Tunnel construction safety monitoring system based on the Internet of Things

Abstract

The present invention discloses a tunnel construction safety monitoring system based on the Internet of Things (IoT), belonging to the technical field of tunnel construction safety monitoring. The system includes a data acquisition module, a data processing and mapping module, an early warning information processing module, a data analysis and comparison module, and a real-time monitoring and notification module. The data acquisition module is responsible for acquiring tunnel construction monitoring data and monitoring point location data. The data processing and mapping module maps historical tunnel construction monitoring data with historical monitoring point location data to construct a historical data set. The early warning information processing module divides early warning information into false early warning information and true early warning information. The data analysis and comparison module performs further data analysis and comparison on false early warning information and true early warning information. The real-time monitoring and notification module acquires real-time tunnel construction monitoring data and real-time monitoring point location data, and notifies relevant personnel to process or adjust them.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel construction safety monitoring, and in particular to a tunnel construction safety monitoring system based on the Internet of Things. Background Art

[0002] With the rapid development of the Internet of Things (IoT), its application is becoming increasingly widespread across various fields, extending from its initial focus on computer networks and communications to encompass a wide range of sectors, including industry, home, healthcare, transportation, and agriculture. Tunnel construction safety monitoring is also benefiting from the continuous advancement of IoT technology. IoT technology plays a crucial role in this area, enabling personnel to gain real-time access to data from the tunnel construction process, effectively preventing accidents.

[0003] Although the existing tunnel construction safety monitoring system can meet current needs to a certain extent, it still has certain defects. Specifically, during the tunnel construction process, data monitoring points are usually determined in advance. However, when new risk points arise or monitoring points need to be adjusted during the actual construction process, the traditional tunnel construction safety monitoring system cannot respond flexibly. Relevant staff need to adjust the monitoring points, which often takes a lot of time and is prone to certain human errors. Summary of the Invention

[0004] The purpose of the present invention is to provide a tunnel construction safety monitoring system based on the Internet of Things to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] The tunnel construction safety monitoring system based on the Internet of Things includes: data acquisition module, data processing and mapping module, early warning information processing module, data analysis and comparison module, and real-time monitoring and notification module;

[0007] The data acquisition module is responsible for acquiring tunnel construction monitoring data and monitoring point location data; the data processing and mapping module performs a one-to-one mapping of historical tunnel construction monitoring data with historical monitoring point location data to construct a historical data set; the early warning information processing module divides the early warning information into false early warning information and true early warning information based on the subsequent processing results of the early warning information recorded in the historical tunnel construction safety log; the data analysis and comparison module conducts further data analysis and comparison on false early warning information and true early warning information, obtains the difference index between false early warning information and true early warning information of the same type, and obtains the monitoring point adjustment data of the false early warning information based on the difference index; the real-time monitoring and notification module obtains real-time tunnel construction monitoring data and real-time monitoring point location data, and calculates the similarity between the early warning category of the early warning information and the historical early warning information; based on the calculation results, the relevant personnel are notified to handle the situation or make adjustments based on the monitoring point adjustment data.

[0008] Furthermore, the data acquisition module includes a sensor and monitoring device unit and a data communication unit;

[0009] The sensor and monitoring equipment unit is responsible for collecting tunnel construction monitoring data and monitoring point location data; the data communication unit is responsible for transmitting the collected data to the data processing and mapping module. Tunnel construction monitoring data includes displacement and deformation data, hydrological and water quality data, temperature and humidity data, pressure data, vibration data, and environmental pollution data.

[0010] The data processing and mapping module includes a data cleaning unit, a data storage unit, and a mapping association unit;

[0011] The data cleaning unit preprocesses and cleans the collected raw data to remove interference factors such as outliers and noise to ensure the accuracy and consistency of the data; the data storage unit stores the cleaned data in the database for subsequent data analysis and query operations; the mapping association unit performs a one-to-one mapping of historical tunnel construction monitoring data with historical monitoring point location data to construct a historical data set.

