A remote monitoring method and system for tunnels using IoT and BS architecture
The remote monitoring system based on IoT and BS architecture solves the problem of insufficient tunnel monitoring methods under train traffic conditions, realizes comprehensive tunnel data monitoring and accurate early warning information, and ensures tunnel safety and utilization efficiency.
Patent Information
- Application Number
- CN202411089987.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing tunnel monitoring methods cannot be used in tunnels where trains cannot pass, and sensor monitoring thresholds are not adapted to different environments, leading to errors in early warning information and failing to detect tunnel problems in advance.
The remote monitoring system, which adopts IoT and BS architecture, acquires sensor information, user needs, and tunnel information to build predictive models, set level threshold ranges, output early warning information, and combines timestamps and environmental information for data processing and classification, thereby improving the accuracy of monitoring information and the timeliness of early warning.
It enables comprehensive data monitoring in any tunnel, improving the accuracy of early warning information and the response time of staff, thus ensuring tunnel safety and operational efficiency.
Smart Images

Figure CN118706078B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of tunnel monitoring, and in particular to a remote monitoring method and system for tunnels using IoT and BS architecture. Background Art
[0002] Tunnels are engineering structures buried in the ground. They are a form of human use of underground space. Tunnels can be divided into traffic tunnels, hydraulic tunnels, municipal tunnels, mining tunnels, and military tunnels. Tunnels are one of the important infrastructures in people's lives and transportation. The stability and safety of tunnels are directly related to the safety of people's lives and property. Through tunnel monitoring, abnormal conditions of tunnel structures, support systems or surrounding rocks can be discovered in time, hidden dangers can be warned, and safety measures can be taken in time to ensure the safe use of tunnels.
[0003] Patent publication number CN113252004A is a tunnel comprehensive detection and monitoring system and method. The detection system is installed on a train and adopts an on-board automatic detection and monitoring method to obtain tunnel data more comprehensively. The limit detection module can obtain real-time tunnel section information of the tunnel where the train is located and vehicle dynamic envelope information. The inspection module obtains 360° image information of the entire tunnel. The on-board processing module reconstructs the train dynamic envelope and the real-time status of the tunnel based on the information obtained, and comprehensively analyzes the tunnel equipment over-limit and vehicle over-limit information and their locations, and can also review the defects that have been found.
[0004] The above method solves the problem of more comprehensive acquisition of tunnel data by installing the detection system on the train, but the method cannot be used in tunnels that do not have the conditions for train passage. At present, in order to obtain tunnel data more comprehensively, a large number of sensors are usually laid and installed in the tunnel. In order to promptly respond to the problem of tunnel data response, an early warning function is usually provided in the existing method, but the triggering condition of the early warning function is mostly triggered when the sensor monitoring data exceeds the monitoring threshold, which makes it inconvenient to further discover the problem in advance and to reserve more time for the staff to deal with the problem. At the same time, due to the different internal environments of the tunnel, the monitoring objects of the same sensor are different. If the monitoring threshold is not preset for different environments, errors will occur in the early warning information, and thus the present invention is proposed. Summary of the invention
[0005] The purpose of the present invention is to provide a remote monitoring method and system for tunnels using IoT and BS architecture to solve the problems raised in the above background technology.
[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a remote monitoring method and system for tunnels using IoT and BS architecture, comprising: data acquisition: acquiring sensor information, user needs, basic feedback information and tunnel information, the sensor information including target sensor and target sensor location information, obtaining real-time monitoring data and past monitoring data based on the target sensor, integrating the real-time monitoring data and past monitoring data to obtain monitoring information, and the tunnel information including tunnel location information and tunnel environment information;
[0007] Data processing: The monitoring information is processed by information processing methods to obtain a monitoring information set, the target sensor is connected based on the IoT platform, and a Web application is developed based on the BS architecture to display and manage the data collected by the devices in the IoT platform;
[0008] Information generation: Based on user needs, real-time monitoring data and previous monitoring data are compared to obtain the monitoring data change trend. Based on the monitoring data change trend, the result information is obtained through the prediction model. Based on the tunnel information and the monitoring object of the target sensor, the level threshold range corresponding to the target sensor is obtained through the threshold establishment method. The real-time monitoring data is compared with the level threshold range to obtain the inclusion relationship;
[0009] Information output: Feedback the result information to the staff based on the basic feedback information, and output the warning information based on the inclusion relationship and basic feedback information;
[0010] The methods for building the prediction model include:
[0011] Step 1: Data collection: Obtain the sensor value change trend corresponding to the target sensor and the result of the sensor value change trend to obtain the initial data set, and combine the data in the initial data set through the data combination method to obtain the relevant data set;
[0012] Step 2: Data storage: Create a database to store the initial data set and related data sets;
[0013] Step 3: Information matching: Based on the changing trend of monitoring data, the result information is retrieved in the database through matching method;
[0014] Step 4: Model generation: Combine data collection, data storage and information matching to obtain a prediction model.
