A method and system for collecting deep foundation pit monitoring data

Abstract

The present invention relates to the technical field of civil engineering monitoring, and specifically to a method and system for collecting deep foundation pit monitoring data, which includes the following steps: based on a ground penetrating radar and acoustic sensors, using a signal acquisition algorithm to collect formation reflection data and perform preliminary data filtering to generate enhanced formation reflection data. In the present invention, the method for collecting deep foundation pit monitoring data combines a ground penetrating radar and acoustic sensors, and through the fast Fourier transform algorithm, improves the data accuracy and the fineness of frequency domain characteristics. The double encryption of the elliptic curve encryption algorithm and the RSA asymmetric encryption algorithm is used to ensure data security, and the neural network pattern recognition algorithm is used for abnormal pattern analysis to enhance the accurate recognition ability of potential hazards and make the risk assessment more accurate. Through the multi-level early warning algorithm, fine division and timely early warning are realized, the timeliness and accuracy of the early warning response are improved, and an efficient and accurate technical means is provided for the safety monitoring of deep foundation pits.

Description

Technical Field

[0001] The present invention relates to the technical field of civil engineering monitoring, and particularly to a method and system for collecting deep foundation pit monitoring data. Background Art

[0002] Civil engineering monitoring is a technical field covering multiple sub - fields, mainly used for monitoring and evaluating the performance, safety and stability of civil engineering structures. This includes buildings, bridges, tunnels, dams, underground foundation works, etc. The collection and analysis of monitoring data are crucial for ensuring the reliability and durability of engineering structures.

[0003] Among them, the method for collecting deep foundation pit monitoring data is used to collect data related to deep foundation pit projects in real - time, regularly or at fixed points, in order to monitor and evaluate the performance and stability of deep foundation pit structures. The main purpose is to ensure the safety of deep foundation pit projects, avoid geological disasters or structural damage, and at the same time monitor and manage the project progress to ensure that the project proceeds as planned. Through the collection of deep foundation pit monitoring data, key information of the engineering structure can be obtained in real - time, so as to make decisions to ensure the smooth progress of construction and the project, reduce risks and costs. In addition, the monitoring data can also be used to verify design assumptions, improve engineering planning, and provide useful empirical data for subsequent civil engineering projects.

[0004] Traditional methods lack efficient algorithm support in abnormal pattern recognition and risk assessment, making it difficult to accurately locate and predict potential risks, thus weakening the practicality and reliability of the early warning system. At the same time, the processing of risk level classification is not detailed enough, resulting in untimely or inaccurate early warning signals, and thus unable to provide the most effective decision - making support for decision - makers. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art, and to propose a method and system for collecting deep foundation pit monitoring data.

[0006] To achieve the above - mentioned purpose, the present invention adopts the following technical scheme: A method for collecting deep foundation pit monitoring data, comprising the following steps:

[0007] S1: Based on a ground penetration radar and acoustic sensors, using a signal acquisition algorithm, collect formation reflection data and perform preliminary data filtering to generate enhanced formation reflection data;

[0008] S2: Based on the enhanced formation reflection data, using the fast Fourier transform algorithm, perform signal spectrum analysis and extract characteristic frequencies to generate frequency - domain characteristic data;

[0009] S3: Based on the frequency - domain characteristic data, using the elliptic curve encryption algorithm, perform secure data encapsulation and prepare for transmission to generate encrypted monitoring data to be sent;

[0010] S4: Based on the encrypted monitoring data to be sent, send it to the background server. The background server uses the RSA asymmetric encryption algorithm to decrypt the data and perform data verification to generate the decrypted monitoring data;

[0011] S5: Based on the decrypted monitoring data, use the neural network pattern recognition algorithm to perform abnormal pattern analysis and risk assessment to generate a stability analysis report;

[0012] S6: Based on the stability analysis report, when risk features are identified, use a multi-level early warning algorithm to divide the risk levels and send out early warning signals;

[0013] The formation reflection data is specifically the acoustic wave reflection intensity information at the junction of multiple underground media. The frequency domain feature data is specifically the signal features of frequency distribution and amplitude size. The encrypted monitoring data to be sent is specifically the data packet encrypted by the ECC algorithm. The decrypted monitoring data is specifically the original monitoring data. The stability analysis report is specifically the key monitoring indicators generated by combining the potential landslide area, the formation subsidence speed, and the expected change trend. The early warning signal is specifically the graded early warning information.

[0014] As a further solution of the present invention, the steps of collecting formation reflection data and performing preliminary data filtering based on a ground penetrating radar and acoustic wave sensors using a signal acquisition algorithm are specifically as follows:

[0015] S101: Based on the ground penetrating radar equipment, deploy an acoustic wave sensor array, emit acoustic waves to a specified monitoring area, and receive the acoustic wave signals reflected by the formation to generate the original formation acoustic wave reflection data;

[0016] S102: Based on the original formation acoustic wave reflection data, use a digital signal processing algorithm to perform data synchronization and time marking to generate the time-sequence calibrated formation acoustic wave reflection data;

[0017] S103: Based on the time-sequence calibrated formation acoustic wave reflection data, use a high-pass filter to filter out low-frequency noise and retain the high-frequency components of the formation reflection signal to generate high-frequency formation reflection signal data;

[0018] S104: Based on the high-frequency formation reflection signal data, apply a signal enhancement algorithm of adaptive filtering to improve the signal-to-noise ratio and strengthen the formation reflection signal to generate enhanced formation reflection data.