[0012] Furthermore, the mapping association unit includes:

[0013] Historical tunnel construction monitoring data and historical monitoring point location data are obtained from the original tunnel construction safety monitoring system. The historical monitoring point location data are randomly numbered, and a one-to-one mapping is performed between the historical tunnel construction monitoring data and the historical monitoring point location data to form a historical data set A, where A = {a1, a2, ..., an}, where a1 represents the historical monitoring point location data numbered 1 and the corresponding historical tunnel construction monitoring data, a2 represents the historical monitoring point location data numbered 2 and the corresponding historical tunnel construction monitoring data, and so on. An represents the historical monitoring point location data numbered n and the corresponding historical tunnel construction monitoring data, and n represents the number of historical monitoring points.

[0014] Historical dataset A contains the correspondence between historical tunnel construction monitoring data and monitoring point location data, providing basic data for subsequent analysis and processing. By mapping historical tunnel construction monitoring data to monitoring point location data one-to-one, early warning information can be associated with the corresponding historical data, thereby better understanding and analyzing early warning information. Constructing historical dataset A can help determine the difference between false and true early warning information and provide corresponding comparison data and monitoring point adjustment data. These data can be used to assist staff in processing and adjusting early warning information, improving the efficiency and accuracy of responses to early warning information.

[0015] Furthermore, the warning information processing module includes a warning information classification unit and a historical data association unit;

[0016] The warning information classification unit includes: obtaining historical tunnel construction safety logs to obtain warning information from the original tunnel safety monitoring system; and classifying the warning information into false warning information and true warning information based on the subsequent processing results of the warning information recorded in the historical tunnel construction safety logs;

[0017] The historical data association unit includes: obtaining the time point when the warning information is issued, selecting the time period T as the time period for issuing the warning information according to the time point, and obtaining the corresponding warning occurrence area according to the warning information; obtaining the historical monitoring point location data of the warning occurrence area corresponding to the historical tunnel construction monitoring data of the time period T, and associating the warning information with the corresponding historical tunnel construction monitoring data.

[0018] By obtaining the time point when the warning information is issued and the corresponding warning area, the historical monitoring point location data and tunnel construction monitoring data related to the warning can be obtained. These data can provide background information to help better understand and analyze the cause and impact scope of the warning information; by associating the warning information with historical monitoring data, a more in-depth analysis can be carried out. By comparing with historical data, potential abnormal patterns or trends can be discovered, providing more clues for the interpretation of the warning information.

[0019] Furthermore, the data analysis and comparison module includes a monitoring point quantity comparison unit, a data analysis unit, and a monitoring point adjustment unit;

[0020] The monitoring point quantity comparison unit includes: further classifying the false warning information and the real warning information according to the warning category, wherein the warning category of the real warning information includes the warning category of the false warning information; obtaining the corresponding warning category for each false warning information, finding the real warning information of the same warning category according to the warning category, and comparing the number of historical monitoring points corresponding to the false warning information and the real warning information; wherein the number of real warning information of the same warning category is more than one;

[0021] The data analysis unit analyzes the comparison results of the monitoring point quantity comparison unit and calculates the difference index;

[0022] The monitoring point adjustment unit includes: arranging the calculated difference indexes in ascending order, extracting the historical monitoring point location data of the real warning information with the difference index accounting for the top a% as the control data, where a is a set percentage threshold; obtaining the monitoring point location data adjusted for the false warning information based on the historical tunnel construction safety log records as the template data; and calculating the matching degree P between the control data and the template data, and the calculation formula is:

[0023]

[0024] Among them, σ represents the adjustment parameter, G represents the difference index between the control data and the template data, and the value of the difference index is related to the number of monitoring points corresponding to the control data and the template data. When the number of monitoring points of the control data and the template data is not equal, the difference index is G1, and when the number of monitoring points of the control data and the template data is equal, the difference index is G2; the monitoring point adjustment data with the largest matching degree is selected as the monitoring point adjustment data, and the monitoring point adjustment data is associated with the corresponding false warning information.