[0015] Furthermore, the information processing method includes: obtaining timestamp information of monitoring information based on the target sensor, segmenting the tunnel environment information through a segmentation method to obtain sub-tunnel location information and specific environment information corresponding to the sub-tunnel location information, comparing the target sensor location information with the sub-tunnel location information to obtain an inclusion relationship, extracting the corresponding specific environment information based on the inclusion relationship to obtain the target environment information, integrating the target sensor location information, the target environment information and the timestamp information to obtain a rich data set, embedding the rich data set into the monitoring information to obtain the final monitoring information, and classifying the final monitoring information through a classification method to obtain a monitoring information set.
[0016] Furthermore, the segmentation method includes: presetting the number of segments and the interval length, segmenting the tunnel based on the number of segments and the interval length to obtain sub-tunnels, obtaining sub-tunnel location information based on the tunnel location information and the sub-tunnel, and obtaining specific environmental information corresponding to the sub-tunnel location information by combining the sub-tunnel location information with the tunnel environmental information.
[0017] Furthermore, the classification method includes: classifying the target sensors into categories to obtain category relationships, classifying the final monitoring information based on the category relationships to obtain category monitoring information, presetting a sorting standard, sorting the category monitoring information based on the sorting standard and integrating it to obtain a monitoring information set.
[0018] Furthermore, the threshold establishment method includes: obtaining a standard monitoring object of the target sensor based on the target sensor, presetting a standard threshold range based on the standard monitoring object, determining a specific monitoring object according to the target sensor position information and the tunnel position information, judging the difference relationship between the standard monitoring object and the specific monitoring object to obtain a difference factor, and adjusting the standard threshold range based on the difference factor to obtain a level threshold range.
[0019] Furthermore, the level threshold range includes: a first-level level threshold range, a second-level threshold range and a third-level level threshold range. Any one of the level threshold ranges is preset as the optimal level threshold range. When the inclusion relationship is expressed as the real-time monitoring data is not within the optimal level threshold range, warning information is output; when the inclusion relationship is expressed as the real-time monitoring data is within the optimal level threshold range, no warning information is output.
[0020] Furthermore, the data combination method includes: splitting the initial data set to obtain sensor value change trend information and resulting result information, presetting a combination standard, combining the sensor value change trend information according to the combination standard to obtain combined sensor value change trend information and combined result information, judging whether the combined sensor value change trend information has a chain relationship, if so, obtaining the result information generated by the chain relationship and embedding it into the corresponding combined result information to obtain enriched result information, if there is no chain relationship, no operation is required, classifying and integrating the combined sensor value change trend information and the combined result information or the combined sensor value change trend information and the enriched result information into data subsets according to the number of combinations, embedding the name of the data subset into the combination number information, and integrating the data subsets to obtain the relevant data set.
[0021] Furthermore, the matching method includes: determining the number of monitoring data change trends; when the number of monitoring data change trends is multiple, searching in the database for a data subset whose number of combinations in the relevant data set is consistent with the number of monitoring data change trends; traversing the monitoring data change trend through the data subset to obtain result information; and when the monitoring data change trend is single, traversing the monitoring data change trend through the initial data set in the database to obtain result information.
