Rock high slope and deep foundation pit safety on-line early warning and monitoring method

Abstract

The invention discloses a rock high slope and deep foundation pit safety online early warning monitoring method, and relates to the technical field of rock high slope and deep foundation pit safety monitoring, and the method comprises the steps: employing a plurality of sensors to collect the state data of a rock high slope and a deep foundation pit, and obtaining the preliminary monitoring data; denoising and calibrating the preliminary monitoring data by adopting a data preprocessing method to obtain high-quality monitoring data; comprehensively analyzing the high-quality monitoring data by adopting a big data analysis technology in combination with meteorological information and environmental parameters to obtain a state evaluation result of the side slope or the foundation pit; constructing a risk assessment model based on the high-quality monitoring data and an intelligent early warning algorithm, inputting a state assessment result into the risk assessment model, and outputting a risk assessment level; and processing the risk assessment levels by adopting a grading early warning mechanism, generating corresponding early warning signals according to different risk levels, and sending the early warning signals to a remote monitoring platform.

Description

Technical Field

[0001] The invention relates to the technical field of safety monitoring of high rock slopes and deep foundation pits, in particular to an online early warning monitoring method for the safety of high rock slopes and deep foundation pits. Background Art

[0002] Safety monitoring technology for high rock slopes and deep foundation pits refers to a series of technical means that continuously monitor the physical state of slopes and foundation pits, as well as external environmental conditions, to assess their stability and predict potential risks. Therefore, how to utilize advanced technologies to improve the intelligence and safety of safety monitoring for high rock slopes and deep foundation pits has become a pressing issue.

[0003] In the field of safety monitoring of high rock slopes and deep foundation pits, the original monitoring data usually contains noise or measurement errors, which affects the accuracy of subsequent analysis. In addition, most existing monitoring methods fail to fully combine meteorological information and environmental parameters composed of temperature, humidity, rainfall, wind speed and air pressure for comprehensive analysis, making it difficult to comprehensively assess the changes in the status of slopes or foundation pits. When high-risk situations occur, existing methods cannot promptly notify relevant personnel and take effective measures. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an online early warning monitoring method for the safety of high rock slopes and deep foundation pits to solve the problem that the original monitoring data usually contains noise or measurement errors, which affects the accuracy of subsequent analysis, and most existing monitoring methods fail to fully combine meteorological information and environmental parameters composed of temperature, humidity, rainfall, wind speed and air pressure for comprehensive analysis, making it difficult to comprehensively evaluate the changes in the status of slopes or foundation pits.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides an online early warning monitoring method for high rock slopes and deep foundation pits, comprising: A variety of sensors are used to collect status data of high rock slopes and deep foundation pits to obtain preliminary monitoring data; The preliminary monitoring data is preprocessed using an adaptive filtering algorithm based on deep learning to obtain high-quality monitoring data; Combining meteorological information and environmental parameters, big data analysis technology is used to comprehensively analyze high-quality monitoring data to obtain the status assessment results of the slope or foundation pit; Build a risk assessment model based on high-quality monitoring data and intelligent early warning algorithms, input status assessment results into the risk assessment model, and output the risk assessment level; A hierarchical early warning mechanism is used to process risk assessment levels, generate corresponding early warning signals according to different risk levels, and send them to the remote monitoring platform; Adopt remote real-time monitoring methods to respond immediately to received warning signals, allowing technicians to access monitoring data and warning information through the Internet and take corresponding measures; Perform regular checks on the monitoring platform and update the software version to fix vulnerabilities or add new features.

[0008] As a preferred solution of the online early warning monitoring method for the safety of high rock slopes and deep foundation pits of the present invention, wherein: the state data of high rock slopes and deep foundation pits are collected using multiple sensors to obtain preliminary monitoring data, and the specific steps are as follows: Use displacement sensors to continuously monitor key locations of high rock slopes and deep foundation pits to obtain displacement changes; Use stress sensors to measure the stress state of high rock slopes and deep foundation pits to obtain stress values; Use groundwater level sensors to detect groundwater levels in high rock slopes and deep foundation pits to obtain groundwater level heights; The weighted average method is used to integrate the displacement change, stress value and groundwater level to obtain the comprehensive monitoring index , the expression is: ; in, Represents the data measured by the displacement sensor, Represents the data measured by the stress sensor, Represents the data measured by the groundwater level sensor; Meteorological information is obtained from environmental meteorological stations, and displacement changes, stress values, groundwater level height and meteorological information are integrated to form preliminary monitoring data.