[0025] Furthermore, the data analysis unit includes:

[0026] The number of monitoring points comparison unit is used to compare the number of false warning information and the corresponding number of historical data monitoring points; if the number of historical data monitoring points corresponding to the false warning information is not equal to the number of historical data monitoring points corresponding to the true warning information, it means that the main reason for the warning information being false warning information is that there are too many or too few historical data monitoring points, and the false information analyzed here excludes the influence of monitoring equipment failure; then the historical monitoring point location data of the false warning information and the true warning information are analyzed; based on the historical monitoring point location data of the false warning information and the true warning information, the historical monitoring point monitoring ranges of the false warning information and the true warning information are calculated respectively, expressed as S1 and S2 respectively; the difference index G1 of the historical monitoring point location data of the false warning information and the true warning information of the same warning category is calculated, and the specific calculation formula is:

[0027]

[0028] Among them, N1 represents the number of historical monitoring points in the warning area where false warning information occurs, N 2i It represents the number of historical monitoring points in the warning occurrence area of ​​the i-th real warning information of the same warning category as the false warning information, S2i represents the monitoring range of the historical monitoring points of the i-th real warning information of the same warning category as the false warning information, α and β represent different parameters, and m represents the number of real warning information of the same warning category as the false warning information.

[0029] Furthermore, the data analysis unit also includes:

[0030] If the number of historical data monitoring points corresponding to the false warning information is equal to the number of historical data monitoring points corresponding to the true warning information, it means that the historical monitoring point location and the historical tunnel construction monitoring data jointly caused the warning information to be false warning information. Similarly, the false warning information analyzed here excludes the influence of monitoring equipment failure; then the historical monitoring point location data and historical tunnel construction monitoring data of the false warning information and the true warning information are analyzed; based on the historical monitoring point location data of the false warning information and the true warning information, the distances between adjacent historical monitoring points of the false warning information and the true warning information are calculated, respectively, and expressed as L1 and L2; based on the historical tunnel construction monitoring data of the false warning information and the true warning information, a curve graph of the historical tunnel construction monitoring data changing with time in time period T is drawn, and expressed as Q1 and Q2 respectively; the difference index G2 between the historical monitoring point location data and the historical tunnel construction monitoring data of the false warning information and the true warning information of the same warning category is calculated, and the specific calculation formula is:

[0031]

[0032] Among them, γ and μ represent parameters, L 1jrepresents the distance between adjacent historical monitoring points of the jth false warning information, L 2j represents the distance between adjacent historical monitoring points of the jth real warning information, M represents the data number of the distance between adjacent historical monitoring points, S Q1 represents the area of ​​the coordinate axis surrounded by the curve Q1, S Q2 represents the area of ​​the coordinate axis surrounded by the curve Q2, S Q2_k It represents the area of ​​the coordinate axis surrounded by the k-th Q2 curve, and K represents the number of Q2 curves of true warning information of the same warning category as the false warning information.

[0033] Furthermore, the real-time monitoring and notification module includes:

[0034] Real-time tunnel construction monitoring data and real-time monitoring point location data are obtained. When the tunnel construction safety monitoring system issues an early warning message, the early warning category of the current early warning message is obtained and the similarity is calculated with the historical early warning message of the same early warning category. This helps to quickly and accurately judge the credibility and urgency of the current early warning message. If the one with the greatest similarity is a true early warning message in the historical early warning message, the relevant staff will be notified to carry out corresponding processing, so that timely action can be taken to ensure the safety of the construction site and avoid the occurrence or further deterioration of accidents. If the one with the greatest similarity is a false early warning message in the historical early warning message, the corresponding template data and monitoring point adjustment data are output to the relevant staff, who will make corresponding adjustments to the current monitoring point. This helps to reduce the misjudgment of false early warning information, provide correct reference data and adjustment plans, and avoid unnecessary emergency processing and waste of resources.