[0022] Furthermore, a remote monitoring system for tunnels using IoT and BS architecture uses the above-mentioned remote monitoring method for tunnels using IoT and BS architecture.
[0023] Compared with the prior art, the present invention has the following beneficial effects:
[0024] This remote monitoring method and system for tunnels using IoT and BS architecture can obtain corresponding result information based on the changing trend of monitoring data and output it to the staff through the setting of a prediction model, so that the staff can respond in advance to future problems in the tunnel based on the result information, so as to gain more response time for the staff, improve the safety of the tunnel, and ensure the safe use of the tunnel. Through the set threshold establishment method, a level threshold range related to the monitoring object that fits the tunnel situation can be established according to the tunnel information and the monitoring object of the target sensor, which is conducive to improving the accuracy of the early warning information.
[0025] At the same time, through the set information processing method, the monitoring timestamp information, specific environmental information and monitoring location information are embedded in the monitoring information, which is convenient for subsequent staff to use and helps to improve the work efficiency of the staff. Through the setting of the segmentation method, the specific environmental information related to the monitoring information can be obtained more accurately, and the accuracy of the information can be improved. Through classification and sorting, it is beneficial for subsequent staff to find the required information in the monitoring information set more quickly according to needs.
[0026] At the same time, through the data combination method, more information corresponding to the changing trend of the monitoring data can be obtained, which is conducive to increasing the diversity of the database. The rich result information generated by the chain relationship can improve the richness of the result information, which is convenient for the staff to use the result information to fully understand the results of the changing trend of the monitoring data in the tunnel. The information generated by the combination is classified by the number of combinations, which is conducive to the matching method to directly select the corresponding data subset or initial data set for matching according to the number of changing trends of the monitoring data, which is conducive to shortening the time required for matching and improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Figure 1 It is a schematic diagram of the overall process structure of the present invention;
[0028] Figure 2 This is a schematic diagram of the structure of the early warning information output process of the present invention;
[0029] Figure 3 It is a schematic diagram of the prediction model process structure of the present invention. DETAILED DESCRIPTION
[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.
[0031] Tunnel monitoring refers to real-time or regular monitoring of tunnel construction, operation or environmental conditions to obtain relevant data information, evaluate the safety status of the tunnel, warn of hidden dangers, and guide the management and maintenance of the tunnel. By monitoring and analyzing the deformation and displacement of the tunnel, the working status of the tunnel can be understood, and protective measures can be taken in time to slow down the destruction of the surrounding rock, thereby extending the service life of the tunnel. Tunnel managers or maintenance personnel can download or browse monitoring data online through Web applications to help them understand the actual situation of the tunnel, formulate reasonable maintenance plans and management strategies, and ensure the efficiency and sustainability of tunnel operation.
[0032] like Figure 1-Figure 3 As shown, the present invention provides a technical solution: a remote monitoring method and system for tunnels using IoT and BS architecture, including:
[0033] Data acquisition: obtain sensor information, user needs, basic feedback information and tunnel information. Sensor information includes target sensor and target sensor location information. Real-time monitoring data and past monitoring data are obtained based on the target sensor. Monitoring information is obtained by integrating real-time monitoring data and past monitoring data. Tunnel information includes tunnel location information and tunnel environment information.