[0009] As a preferred solution of the online early warning monitoring method for high rock slopes and deep foundation pits described in the present invention, the method of using an adaptive filtering algorithm based on deep learning to preprocess preliminary monitoring data to obtain high-quality monitoring data is specifically carried out as follows: Adopting an adaptive filtering algorithm based on deep learning to remove noise from preliminary monitoring data; The deep learning-based adaptive filtering algorithm includes building a dual-channel filtering network, where channel one uses an improved wavelet threshold denoising algorithm to process high-frequency noise, and channel two uses a GRU neural network to predict sensor drift errors; Application results of dual-channel output filtering algorithm fused by attention mechanism , the expression is: ; in, is the wavelet filtering result, is the GRU output, , is the trainable weight matrix, is the bias term, is the Sigmoid activation function; The filtered data were calibrated using a standardization method; Construct a linear regression model based on known standard values and actual measured values, and correct the existing errors to obtain the final high-quality monitoring data , the expression is: ; in, represents the result of applying the filtering algorithm, Represents the result of normalization processing, represents the modified result of the linear regression model, It is a correction factor derived from historical data and used to adjust the final high-quality monitoring data , It is the preliminary monitoring data, which contains the original sensor data of displacement, stress and groundwater level.

[0010] As a preferred embodiment of the online early warning monitoring method for high rock slopes and deep foundation pits of the present invention, the method combines meteorological information and environmental parameters, uses big data analysis technology to comprehensively analyze high-quality monitoring data, and obtains the status assessment results of the slope or foundation pit. The specific steps are as follows: Use time series analysis methods to process high-quality monitoring data and identify potential abnormal patterns by analyzing the changing trends of data over time; A prediction model is constructed by combining a machine learning algorithm with environmental parameters consisting of temperature, humidity, and rainfall. The model is trained to identify key factors affecting the stability of slopes or foundation pits and predict possible future state changes. The expression is: ; in, represents the application results of time series analysis, Including temperature ,humidity and rainfall , , , , , It is a model parameter trained based on historical data and is used to adjust the output of the prediction model. , It is a machine learning algorithm used to build predictive models; The prediction results were analyzed using cluster analysis method. Classification, by grouping similar prediction results together to identify areas with different risk levels; Summarize all analysis results to form the condition assessment results of the slope or foundation pit.

[0011] As a preferred solution of the online early warning monitoring method for high rock slopes and deep foundation pits described in the present invention, the risk assessment model is constructed based on high-quality monitoring data and an intelligent early warning algorithm, the status assessment results are input into the risk assessment model, and the risk assessment level is output. The specific steps are as follows: Use historical data analysis methods to analyze existing slope or foundation pit status data, and use statistical methods to determine the basic parameters of the risk assessment model; The risk assessment model is established using fuzzy logic method, which describes the risk level under different states by defining fuzzy sets and rule bases, and inputs the state assessment results. In the risk assessment model, the corresponding risk score is calculated, and the expression is: ; in, Indicates the The membership function of a fuzzy set is is the weight coefficient of the corresponding fuzzy set, is the number of fuzzy sets, It is a filtering algorithm function used to remove data noise; The risk score is divided into Convert to risk assessment level , by setting different threshold intervals to distinguish different risk levels, the expression is: ; in, represents the risk score, is the threshold partitioning function.