[0035] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: through the data acquisition module and the data processing and mapping module, the present system can collect and process various tunnel construction monitoring data in real time and accurately. Compared with the traditional manual monitoring method, the system can obtain data more comprehensively and meticulously, eliminate human errors, and improve the accuracy and reliability of monitoring data; through the data processing and mapping module, the present system can convert monitoring data into intuitive graphical displays for user understanding and analysis, which can help users better understand the situation and trends of tunnel construction and make timely decisions and adjustments; and through the construction and comparative analysis of historical data set A, the system can identify false warning information and distinguish it from real warning information, which can reduce the trouble caused by false warnings to staff and improve the timeliness and accuracy of real warning information; through the warning signal Through the information processing module and the real-time monitoring and notification module, this system can conduct real-time analysis of monitoring data and automatically issue early warning information, reducing the subjectivity and delay of human judgment, so that potential risks and problems can be identified in time, and corresponding measures can be taken to improve the accuracy and timeliness of early warning information; through the data analysis and comparison module and the monitoring point adjustment function, this system can conduct in-depth analysis and comparison of monitoring data, and adjust monitoring points according to historical data, improving the matching and accuracy of data, which can reduce the false alarm rate and missed alarm rate and improve the management efficiency of construction safety; by calculating indicators such as the difference index and matching degree, the system can provide monitoring point position adjustment data to staff to help them make reasonable adjustments to the current monitoring points, which can minimize the generation of false early warning information and improve the accuracy and effectiveness of monitoring points. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0037] Figure 1 It is a schematic diagram of the module of the tunnel construction safety monitoring system based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0038] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0039] See also Figure 1 , the present invention provides a technical solution:

[0040] The tunnel construction safety monitoring system based on the Internet of Things includes: data acquisition module, data processing and mapping module, early warning information processing module, data analysis and comparison module, and real-time monitoring and notification module;

[0041] The data acquisition module is responsible for acquiring tunnel construction monitoring data and monitoring point location data; the data processing and mapping module performs a one-to-one mapping of historical tunnel construction monitoring data with historical monitoring point location data to construct a historical data set; the early warning information processing module divides the early warning information into false early warning information and true early warning information based on the subsequent processing results of the early warning information recorded in the historical tunnel construction safety log; the data analysis and comparison module conducts further data analysis and comparison on false early warning information and true early warning information, obtains the difference index between false early warning information and true early warning information of the same type, and obtains the monitoring point adjustment data of the false early warning information based on the difference index; the real-time monitoring and notification module obtains real-time tunnel construction monitoring data and real-time monitoring point location data, and calculates the similarity between the early warning category of the early warning information and the historical early warning information; based on the calculation results, the relevant personnel are notified to handle the situation or make adjustments based on the monitoring point adjustment data.

[0042] The data acquisition module includes a sensor and monitoring equipment unit and a data communication unit;

[0043] The sensor and monitoring equipment unit is responsible for collecting tunnel construction monitoring data and monitoring point location data; the data communication unit is responsible for transmitting the collected data to the data processing and mapping module. Tunnel construction monitoring data includes displacement and deformation data, hydrological and water quality data, temperature and humidity data, pressure data, vibration data, and environmental pollution data.

[0044] The data processing and mapping module includes a data cleaning unit, a data storage unit, and a mapping association unit;

[0045] The data cleaning unit preprocesses and cleans the collected raw data to remove interference factors such as outliers and noise to ensure the accuracy and consistency of the data; the data storage unit stores the cleaned data in the database for subsequent data analysis and query operations; the mapping association unit performs a one-to-one mapping of historical tunnel construction monitoring data with historical monitoring point location data to construct a historical data set.

[0046] The mapping association units include:

[0047] Historical tunnel construction monitoring data and historical monitoring point location data are obtained from the original tunnel construction safety monitoring system. The historical monitoring point location data are randomly numbered, and a one-to-one mapping is performed between the historical tunnel construction monitoring data and the historical monitoring point location data to form a historical data set A, where A = {a1, a2, ..., an}, where a1 represents the historical monitoring point location data numbered 1 and the corresponding historical tunnel construction monitoring data, a2 represents the historical monitoring point location data numbered 2 and the corresponding historical tunnel construction monitoring data, and so on. An represents the historical monitoring point location data numbered n and the corresponding historical tunnel construction monitoring data, and n represents the number of historical monitoring points.

