a histogram or a density chart to show the distribution of vibration data.

[0024] X-axis: Vibration intensity or characteristic value; Y-axis: Frequency or probability density; Mark the positions of each edge monitoring unit on the map.

[0025] According to the intensity or mutation situation of the vibration data, use different colors or icons to show the vibration situation of each monitoring unit on the map.

[0026] Set up an interactive interface to allow users to view the detailed information of different monitoring units through operations such as clicking and zooming. Provide filtering and searching functions, and users can view the data according to conditions such as time, location, and vibration intensity.

[0027] Integrate the charts and maps into a report or provide them to users through a web interface.

[0028] Provide a download function to allow users to download the charts and the original data.

[0029] In the form of charts and maps, users can intuitively understand the blasting vibration situation, which is convenient for making quick decisions. Displaying complex data in a graphical way reduces the threshold for users to understand the data.

[0030] Users can deeply explore the data through an interactive interface to discover potential problems or patterns.

[0031] Integrating multiple charts and maps provides a comprehensive information perspective to help users gain a deeper understanding.

[0032] Through real-time updated charts and maps, users can monitor the blasting vibration situation in real time and respond to abnormal events in a timely manner.

[0033] Optionally, physical protection is respectively carried out on multiple edge computing units. The physical protection is to place the edge data analysis unit in a pre-set monitoring pit and install an explosion-proof cover above the edge data analysis unit.

[0034] By adopting the above technical solution, in order to protect the edge computing unit from physical damage caused by blasting, the edge computing unit does not need to be exposed for monitoring, and only needs to receive the monitoring signals of the vibration sensors during the blasting duration. Therefore, by adopting the method of placing it in a pre-set monitoring pit and installing an explosion-proof cover above the edge data analysis unit, the physical protection ensures that the edge data analysis unit can continuously and stably collect and transmit data during the blasting process, ensuring the integrity and accuracy of the data.

[0035] Optionally, in step 2, multiple vibration sensors in the edge monitoring unit are communicatively connected to the edge data analysis unit at the geometric center based on communication lines.

[0036] Optionally, the multiple vibration sensors are respectively wireless vibration sensors. While being communicatively connected via communication lines, the multiple vibration sensors are respectively wirelessly communicatively connected to the edge data analysis unit at the geometric center based on a wireless communication network.

[0037] By adopting the above technical solution, the vibration monitoring values of multiple vibration sensors are collected by both wireless and wired methods to ensure the integrity of data collection.

[0038] Optionally, step 6 includes the following sub-steps: Step 61, vibration waveform feature extraction and analysis. The vibration waveform features include vibration maximum value, vibration minimum value, mean value, variance, kurtosis, and skewness. Step 62, calculate the first-order waveform derivative and the second-order waveform derivative respectively. Step 63, set the mutation detection threshold. Step 64: Compare the vibration waveform features, the first-order waveform derivative, and the second-order waveform derivative with the mutation detection threshold respectively. If any value is greater than the vibration waveform feature, it is determined that there is a mutation in the corresponding vibration waveform.

[0039] By adopting the above technical solution, by extracting multiple features (maximum value, minimum value, mean value, variance, kurtosis, and skewness) of the vibration waveform and combining the first-order and second-order waveform derivatives, the vibration data can be analyzed more comprehensively, thereby improving the accuracy of mutation detection. The calculation of the first-order and second-order waveform derivatives helps to identify the subtle changes and trends in the vibration waveform, enabling the algorithm to detect potential mutation points more sensitively.

[0040] Set the mutation detection threshold and compare it with multiple vibration waveform features, which can effectively reduce false alarms caused by random noise or normal fluctuations.

[0041] The local processing of the edge computing unit enables real-time mutation analysis. Once a mutation is detected, corresponding measures can be taken immediately to improve the rapid response ability. Through step-by-step feature extraction and comparison, the algorithm process is clear, facilitating optimization and adjustment to adapt to different monitoring environments and requirements.

[0042] After mutation analysis at the edge, the information of the detected mutation needs to be preferentially transmitted to the central server, reducing the data transmission volume of key data and avoiding network congestion.

[0043] By comprehensively considering multiple waveform features, the algorithm has strong adaptability to different types of vibration events, improving the robustness of the system.