[0012] As a preferred solution of the online early warning monitoring method for high rock slopes and deep foundation pits described in the present invention, the risk assessment level is processed using a graded early warning mechanism, corresponding early warning signals are generated according to different risk levels, and sent to a remote monitoring platform. The specific steps are as follows: A hierarchical warning algorithm is used to classify risk assessment levels. By setting different threshold intervals, the risk assessment results are divided into three levels: low, medium, and high. The expression is: ; in, Based on risk assessment level The determined warning signal colors correspond to different risk levels: green for low risk, yellow for medium risk, and red for high risk. It is a hierarchical early warning algorithm used to convert risk assessment levels into early warning signals; Use color coding to map risk levels to specific warning signals, and improve the readability and intuitiveness of warning information by defining the corresponding relationship between colors and risk levels; Use communication protocol to send warning signals Send to the remote monitoring platform, and ensure data security through encrypted transmission. The expression is: ; in, Represents the transmission result, It is a communication protocol function used to encrypt and transmit warning signals; A remote monitoring platform is used to display and record received warning signals, and a visual interface and database storage function are used to ensure that managers can view warning information and historical records.

[0013] As a preferred solution of the online early warning monitoring method for high rock slopes and deep foundation pits described in the present invention, the remote real-time monitoring method is used to immediately respond to received early warning signals, allowing technicians to access monitoring data and early warning information via the Internet and take corresponding measures. The specific steps are as follows: Use cloud servers to store all monitoring data and early warning information; An authentication mechanism is used to protect sensitive information from being accessed by unauthorized users using usernames and passwords. The expression is: ; in, It is the result of authentication based on the user name and password. If the authentication succeeds, access is allowed; if the authentication fails, access is denied. It is an authentication function used for user access control; Use a visual interface to display monitoring data and early warning information, and present it to technical personnel in the form of charts and maps; A response measure recommendation system based on machine learning algorithms is used to propose response measures. Based on historical data and current conditions, the response strategy that best suits the current situation is recommended through machine learning algorithms. The expression is: ; in, Based on update time and risk assessment levels The recommended measures obtained are functions Used to generate specific countermeasure recommendations.

[0014] As a preferred solution of the online early warning monitoring method for high rock slopes and deep foundation pits of the present invention, the monitoring platform is regularly inspected and the software version is updated to fix vulnerabilities or add new functions. The specific steps are as follows: Use automated detection tools to conduct a comprehensive inspection of the monitoring platform, automatically scanning for potential problems in the platform; The potential issues include software vulnerabilities, hardware failures, and configuration errors; Use log analysis technology to identify abnormal behaviors and potential threats. Through in-depth analysis of platform log files, discover existing security threats or performance bottlenecks. Use the patch management platform to repair known vulnerabilities and patch existing security risks by downloading and applying the latest security patches. The expression is: ; in, is scored based on abnormal behavior The determined repair strategies correspond to different repair levels: no update required, partial update, and full update. It is the preliminary monitoring data, which contains the original sensor data of displacement, stress and groundwater level.

[0015] In a second aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the online early warning monitoring method for safety of high rock slopes and deep foundation pits as described in the first aspect of the present invention is implemented.

[0016] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the online early warning monitoring method for safety of high rock slopes and deep foundation pits as described in the first aspect of the present invention.

[0017] The beneficial effects of the present invention are as follows: by using a data preprocessing method, the preliminary monitoring data is denoised and calibrated to obtain high-quality monitoring data, which realizes effective purification and standardization of the original monitoring data, improves the quality and consistency of the data, and ensures that the data used in subsequent analysis is more stable and reliable, thereby improving the accuracy and credibility of the overall risk assessment; by combining meteorological information and environmental parameters, the high-quality monitoring data is comprehensively analyzed using big data analysis technology to obtain the status assessment results of the slope or foundation pit, and realizes a comprehensive and integrated analysis of the status of the slope or foundation pit, taking into account the influence of various environmental factors, which not only improves the accuracy of the prediction, but also can identify potential risks in advance, and provides a basis for timely preventive measures; by outputting the risk assessment level, a quantitative assessment of the slope or foundation pit risk is realized, and it is divided into different risk levels, which not only makes the risk assessment more intuitive and easy to understand, but also provides a scientific basis for subsequent graded warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 This is a flow chart of the online early warning monitoring method for high rock slopes and deep foundation pits in Example 1. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0023] Example 1, with reference to Figure 1, which is the first embodiment of the present invention, provides an online early warning monitoring method for the safety of high rock slopes and deep foundation pits, comprising the following steps:

[0024] S1. Use multiple sensors to collect status data of high rock slopes and deep foundation pits to obtain preliminary monitoring data; Furthermore, displacement sensors are used to continuously monitor key locations of high rock slopes and deep foundation pits to obtain displacement changes; Use stress sensors to measure the stress state of high rock slopes and deep foundation pits to obtain stress values; Use groundwater level sensors to detect groundwater levels in high rock slopes and deep foundation pits to obtain groundwater level heights; The weighted average method is used to integrate the displacement change, stress value and groundwater level to obtain the comprehensive monitoring index , the expression is: ; in, Represents the data measured by the displacement sensor, Represents the data measured by the stress sensor, Represents the data measured by the groundwater level sensor; Obtain meteorological information from environmental meteorological stations and integrate displacement changes, stress values, groundwater level height and meteorological information to form preliminary monitoring data; It should be noted that by using multiple types of sensors to continuously monitor key locations of rock high-side pits and deep foundation pits, not only can comprehensive and accurate data be obtained, but also subtle changes can be captured under complex geological conditions. This method greatly improves the reliability and real-time nature of the data, providing a solid foundation for subsequent risk assessments.

[0025] S2. Preprocess the preliminary monitoring data using an adaptive filtering algorithm based on deep learning to obtain high-quality monitoring data; Furthermore, an adaptive filtering algorithm based on deep learning is used to remove noise from the preliminary monitoring data; The deep learning-based adaptive filtering algorithm involves building a dual-channel filtering network. Channel one uses an improved wavelet threshold denoising algorithm to process high-frequency noise, while channel two uses a GRU neural network to predict sensor drift errors. Application results of dual-channel output filtering algorithm fused by attention mechanism , the expression is: ; in, is the wavelet filtering result, is the GRU output, , is the trainable weight matrix, is the bias term, is the Sigmoid activation function; The filtered data were calibrated using a standardization method; Construct a linear regression model based on known standard values and actual measured values, and correct the existing errors to obtain the final high-quality monitoring data , the expression is: ; in, represents the result of applying the filtering algorithm, Represents the result of normalization processing, represents the modified result of the linear regression model, It is a correction factor derived from historical data and used to adjust the final high-quality monitoring data , The primary monitoring data include raw sensor data of displacement, stress and groundwater level; It should be noted that by filtering and standardizing the preliminary monitoring data and constructing a linear regression model based on historical data for error correction, noise can be effectively removed and the data can be calibrated to ensure data quality and consistency. The preprocessing step can not only improve the accuracy of the data, but also reduce the errors caused by sensor drift or environmental interference, thereby providing more reliable input for subsequent big data analysis.

[0026] S3. Combine meteorological information and environmental parameters, and use big data analysis technology to conduct a comprehensive analysis of high-quality monitoring data to obtain the status assessment results of the slope or foundation pit; Furthermore, time series analysis methods are used to process high-quality monitoring data, and potential abnormal patterns are identified by analyzing the changing trends of data over time; A prediction model is constructed by combining a machine learning algorithm with environmental parameters consisting of temperature, humidity, and rainfall. The model is trained to identify key factors affecting the stability of slopes or foundation pits and predict possible future state changes. The expression is: ; in, represents the application results of time series analysis, Including temperature ,humidity and rainfall , , , , , It is a model parameter trained based on historical data and is used to adjust the output of the prediction model. , It is a machine learning algorithm used to build predictive models; The prediction results were analyzed using cluster analysis method. Classification, by grouping similar prediction results together to identify areas with different risk levels; Summarize all analysis results to form the status assessment results of the slope or foundation pit; It should be noted that the use of time series analysis methods to identify potential abnormal patterns and the construction of a prediction model combining machine learning algorithms with meteorological information and environmental parameters consisting of temperature, humidity, rainfall, wind speed and air pressure can comprehensively consider the impact of various factors on the stability of slopes or foundation pits, classify the prediction results through cluster analysis, and further refine the risk assessment. This method not only improves the prediction accuracy, but also can detect potential risks in advance, providing a scientific basis for formulating effective preventive measures.