[0048] Historical dataset A contains the correspondence between historical tunnel construction monitoring data and monitoring point location data, providing basic data for subsequent analysis and processing. By mapping historical tunnel construction monitoring data to monitoring point location data one-to-one, early warning information can be associated with the corresponding historical data, thereby better understanding and analyzing early warning information. Constructing historical dataset A can help determine the difference between false and true early warning information and provide corresponding comparison data and monitoring point adjustment data. These data can be used to assist staff in processing and adjusting early warning information, improving the efficiency and accuracy of responses to early warning information.

[0049] In this embodiment, it is assumed that there are five monitoring point location data, namely:

[0050] Monitoring point 1: (10,20,5),

[0051] Monitoring point 2: (15,25,6),

[0052] Monitoring point 3: (12,22,7),

[0053] Monitoring point 4: (18,30,8),

[0054] Monitoring point 5: (22,35,9);

[0055] At the same time, there are corresponding tunnel construction monitoring data, including surface subsidence, groundwater level and other data.

[0056] The location data of these monitoring points can be randomly numbered and then mapped one-to-one with the corresponding tunnel construction monitoring data to form a historical data set A.

[0057] For example, the numbered monitoring point location data and the corresponding tunnel construction monitoring data are shown below:

[0058] a1: (monitoring point 1 location data, tunnel construction monitoring data 1),

[0059] a2: (monitoring point 2 location data, tunnel construction monitoring data 2),

[0060] a3: (monitoring point 3 location data, tunnel construction monitoring data 3),

[0061] a4: (monitoring point 4 location data, tunnel construction monitoring data 4),

[0062] a5: (monitoring point 5 location data, tunnel construction monitoring data 5).

[0063] The early warning information processing module includes an early warning information classification unit and a historical data association unit;

[0064] The warning information classification unit includes: obtaining historical tunnel construction safety logs to obtain warning information from the original tunnel safety monitoring system; and classifying the warning information into false warning information and true warning information based on the subsequent processing results of the warning information recorded in the historical tunnel construction safety logs;

[0065] The historical data association unit includes: obtaining the time point when the warning information is issued, selecting the time period T as the time period for issuing the warning information according to the time point, and obtaining the corresponding warning occurrence area according to the warning information; obtaining the historical monitoring point location data of the warning occurrence area corresponding to the historical tunnel construction monitoring data of the time period T, and associating the warning information with the corresponding historical tunnel construction monitoring data.

[0066] By obtaining the time point when the warning information is issued and the corresponding warning area, the historical monitoring point location data and tunnel construction monitoring data related to the warning can be obtained. These data can provide background information to help better understand and analyze the cause and impact scope of the warning information; by associating the warning information with historical monitoring data, a more in-depth analysis can be carried out. By comparing with historical data, potential abnormal patterns or trends can be discovered, providing more clues for the interpretation of the warning information.

[0067] The data analysis and comparison module includes a monitoring point quantity comparison unit, a data analysis unit, and a monitoring point adjustment unit;

[0068] The monitoring point quantity comparison unit includes: further classifying the false warning information and the real warning information according to the warning category, wherein the warning category of the real warning information includes the warning category of the false warning information; obtaining the corresponding warning category for each false warning information, finding the real warning information of the same warning category according to the warning category, and comparing the number of historical monitoring points corresponding to the false warning information and the real warning information; wherein the number of real warning information of the same warning category is more than one;

[0069] The data analysis unit analyzes the comparison results of the monitoring point quantity comparison unit and calculates the difference index;

[0070] The monitoring point adjustment unit includes: arranging the calculated difference indexes in ascending order, extracting the historical monitoring point location data of the real warning information with the difference index accounting for the top a% as the control data, where a is a set percentage threshold; obtaining the monitoring point location data adjusted for the false warning information based on the historical tunnel construction safety log records as the template data; and calculating the matching degree P between the control data and the template data, and the calculation formula is:

[0071]

[0072] Among them, σ represents the adjustment parameter, G represents the difference index between the control data and the template data, and the value of the difference index is related to the number of monitoring points corresponding to the control data and the template data. When the number of monitoring points of the control data and the template data is not equal, the difference index is G1, and when the number of monitoring points of the control data and the template data is equal, the difference index is G2; the monitoring point adjustment data with the largest matching degree is selected as the monitoring point adjustment data, and the monitoring point adjustment data is associated with the corresponding false warning information.