[0044] Optionally, in step 6, calculate the characteristic values of the vibration waveform: Vibration maximum value ; Vibration minimum value ; Mean value ; Variance ; Kurtosis ; Skewness ; Where is the vibration value at time t, and N is the total quantity; Calculate the difference between the vibration maximum value and the mean value of the vibration maximum value, calculate the difference between the vibration minimum value and the mean value of the vibration minimum value, calculate the difference between the kurtosis and the mean value of the kurtosis, calculate the difference between the skewness and the mean value of the skewness. If any difference is greater than the mutation detection threshold, it is determined that there is a mutation in the corresponding vibration waveform; otherwise, continue to calculate the first-order waveform derivative and the second-order waveform derivative; First-order waveform derivative The calculation formula is: ; Where is the time interval; is the vibration value at time t + 1; Second-order waveform derivative The calculation formula is: ; Where is the first-order waveform derivative at time t + 1.

[0045] A blasting vibration monitoring data processing device based on edge computing is used to implement a blasting vibration monitoring data processing method based on edge computing. The blasting vibration monitoring data processing device includes multiple groups of vibration sensors, multiple edge data analysis units, and a central server. The multiple groups of vibration sensors are respectively and uniformly arranged at multiple edge monitoring units at the blasting site. The multiple edge data analysis units are respectively installed in monitoring pits preset at the physical centers of the multiple edge monitoring units, and an explosion-proof cover is installed above the edge data analysis units; The multiple vibration sensors within the same edge monitoring unit are respectively communicatively connected to the edge data analysis unit at the physical center of the edge monitoring unit in a wired and wireless manner, and the multiple edge data analysis units are respectively wirelessly communicatively connected to the central server.

[0046] Optionally, the edge data analysis unit includes a wireless communication module, a multi-channel data collector, a memory, and a data analysis chip. The multiple vibration sensors within the same edge monitoring unit are respectively wirelessly communicatively connected to the wireless communication module in a wireless manner, and are respectively communicatively connected to the signal input ends of the multi-channel data collector through communication lines. The wireless communication module and the multi-channel data collector are respectively communicatively connected to the memory, the data analysis chip is communicatively connected to the memory, and the memory is wirelessly communicatively connected to the central server through the wireless communication module.

[0047] In summary, the present invention includes at least one of the following beneficial technical effects: The edge data analysis unit realizes the local processing of data, reduces the delay of data transmission, and improves the ability of real-time monitoring and rapid response. The local processing of the edge computing unit enables mutation analysis to be carried out in real time. Once a mutation is detected, corresponding measures can be taken immediately to improve the rapid response ability. Through step-by-step feature extraction and comparison, the algorithm flow is clear, which is convenient for optimization and adjustment to adapt to different monitoring environments and requirements.

[0048] After mutation analysis at the edge, the information of the detected mutation needs to be preferentially transmitted to the central server, reducing the data transmission volume of key data and avoiding network congestion.

[0049] By comprehensively considering multiple waveform features, the algorithm has strong adaptability to different types of vibration events, improving the robustness of the system.

[0050] Compress and downsample ordinary vibration data, reducing the resource requirements for storage and transmission and optimizing resource utilization. The central server performs global vibration pattern recognition and anomaly detection. Combining with the local detail analysis of the edge unit, it can comprehensively understand the vibration data and generate more accurate statistical analysis results.

[0051] According to the monitoring range and requirements, the edge monitoring units and the edge data analysis units can be flexibly divided and deployed, which is easy to expand to a larger monitoring area or a more complex monitoring scenario. Description of the Drawings

[0052] Figure 1 is a schematic flowchart of the method for processing blasting vibration monitoring data based on edge computing according to the present invention; Figure 2 is a schematic diagram of the electrical component connection principle of the device for processing blasting vibration monitoring data based on edge computing according to the present invention.

[0053] Description of the reference numerals: 1. Edge data analysis unit; 11. Wireless communication module; 12. Multichannel data collector; 13. Memory; 14. Data analysis chip; 2. Vibration sensor; 3. Central server. Detailed Embodiment

[0054] The following further describes the present invention in detail with reference to the drawings.

[0055] The embodiments of the present invention disclose a method and a device for processing blasting vibration monitoring data based on edge computing.