[0027] S4. Build a risk assessment model based on high-quality monitoring data and intelligent early warning algorithms, input the status assessment results into the risk assessment model, and output the risk assessment level; Furthermore, the historical data analysis method is used to analyze the existing slope or foundation pit status data, and the basic parameters of the risk assessment model are determined through statistical methods; The risk assessment model is established using fuzzy logic method, which describes the risk level under different states by defining fuzzy sets and rule bases, and inputs the state assessment results. In the risk assessment model, the corresponding risk score is calculated, and the expression is: ; in, Indicates the The membership function of a fuzzy set is is the weight coefficient of the corresponding fuzzy set, is the number of fuzzy sets, It is a filtering algorithm function used to remove data noise; The risk score is divided into Convert to risk assessment level , by setting different threshold intervals to distinguish different risk levels, the expression is: ; in, represents the risk score, is the threshold partition function; It should be noted that the basic parameters of the risk assessment model are determined through historical data analysis, and the risk assessment model is established using the fuzzy logic method. The risk score can be dynamically adjusted according to the actual measurement data, and the threshold division method is used to convert the risk score into a specific risk level, making the risk assessment results more intuitive and easy to understand. This method not only optimizes the early warning mechanism, but also significantly improves the speed and efficiency of emergency response, helps to take necessary protective measures in a timely manner, and minimizes disaster risks.

[0028] S5. Use a hierarchical early warning mechanism to process risk assessment levels, generate corresponding early warning signals according to different risk levels, and send them to the remote monitoring platform; Furthermore, a hierarchical warning algorithm is used to classify the risk assessment level. By setting different threshold intervals, the risk assessment results are divided into three levels: low, medium, and high. The expression is: ; in, Based on risk assessment level The determined warning signal colors correspond to different risk levels: green for low risk, yellow for medium risk, and red for high risk. It is a hierarchical early warning algorithm used to convert risk assessment levels into early warning signals; Use color coding to map risk levels to specific warning signals, and improve the readability and intuitiveness of warning information by defining the corresponding relationship between colors and risk levels; Use communication protocol to send warning signals Send to the remote monitoring platform, and ensure data security through encrypted transmission. The expression is: ; in, Represents the transmission result, It is a communication protocol function used to encrypt and transmit warning signals; A remote monitoring platform is used to display and record received warning signals, and a visual interface and database storage function are used to ensure that managers can view warning information and historical records; It should be noted that by adopting a hierarchical warning algorithm to classify risk assessment levels and setting different threshold intervals to divide the risk assessment results into three levels: low, medium, and high, not only the risk assessment results are made more intuitive and easy to understand, but also the color coding of the warning signal can be dynamically adjusted according to the actual situation. This method ensures that at different risk levels, relevant personnel can quickly identify and take corresponding measures, greatly improving the speed and efficiency of emergency response. In addition, the communication protocol is used to standardize the transmission of warning signals to the remote monitoring platform, ensuring the timeliness and accuracy of information transmission, and further enhancing the reliability and practicality of the method.

[0029] S6. Use remote real-time monitoring methods to respond immediately to received warning signals, allowing technicians to access monitoring data and warning information via the Internet and take corresponding measures; Furthermore, a cloud server is used to store all monitoring data and warning information; An authentication mechanism is used to protect sensitive information from being accessed by unauthorized users using usernames and passwords. The expression is: ; in, It is the result of authentication based on the user name and password. If the authentication succeeds, access is allowed; if the authentication fails, access is denied. It is an authentication function used for user access control; Use a visual interface to display monitoring data and early warning information, and present it to technical personnel in the form of charts and maps; A response measure recommendation system based on machine learning algorithms is used to propose response measures. Based on historical data and current conditions, the response strategy that best suits the current situation is recommended through machine learning algorithms. The expression is: ; in, Based on update time and risk assessment levels The recommended measures obtained are functions To generate specific response recommendations; It should be noted that by using cloud servers to store all monitoring data and early warning information, and combining cloud computing technology to ensure data security and accessibility, not only the convenience and security of data management are improved, but also the ability to access the latest data anytime and anywhere is provided to technicians. The authentication mechanism protects sensitive information through usernames and passwords to prevent unauthorized access, thereby ensuring the security of the method. The visual interface and the response recommendation system based on machine learning algorithms further enhance the user-friendliness of the method, helping technicians to quickly understand and process complex monitoring data, and propose the optimal response strategy based on historical data and current conditions, thereby significantly improving decision-making efficiency and emergency response capabilities.