[0034] Data processing: The monitoring information is processed by information processing methods to obtain a monitoring information set, the target sensor is connected based on the IoT platform, and a Web application is developed based on the BS architecture to display and manage the data collected by the devices in the IoT platform;
[0035] Information generation: Based on user needs, real-time monitoring data and previous monitoring data are compared to obtain the monitoring data change trend. Based on the monitoring data change trend, the result information is obtained through the prediction model. Based on the tunnel information and the monitoring object of the target sensor, the level threshold range corresponding to the target sensor is obtained through the threshold establishment method. The real-time monitoring data is compared with the level threshold range to obtain the inclusion relationship;
[0036] Information output: Feedback the result information to the staff based on the basic feedback information, and output the warning information based on the inclusion relationship and basic feedback information;
[0037] It should be noted that: in the data acquisition stage, the basic feedback information is the address of the staff, including but not limited to: IP address, telephone number, email address, target sensor is a tool for monitoring tunnel information, and the corresponding sensor can be selected for special monitoring according to the actual tunnel conditions. The installation location of the sensor is determined according to the actual usage situation. The target sensor location information is the location information of the target sensor installed in the tunnel. The target sensor is usually equipped with a positioning module, and the target sensor location information is obtained through the positioning module. If there is no positioning module inside the target sensor, a GPS locator can be installed in the target sensor or next to the target sensor installation location to obtain the target sensor location information. Tunnel location information refers to the geographical location information of the tunnel, and tunnel environment information refers to the environment information inside or outside the tunnel. In the data processing stage, multiple target sensors are connected through the loT platform to realize data transmission, information processing and control operations between devices. Web applications are developed through the BS architecture and the loT platform. The display and control functions of IoT device data are realized, so that staff can access device data, monitor device status and perform remote control operations, so as to more conveniently manage and control IoT devices. The combination of IoT and BS architecture can provide IoT applications with more powerful and flexible functions and user experience. The monitoring information is processed through the set information processing method to enrich the monitoring information, so that the monitoring information obtained by the user is richer, which is convenient for the staff to further use the monitoring information. In the information generation stage, the user needs the monitoring information generated by the target sensor fed back by the staff, such as the monitoring information generated by a single target sensor and the monitoring information generated by multiple target sensors. In actual use, the program can be set to automatically feedback the monitoring information generated by the target sensor after a set interval. Through the set threshold establishment method, the level threshold range related to the monitoring object that fits the tunnel situation can be established according to the tunnel information and the monitoring object of the target sensor, which is conducive to improving the accuracy of the early warning information.
[0038] The methods for building the prediction model include:
[0039] Step 1: Data collection: Obtain the sensor value change trend corresponding to the target sensor and the result of the sensor value change trend to obtain the initial data set, and combine the data in the initial data set through the data combination method to obtain the relevant data set;
[0040] Step 2: Data storage: Create a database to store the initial data set and related data sets;
[0041] Step 3: Information matching: Based on the changing trend of monitoring data, the result information is retrieved in the database through matching method;
[0042] Step 4: Model generation: Combine data collection, data storage and information matching to obtain a prediction model.
[0043] It should be noted that: during the data collection stage, data can be collected manually or by training a proprietary data collection model. In order to improve the efficiency of data collection, data can be collected through a proprietary model in conjunction with manual review. Through the data combination method, the information in the initial data set is combined to increase the diversity of the database, which is conducive to quickly finding the result information corresponding to the changing trend of the monitoring data in the database through the matching method. Through the setting of the prediction model, the corresponding result information can be obtained according to the changing trend of the monitoring data generated by the real-time monitoring data and the previous monitoring data and output to the staff, so that the staff can respond to future problems in the tunnel in advance according to the result information, so as to obtain more response time for the staff, improve the safety of the tunnel, and ensure the safe use of the tunnel.
[0044] like Figure 1 As shown, the information processing method includes: obtaining timestamp information of monitoring information based on the target sensor, segmenting the tunnel environment information through a segmentation method to obtain sub-tunnel position information and specific environment information corresponding to the sub-tunnel position information, comparing the target sensor position information with the sub-tunnel position information to obtain an inclusion relationship, extracting the corresponding specific environment information based on the inclusion relationship to obtain the target environment information, integrating the target sensor position information, the target environment information and the timestamp information to obtain a rich data set, embedding the rich data set into the monitoring information to obtain the final monitoring information, and classifying the final monitoring information through a classification method to obtain a monitoring information set.
[0045] It should be noted that: monitoring information will be generated during the tunnel monitoring process. In order for the staff to further understand the tunnel situation, the staff often use monitoring information and other information to establish a BIM model. In order to enrich the information collected by the staff, the monitoring timestamp information, specific environmental information and monitoring location information are embedded in the monitoring information through the set information processing method, so that the subsequent staff can use this information, which is conducive to improving the work efficiency of the staff. When the target sensor generates monitoring information, the monitoring information will be accompanied by the generation time information. The timestamp information can be obtained by generating the time information. By judging that the target sensor location information is in one of several sub-tunnel location information, the result obtained is an inclusion relationship.