[0019] As a further solution of the present invention, based on the enhanced formation reflection data, the steps of performing signal spectrum analysis using the fast Fourier transform algorithm, extracting characteristic frequencies, and generating frequency-domain characteristic data are specifically as follows:

[0020] S201: Based on the enhanced formation reflection data, using the window function processing technology, segment the signal for local analysis, and generate the formation reflection data after window function processing;

[0021] S202: Based on the formation reflection data after window function processing, apply the fast Fourier transform algorithm to convert the time-domain signal into a frequency-domain signal, perform signal spectrum analysis, and generate the formation reflection spectrum data;

[0022] S203: Based on the formation reflection spectrum data, using the spectrum analysis technology, separate and identify the main frequency components, extract the characteristic frequencies, and generate the characteristic frequency analysis data;

[0023] S204: Based on the characteristic frequency analysis data, use the peak detection algorithm to determine the characteristic frequencies and amplitudes in the spectrum, and generate the frequency-domain characteristic data.

[0024] As a further solution of the present invention, based on the frequency-domain characteristic data, the steps of performing secure data encapsulation using the elliptic curve encryption algorithm, preparing for transmission, and generating the encrypted monitoring data to be sent are specifically as follows:

[0025] S301: Based on the frequency-domain characteristic data, perform data encryption using the elliptic curve encryption algorithm to generate the ECC-encrypted monitoring data;

[0026] S302: Based on the ECC-encrypted monitoring data, construct a data encapsulation protocol, encapsulate the data information, and generate the encapsulated monitoring data packet;

[0027] S303: Based on the encapsulated monitoring data packet, perform integrity verification, generate a data hash value using the MD5 algorithm, append it to the end of the data packet, and generate the monitoring data packet with verification appended;

[0028] S304: Based on the monitoring data packet with verification appended, connect to the background server through the TLS transmission protocol to generate the encrypted monitoring data to be sent.

[0029] As a further solution of the present invention, based on the encrypted monitoring data to be sent, send it to the background server. The server uses the RSA asymmetric encryption algorithm to decrypt the data and perform data verification. The steps of generating the decrypted monitoring data are specifically as follows:

[0030] S401: Based on the encrypted monitoring data to be sent, send it to the background server through the TLS transmission protocol to establish a secure communication channel;

[0031] S402: Based on the secure communication channel, send the encrypted monitoring data to the background server to generate the encrypted data after transmission;

[0032] S403: Based on the encrypted data after transmission, use the RSA asymmetric encryption algorithm to decrypt the data to generate the decrypted data on the server side;

[0033] S404: Based on the decrypted data on the server side, perform integrity and consistency verification to generate the monitored data after decryption.

[0034] As a further solution of the present invention, based on the monitored data after decryption, adopt the neural network pattern recognition algorithm to perform abnormal pattern analysis and risk assessment, and the steps of generating the stability analysis report are specifically as follows:

[0035] S501: Based on the monitored data after decryption, perform data normalization processing to generate the monitored data after preprocessing;

[0036] S502: Based on the monitored data after preprocessing, perform learning and training through the neural network pattern recognition algorithm to generate the trained neural network model;

[0037] S503: Based on the trained neural network model, perform real-time abnormal pattern analysis, identify potential monitoring risks, and generate the identified abnormal pattern data;

[0038] S504: Based on the identified abnormal pattern data, perform risk assessment, determine the risk level, and generate the stability analysis report.

[0039] As a further solution of the present invention, based on the stability analysis report, when risk characteristics are identified, adopt a multi-level early warning algorithm to classify the risk level and send out early warning signals. The steps are specifically as follows:

[0040] S601: Based on the stability analysis report, analyze the risk level in the analysis report to determine whether to enter the early warning process and generate the risk level judgment result;

[0041] S602: Based on the risk level judgment result, adopt a multi-level early warning algorithm to classify the urgency and severity of the early warning signal according to the risk level, and generate the risk level classification result;

[0042] S603: Based on the risk level classification result, determine the early warning signal, prepare the early warning notice content and dissemination method, and generate the prepared early warning signal;

[0043] S604: Send a warning signal through a preset propagation channel based on the prepared warning signal.

[0044] A deep foundation pit monitoring data acquisition system, which includes an acoustic wave sensing array module, a data processing module, a signal transformation and analysis module, an encryption and transmission module, a neural network model module, a risk assessment module, and a warning signal module.

[0045] As a further solution of the present invention, the acoustic wave sensing array module is based on a ground penetrating radar device, deploys an acoustic wave sensor array, receives the acoustic wave signals reflected by the formation, and generates original formation acoustic wave reflection data;

[0046] The data processing module is based on the original formation acoustic wave reflection data, uses digital signal processing and filtering algorithms to enhance the signal, and generates enhanced formation reflection data;

[0047] The signal transformation and analysis module is based on the enhanced formation reflection data, applies window function processing and fast Fourier transform to extract the characteristic frequency, and generates frequency domain characteristic data;

[0048] The encryption and transmission module is based on the frequency domain characteristic data, uses the elliptic curve encryption algorithm to encrypt the data, and sends it to the background server through the TLS protocol to generate the encrypted monitoring data to be sent;

[0049] The neural network model module is based on the decrypted monitoring data, conducts data learning and identification of abnormal patterns through the neural network model, and generates the identified abnormal pattern data;

[0050] The risk assessment module is based on the identified abnormal pattern data, conducts risk assessment to determine the risk level, and generates a stability analysis report;

[0051] The warning signal module is based on the stability analysis report, uses a multi-level warning algorithm to divide the risk level and send out a warning signal, and generates the sent warning signal.