[0030] S7. Regularly check the monitoring platform and update the software version to fix vulnerabilities or add new features; Furthermore, automated detection tools are used to conduct a comprehensive inspection of the monitoring platform by automatically scanning for potential problems in the platform; Potential issues include software vulnerabilities, hardware failures, and configuration errors; Use log analysis technology to identify abnormal behaviors and potential threats. Through in-depth analysis of platform log files, discover existing security threats or performance bottlenecks. Use the patch management platform to repair known vulnerabilities and patch existing security risks by downloading and applying the latest security patches. The expression is: ; in, is scored based on abnormal behavior The determined repair strategies correspond to different repair levels: no update required, partial update, and full update. The primary monitoring data includes raw sensor data of displacement, stress and groundwater level; Abnormal behavior score The calculation expression is: ; in, For the The frequency of occurrence of such abnormal events within the statistical period, For the The weight coefficient of abnormal events, For the The average duration of abnormal-like events, is the total duration of the statistical period, is the total number of system monitoring points, The index of abnormal event type; It should be noted that by using automated detection tools to conduct comprehensive inspections of the monitoring platform and utilizing log analysis technology to identify abnormal behaviors and potential threats, various problems in the method can be effectively discovered and resolved. The application of the patch management platform ensures that known vulnerabilities can be patched in a timely manner, and the stability and security of the system can be improved by downloading and applying the latest security patches. The regular maintenance and update mechanism not only ensures the long-term and efficient operation of the method, but also provides a solid foundation for continuous optimization and functional expansion, thereby extending the life cycle of the method and improving the user experience.

[0031] This embodiment also provides a computer device suitable for the case of an online early warning monitoring method for the safety of high rock slopes and deep foundation pits, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the online early warning monitoring method for the safety of high rock slopes and deep foundation pits proposed in the above embodiment.

[0032] The computer device may be a terminal, comprising a processor, memory, a communication interface, a display, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system and computer programs. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage media. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication. Wireless communication may be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. The display of the computer device may be a liquid crystal display or an electronic ink display. The input device may be a touchscreen overlay on the display, buttons, a trackball, or a touchpad on the computer device housing, or an external keyboard, touchpad, or mouse.

[0033] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the online early warning monitoring method for the safety of high rock slopes and deep foundation pits proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0034] In summary, the present invention denoises and calibrates the preliminary monitoring data through a data preprocessing method to obtain high-quality monitoring data, realizes effective purification and standardization of the original monitoring data, improves the quality and consistency of the data, ensures that the data used in subsequent analysis is more stable and reliable, thereby improving the accuracy and credibility of the overall risk assessment, and by combining meteorological information and environmental parameters, adopts big data analysis technology to conduct a comprehensive analysis of the high-quality monitoring data to obtain the status assessment results of the slope or foundation pit, and realizes a comprehensive and comprehensive analysis of the status of the slope or foundation pit, taking into account the influence of various environmental factors, not only improving the accuracy of the prediction, but also identifying potential risks in advance, providing a basis for timely preventive measures, and by outputting the risk assessment level, realizing a quantitative assessment of the slope or foundation pit risk, and dividing it into different risk levels, which not only makes the risk assessment more intuitive and easy to understand, but also provides a scientific basis for subsequent graded warnings.