[0046] The segmentation method includes: presetting the number of segments and the interval length, segmenting the tunnel based on the number of segments and the interval length to obtain sub-tunnels, obtaining sub-tunnel location information based on tunnel location information and sub-tunnels, and obtaining specific environmental information corresponding to the sub-tunnel location information by combining the sub-tunnel location information with tunnel environmental information.
[0047] It should be noted that the number of segments and the interval length are determined according to actual usage. The optimal number of segments and the interval length can be determined according to the intervals at which the target sensors are laid and installed. By setting the segmentation method, specific environmental information related to the monitoring information can be obtained more accurately, which is convenient for enriching the monitoring information, facilitating further use by staff, and improving the accuracy of the information.
[0048] The classification method includes: classifying the target sensors to obtain category relationships, classifying the final monitoring information based on the category relationships to obtain category monitoring information, presetting a sorting standard, sorting the category monitoring information based on the sorting standard and integrating it to obtain a monitoring information set.
[0049] It should be noted that the final monitoring information generated by the target sensor is classified according to the category of the target sensor, and the sorting criteria are formulated according to the actual usage. For example, the sorting criteria are the size of the information or the time sequence, etc. Through classification and sorting, it is helpful for subsequent staff to find the required information in the monitoring information set more quickly according to needs.
[0050] like Figure 2 As shown, the threshold establishment method includes: obtaining a standard monitoring object of the target sensor based on the target sensor, presetting a standard threshold range based on the standard monitoring object, determining a specific monitoring object according to the target sensor position information and the tunnel position information, determining the difference relationship between the standard monitoring object and the specific monitoring object to obtain a difference factor, and adjusting the standard threshold range based on the difference factor to obtain a level threshold range.
[0051] It should be noted that: based on the application of the target sensor, the standard monitoring object of the target sensor can be obtained, the standard threshold range is formulated according to the standard detection object, the judgment of the difference factor is specifically to judge the material, surrounding environment, etc. of the standard detection object and the specific monitoring object, and the level threshold range can be obtained according to the difference factor and the standard threshold range. The specific process of adjusting the difference factor is to analyze the influence of the difference factor through staff analysis or training a special model, and adjust the standard threshold range according to the specific influence to obtain the level threshold range. For example: the rock texture in different sections of the tunnel may be different, so the internal pressure requirements of the surrounding rock of the tunnel rock will be different, and the corresponding level threshold range needs to be set according to the rock status of different sections.
[0052] The level threshold range includes: a first-level level threshold range, a second-level threshold range and a third-level level threshold range. Any one of the level threshold ranges is preset as the optimal level threshold range. When the inclusion relationship is expressed as the real-time monitoring data is not within the optimal level threshold range, warning information is output; when the inclusion relationship is expressed as the real-time monitoring data is within the optimal level threshold range, no warning information is output.
[0053] It should be noted that the number and relationship of the level threshold ranges correspond to the monitoring information generated by the target sensor. The optimal level threshold range is preset according to the attributes of the standard threshold range. For example, when the standard threshold range contains the boundary, the first-level threshold range and the third-level threshold range can be selected as the optimal level threshold range. When the standard threshold range is in the middle range value, the second-level threshold range can be selected as the optimal level range threshold. The division of the level threshold range is conducive to more accurate generation of warning information and to improving the accuracy of the warning information.
[0054] like Figure 3 As shown, the data combination method includes: splitting the initial data set to obtain sensor value change trend information and resulting result information, presetting a combination standard, combining the sensor value change trend information through the combination standard to obtain combined sensor value change trend information and combined result information, judging whether the combined sensor value change trend information has a chain relationship, if there is a chain relationship, obtaining the result information generated by the chain relationship and embedding it into the corresponding combined result information to obtain enriched result information, if there is no chain relationship, no operation is required, and according to the number of combinations, the combined sensor value change trend information and the combined result information or the combined sensor value change trend information and the enriched result information are classified and integrated into data subsets, the name of the data subset is embedded in the combination number information, and the data subsets are integrated to obtain the relevant data set.
