Tunnel risk management system and method based on Internet of Things

Abstract

The invention discloses a tunnel risk management system and method based on the Internet of Things, and the system comprises a data collection module which is used for obtaining sensor data, collected by different monitoring systems, in a tunnel through a standardized data interface, and obtaining multi-dimensional original data; the data transmission module is used for transmitting the multi-dimensional original data to a cloud server; the data analysis module is used for allocating weights to the multi-dimensional original data for data fusion to obtain fused data; and updating the multi-dimensional original data through the fusion data, and performing classification and / or linear prediction on the updated multi-dimensional original data to obtain a risk classification result and / or a risk linear prediction result, and the risk monitoring module is used for generating a risk report according to the risk classification result and / or the risk linear prediction result. According to the technical scheme, the tunnel risk management level is improved, and accidents in tunnel engineering are reduced.

Description

Technical Field

[0001] The present invention relates to the field of tunnel risk management, and particularly to an Internet of Things-based tunnel risk management system and method. Background Art

[0002] Tunnel construction refers to the general term for the construction methods, construction techniques, and construction management of tunnels and underground chambers. The tunnel construction process usually includes: excavating earth and stone in the strata to form an underground space that conforms to the design cross-section, carrying out necessary support and lining, controlling the deformation of the tunnel surrounding rock, and ensuring the safety of tunnel construction and long-term safe use. Tunnel safety management is an important link to ensure the safety of tunnel construction and operation.

[0003] Underground construction consists of multiple operations, such as excavation, support, muck transportation, ventilation and dust removal, waterproofing and drainage, power supply, air supply, and water supply. None of these operations can be missing. It is required to have good construction management and construction organization experience to enable the project to proceed orderly and quickly.

[0004] Currently, traditional monitoring methods are generally used in tunnel engineering to monitor the safety of tunnels, such as manual inspections and wired sensor monitoring. These methods have problems such as untimely data collection, low data processing efficiency, and information silos. This leads to poor tunnel risk management and support effects, and may even cause safety accidents. Summary of the Invention

[0005] An embodiment of the present invention provides an Internet of Things-based tunnel risk management system and method, aiming to improve the real-time data collection, data processing efficiency, and ensure the integrity, consistency, accuracy, and reliability of data, thereby improving the effect of tunnel risk management.

[0006] In a first aspect, an embodiment of the present invention provides an Internet of Things-based tunnel risk management system, including:

[0007] A data collection module, configured to obtain sensor data in the tunnel collected by different monitoring systems through a standardized data interface, and obtain multi-dimensional raw data;

[0008] A data transmission module, configured to transmit the multi-dimensional raw data to a cloud server;

[0009] A data analysis module, configured to align the multi-dimensional raw data in time and space on the cloud server, assign weights to the multi-dimensional raw data for data fusion according to the reliability and accuracy of the different monitoring systems, and obtain fusion data; and update the multi-dimensional raw data through the fusion data, classify and / or linearly predict the updated multi-dimensional raw data, and obtain a risk classification result and / or a risk linear prediction result;

[0010] A risk monitoring module, configured to generate a risk report based on the risk classification result and / or the risk linear prediction result.

[0011] Furthermore, the differences of the monitoring system include: sensor types and models, data formats and storage structures, communication protocols, and / or business logics and application scenarios.

[0012] Furthermore, the sensor types include: strain gauges, displacement gauges, crack gauges, anchor stress gauges, convergence meters, temperature sensors, humidity sensors, gas sensors, water level sensors, video surveillance cameras, noise sensors, and / or vibration sensors.

[0013] Furthermore, the data analysis module is further configured to: before aligning the multi-dimensional raw data, perform data verification, anomaly detection, and / or redundancy processing on the multi-dimensional raw data;

[0014] The data verification includes: format verification in a preset data format, integrity verification based on the integrity of data packets, and / or logical verification based on business rules;

[0015] The anomaly detection includes: detecting anomaly points with a preset threshold, detecting deviation conditions based on the data dispersion degree, and / or detecting abnormal fluctuation conditions based on the time series prediction result;

[0016] The redundancy processing includes: comparing the data of the same sensor in different monitoring systems in the multi-dimensional raw data, and if the difference exceeds the normal range, triggering an alarm and discarding it.