[0073] In this embodiment, assuming that the number of historical data monitoring points corresponding to the false warning information is not equal to the number of historical data monitoring points corresponding to the real warning information, the difference index G1 is calculated, and it is assumed that the historical monitoring point location data of the real warning information with the difference index accounting for the top 30% are extracted as the control data, and the number of control data is three, namely A, B and C; then the difference index between the template data and the control data is calculated, assuming that the number of monitoring points of A and B is equal to the number of monitoring points of the template data, then G2 is calculated; for C and the template data, G1 is calculated; then the calculated value is substituted into the matching degree calculation formula, assuming that A has the largest matching degree, then A is selected as the monitoring point adjustment data, and the monitoring point adjustment data is associated with the corresponding false warning information; and when the largest matching degree is not unique, all the ones with the largest matching degrees are used as monitoring point adjustment data.

[0074] The data analysis unit includes:

[0075] The number of monitoring points comparison unit is used to compare the number of false warning information and the corresponding number of historical data monitoring points; if the number of historical data monitoring points corresponding to the false warning information is not equal to the number of historical data monitoring points corresponding to the true warning information, it means that the main reason for the warning information being false warning information is that there are too many or too few historical data monitoring points, and the false information analyzed here excludes the influence of monitoring equipment failure; then the historical monitoring point location data of the false warning information and the true warning information are analyzed; based on the historical monitoring point location data of the false warning information and the true warning information, the historical monitoring point monitoring ranges of the false warning information and the true warning information are calculated respectively, expressed as S1 and S2 respectively; the difference index G1 of the historical monitoring point location data of the false warning information and the true warning information of the same warning category is calculated, and the specific calculation formula is:

[0076]

[0077] Among them, N1 represents the number of historical monitoring points in the warning area where false warning information occurs, N 2i It represents the number of historical monitoring points in the warning occurrence area of ​​the i-th real warning information of the same warning category as the false warning information, S2i represents the monitoring range of the historical monitoring points of the i-th real warning information of the same warning category as the false warning information, α and β represent different parameters, and m represents the number of real warning information of the same warning category as the false warning information.

[0078] The Data Analysis Unit also includes:

[0079] If the number of historical data monitoring points corresponding to the false warning information is equal to the number of historical data monitoring points corresponding to the true warning information, it means that the historical monitoring point location and the historical tunnel construction monitoring data jointly caused the warning information to be false warning information. Similarly, the false warning information analyzed here excludes the influence of monitoring equipment failure; then the historical monitoring point location data and historical tunnel construction monitoring data of the false warning information and the true warning information are analyzed; based on the historical monitoring point location data of the false warning information and the true warning information, the distances between adjacent historical monitoring points of the false warning information and the true warning information are calculated, respectively, and expressed as L1 and L2; based on the historical tunnel construction monitoring data of the false warning information and the true warning information, a curve graph of the historical tunnel construction monitoring data changing with time in time period T is drawn, and expressed as Q1 and Q2 respectively; the difference index G2 between the historical monitoring point location data and the historical tunnel construction monitoring data of the false warning information and the true warning information of the same warning category is calculated, and the specific calculation formula is:

[0080]

[0081] Among them, γ and μ represent parameters, L 1jrepresents the distance between adjacent historical monitoring points of the jth false warning information, L 2j represents the distance between adjacent historical monitoring points of the jth real warning information, M represents the data number of the distance between adjacent historical monitoring points, S Q1 represents the area of ​​the coordinate axis surrounded by the curve Q1, S Q2 represents the area of ​​the coordinate axis surrounded by the curve Q2, S Q2_k It represents the area of ​​the coordinate axis surrounded by the k-th Q2 curve, and K represents the number of Q2 curves of true warning information of the same warning category as the false warning information.