[0055] It should be noted that: the combination standard is to combine the sensor value change trend information according to the maximum number of target sensor types decreasing to 2 in sequence, including the maximum number and 2. The combination process is a random combination, ensuring that the sensor value change trend information is completely combined with each other. Through the data combination method, more information corresponding to the monitoring data change trend can be obtained, which is conducive to increasing the diversity of the database. The chain relationship can be analyzed and judged by the staff manually or through the Internet. The rich result information generated by the chain relationship can improve the richness of the result information, which is convenient for the staff to use the result information to fully understand the results of the monitoring data change trend in the tunnel.
[0056] like Figure 3 As shown, the matching method includes: determining the number of monitoring data change trends; when the number of monitoring data change trends is multiple, searching in the database for a data subset whose number of combinations in the relevant data set is consistent with the number of monitoring data change trends; traversing the monitoring data change trend through the data subset to obtain result information; and when the monitoring data change trend is single, traversing the monitoring data change trend through the initial data set in the database to obtain result information.
[0057] It should be noted that: during the matching process, it is necessary to obtain the number of changing trends of the monitoring data involved in the matching, and select the matching range based on the quantitative relationship. When the number is single, the matching range is the initial data set in the database. When the number is multiple, the matching range is the data subset corresponding to the number in the relevant data set in the database. The information generated by the combination is classified by the combination quantity, which is beneficial for the matching method to directly select the corresponding data subset or initial data set for matching according to the number of changing trends of the monitoring data, which is beneficial to shorten the time required for matching and improve work efficiency.
[0058] Embodiment 1: For highway tunnels in high-intensity deep canyon sections, relevant monitoring parameters are designed according to relevant tunnel monitoring specifications. In view of the low grade of surrounding rock of such tunnels, the following parameters are monitored in particular: settlement, convergence deformation, internal deformation of surrounding rock, cracks, steel stress, earth pressure, surface strain, anchor tension, displacement, and monitoring positions are selected. Corresponding Internet of Things monitoring sensors are installed at the monitoring positions. The Internet of Things monitoring sensors are target sensors, including but not limited to magnetostatic levels, laser displacement sensors, crack meters, steel bar meters, multi-point displacement meters, earth pressure meters, surface strain meters, anchor cable meters, and intelligent total stations. The installation positions of the sensors are determined according to actual usage conditions. Intelligent remote monitoring of the health status of the tunnel is implemented. In view of the surrounding rock characteristics of high-intensity deep canyon tunnels: complex lithology; developed rock cracks; severe rock weathering; high rock stress; severe water filtration; uneven rock and large deformation; focus on monitoring the deformation, pressure, and anchor tension inside the surrounding rock, select multi-point displacement meters, earth pressure meters, and anchor cable meters, and conduct detailed monitoring of key sections.
[0059] Table 1: Summary of sensor applications
[0060]
[0061] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is limited by the attached embodiments and their equivalents.