[0052] As a further solution of the present invention, the acoustic wave sensing array module includes an acoustic wave transmitting sub-module, an acoustic wave receiving sub-module, and a data generating sub-module;

[0053] The data processing module includes a signal processing sub-module, a filtering sub-module, and a signal enhancement sub-module;

[0054] The signal transformation and analysis module includes a window function processing sub-module, a signal transformation sub-module, and a spectrum analysis sub-module;

[0055] The encryption and transmission module includes a data encryption sub-module, a data encapsulation sub-module, and a data sending sub-module;

[0056] The neural network model module includes a data preprocessing sub-module, a model training sub-module, and an abnormal pattern recognition sub-module;

[0057] The risk assessment module includes a risk identification sub-module, a risk assessment sub-module, and a report generation sub-module;

[0058] The warning signal module includes a risk level judgment sub-module, a risk level classification sub-module, and a warning signal generation sub-module.

[0059] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0060] In the present invention, the deep foundation pit monitoring data acquisition method accurately acquires formation reflection data by combining ground penetrating radar and acoustic sensors, and uses the fast Fourier transform algorithm for detailed signal spectrum analysis and characteristic frequency extraction, effectively improving the accuracy of data acquisition and the fineness of frequency domain characteristics. Through the dual data encryption protection of the elliptic curve encryption algorithm and the RSA asymmetric encryption algorithm, the security of data during transmission is enhanced, and the risk of leakage of important information is avoided. In addition, the neural network pattern recognition algorithm is used for abnormal pattern analysis, improving the accurate recognition ability of potential landslide areas, formation subsidence speed, and expected change trends, making the risk assessment more accurate. Finally, through the multi-level warning algorithm, the risk is finely divided and timely warned, significantly improving the timeliness and accuracy of warning response, providing a more efficient and accurate technical means for the safety monitoring of deep foundation pits. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 is a schematic diagram of the working process of the present invention;

[0062] Figure 2 is a detailed flowchart of S1 of the present invention;

[0063] Figure 3 is a detailed flowchart of S2 of the present invention;

[0064] Figure 4 is a detailed flowchart of S3 of the present invention;

[0065] Figure 5 is a detailed flowchart of S4 of the present invention;

[0066] Figure 6 is a detailed flowchart of S5 of the present invention;

[0067] Figure 7 is a detailed flowchart of S6 of the present invention;

[0068] Figure 8 is a system flowchart of the present invention;

[0069] Figure 9 This is a schematic diagram of the system framework of the present invention. Detailed implementation manners

[0070] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0071] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. In addition, in the description of the present invention, the meaning of "a plurality" is two or more, unless otherwise specifically defined.

[0072] Embodiment 1

[0073] Please refer to Figure 1 , the present invention provides a technical solution: a method for collecting deep foundation pit monitoring data, including the following steps:

[0074] S1: Based on a ground penetration radar and a sonic sensor, using a signal acquisition algorithm, collect formation reflection data, and perform preliminary data filtering to generate enhanced formation reflection data;

[0075] S2: Based on the enhanced formation reflection data, using a fast Fourier transform algorithm, perform signal spectrum analysis, and extract characteristic frequencies to generate frequency domain characteristic data;

[0076] S3: Based on the frequency domain characteristic data, using an elliptic curve encryption algorithm, perform secure data encapsulation, and perform transmission preparation to generate encrypted monitoring data to be sent;

[0077] S4: Based on the encrypted monitoring data to be sent, send it to the background server. The background server uses an RSA asymmetric encryption algorithm to decrypt the data and perform data verification to generate decrypted monitoring data;

[0078] S5: Based on the decrypted monitoring data, using a neural network pattern recognition algorithm, perform abnormal pattern analysis and risk assessment to generate a stability analysis report;

[0079] S6: Based on the stability analysis report, when risk characteristics are identified, use a multi-level early warning algorithm to divide the risk level and send out an early warning signal;

[0080] The formation reflection data specifically refers to the acoustic wave reflection intensity information at the junction of multiple underground media. The frequency-domain characteristic data specifically refers to the frequency distribution and amplitude signal characteristics. The encrypted monitoring data to be sent specifically refers to the data packet encrypted by the ECC algorithm. The decrypted monitoring data specifically refers to the original monitoring data. The stability analysis report specifically refers to the key monitoring indicators generated by combining the potential landslide area, the formation subsidence speed, and the expected change trend. The warning signal specifically refers to the warning information at different levels.

[0081] This deep foundation pit monitoring data acquisition method integrates multiple modern technologies and algorithms. First, high-precision formation reflection data is acquired through ground penetrating radar and acoustic wave sensors, providing a detailed understanding of the underground situation. The fast Fourier transform algorithm is used for spectrum analysis and feature extraction, which helps to detect abnormal changes in the underground structure in a timely manner, such as cracks or displacements.

[0082] In addition, the security of the data is fully guaranteed. Through the elliptic curve encryption algorithm, the transmitted monitoring data always maintains security, reducing the risk of data leakage. The neural network pattern recognition algorithm is used, and the monitoring data can be analyzed in real time, so as to quickly identify abnormal patterns and conduct risk assessment. This ability to respond to risks in real time is crucial for taking emergency measures.