[0017] Furthermore, the objects of data fusion include: different data of the same type of sensor, data of different types of sensors, and / or sensor data in different time periods.

[0018] Furthermore, the data analysis module is further configured to: before classifying or linearly predicting the updated multi-dimensional raw data, perform cleaning processing, standardization processing, and / or feature extraction processing on the updated multi-dimensional raw data;

[0019] The cleaning processing includes: removing noise in the updated multi-dimensional raw data, filling missing values, and / or smoothing curves;

[0020] The standardization processing includes: converting sensor data of different scales into a unified standard;

[0021] The feature extraction processing includes: extracting the mean value, variance, change rate, skewness coefficient, and / or kurtosis coefficient of the updated multi-dimensional raw data.

[0022] Further, the process of classifying or linearly predicting the updated multi-dimensional raw data is specifically as follows:

[0023] Classify or linearly predict the updated multi-dimensional raw data through a random forest algorithm, a support vector machine algorithm, and / or a long short-term memory network algorithm;

[0024] Based on the risk classification result, confirm whether there is structural abnormality and / or environmental abnormality in the tunnel; and / or

[0025] Based on the risk linear prediction result, confirm the risk of structural abnormality and / or environmental abnormality in the tunnel.

[0026] Further, the risk report includes: risk level, risk impact range, and / or possible cause of risk.

[0027] Further, the risk monitoring module is further configured to: display the updated multi-dimensional raw data and / or the risk report in real time through a visualization tool on a front-end large screen and / or a mobile terminal device; return the updated multi-dimensional raw data to the backend through an RPC protocol, and call the corresponding tunnel, geological structure, and / or support model to generate a corresponding two-dimensional or three-dimensional model.

[0028] In a second aspect, an embodiment of the present invention provides an Internet of Things-based tunnel risk management method, including:

[0029] Obtain sensor data in the tunnel collected by different monitoring systems through a standardized data interface to obtain multi-dimensional raw data;

[0030] Transmit the multi-dimensional raw data to a cloud server;

[0031] Align the multi-dimensional raw data in time and space on the cloud server, assign weights to the multi-dimensional raw data for data fusion according to the reliability and accuracy of different monitoring systems to obtain fusion data; and update the multi-dimensional raw data through the fusion data, classify and / or linearly predict the updated multi-dimensional raw data to obtain a risk classification result and / or a risk linear prediction result;

[0032] Generate a risk report based on the risk classification result and / or the risk linear prediction result.

[0033] In a third aspect, an embodiment of the present invention provides an electronic device, which includes:

[0034] At least one processor; and

[0035] A memory communicatively connected to the at least one processor; wherein,

[0036] The memory stores a computer program that can be executed by the at least one processor. When the computer program is executed by the at least one processor, the at least one processor is enabled to execute the Internet of Things-based tunnel risk management method according to any embodiment of the present invention.

[0037] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer instructions for causing a processor to implement the Internet of Things-based tunnel risk management method according to any embodiment of the present invention when executed.

[0038] In the embodiments of the present invention, through Internet of Things technology, the present invention can achieve 24-hour uninterrupted tunnel monitoring, greatly shortening the discovery time of potential safety hazards and improving the emergency response speed. Through the application of data processing and analysis algorithms, risk assessment is made more accurate, which helps to early warn of potential safety risks and reduce the accident rate. Compared with the prior art, the technical solutions in the embodiments of the present invention improve the real-time performance of data collection and data processing efficiency, ensuring the integrity, consistency, accuracy, and reliability of data, thereby improving the effect of tunnel risk management and support. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for the description of the embodiments. Obviously, the following-described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1 is a schematic structural diagram of an Internet of Things-based tunnel risk management system according to an embodiment of the present invention;