[0056] Referring to Figure 1 and Figure 2 , Embodiment 1, a method for processing blasting vibration monitoring data based on edge computing, includes the following steps: Step 1, divide the monitoring range of the blasting point at the blasting site into multiple edge monitoring units, and deploy multiple edge data analysis units 1 at the geometric centers of the multiple edge monitoring units respectively; Step 2, respectively communicate and connect multiple vibration sensors 2 in the edge monitoring unit with the edge data analysis unit 1 at the geometric center; Step 3, start the blasting, and all vibration sensors 2 monitor the vibration data during the duration of the blasting effect; Step 4, after the duration of the blasting effect ends, multiple edge data analysis units 1 respectively collect the vibration data packets based on time series of multiple vibration sensors 2 in the edge monitoring unit; Step 5, the edge data analysis unit 1 analyzes the vibration data packet based on time series, and performs edge computing and analysis on the vibration data of each vibration sensor 2 respectively to obtain vibration waveforms; Step 6, the edge data analysis unit 1 extracts waveform features from the vibration waveforms corresponding to the vibration data of each vibration sensor 2 within the same edge monitoring unit, and performs mutation analysis based on the waveform features; Step 7, if the difference between the eigenvalue and the corresponding eigen-mean value is greater than the set mutation detection threshold, or the first derivative of the characteristic waveform is greater than the mutation detection threshold, or the second derivative of the characteristic waveform is greater than the mutation detection threshold, then it is determined that the eigenvalue is a mutation value; Step 8, the edge data analysis unit 1 marks the identified mutation values and their corresponding waveform features, extracts the key information of the features, and packs the mutation values and key information data into a mutation value data packet; the edge data analysis unit 1 performs data compression and downsampling processing on the normal vibration data without mutation to form a normal vibration data packet; Step 9, all edge data analysis units 1 first transmit the mutation value data packets to the central server 3 through the wireless communication network. After the central server 3 receives all the mutation value data packets from all edge data analysis units 1, it respectively sends signals of the normal vibration data packets to all edge data analysis units 1, and then all edge data analysis units 1 transmit the normal vibration data packets to the central server 3 through the wireless communication network; Step 10, the central server 3 performs global vibration mode recognition and anomaly detection on the received mutation value data packets, and the central server 3 performs statistical analysis on the normal vibration data packets to generate trend charts and distribution charts of the vibration data.

[0057] By deploying the edge data analysis unit 1 in the edge monitoring unit, the local processing of data is realized, the data transmission delay is reduced, and the real-time monitoring and rapid response capabilities are improved. At the source of data generation, the edge data analysis unit 1 is used for edge computing processing, important information is screened out, key features are extracted and mutation analysis is performed, so that abnormal events in blasting vibration can be more accurately identified, the reliability of data can be improved, the overall data processing efficiency can be greatly improved, and the computing burden on the central server 3 can be reduced.

[0058] The compression and downsampling processing of the normal vibration data reduces the resource requirements for storage and transmission, and optimizes the resource utilization. The central server 3 performs global vibration mode recognition and anomaly detection, and combines the local detail analysis of the edge unit, so as to more comprehensively understand the vibration data and generate more accurate statistical analysis results.

[0059] This method can flexibly divide the edge monitoring unit and deploy the edge data analysis unit 1 according to the monitoring scope and requirements, and is easy to expand to a larger monitoring area or a more complex monitoring scenario.

[0060] The edge computing unit 1 can adapt to various harsh environments. When transmitting data to the central server 3, it does so after the duration of the blasting impact, so wireless communication is not affected by the explosion.

[0061] In Embodiment 2, if the central server 3 analyzes that multiple edge monitoring units 1 with more than a set number threshold simultaneously show mutation values, an alarm mechanism is triggered.

[0062] In Embodiment 3, the central server 3 visualizes the analysis results in the form of charts, maps, etc., and visually shows the blasting vibration situation to the user.

[0063] The detailed steps for the central server 3 to visualize the analysis results are as follows: Ensure that the mutation value data packets and normal vibration data packets received from the edge data analysis unit 1 are complete and accurate. Clean the data to remove invalid or incorrect data points.

[0064] Integrate the mutation value data packets and normal vibration data packets uploaded by all edge data analysis units 1.

[0065] Sort the data according to the timestamp to ensure the correctness of the time-series data.

[0066] Conduct statistical analysis on the integrated data, including calculating the average value, standard deviation, frequency distribution, etc. of the vibration data.

[0067] Trend chart: Use a time-series chart to show the trend of vibration data, such as a line chart or a curve chart.

[0068] X-axis: Time; Y-axis: Vibration intensity or specific vibration characteristics; Distribution chart: Use a histogram or a density chart to show the distribution of vibration data.

[0069] X-axis: Vibration intensity or characteristic value; Y-axis: Frequency or probability density; Mark the positions of each edge monitoring unit on the map.