[0083] The multi-level warning system allows warning signals at different levels to be issued according to the severity of the risk, helping relevant stakeholders to take appropriate measures to mitigate potential risks or hazards. The whole process reduces human intervention, reduces the risk of errors and inconsistencies, and at the same time provides a comprehensive stability analysis report, including key monitoring indicators such as potential landslide areas, formation subsidence speeds, and expected change trends.

[0084] Please refer to Figure 2 , based on ground penetrating radar and acoustic wave sensors, using a signal acquisition algorithm, to acquire formation reflection data and conduct preliminary data filtering. The steps to generate formation reflection data are specifically as follows:

[0085] S101: Based on the ground penetrating radar equipment, deploy an acoustic wave sensor array, emit acoustic waves to the specified monitoring area, and receive the acoustic wave signals reflected by the formation to generate the original formation acoustic wave reflection data;

[0086] S102: Based on the original formation acoustic wave reflection data, use a digital signal processing algorithm to perform data synchronization and time marking to generate the time-sequence calibrated formation acoustic wave reflection data;

[0087] S103: Based on the time-sequence calibrated formation acoustic wave reflection data, use a high-pass filter to filter out low-frequency noise and retain the high-frequency components of the formation reflection signal to generate the high-frequency formation reflection signal data;

[0088] S104: Apply a signal enhancement algorithm with adaptive filtering to the high-frequency formation reflection signal data to improve the signal-to-noise ratio, strengthen the formation reflection signal, and generate enhanced formation reflection data.

[0089] First, in step S101, deploy an acoustic sensor array through a ground penetrating radar device, emit acoustic waves, and receive the signals reflected by the formation to generate original formation acoustic reflection data. This step ensures the correct deployment of the sensors and the accurate acquisition of signals.

[0090] Next, in step S102, use a digital signal processing algorithm for data synchronization and time stamping to generate time-sequence calibrated original formation acoustic reflection data. This step ensures that the data received by different sensors has a consistent time reference, providing an accurate time reference for subsequent analysis.

[0091] In step S103, filter out low-frequency noise through a high-pass filter, retain the high-frequency components of the formation reflection signal, and generate high-frequency formation reflection signal data. This step ensures the quality of the data and removes noise interference that may affect the analysis results.

[0092] Finally, in step S104, apply a signal enhancement algorithm with adaptive filtering to improve the signal-to-noise ratio of the formation reflection signal and generate enhanced formation reflection data. This step strengthens the formation reflection signal, making it easier to analyze and identify, providing a better basis for subsequent data analysis.

[0093] In the whole process, advanced algorithms and technologies are adopted in each step to ensure the accuracy and reliability of the formation reflection data.

[0094] Please refer to Figure 3 , for the steps of performing signal spectrum analysis and extracting characteristic frequencies based on the enhanced formation reflection data using the fast Fourier transform algorithm to generate frequency-domain characteristic data, specifically:

[0095] S201: Based on the enhanced formation reflection data, use window function processing technology to segment the signal for local analysis and generate formation reflection data after window function processing;

[0096] S202: Based on the formation reflection data after window function processing, apply the fast Fourier transform algorithm to convert the time-domain signal into a frequency-domain signal for signal spectrum analysis and generate formation reflection spectrum data;

[0097] S203: Based on the formation reflection spectrum data, use spectrum analysis technology to separate and identify the main frequency components, extract the characteristic frequencies, and generate characteristic frequency analysis data;

[0098] S204: Based on the feature frequency analysis data, use the peak detection algorithm to determine the feature frequencies and amplitudes in the frequency spectrum, and generate frequency domain feature data.

[0099] First, in S201, according to the characteristics and requirements of the enhanced formation reflection data, select an appropriate window function for processing. The window function can be used to limit the spectral resolution and frequency range of the signal to meet the needs of local analysis. Convolve the enhanced formation reflection data with the window function to generate the formation reflection data processed by the window function.

[0100] Next, in S202, apply the fast Fourier transform algorithm (FFT) to perform spectral analysis on the formation reflection data processed by the window function. FFT can convert the time-domain signal into a frequency-domain signal to obtain the formation reflection spectrum data. Spectral analysis can help us understand the frequency components and energy distribution of the signal.

[0101] In S203, based on the formation reflection spectrum data, use spectral analysis techniques to extract feature frequencies. By separating and identifying the main frequency components, the important feature frequencies in the signal can be determined. These feature frequencies may be related to geological structures, underground substances, etc., and are of great significance for fields such as geological exploration and geological disaster warning.

[0102] Finally, in S204, use the peak detection algorithm to analyze the feature frequencies. By determining the peaks in the frequency spectrum and their corresponding amplitudes, the feature frequency and amplitude information of the signal can be further extracted. These frequency domain feature data can be used for subsequent data analysis, model establishment, and applications.

[0103] The entire process can ensure the specific implementation of the spectral analysis and feature frequency extraction scheme based on the enhanced formation reflection data.

[0104] Please refer to Figure 4 , based on the frequency domain feature data, use the elliptic curve encryption algorithm to perform secure data encapsulation and prepare for transmission. The specific steps for generating the encrypted monitoring data to be sent are as follows:

[0105] S301: Based on the frequency domain feature data, use the elliptic curve encryption algorithm to encrypt the data and generate the ECC-encrypted monitoring data;

[0106] S302: Based on the ECC-encrypted monitoring data, construct a data encapsulation protocol, encapsulate the data information, and generate the encapsulated monitoring data packet;

[0107] S303: Based on the encapsulated monitoring data packet, perform integrity verification, use the MD5 algorithm to generate a data hash value, append it to the end of the data packet, and generate the monitoring data packet with verification appended;

[0108] S304: Connect to the background server through the TLS transmission protocol based on the monitored data with attached verification, and generate the encrypted monitored data to be sent.