[0041] Figure 2 is a schematic flowchart of an Internet of Things-based tunnel risk management method according to an embodiment of the present invention;

[0042] Figure 3 is a schematic structural diagram of an electronic device for implementing the Internet of Things-based tunnel risk management method according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] The following further elaborates on the present invention in conjunction with the drawings and embodiments. It can be understood that the specific embodiments described herein are only for explaining the present invention and not for limiting the present invention. Additionally, it should be noted that for the sake of description, only parts related to the present invention are shown in the drawings rather than all the structures.

[0044] Embodiment 1

[0045] Figure 1 It is a schematic structural diagram of a tunnel risk management system based on the Internet of Things provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of monitoring tunnel structures. The tunnel risk management system based on the Internet of Things can be implemented in the form of hardware and / or software, and can be configured in an electronic device. As Figure 1 shown, the system includes: a data acquisition module 10, a data transmission module 20, a data processing module 30, and a risk monitoring module 40.

[0046] The data acquisition module 10 is used to obtain multi-dimensional raw data in the tunnel collected by different detection systems through a standardized data interface.

[0047] Among them, the process of building the standardized data interface is as follows:

[0048] Select a common JSON data format and create a RESTful API;

[0049] Clarify the function description and input / output specifications of each API;

[0050] Different monitoring systems interact through a unified data interface.

[0051] Aiming at the problem that there are information islands among existing tunnel monitoring systems and data cannot be effectively shared and integrated, in the embodiment of the present invention, the data acquisition module 10 can be configured as an integration platform. By selecting a common JSON data format, creating a RESTful API, and clarifying the function description and input / output specifications of each API, it is ensured that different monitoring systems can interact through a unified data interface. RESTful API refers to Representational State Transfer, which is an architectural style widely used in web services.

[0052] In the embodiment of the present invention, by creating a standardized data interface and communication protocol, the data of monitoring systems with different sensor types and data acquisition methods, different data models and representation methods, different communication protocols, and different business logics and application scenarios are unified and integrated, realizing seamless data sharing and linkage, and improving the overall efficiency of tunnel safety management.

[0053] The differences in monitoring systems include: sensor type and data acquisition method, data model and representation method, communication protocol, and / or business logic and application scenario. Specifically:

[0054] Sensor types and data acquisition refer to the fact that different monitoring systems can use different sensors to measure environmental parameters or structural health conditions inside the tunnel. For example, some systems focus on environmental parameters such as temperature and humidity, while others focus on structural health parameters such as stress and displacement. The brands and models of sensors may also vary, resulting in differences in data formats and accuracies.

[0055] Data models and representation methods refer to the fact that the internal data representation methods of each system can be different. For example, timestamp formats (UTC, local time), unit systems (metric, imperial), etc. The data storage structures can also be different. Some systems use relational databases, while others use NoSQL databases or other forms of data warehouses.

[0056] Communication protocols refer to the fact that the communication protocols used between different systems may be different. Some systems perform data transmission based on the TCP / IP protocol stack, while others use more specialized industrial communication protocols such as Modbus, CAN bus, etc. Security and reliability requirements also affect the choice of communication protocols. For example, whether encrypted transmission is required, etc.

[0057] Business logic and application scenarios refer to the fact that the specific business requirements and logic processing flows targeted by different monitoring systems can vary greatly. For example, one system is specifically used for real-time warning, while another focuses on long-term data analysis and trend prediction. Different application scenarios also lead to differences in system design. For example, the monitoring requirements for urban tunnels and mountain tunnels are completely different.

[0058] Furthermore, sensor types include: strain gauges, displacement gauges, crack gauges, anchor stress gauges, convergence meters, temperature sensors, humidity sensors, gas sensors, water level sensors, video surveillance cameras, noise sensors, vibration sensors, and so on.