[0070] According to the intensity or mutation situation of the vibration data, use different colors or icons to show the vibration situation of each monitoring unit on the map.

[0071] Set up an interactive interface to allow users to view the detailed information of different monitoring units through operations such as clicking and zooming. Provide filtering and searching functions, and users can view the data according to conditions such as time, location, and vibration intensity.

[0072] Integrate the charts and maps into a report or provide them to users through a web interface.

[0073] Provide a download function to allow users to download the charts and the original data.

[0074] In the form of charts and maps, users can intuitively understand the blasting vibration situation, which is convenient for making quick decisions. Displaying complex data in a graphical way reduces the threshold for users to understand the data.

[0075] Users can deeply explore the data through an interactive interface to discover potential problems or patterns.

[0076] Integrating multiple charts and maps provides a comprehensive information perspective to help users gain a deeper understanding.

[0077] Through real-time updated charts and maps, users can monitor the blasting vibration situation in real time and respond to abnormal events in a timely manner.

[0078] Example 4: Physical protection is carried out on multiple edge computing units 1 respectively. The physical protection is to place the edge data analysis unit 1 in a pre-set monitoring pit and install an explosion-proof cover above the edge data analysis unit 1.

[0079] In order to protect the edge computing unit 1 from physical damage caused by blasting, the edge computing unit 1 does not need to be monitored naked. It only needs to receive the monitoring signals of the vibration sensors 2 during the blasting duration. Therefore, by using the method of placing it in a pre-set monitoring pit and installing an explosion-proof cover above the edge data analysis unit 1, the physical protection ensures that the edge data analysis unit 1 can continuously and stably collect and transmit data during the blasting process, guaranteeing the integrity and accuracy of the data.

[0080] Example 5: In step 2, multiple vibration sensors 2 in the edge monitoring unit are communicatively connected to the edge data analysis unit 1 at the geometric center based on communication lines.

[0081] Example 6: The multiple vibration sensors 2 are respectively wireless vibration sensors. While being communicatively connected through communication lines, the multiple vibration sensors 2 are respectively wirelessly communicatively connected to the edge data analysis unit 1 at the geometric center based on a wireless communication network.

[0082] Simultaneously adopting wireless and wired methods to collect the vibration monitoring values of the multiple vibration sensors 2 ensures the integrity of data collection.

[0083] Example 7: Step 6 includes the following sub-steps: Step 61: Extract and analyze vibration waveform features. The vibration waveform features include vibration maximum value, vibration minimum value, mean value, variance, kurtosis, and skewness. Step 62: Calculate the first-order waveform derivative and the second-order waveform derivative respectively. Step 63: Set a mutation detection threshold. Step 64: Compare the vibration waveform features, the first-order waveform derivative, and the second-order waveform derivative with the mutation detection threshold respectively. If any value is greater than the vibration waveform feature, it is determined that there is a mutation in the corresponding vibration waveform.

[0084] By extracting multiple features of the vibration waveform (maximum value, minimum value, mean value, variance, kurtosis, and skewness) and combining the first-order and second-order waveform derivatives, the vibration data can be analyzed more comprehensively, thereby improving the accuracy of mutation detection. The calculation of the first-order and second-order waveform derivatives helps to identify the subtle changes and trends in the vibration waveform, enabling the algorithm to detect potential mutation points more sensitively.

[0085] Setting the mutation detection threshold and comparing it with multiple vibration waveform features can effectively reduce false alarms caused by random noise or normal fluctuations.

[0086] The localization processing of the edge computing unit 1 enables real-time mutation analysis. Once a mutation is detected, corresponding measures can be taken immediately to improve the rapid response ability. Through step-by-step feature extraction and comparison, the algorithm flow is clear, facilitating optimization and adjustment to adapt to different monitoring environments and requirements.

[0087] After mutation analysis at the edge, the information of the detected mutation needs to be preferentially transmitted to the central server, reducing the data transmission volume of key data and avoiding network congestion.

[0088] By comprehensively considering multiple waveform features, the algorithm has strong adaptability to different types of vibration events, improving the robustness of the system.