[0082] Real-time monitoring and notification modules include:

[0083] Real-time tunnel construction monitoring data and real-time monitoring point location data are obtained. When the tunnel construction safety monitoring system issues an early warning message, the early warning category of the current early warning message is obtained and the similarity is calculated with the historical early warning message of the same early warning category. This helps to quickly and accurately judge the credibility and urgency of the current early warning message. If the one with the greatest similarity is a true early warning message in the historical early warning message, the relevant staff will be notified to carry out corresponding processing, so that timely action can be taken to ensure the safety of the construction site and avoid the occurrence or further deterioration of accidents. If the one with the greatest similarity is a false early warning message in the historical early warning message, the corresponding template data and monitoring point adjustment data are output to the relevant staff, who will make corresponding adjustments to the current monitoring point. This helps to reduce the misjudgment of false early warning information, provide correct reference data and adjustment plans, and avoid unnecessary emergency processing and waste of resources.

[0084] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0085] Finally, it should be noted that the above descriptions are merely preferred embodiments 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 aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. The tunnel construction safety monitoring system based on the Internet of Things is characterized by: The system includes: a data acquisition module, a data processing and mapping module, an early warning information processing module, a data analysis and comparison module, and a real-time monitoring and notification module; The data acquisition module is responsible for acquiring tunnel construction monitoring data and monitoring point location data; the data processing and mapping module performs a one-to-one mapping of historical tunnel construction monitoring data and historical monitoring point location data to construct a historical data set; the warning information processing module divides the warning information into false warning information and true warning information based on the subsequent processing results of the warning information recorded in the historical tunnel construction safety log; the data analysis and comparison module performs further data analysis and comparison on the false warning information and the true warning information to obtain the difference index between the false warning information and the true warning information of the same type, and obtains the monitoring point adjustment data of the false warning information based on the difference index; the real-time monitoring and notification module obtains real-time tunnel construction monitoring data and real-time monitoring point location data, and calculates the similarity between the warning category of the warning information and the historical warning information; notifies relevant personnel to handle it according to the calculation results or adjusts it according to the monitoring point adjustment data; The data analysis and comparison module includes a monitoring point quantity comparison unit, a data analysis unit and a monitoring point adjustment unit; The monitoring point quantity comparison unit includes: further classifying the false warning information and the true warning information according to the warning category, and the warning category of the true warning information includes the warning category of the false warning information; obtaining the corresponding warning category for each false warning information, finding the true warning information of the same warning category according to the warning category, and comparing the number of historical monitoring points corresponding to the false warning information and the true warning information; The data analysis unit performs analysis based on the comparison result of the monitoring point quantity comparison unit to calculate the difference index; The monitoring point adjustment unit includes: arranging the calculated difference indexes in ascending order, extracting historical monitoring point location data of true warning information whose difference index accounts for the top a% as control data, where a is a set percentage threshold; obtaining the monitoring point location data adjusted for false warning information based on historical tunnel construction safety log records as template data; and calculating the matching degree P between the control data and the template data, and the calculation formula is: Where σ represents the adjustment parameter, G represents the difference index between the control data and the template data; the data with the largest matching degree is selected as the monitoring point adjustment data, and the monitoring point adjustment data is associated with the corresponding false warning information; The data analysis unit includes: using a monitoring point number comparison unit to compare the false warning information with the corresponding number of historical data monitoring points; If the number of historical data monitoring points corresponding to the false warning information is not equal to the number of historical data monitoring points corresponding to the true warning information, the historical monitoring point location data of the false warning information and the true warning information are analyzed; based on the historical monitoring point location data of the false warning information and the true warning information, the historical monitoring point monitoring ranges of the false warning information and the true warning information are calculated respectively, expressed as S1 and S2 respectively; the difference index G1 of the historical monitoring point location data of the false warning information and the true warning information of the same warning category is calculated, and the specific calculation formula is: Among them, N1 represents the number of historical monitoring points in the warning area where false warning information occurs, N 2i represents the number of historical monitoring points in the warning occurrence area of ​​the i-th real warning information of the same warning category as the false warning information, S2i represents the monitoring range of the historical monitoring points of the i-th real warning information of the same warning category as the false warning information, α and β represent different parameters, and m represents the number of real warning information of the same warning category as the false warning information; The real-time monitoring and notification module includes: Real-time tunnel construction monitoring data and real-time monitoring point location data are obtained. When the tunnel construction safety monitoring system issues an early warning message, the early warning category of the current early warning information is obtained and the similarity is calculated with the historical early warning information of the same early warning category. If the one with the greatest similarity is a true early warning message in the historical early warning information, the relevant staff is notified to perform corresponding processing. If the one with the greatest similarity is a false early warning message in the historical early warning information, the corresponding template data and monitoring point adjustment data are output to the relevant staff, who then make corresponding adjustments to the current monitoring point.