[0059] Strain gauges are used to measure strain and stress in tunnel linings or surrounding rocks. Strain: The change in length per unit length, usually expressed in microstrain. Stress: Calculated through the elastic modulus of the material, with the unit of Pascal or Megapascal.

[0060] Displacement gauges are used to measure displacement changes in tunnel linings or surrounding rocks. Displacement: The change in position. Settlement: The vertical displacement of a specific point. Convergence deformation: The change in the cross-sectional size of the tunnel.

[0061] Crack gauges are used to monitor the development of cracks. Crack width: The maximum opening distance of the crack. Crack propagation rate: The rate of change of crack width over time.

[0062] Anchor stress gauges are used to measure the axial force of the anchor. Axial force: The tensile force borne by the anchor. Prestress loss: The percentage of the reduction in the prestress of the anchor over time after installation.

[0063] Convergence meter, used to measure the change of the tunnel cross-section; Convergence value: the change amount of the tunnel cross-section size; Convergence rate: the speed of the tunnel cross-section size change.

[0064] Temperature sensor, used to measure the ambient temperature inside the tunnel.

[0065] Humidity sensor, used to measure the relative humidity inside the tunnel; Relative humidity: the percentage of the water vapor content in the air relative to the saturated state.

[0066] Gas sensor, used to detect the concentration of harmful gases inside the tunnel; Concentration: carbon monoxide concentration, carbon dioxide concentration, methane concentration.

[0067] Water level sensor, used to monitor the groundwater level inside the tunnel; Water level height: the height relative to a certain reference plane.

[0068] Video surveillance camera, used to monitor the internal condition of the tunnel in real time; Parameters: image clarity, frame rate; Frame rate: the number of images displayed per second.

[0069] Noise sensor, used to measure the noise level inside the tunnel; Parameter: sound pressure level.

[0070] Vibration sensor, used to monitor the vibration of the surrounding environment of the tunnel; Parameters: vibration acceleration, frequency; Frequency: the frequency range of vibration.

[0071] Aiming at the problems of poor real-time performance of the existing tunnel monitoring technology and difficulty in dealing with sudden safety hazards, in the embodiments of the present invention, various types of sensors are precisely arranged at various key positions of the tunnel and different areas of the support equipment (such as steel arches, anchor bolts) to realize the real-time monitoring of the tunnel environment (such as temperature, humidity) and structural parameters (such as pressure, deformation). Through the Internet of Things technology, a wireless sensor network is arranged to realize the real-time monitoring of the tunnel structure health and environmental parameters, ensure the instant acquisition and transmission of data, and thus be able to discover and handle sudden safety hazards in a timely manner.

[0072] Data transmission module 20, used to transmit multi-dimensional raw data to the cloud server.

[0073] In the embodiments of the present invention, the data transmission module 20 uses wireless communication technologies (such as Wi-Fi, LoRa, NB-IoT) or wired networks (such as optical fibers, Ethernet) to efficiently and stably transmit the collected data to the cloud server.

[0074] The data analysis module 30 is used to align multi-dimensional raw data in terms of time and space on the cloud server, assign weights to the multi-dimensional raw data for data fusion according to the reliability and accuracy of different monitoring systems to obtain fused data; and, update the multi-dimensional raw data through the fused data, classify and / or linearly predict the updated multi-dimensional raw data to obtain a risk classification result and / or a risk linear prediction result.

[0075] Furthermore, the data analysis module 30 is also used to: before aligning the multi-dimensional raw data, perform data verification, anomaly detection, and / or redundancy processing on the multi-dimensional raw data.

[0076] Furthermore, the data verification includes: performing format verification in a preset data format, performing integrity verification based on the integrity of the data packet, and / or performing logical verification based on business rules.

[0077] In the embodiments of the present invention, through format verification, it is ensured that the data conforms to predefined format requirements (such as date format, value range, etc.); by checking whether the data packet is complete, for example, by calculating the checksum or using a hash function to verify whether the data has been tampered with or lost; based on business rules for logical verification, it is ensured that the data is logical, for example, the temperature sensor readings should be within a reasonable range.