[0089] Example 8, in step 6, calculate the characteristic values of the vibration waveform: Vibration maximum value ; Vibration minimum value ; Mean value ; Variance ; Kurtosis ; Skewness ; Where is the vibration value at time t, and N is the total quantity; Calculate the difference between the vibration maximum value and the mean value of the vibration maximum value, calculate the difference between the vibration minimum value and the mean value of the vibration minimum value, calculate the difference between the kurtosis and the mean value of the kurtosis, calculate the difference between the skewness and the mean value of the skewness. If any difference is greater than the mutation detection threshold, it is determined that there is a mutation in the corresponding vibration waveform; otherwise, continue to calculate the first-order waveform derivative and the second-order waveform derivative; First-order waveform derivative The calculation formula of is: ; where is the time interval; is the vibration value at time t + 1; second-order waveform derivative The calculation formula of is: ; where is the first-order waveform derivative at time t + 1.

[0090] Embodiment 9. A blasting vibration monitoring data processing device based on edge computing is used to implement a blasting vibration monitoring data processing method based on edge computing. The blasting vibration monitoring data processing device includes multiple groups of vibration sensors 2, multiple edge data analysis units 1, and a central server 3. The multiple groups of vibration sensors 2 are respectively and evenly arranged at multiple edge monitoring units at the blasting site. The multiple edge data analysis units 1 are respectively installed in monitoring pits preset at the physical centers of the multiple edge monitoring units, and an explosion-proof cover is installed above the edge data analysis unit 1; The multiple vibration sensors 2 within the same edge monitoring unit are respectively communicatively connected to the edge data analysis unit 1 at the physical center of the edge monitoring unit in a wired and wireless manner, and the multiple edge data analysis units 1 are respectively wirelessly communicatively connected to the central server 3.

[0091] Embodiment 10. The edge data analysis unit 1 includes a wireless communication module 11, a multi-channel data collector 12, a memory 13, and a data analysis chip 14. The multiple vibration sensors 2 within the same edge monitoring unit are respectively wirelessly communicatively connected to the wireless communication module 11 in a wireless manner, and are respectively communicatively connected to the signal input ends of the multi-channel data collector 12 through communication lines. The wireless communication module 11 and the multi-channel data collector 12 are respectively communicatively connected to the memory 13. The data analysis chip 14 is communicatively connected to the memory 13, and the memory 13 is wirelessly communicatively connected to the central server 3 through the wireless communication module 11.

[0092] The above are all preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby. Therefore, all equivalent changes made according to the structure, shape, and principle of the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for processing blasting vibration monitoring data based on edge computing, characterized in that: It includes the following steps: Step 1: Divide the monitoring range of the blasting point at the blasting site into multiple edge monitoring units, and deploy multiple edge data analysis units (1) at the geometric centers of the multiple edge monitoring units respectively; Step 2: Connect multiple vibration sensors (2) within the edge monitoring unit to the edge data analysis unit (1) at the geometric center through communication respectively; Step 3: Initiate the blasting, and all vibration sensors (2) monitor vibration data during the duration of the blasting impact; Step 4: After the duration of the blasting impact ends, multiple edge data analysis units (1) respectively collect the vibration data packets based on time series of multiple vibration sensors (2) within the edge monitoring unit; Step 5: The edge data analysis unit (1) analyzes the vibration data packets based on time series, and performs edge computing analysis on the vibration data of each vibration sensor (2) respectively to obtain vibration waveforms; Step 6: The edge data analysis unit (1) extracts waveform features from the vibration waveforms corresponding to the vibration data of each vibration sensor (2) within the same edge monitoring unit, and performs mutation analysis based on the waveform features; Step 7: If the difference between the eigenvalue and the corresponding feature mean value is greater than the set mutation detection threshold, or the first derivative of the feature waveform is greater than the mutation detection threshold, or the second derivative of the feature waveform is greater than the mutation detection threshold, then it is determined that the eigenvalue is a mutation value; Step 8: The edge data analysis unit (1) marks the identified mutation values and their corresponding waveform features, extracts the key feature information, and packs the mutation values and key information data into a mutation value data packet; the edge data analysis unit (1) performs data compression and downsampling processing on the ordinary vibration data without mutation to form an ordinary vibration data packet; Step 9: All edge data analysis units (1) first transmit the mutation value data packet to the central server (3) through the wireless communication network. After the central server (3) receives all the mutation value data packets from all edge data analysis units (1), it respectively sends signals of the ordinary vibration data packets to all edge data analysis units (1), and then all edge data analysis units (1) transmit the ordinary vibration data packets to the central server (3) through the wireless communication network; Step 10: The central server (3) performs global vibration mode recognition and anomaly detection on the received mutation value data packet, and the central server (3) performs statistical analysis on the ordinary vibration data packet to generate a trend chart and a distribution chart of the vibration data.