[0109] First, in S301, according to the characteristics and requirements of the frequency-domain feature data, select a suitable elliptic curve encryption algorithm for data encryption. The elliptic curve encryption algorithm (ECC) is an asymmetric encryption algorithm with high security and efficiency. Input the frequency-domain feature data as the plaintext into the ECC encryption algorithm to generate the monitored data encrypted by ECC.

[0110] Next, in S302, based on the monitored data encrypted by ECC, construct a data encapsulation protocol. The data encapsulation protocol is used to encapsulate the monitored data information to protect the confidentiality and integrity of the data. In the data encapsulation protocol, information such as data type, length, and encryption algorithm identifier can be included. Through the encapsulation protocol, the encapsulated monitored data packet is generated.

[0111] Then, in S303, perform integrity verification on the encapsulated monitored data packet. Use the MD5 algorithm to perform a hash calculation on the monitored data packet to generate a data hash value. Append the data hash value to the end of the monitored data packet to generate the monitored data packet with attached verification. Integrity verification can ensure that the data has not been tampered with or damaged during transmission.

[0112] Finally, in S304, connect to the background server through the TLS transmission protocol to generate the encrypted monitored data to be sent. TLS is a secure transmission protocol used to provide reliable data transmission and communication in the network. Using TLS to connect to the background server can ensure the confidentiality, integrity, and reliability of the monitored data.

[0113] The entire process can ensure the specific implementation of the generation and transmission scheme of the encrypted monitored data based on the frequency-domain feature data.

[0114] Please refer to Figure 5 , for the steps of sending the encrypted monitored data to be sent to the background server, where the server uses the RSA asymmetric encryption algorithm to decrypt the data and perform data verification to generate the decrypted monitored data, which are as follows:

[0115] S401: Based on the encrypted monitored data to be sent, send it to the background server through the TLS transmission protocol to establish a secure communication channel;

[0116] S402: Based on the secure communication channel, send the encrypted monitored data to the background server to generate the encrypted data after transmission;

[0117] S403: Based on the encrypted data after transmission, use the RSA asymmetric encryption algorithm to decrypt the data to generate the decrypted data on the server side;

[0118] S404: Decrypt the data based on the server side, perform integrity and consistency verification, and generate the decrypted monitoring data.

[0119] First in S401, establish a secure communication channel with the background server through the TLS transmission protocol. TLS can provide encryption and authentication functions to ensure the security and integrity of data during transmission.

[0120] Then in S402, send the encrypted monitoring data to be sent to the background server. Use a network communication protocol (such as TCP / IP) for data transmission to ensure that the monitoring data can reach the destination accurately.

[0121] Next in S403, use the RSA asymmetric encryption algorithm to decrypt the transmitted encrypted data on the background server side. RSA is a commonly used asymmetric encryption algorithm with characteristics such as high security and convenient key management. Decrypt the transmitted encrypted data with the private key to generate the server-side decrypted data.

[0122] Finally in S404, perform integrity and consistency verification on the server-side decrypted data. Use a hash algorithm (such as MD5 or SHA-256) to calculate the hash of the decrypted data and compare it with the pre-generated hash value. If the hash values match, it means the data is complete and has not been tampered with; if they do not match, there may be a situation of data corruption or tampering. According to the verification result, generate the decrypted monitoring data.

[0123] The entire process can ensure the specific implementation of the decryption and verification scheme based on the encrypted monitoring data to be sent.

[0124] Please refer to Figure 6 , based on the decrypted monitoring data, adopt the neural network pattern recognition algorithm to perform abnormal pattern analysis and risk assessment, and the steps to generate the stability analysis report are specifically as follows:

[0125] S501: Based on the decrypted monitoring data, perform data normalization processing to generate the preprocessed monitoring data;

[0126] S502: Based on the preprocessed monitoring data, perform learning and training through the neural network pattern recognition algorithm to generate the trained neural network model;

[0127] S503: Based on the trained neural network model, perform real-time abnormal pattern analysis, identify potential monitoring risks, and generate the identified abnormal pattern data;

[0128] S504: Based on the identified abnormal pattern data, perform risk assessment, determine the risk level, and generate the stability analysis report.

[0129] First, in S501, the decrypted monitoring data is subjected to data normalization. Data normalization is to scale the data to a specific range according to certain rules to eliminate the differences between different data. Methods such as standardization and normalization are used to process the monitoring data to generate preprocessed monitoring data.

[0130] Next, in S502, the neural network pattern recognition algorithm is used to learn and train the preprocessed monitoring data. The neural network pattern recognition algorithm is a pattern classification method based on artificial neural networks and can be used to identify and classify complex non-linear relationships. By using the preprocessed monitoring data as input, the neural network is trained and learned to generate a trained neural network model.

[0131] Then, in S503, the trained neural network model is used for real-time abnormal pattern analysis. The real-time monitoring data is input into the neural network model for pattern recognition and classification to identify potential abnormal patterns. According to the recognition results, the recognized abnormal pattern data is generated.

[0132] Finally, in S504, a risk assessment is performed based on the recognized abnormal pattern data to determine the risk level and generate a stability analysis report. According to the severity and frequency of the abnormal pattern data, the stability and potential risks of the system are evaluated. According to the evaluation results, the corresponding stability analysis report is generated.