[0035] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for online early warning monitoring of high rock slopes and deep foundation pits, characterized by: include: A variety of sensors are used to collect status data of high rock slopes and deep foundation pits to obtain preliminary monitoring data; Adopting deep learning-based adaptive filtering algorithm to pre-process the preliminary monitoring data and obtain high-quality monitoring data; Combining meteorological information and environmental parameters, big data analysis technology is used to comprehensively analyze high-quality monitoring data to obtain the status assessment results of the slope or foundation pit; Build a risk assessment model based on high-quality monitoring data and intelligent early warning algorithms, input status assessment results into the risk assessment model, and output the risk assessment level; A hierarchical early warning mechanism is used to process risk assessment levels, generate corresponding early warning signals according to different risk levels, and send them to the remote monitoring platform; Adopt remote real-time monitoring methods to respond immediately to received warning signals, allowing technicians to access monitoring data and warning information through the Internet and take corresponding measures; Perform regular checks on the monitoring platform and update the software version to fix vulnerabilities or add new features.

2. The online early warning monitoring method for high rock slopes and deep foundation pits according to claim 1 is characterized by: The method uses a variety of sensors to collect status data of high rock slopes and deep foundation pits to obtain preliminary monitoring data. The specific steps are as follows: Use displacement sensors to continuously monitor key locations of high rock slopes and deep foundation pits to obtain displacement changes; Use stress sensors to measure the stress state of high rock slopes and deep foundation pits to obtain stress values; Use groundwater level sensors to detect groundwater levels in high rock slopes and deep foundation pits to obtain groundwater level heights; The weighted average method is used to integrate the displacement change, stress value and groundwater level to obtain the comprehensive monitoring index , the expression is: ; in, Represents the data measured by the displacement sensor, Represents the data measured by the stress sensor, Represents the data measured by the groundwater level sensor; Meteorological information is obtained from environmental meteorological stations, and displacement changes, stress values, groundwater level height and meteorological information are integrated to form preliminary monitoring data.

3. The method for online early warning monitoring of high rock slopes and deep foundation pits according to claim 2, characterized in that: The adaptive filtering algorithm based on deep learning is used to preprocess the preliminary monitoring data to obtain high-quality monitoring data. The specific steps are as follows: Adopting an adaptive filtering algorithm based on deep learning to remove noise from preliminary monitoring data; The deep learning-based adaptive filtering algorithm includes building a dual-channel filtering network, where channel one uses an improved wavelet threshold denoising algorithm to process high-frequency noise, and channel two uses a GRU neural network to predict sensor drift errors; Application results of dual-channel output filtering algorithm fused by attention mechanism , the expression is: ； in, is the wavelet filtering result, is the GRU output, , is the trainable weight matrix, is the bias term, is the Sigmoid activation function; The filtered data were calibrated using a standardization method; Construct a linear regression model based on known standard values and actual measured values, and correct the existing errors to obtain the final high-quality monitoring data , the expression is: ； in, represents the result of applying the filtering algorithm, Represents the result of normalization processing, represents the modified result of the linear regression model, It is a correction factor derived from historical data and used to adjust the final high-quality monitoring data , It is the preliminary monitoring data, which contains the original sensor data of displacement, stress and groundwater level.

4. The online early warning monitoring method for high rock slopes and deep foundation pits according to claim 3 is characterized by: The method combines meteorological information and environmental parameters, uses big data analysis technology to conduct a comprehensive analysis of high-quality monitoring data, and obtains the status assessment results of the slope or foundation pit. The specific steps are: Use time series analysis methods to process high-quality monitoring data and identify potential abnormal patterns by analyzing the changing trends of data over time; A prediction model is constructed by combining a machine learning algorithm with environmental parameters consisting of temperature, humidity, and rainfall. The model is trained to identify key factors affecting the stability of slopes or foundation pits and predict possible future state changes. The expression is: ; in, represents the application results of time series analysis, Including temperature ,humidity and rainfall , , , , , It is a model parameter trained based on historical data and is used to adjust the output of the prediction model. , It is a machine learning algorithm used to build predictive models; The prediction results were analyzed using cluster analysis method. Classification, by grouping similar prediction results together to identify areas with different risk levels; Summarize all analysis results to form the condition assessment results of the slope or foundation pit.