[0078] Through data verification, the data integrity is improved: ensuring that all necessary fields exist and are in the correct format, avoiding incorrect analysis caused by missing partial data; enhancing the data credibility: through verification, data that does not meet expectations can be identified and filtered out, reducing the false alarm rate and the missed alarm rate.

[0079] Furthermore, the anomaly detection includes: detecting anomaly points with a preset threshold, detecting deviation conditions based on the data dispersion degree, and / or detecting abnormal fluctuation conditions based on the time series prediction results.

[0080] In the embodiments of the present invention, through the threshold method, reasonable upper and lower threshold values are set to detect anomaly points, and data points outside this range are regarded as anomalies; through statistical methods, statistical quantities such as standard deviation and average value are used to judge whether the data deviates from the normal distribution; through a machine learning model, the model is trained to identify abnormal patterns. For example, a time series prediction model can be used to detect abnormal fluctuations.

[0081] Through anomaly detection, real-time monitoring and early warning are achieved: quickly discovering and responding to potential problems, and taking timely measures to prevent accidents; improving the data accuracy: after removing outliers, the remaining data is closer to the real situation, which helps to make an accurate safety assessment.

[0082] Furthermore, the redundancy processing includes: comparing the data of the same sensor in different monitoring systems in the multi-dimensional raw data, and if the difference exceeds the normal range, triggering an alarm and discarding it.

[0083] The process of redundancy processing includes: multi-source acquisition, data backup, and / or cross-verification.

[0084] Multi-source acquisition: Obtain the same type of data from multiple independent sensors or systems.

[0085] Data backup: Regularly back up important data to prevent loss.

[0086] Cross-verification: Compare data from different sources, and if the differences are too large, trigger an alarm and re-acquire the data.

[0087] Through redundancy processing, data reliability is increased: Even if a certain sensor fails, other sensors can still provide valid information; data continuous availability is guaranteed: Through the backup mechanism, historical data is ensured not to be lost, facilitating subsequent analysis.

[0088] Furthermore, the specific steps of data fusion include: data alignment: Ensure that all data to be fused is aligned in time and space, that is, has the same sampling frequency and geographical location; weight assignment: Assign different weights according to the reliability and accuracy of each data source; fusion algorithm selection: Methods such as weighted average, Kalman filter, and Bayesian estimation can be selected for data fusion; result verification: Conduct secondary verification on the fused data to ensure that it meets the expected quality standards.

[0089] Furthermore, the objects of data fusion include: different data from the same type of sensors, data from different types of sensors, and / or sensor data from different time periods.

[0090] After redundancy processing, data fusion mainly targets the following types of objects:

[0091] Different data from the same type of sensors: For example, the readings of multiple temperature sensors at the same location.

[0092] Data from different types of sensors: Such as combining the analysis of humidity, temperature, and stress changes.

[0093] Sensor data from different time periods: Records over a past period of time need to be integrated for long-term trend analysis.

[0094] The characteristics of the fused data include:

[0095] Higher consistency: By fusing data from multiple independent sources, the deviation caused by the error of a single sensor is reduced, improving the overall data consistency; enhanced accuracy: Data considering multiple factors can often reflect the actual situation better than single-dimensional data, thus improving the precision of the evaluation results; rich information content: The fused data set contains more dimensions of information, which helps to deeply understand the operating state of the system and supports more complex analysis tasks.

[0096] Furthermore, the data analysis module 30 is further configured to: before classifying or linearly predicting the updated multi-dimensional raw data, perform cleaning processing, normalization processing, and / or feature extraction processing on the updated multi-dimensional raw data.

[0097] In the cloud, big data processing technologies and machine learning algorithms can be used to perform preprocessing such as cleaning, normalization, and feature extraction on the updated multi-dimensional raw data, and then perform analysis and modeling to identify potential risks.