[0133] The entire process can ensure the specific implementation of the abnormal pattern analysis and risk assessment scheme based on the decrypted monitoring data.

[0134] Please refer to Figure 7 , based on the stability analysis report, when risk characteristics are identified, the multi-level warning algorithm is adopted to classify the risk level and issue a warning signal. The specific steps are as follows:

[0135] S601: Based on the stability analysis report, analyze the risk level in the analysis report to decide whether to enter the warning process and generate a risk level judgment result;

[0136] S602: Based on the risk level judgment result, adopt the multi-level warning algorithm to classify the urgency and severity of the warning signal according to the risk level and generate a risk level classification result;

[0137] S603: Based on the risk level classification result, determine the warning signal, prepare the warning notice content and dissemination method, and generate a prepared warning signal;

[0138] S604: Based on the prepared warning signal, issue the warning signal through the preset dissemination channels.

[0139] First, in S601, based on the risk level in the stability analysis report, a risk level judgment is made. According to the high or low risk level, it is decided whether to enter the early warning process. If the risk level is high, enter the early warning process; if the risk level is low, there is no need to issue an early warning signal, and a risk level judgment result is generated.

[0140] Next, in S602, a multi-level early warning algorithm is used to classify the early warning signals. According to different risk levels, the early warning signals are divided into different levels of urgency and severity. For example, the early warning signals can be divided into different levels such as first-level early warning, second-level early warning, and third-level early warning, and a risk level classification result is generated.

[0141] Then, in S603, according to the risk level classification result, specific early warning signals are determined, and the corresponding early warning notice content and dissemination methods are prepared. The early warning notice content should include information such as risk description, possible impacts, and recommended countermeasures. The dissemination methods can be selected from SMS, email, phone calls, etc., to ensure that the early warning information can be conveyed to relevant personnel in a timely and accurate manner. A prepared early warning signal is generated.

[0142] Finally, in S604, the early warning signal is sent through a preset dissemination channel. According to the early warning notice content and dissemination method, the early warning signal is sent to relevant personnel or departments. Existing communication tools or systems are used to send the early warning signal to ensure that the early warning information can reach the target personnel in a timely manner.

[0143] The entire process can ensure the specific implementation of the multi-level early warning plan based on the stability analysis report.

[0144] Please refer to Figure 8 , a deep foundation pit monitoring data acquisition system, which includes an acoustic sensor array module, a data processing module, a signal transformation and analysis module, an encryption and transmission module, a neural network model module, a risk assessment module, and an early warning signal module.

[0145] The acoustic sensor array module is based on a ground penetrating radar device, deploys an acoustic sensor array, receives the acoustic signals reflected from the formation, and generates the original formation acoustic reflection data;

[0146] The data processing module is based on the original formation acoustic reflection data, uses digital signal processing and filtering algorithms to enhance the signal, and generates enhanced formation reflection data;

[0147] The signal transformation and analysis module is based on the enhanced formation reflection data, applies window function processing and fast Fourier transform, extracts the characteristic frequency, and generates frequency domain characteristic data;

[0148] The encryption and transmission module encrypts the data using the elliptic curve encryption algorithm based on the frequency domain feature data and sends it to the background server via the TLS protocol to generate the encrypted monitoring data to be sent.

[0149] The neural network model module performs data learning and abnormal pattern recognition through the neural network model based on the decrypted monitoring data to generate the recognized abnormal pattern data.

[0150] The risk assessment module conducts risk assessment to determine the risk level based on the recognized abnormal pattern data and generates a stability analysis report.

[0151] The warning signal module divides the risk level and issues warning signals using the multi-level warning algorithm based on the stability analysis report to generate the issued warning signals.

[0152] This deep foundation pit monitoring data acquisition system has beneficial effects such as improving data accuracy, extracting key features, securely transmitting data, identifying abnormal patterns, and risk assessment and warning. The acoustic wave sensing array module receives the acoustic wave signals reflected from the formation to generate the original formation acoustic wave reflection data, and then the data processing module uses digital signal processing and filtering algorithms for signal enhancement to generate the enhanced formation reflection data. The signal transformation and analysis module applies window function processing and fast Fourier transform to extract the key characteristic frequencies from the enhanced formation reflection data to generate the frequency domain feature data. The encryption and transmission module encrypts the frequency domain feature data using the elliptic curve encryption algorithm and sends it to the background server via the TLS protocol to generate the encrypted monitoring data to be sent. The neural network model module performs data learning and abnormal pattern recognition through the neural network model based on the decrypted monitoring data to generate the recognized abnormal pattern data. The risk assessment module conducts risk assessment to determine the risk level based on the recognized abnormal pattern data and generates a stability analysis report. The warning signal module divides the risk level and issues warning signals using the multi-level warning algorithm to generate the issued warning signals. The system can effectively monitor the stability of the deep foundation pit, timely detect potential risks, and provide corresponding warning signals, thus ensuring the safe and stable operation of the project.

[0153] Please refer to Figure 9 , the acoustic wave sensing array module includes an acoustic wave transmitting sub-module, an acoustic wave receiving sub-module, and a data generation sub-module;

[0154] The data processing module includes a signal processing sub-module, a filtering sub-module, and a signal enhancement sub-module;

[0155] The signal transformation and analysis module includes a window function processing sub-module, a signal transformation sub-module, and a spectrum analysis sub-module;

[0156] The encryption and transmission module includes a data encryption sub-module, a data encapsulation sub-module, and a data sending sub-module;

[0157] The neural network model module includes a data preprocessing sub-module, a model training sub-module, and an abnormal pattern recognition sub-module;

[0158] The risk assessment module includes a risk identification sub-module, a risk assessment sub-module, and a report generation sub-module;

[0159] The early warning signal module includes a risk level judgment sub-module, a risk level classification sub-module, and an early warning signal generation sub-module.