Claims
1. A remote monitoring method for tunnels using IoT and BS architecture, characterized by: The method comprises: Data acquisition: obtain sensor information, user needs, basic feedback information and tunnel information. Sensor information includes target sensor and target sensor location information. Real-time monitoring data and past monitoring data are obtained based on the target sensor. Monitoring information is obtained by integrating real-time monitoring data and past monitoring data. Tunnel information includes tunnel location information and tunnel environment information. Data processing: The monitoring information is processed by information processing methods to obtain a monitoring information set, the target sensor is connected based on the IoT platform, and a Web application is developed based on the BS architecture to display and manage the data collected by the devices in the IoT platform; Information generation: Based on user needs, real-time monitoring data and previous monitoring data are compared to obtain the monitoring data change trend. Based on the monitoring data change trend, the result information is obtained through the prediction model. Based on the tunnel information and the monitoring object of the target sensor, the level threshold range corresponding to the target sensor is obtained through the threshold establishment method. The real-time monitoring data is compared with the level threshold range to obtain the inclusion relationship; Information output: Feedback the result information to the staff based on the basic feedback information, and output the warning information based on the inclusion relationship and basic feedback information; The methods for building the prediction model include: Step 1: Data collection: Obtain the sensor value change trend corresponding to the target sensor and the result of the sensor value change trend to obtain the initial data set, and combine the data in the initial data set through the data combination method to obtain the relevant data set; Step 2: Data storage: Create a database to store the initial data set and related data sets; Step 3: Information matching: Based on the changing trend of monitoring data, the result information is retrieved in the database through matching method; Step 4: Model generation: Combine data collection, data storage and information matching to obtain a prediction model; The data combination method comprises: splitting an initial data set to obtain sensor value change trend information and result information, presetting a combination standard, combining the sensor value change trend information according to the combination standard to obtain combined sensor value change trend information and combined result information, judging whether the combined sensor value change trend information has a chain relationship, if there is a chain relationship, obtaining the result information generated by the chain relationship and embedding it into the corresponding combined result information to obtain enriched result information, if there is no chain relationship, no operation is required, classifying and integrating the combined sensor value change trend information and the combined result information or the combined sensor value change trend information and the enriched result information into data subsets according to the number of combinations, embedding the name of the data subset into the combination number information, and integrating the data subsets to obtain the relevant data set; The matching method includes: determining the number of monitoring data change trends; when the number of monitoring data change trends is multiple, searching in a database for a data subset whose number of combinations in a related data set is consistent with the number of monitoring data change trends; traversing the monitoring data change trend through the data subset to obtain result information; and when the monitoring data change trend is single, traversing the monitoring data change trend through the initial data set in the database to obtain result information.
2. According to claim 1, a remote monitoring method for tunnels using IoT and BS architecture is characterized in that: The information processing method includes: obtaining timestamp information of monitoring information based on a target sensor, performing segmentation processing on tunnel environment information by a segmentation method to obtain sub-tunnel location information and specific environment information corresponding to the sub-tunnel location information, comparing the target sensor location information with the sub-tunnel location information to obtain an inclusion relationship, extracting the corresponding specific environment information based on the inclusion relationship to obtain target environment information, integrating the target sensor location information, the target environment information and the timestamp information to obtain an enriched data set, embedding the enriched data set into the monitoring information to obtain final monitoring information, and classifying the final monitoring information by a classification method to obtain a monitoring information set.
3. According to claim 2, a remote monitoring method for tunnels using IoT and BS architecture is characterized in that: The segmentation method includes: presetting the number of segments and the interval length, segmenting the tunnel based on the number of segments and the interval length to obtain sub-tunnels, obtaining sub-tunnel location information based on tunnel location information and sub-tunnels, and obtaining specific environmental information corresponding to the sub-tunnel location information by combining the sub-tunnel location information with tunnel environmental information.
4. According to claim 2, a remote monitoring method for tunnels using IoT and BS architecture is characterized in that: The classification method includes: classifying the target sensors to obtain category relationships, classifying the final monitoring information based on the category relationships to obtain category monitoring information, presetting a sorting standard, sorting the category monitoring information based on the sorting standard and integrating them to obtain a monitoring information set.
5. According to claim 1, a remote monitoring method for tunnels using IoT and BS architecture is characterized in that: The threshold establishment method includes: obtaining a standard monitoring object of the target sensor based on the target sensor, presetting a standard threshold range based on the standard monitoring object, determining a specific monitoring object according to the target sensor position information and the tunnel position information, determining a difference relationship between the standard monitoring object and the specific monitoring object to obtain a difference factor, and adjusting the standard threshold range based on the difference factor to obtain a level threshold range.
6. The remote monitoring method for tunnels using IoT and BS architecture according to claim 1, characterized in that: The level threshold range includes: a first-level level threshold range, a second-level threshold range and a third-level level threshold range. Any one of the level threshold ranges is preset as the optimal level threshold range. When the inclusion relationship is expressed as the real-time monitoring data is not within the optimal level threshold range, warning information is output; when the inclusion relationship is expressed as the real-time monitoring data is within the optimal level threshold range, no warning information is output.
7. A remote monitoring system for tunnels using IoT and BS architecture, characterized by: A remote monitoring method for tunnels using IoT and BS architecture as described in any one of claims 1 to 6 is used.