2. The method for processing blasting vibration monitoring data based on edge computing according to claim 1, wherein: If the central server (3) analyzes that multiple edge monitoring units (1) exceeding the set quantity threshold simultaneously have mutation values, an alarm mechanism is triggered.

3. The method for processing blasting vibration monitoring data based on edge computing according to claim 2, wherein: The central server (3) visualizes the analysis results in the form of charts and maps, and visually displays the blasting vibration situation to the user.

4. The method for processing blasting vibration monitoring data based on edge computing according to claim 1, wherein: Physically protect multiple edge computing units (1) respectively. The physical protection is to place the edge data analysis unit (1) in a pre-set monitoring pit, and install an explosion-proof cover above the edge data analysis unit (1).

5. The method for processing blasting vibration monitoring data based on edge computing according to claim 4, wherein: In Step 2, multiple vibration sensors (2) within the edge monitoring unit are connected to the edge data analysis unit (1) at the geometric center through communication lines.

6. The method for processing blasting vibration monitoring data based on edge computing according to claim 5, characterized in that: The multiple vibration sensors (2) are respectively wireless vibration sensors. While communicating through communication lines, the multiple vibration sensors (2) are respectively wirelessly communicatively connected to the edge data analysis unit (1) at the geometric center based on a wireless communication network.

7. The method for processing blasting vibration monitoring data based on edge computing according to claim 1, characterized in that: Step 6 includes the following sub-steps: Step 61, vibration waveform feature extraction and analysis. The vibration waveform features include the vibration maximum value, vibration minimum value, mean value, variance, kurtosis, and skewness. Step 62, calculate the first-order waveform derivative and the second-order waveform derivative respectively. Step 63, set the mutation detection threshold. Step 64, compare the vibration waveform features, the first-order waveform derivative, and the second-order waveform derivative with the mutation detection threshold respectively. If any value is greater than the vibration waveform feature, it is determined that there is a mutation in the corresponding vibration waveform.

8. The method for processing blasting vibration monitoring data based on edge computing according to claim 5, wherein: In Step 6, calculate the eigenvalue of the vibration waveform: Maximum vibration ; Minimum vibration ; Mean value ; Variance ; Kurtosis ; Skewness ; where is the vibration value at time t, and N is the total number; Calculate the difference between the maximum vibration value and the mean value of the maximum vibration value, and calculate the difference between the minimum vibration value and the mean value of the minimum vibration value. Calculate the difference between the kurtosis and the mean value of the kurtosis, and calculate the difference between the skewness and the mean value of the skewness. If any of the differences is greater than the mutation detection threshold, it is determined that there is a mutation in the corresponding vibration waveform. Otherwise, continue to calculate the first-order waveform derivative and the second-order waveform derivative; First-order waveform derivative The calculation formula is: ; Among them is the time interval; is the vibration value at the (t + 1)th moment; Second-order waveform derivative The calculation formula is as follows: ; wherein is the first-order waveform derivative at time t+1.

9. A blasting vibration monitoring data processing device based on edge computing, characterized in that: For implementing the blasting vibration monitoring data processing method based on edge computing according to any one of claims 1-8, the blasting vibration monitoring data processing device includes multiple groups of vibration sensors (2), multiple edge data analysis units (1), and a central server (3). The multiple groups of vibration sensors (2) are respectively uniformly arranged at multiple edge monitoring units at the blasting site. The multiple edge data analysis units (1) are respectively installed in monitoring pits preset at the physical centers of the multiple edge monitoring units, and an explosion-proof cover is installed above the edge data analysis unit (1). The multiple vibration sensors (2) within the same edge monitoring unit are respectively communicatively connected to the edge data analysis unit (1) at the physical center of the edge monitoring unit in wired and wireless manners. The multiple edge data analysis units (1) are respectively wirelessly communicatively connected to the central server (3).

10. The blasting vibration monitoring data processing device based on edge computing according to claim 9, characterized in that: The edge data analysis unit (1) includes a wireless communication module (11), a multi-channel data collector (12), a memory (13), and a data analysis chip (14). The multiple vibration sensors (2) within the same edge monitoring unit are respectively wirelessly communicatively connected to the wireless communication module (11) in a wireless manner and are respectively communicatively connected to the signal input ends of the multi-channel data collector (12) through communication lines. The wireless communication module (11) and the multi-channel data collector (12) are respectively communicatively connected to the memory (13). The data analysis chip (14) is communicatively connected to the memory (13). The memory (13) is wirelessly communicatively connected to the central server (3) through the wireless communication module (11).

Images