5. The method for online early warning monitoring of high rock slopes and deep foundation pits according to claim 4, characterized in that: The risk assessment model is constructed based on high-quality monitoring data and intelligent early warning algorithms, the status assessment results are input into the risk assessment model, and the risk assessment level is output. The specific steps are as follows: Use historical data analysis to analyze existing slope or foundation pit status data, and use statistical methods to determine the basic parameters of the risk assessment model; The risk assessment model is established using fuzzy logic method, which describes the risk level under different states by defining fuzzy sets and rule bases, and inputs the state assessment results. In the risk assessment model, the corresponding risk score is calculated, and the expression is: ; in, Indicates the The membership function of a fuzzy set is is the weight coefficient of the corresponding fuzzy set, is the number of fuzzy sets, It is a filtering algorithm function used to remove data noise; The risk score is divided into Convert to risk assessment level , by setting different threshold intervals to distinguish different risk levels, the expression is: ； in, represents the risk score, is the threshold partitioning function.

6. The method for online early warning monitoring of high rock slopes and deep foundation pits according to claim 5, characterized in that: The hierarchical warning mechanism is used to process the risk assessment level, generate corresponding warning signals according to different risk levels, and send them to the remote monitoring platform. The specific steps are as follows: A hierarchical warning algorithm is used to classify risk assessment levels. By setting different threshold intervals, the risk assessment results are divided into three levels: low, medium, and high. The expression is: ； in, Based on risk assessment level The determined warning signal colors correspond to different risk levels: green for low risk, yellow for medium risk, and red for high risk. It is a hierarchical early warning algorithm used to convert risk assessment levels into early warning signals; Use color coding to map risk levels to specific warning signals, and improve the readability and intuitiveness of warning information by defining the corresponding relationship between colors and risk levels; Use communication protocol to send warning signals Send to the remote monitoring platform, and ensure data security through encrypted transmission. The expression is: ； in, Represents the transmission result, It is a communication protocol function used to encrypt and transmit warning signals; A remote monitoring platform is used to display and record received warning signals, and a visual interface and database storage function are used to ensure that managers can view warning information and historical records.

7. The online early warning monitoring method for high rock slopes and deep foundation pits according to claim 6, characterized in that: The remote real-time monitoring method is used to respond immediately to the received warning signals, so that technicians can access monitoring data and warning information through the Internet and take corresponding measures. The specific steps are as follows: Use cloud servers to store all monitoring data and early warning information; An authentication mechanism is used to protect sensitive information from being accessed by unauthorized users using usernames and passwords. The expression is: ； in, It is the result of authentication based on the user name and password. If the authentication succeeds, access is allowed; if the authentication fails, access is denied. It is an authentication function used for user access control; Use a visual interface to display monitoring data and early warning information, and present it to technical personnel in the form of charts and maps; A response measure recommendation system based on machine learning algorithms is used to propose response measures. Based on historical data and current conditions, the response strategy that best suits the current situation is recommended through machine learning algorithms. The expression is: ； in, Based on update time and risk assessment levels The recommended measures obtained are functions Used to generate specific countermeasure recommendations.

8. The method for online early warning monitoring of high rock slopes and deep foundation pits according to claim 7, characterized in that: The monitoring platform is regularly checked and the software version is updated to fix vulnerabilities or add new features. The specific steps are as follows: Use automated detection tools to conduct a comprehensive inspection of the monitoring platform, automatically scanning for potential problems in the platform; The potential issues include software vulnerabilities, hardware failures, and configuration errors; Use log analysis technology to identify abnormal behaviors and potential threats. Through in-depth analysis of platform log files, discover existing security threats or performance bottlenecks. Use the patch management platform to repair known vulnerabilities and patch existing security risks by downloading and applying the latest security patches. The expression is: ； in, is scored based on abnormal behavior The determined repair strategies correspond to different repair levels: no update required, partial update, and full update. It is the preliminary monitoring data, which contains the original sensor data of displacement, stress and groundwater level.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for online early warning monitoring of rocky high slopes and deep foundation pits described in any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for online early warning monitoring of rocky high slopes and deep foundation pits according to any one of claims 1 to 8 are implemented.

Images