2. The tunnel construction safety monitoring system based on the Internet of Things according to claim 1 is characterized by: The data acquisition module includes a sensor and monitoring equipment unit and a data communication unit; The sensor and monitoring equipment unit is responsible for collecting tunnel construction monitoring data and monitoring point location data; the data communication unit is responsible for transmitting the collected data to the data processing and mapping module; The data processing and mapping module includes a data cleaning unit, a data storage unit and a mapping association unit; The data cleaning unit pre-processes and cleans the collected raw data; the data storage unit stores the cleaned data in a database; The mapping association unit performs a one-to-one mapping between the historical tunnel construction monitoring data and the historical monitoring point location data to construct a historical data set.

3. The tunnel construction safety monitoring system based on the Internet of Things according to claim 2 is characterized by: The mapping association unit includes: Historical tunnel construction monitoring data and historical monitoring point location data are obtained from the original tunnel construction safety monitoring system. The historical monitoring point location data are randomly numbered, and a one-to-one mapping is performed between the historical tunnel construction monitoring data and the historical monitoring point location data to form a historical data set A, where A = {a1, a2, ..., an}, where a1 represents the historical monitoring point location data numbered 1 and the corresponding historical tunnel construction monitoring data, a2 represents the historical monitoring point location data numbered 2 and the corresponding historical tunnel construction monitoring data, and so on. An represents the historical monitoring point location data numbered n and the corresponding historical tunnel construction monitoring data, and n represents the number of historical monitoring points.

4. The tunnel construction safety monitoring system based on the Internet of Things according to claim 1 is characterized in that: The warning information processing module includes a warning information classification unit and a historical data association unit; The warning information classification unit includes: obtaining historical tunnel construction safety logs to obtain warning information from the original tunnel safety monitoring system, and classifying the warning information into false warning information and true warning information based on subsequent processing results of the warning information recorded in the historical tunnel construction safety logs; The historical data association unit includes: obtaining the time point when the warning information is issued, selecting a time period T as the time period when the warning information is issued according to the time point, and obtaining the corresponding warning occurrence area according to the warning information; obtaining the historical tunnel construction monitoring data corresponding to the time period T of the historical monitoring point location data of the warning occurrence area, and associating the warning information with the corresponding historical tunnel construction monitoring data.

5. The tunnel construction safety monitoring system based on the Internet of Things according to claim 1 is characterized in that: The data analysis unit further includes: If the number of historical data monitoring points corresponding to the false warning information is equal to the number of historical data monitoring points corresponding to the true warning information, the historical monitoring point location data and historical tunnel construction monitoring data of the false warning information and the true warning information are analyzed; based on the historical monitoring point location data of the false warning information and the true warning information, the distances between adjacent historical monitoring points of the false warning information and the true warning information are calculated, respectively, and expressed as L1 and L2; based on the historical tunnel construction monitoring data of the false warning information and the true warning information, a curve graph of the change of historical tunnel construction monitoring data over time in time period T is drawn, and expressed as Q1 and Q2 respectively; the difference index G2 of the historical monitoring point location data and historical tunnel construction monitoring data of the false warning information and the true warning information of the same warning category is calculated, and the specific calculation formula is: Among them, γ and μ represent parameters, L 1j represents the distance between adjacent historical monitoring points of the jth false warning information, L 2j represents the distance between adjacent historical monitoring points of the jth real warning information, M represents the data number of the distance between adjacent historical monitoring points, S Q1 represents the area of ​​the coordinate axis surrounded by the curve Q1, S Q2 represents the area of ​​the coordinate axis surrounded by the curve Q2, S Q2_k It represents the area of ​​the coordinate axis surrounded by the k-th Q2 curve, and K represents the number of Q2 curves of true warning information of the same warning category as the false warning information.

Images