[0160] In the acoustic wave sensing array module, the acoustic wave transmitting sub-module emits acoustic wave signals to the formation through a ground penetrating radar device, the acoustic wave receiving sub-module receives the acoustic wave signals reflected by the formation, and the data generation sub-module converts the received acoustic wave signals into raw formation acoustic wave reflection data.

[0161] In the data processing module, the signal processing sub-module preprocesses the raw formation acoustic wave reflection data, the filtering sub-module filters the signal using digital signal processing and filtering algorithms, and the signal enhancement sub-module enhances the filtered signal through an enhancement algorithm to generate enhanced formation reflection data.

[0162] In the signal transformation and analysis module, the window function processing sub-module processes the enhanced formation reflection data using a window function, the signal transformation sub-module converts the time-domain signal into a frequency-domain signal using the fast Fourier transform, and the spectrum analysis sub-module extracts the characteristic frequency to generate frequency-domain characteristic data.

[0163] In the encryption and transmission module, the data encryption sub-module encrypts the frequency-domain characteristic data using the elliptic curve encryption algorithm, the data encapsulation sub-module encapsulates the encrypted data, and the data sending sub-module sends the encapsulated data to the background server through the TLS protocol to generate the encrypted monitoring data to be sent.

[0164] In the neural network model module, the data preprocessing sub-module preprocesses the decrypted monitoring data, the model training sub-module uses the neural network model for data learning, and the abnormal pattern recognition sub-module identifies abnormal patterns through the neural network model to generate the identified abnormal pattern data.

[0165] In the risk assessment module, the risk identification sub-module identifies risks based on the identified abnormal pattern data, the risk assessment sub-module assesses the risks to determine the risk level, and the report generation sub-module generates a stability analysis report.

[0166] In the warning signal module, the risk level judgment sub-module judges the risk level according to the stability analysis report, the risk level classification sub-module classifies and divides the risk level, and the warning signal generation sub-module generates the warning signal to be sent according to the risk level classification.

[0167] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A method for collecting deep foundation pit monitoring data, characterized in that, It includes the following steps: Based on ground penetrating radar and acoustic sensors, using a signal acquisition algorithm, collect formation reflection data, and perform preliminary data filtering to generate enhanced formation reflection data; Based on the enhanced formation reflection data, using the fast Fourier transform algorithm, perform signal spectrum analysis and extract characteristic frequencies to generate frequency domain characteristic data; Based on the frequency domain characteristic data, using the elliptic curve encryption algorithm, perform secure data encapsulation and prepare for transmission to generate encrypted monitoring data to be sent; Based on the encrypted monitoring data to be sent, send it to the background server. The background server uses the RSA asymmetric encryption algorithm to decrypt the data and perform data verification to generate decrypted monitoring data; Based on the decrypted monitoring data, using the neural network pattern recognition algorithm, perform abnormal pattern analysis and risk assessment to generate a stability analysis report; Based on the stability analysis report, when risk characteristics are identified, use a multi-level early warning algorithm to classify the risk level and send out an early warning signal; The formation reflection data is specifically the acoustic reflection intensity information at the junction of underground multi-media. The frequency domain characteristic data is specifically signal characteristics such as frequency distribution and amplitude size. The encrypted monitoring data to be sent is specifically a data packet encrypted by the ECC algorithm. The decrypted monitoring data is specifically the original monitoring data. The stability analysis report is specifically the key monitoring indicators generated by combining the potential landslide area, formation subsidence speed, and expected change trend. The early warning signal is specifically graded early warning information; The step of collecting formation reflection data based on ground penetrating radar and acoustic sensors, using a signal acquisition algorithm, and performing preliminary data filtering to generate formation reflection data is specifically as follows: Based on the ground penetrating radar equipment, deploy an acoustic sensor array, emit acoustic waves to the specified monitoring area, and receive the acoustic wave signals reflected by the formation to generate original formation acoustic reflection data; Based on the original formation acoustic reflection data, use a digital signal processing algorithm to perform data synchronization and time marking to generate time sequence calibrated formation acoustic reflection data; Based on the time sequence calibrated formation acoustic reflection data, use a high-pass filter to filter out low-frequency noise and retain the high-frequency components of the formation reflection signal to generate high-frequency formation reflection signal data; Based on the high-frequency formation reflection signal data, apply a signal enhancement algorithm of adaptive filtering to improve the signal-to-noise ratio and strengthen the formation reflection signal to generate enhanced formation reflection data; The step of performing signal spectrum analysis and extracting characteristic frequencies based on the enhanced formation reflection data, using the fast Fourier transform algorithm, to generate frequency domain characteristic data is specifically as follows: Based on the enhanced formation reflection data, use the window function processing technique to segment the signal for local analysis to generate formation reflection data after window function processing; Based on the formation reflection data after window function processing, apply the fast Fourier transform algorithm to convert the time domain signal into a frequency domain signal, perform signal spectrum analysis, and generate formation reflection spectrum data; Based on the formation reflection spectrum data, spectrum analysis technology is used to separate and identify the main frequency components, extract the characteristic frequencies, and generate characteristic frequency analysis data; Based on the characteristic frequency analysis data, the peak detection algorithm is used to determine the characteristic frequencies and amplitudes in the spectrum, and generate frequency domain characteristic data; Based on the decrypted monitoring data, the neural network pattern recognition algorithm is used to perform abnormal pattern analysis and risk assessment, and generate a stability analysis report. The specific steps are as follows: Based on the decrypted monitoring data, data normalization processing is performed to generate preprocessed monitoring data; Based on the preprocessed monitoring data, learning and training are carried out through the neural network pattern recognition algorithm to generate a trained neural network model; Based on the trained neural network model, real-time abnormal pattern analysis is performed to identify potential monitoring risks and generate identified abnormal pattern data; Based on the identified abnormal pattern data, risk assessment is carried out to determine the risk level and generate a stability analysis report.