[0098] The cleaning processing includes: removing noise in the updated multi-dimensional raw data, filling in missing values, and / or smoothing curves.

[0099] The normalization processing includes: converting sensor data of different scales into a unified standard.

[0100] The feature extraction processing includes: extracting the mean, variance, rate of change, skewness coefficient, and / or kurtosis coefficient of the updated multi-dimensional raw data.

[0101] Furthermore, the process of classifying or linearly predicting the updated multi-dimensional raw data is specifically as follows:

[0102] Classify and / or linearly predict the updated multi-dimensional raw data through a random forest algorithm, a support vector machine algorithm, and / or a long short-term memory network algorithm.

[0103] Random forest algorithm: Used for classification and regression tasks, especially good at dealing with high-dimensional data; train a random forest model using the training set data, set hyperparameters such as the number of trees and the maximum depth, evaluate the model performance through cross-validation or reserving a part of the data for testing, and perform classification or regression prediction on new data based on the trained model.

[0104] Support vector machine algorithm: Used for classification and regression tasks, especially suitable for small sample problems in high-dimensional spaces; select an appropriate kernel function (such as a linear kernel, an RBF kernel) and other hyperparameters, train an SVM model using the training set data, evaluate the model performance through cross-validation or reserving a part of the data for testing, and perform classification or regression prediction on new data based on the trained model.

[0105] Long short-term memory network: Specifically designed for processing time series data and capable of capturing long-term dependencies; design the LSTM network architecture, including the number of layers, the number of neurons in each layer, etc., train the LSTM model using the training set data, optimize the loss function, evaluate the model performance through cross-validation or reserving a part of the data for testing, and predict future data based on the trained model.

[0106] Based on the risk classification results, confirm whether there are structural abnormalities and / or environmental abnormalities in the tunnel. Based on the risk linear prediction results, confirm whether there are risks of structural abnormalities and / or environmental abnormalities in the tunnel.

[0107] The risk monitoring module 40 is used to generate a risk report based on the risk classification result and / or the risk linear prediction result.

[0108] Furthermore, the risk report includes: risk level, risk impact scope, and / or possible causes of the risk.

[0109] The risk monitoring module 40 is also used to: display the updated multi-dimensional original data and / or risk report in real time through the front-end large screen and / or mobile terminal device through visualization tools; return the updated multi-dimensional original data to the back end through the RPC protocol, call the corresponding tunnel, geological structure, and / or support model, and generate a corresponding two-dimensional or three-dimensional model.

[0110] In the embodiment of the present invention, the visualization software can use open source visualization software such as Grafana, Superset, ArcGIS and other software, display devices (such as large-screen displays, mobile phones, tablets, computers, etc.). By inputting updated multi-dimensional raw data and / or risk reports, the risk monitoring display interface (processing the detection data into box plots, histograms, scatter plots, pie charts and other required forms for display through visualization devices, or linking the monitored data with the original tunnel model to generate a tunnel risk model for display), real-time risk dynamics and trend analysis are provided.

[0111] Furthermore, through risk assessment software and / or assessment guidelines and standards, input: risk assessment report and risk monitoring display interface; output: risk assessment report, including risk level, construction risk prediction, risk priority, etc. According to industry standards and experience, detailed risk assessment requirements and grading standards are formulated, and then the risks of tunnel environment and structure are objectively evaluated based on these standards.

[0112] Furthermore, through the early warning system (early warning device, if there is a front-end large screen display, the early warning is issued through the front-end large screen, and other notifications are issued through notification devices) and notification devices (such as SMS, email, APP push), input: monitoring parameter information and risk assessment report; output: risk early warning report, including warning level, warning reason, recommended measures, related cases, etc. By setting thresholds and early warning rules, when the risk level output by the risk assessment reaches or exceeds these thresholds or meets the set risk conditions, the system automatically triggers the early warning mechanism and generates a risk early warning report.