2. The deep foundation pit monitoring data acquisition method according to claim 1, characterized in that Based on the frequency domain characteristic data, the elliptic curve encryption algorithm is used to perform secure data encapsulation and transmission preparation, and generate encrypted monitoring data to be sent. The specific steps are as follows: Based on the frequency domain characteristic data, the elliptic curve encryption algorithm is used to encrypt the data to generate ECC-encrypted monitoring data; Based on the ECC-encrypted monitoring data, a data encapsulation protocol is constructed to encapsulate the data information and generate an encapsulated monitoring data packet; Based on the encapsulated monitoring data packet, integrity verification is performed, and the MD5 algorithm is used to generate a data hash value, which is appended to the end of the data packet to generate a verified and appended monitoring data packet; Based on the verified and appended monitoring data packet, the background server is connected through the TLS transmission protocol to generate encrypted monitoring data to be sent.

3. The deep foundation pit monitoring data acquisition method according to claim 1, characterized in that, Based on the encrypted monitoring data to be sent, it is sent to the background server. The server uses the RSA asymmetric encryption algorithm to decrypt the data and perform data verification, and generate decrypted monitoring data. The specific steps are as follows: Based on the encrypted monitoring data to be sent, it is sent to the background server through the TLS transmission protocol to establish a secure communication channel; Based on the secure communication channel, the encrypted monitoring data is sent to the background server to generate transmitted encrypted data; Based on the transmitted encrypted data, the RSA asymmetric encryption algorithm is used to decrypt the data to generate server-side decrypted data; Based on the server-side decrypted data, integrity and consistency verification are performed to generate decrypted monitoring data.

4. The deep foundation pit monitoring data acquisition method according to claim 1, characterized in that Based on the stability analysis report, when risk characteristics are identified, a multi-level early warning algorithm is used to classify the risk level and issue an early warning signal. The specific steps are as follows: Based on the stability analysis report, the risk level in the analysis report is analyzed to determine whether to enter the early warning process and generate a risk level judgment result; Based on the risk level judgment result, a multi-level early warning algorithm is used to classify the urgency and severity of the early warning signal according to the risk level, and generate a risk level classification result; Based on the risk level classification result, determine the warning signal, prepare the content and dissemination method of the warning notice, and generate the prepared warning signal; Based on the prepared warning signal, send out the warning signal through the preset dissemination channels.

5. A deep foundation pit monitoring data acquisition system, characterized in that, According to the deep foundation pit monitoring data acquisition method described in any one of claims 1-4, the system includes an acoustic wave sensing array module, a data processing module, a signal transformation and analysis module, an encryption and transmission module, a neural network model module, a risk assessment module, and a warning signal module.

6. The deep foundation pit monitoring data acquisition system according to claim 5, wherein, The acoustic wave sensing array module is based on a ground penetrating radar device, deploys an acoustic wave sensor array, receives the acoustic wave signals reflected by the formation, and generates the original formation acoustic wave reflection data; The data processing module is based on the original formation acoustic wave reflection data, and uses digital signal processing and filtering algorithms to enhance the signal, generating enhanced formation reflection data; The signal transformation and analysis module is based on the enhanced formation reflection data, applies window function processing and fast Fourier transform to extract the characteristic frequencies, and generates frequency domain characteristic data; The encryption and transmission module is based on the frequency domain characteristic data, uses the elliptic curve encryption algorithm to encrypt the data, and sends it to the background server through the TLS protocol, generating the encrypted monitoring data to be sent; The neural network model module is based on the decrypted monitoring data, conducts data learning and identification of abnormal patterns through the neural network model, and generates the identified abnormal pattern data; The risk assessment module is based on the identified abnormal pattern data, conducts risk assessment to determine the risk level, and generates a stability analysis report; The warning signal module is based on the stability analysis report, uses a multi-level warning algorithm to classify the risk level and send out the warning signal, generating the sent warning signal.

7. The deep foundation pit monitoring data acquisition system according to claim 6, wherein The acoustic wave sensing array module includes an acoustic wave transmitting sub-module, an acoustic wave receiving sub-module, and a data generating sub-module; The data processing module includes a signal processing sub-module, a filtering sub-module, and a signal enhancement sub-module; The signal transformation and analysis module includes a window function processing sub-module, a signal transformation sub-module, and a spectrum analysis sub-module; The encryption and transmission module includes a data encryption sub-module, a data encapsulation sub-module, and a data sending sub-module; The neural network model module includes a data preprocessing sub-module, a model training sub-module, and an abnormal pattern identification sub-module; The risk assessment module includes a risk identification sub-module, a risk assessment sub-module, and a report generation sub-module; The warning signal module includes a risk level judgment sub-module, a risk level classification sub-module, and a warning signal generation sub-module.

Images