[0113] Further, through the support design software and geological exploration data, input: support monitoring data, early warning reports, evaluation reports; output: support plans, including support types, locations, quantities, construction sequences, etc. Based on the risk assessment results and risk early warning reports, combined with factors such as the tunnel geological conditions, as well as the original data stored in the cloud and the construction progress, a scientific and reasonable support plan is formulated.

[0114] Further, through the automated support equipment and monitoring system, input: support plan; output: status data after the installation of support equipment, and further improvement of tunnel structure and environmental parameters. Use automated support equipment (such as intelligent bolt installation machines, grouting machines, automated steel arch construction equipment, etc.) to carry out tunnel support or additional support according to the support plan.

[0115] Through the above steps, the present invention realizes comprehensive monitoring, evaluation, early warning and support decision-making of the tunnel environment and structure, providing a strong guarantee for the safety and efficiency of tunnel construction.

[0116] The technical solutions in the embodiments of the present invention have the following beneficial effects compared with the prior art:

[0117] Real-time: Using the Internet of Things technology to realize real-time collection and transmission of tunnel data; High efficiency: Through data processing and analysis, improve the efficiency of tunnel risk management; Security: Ensure the integrity, consistency, accuracy and reliability of data, and reduce the risk of safety accidents; Economic benefits: Optimize the support plan and reduce project costs; Social benefits: Improve the management level of tunnel projects and ensure the safety of people's lives and property.

[0118] The technical solutions in the embodiments of the present invention, through the Internet of Things technology, the present invention can realize 24-hour uninterrupted tunnel monitoring, greatly shortening the discovery time of potential safety hazards and improving the emergency response speed; The application of the integrated platform eliminates information islands, realizes the maximum utilization of data, and enhances the synergy effect of tunnel safety management; Through the application of data processing and analysis algorithms, the risk assessment is more accurate, which helps to early warn potential safety risks and reduce the accident rate.

[0119] Embodiment 2

[0120] Figure 2 is a schematic flow chart of a tunnel risk management method based on the Internet of Things according to Embodiment 2 of the present invention. As Figure 2 shown, the method includes:

[0121] Through the standardized data interface, obtain the sensor data in the tunnel collected by different monitoring systems to obtain multi-dimensional original data;

[0122] Transmit the multi-dimensional original data to the cloud server;

[0123] The cloud server aligns multi-dimensional raw data in terms of time and space, assigns weights to the multi-dimensional raw data according to the reliability and accuracy of different monitoring systems for data fusion, and obtains fused data; and updates the multi-dimensional raw data through the fused data, classifies and / or linearly predicts the updated multi-dimensional raw data to obtain a risk classification result and / or a risk linear prediction result.

[0124] Generate a risk report based on the risk classification result and / or the risk linear prediction result.

[0125] The technical solution in the embodiment of the present invention monitors in real time through the Internet of Things technology and accurately warns of potential security risks through intelligent analysis technology, improving the overall level of tunnel risk management, and having significant technical effects and social and economic benefits.

[0126] Embodiment III

[0127] Figure 3 It is a schematic structural diagram of an electronic device for implementing the method for tunnel risk management based on the Internet of Things in the embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0128] As Figure 3 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0129] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0130] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the Internet of Things-based tunnel risk management method.

[0131] In some embodiments, the Internet of Things-based tunnel risk management method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the Internet of Things-based tunnel risk management method described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the Internet of Things-based tunnel risk management method by any other suitable means (e.g., by means of firmware).

[0132] The various embodiments of the systems and technologies described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special or general programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0133] A computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, a special purpose computer, or other programmable data processing device, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.

[0134] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0135] In order to provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0136] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected with each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0137] The computing system can include a client and a server. The client and the server are generally remote from each other and typically interact via a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0138] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0139] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A tunnel risk management system based on the Internet of Things, characterized in that: include: The data acquisition module is used to obtain sensor data in the tunnel collected by different monitoring systems through a standardized data interface to obtain multi-dimensional raw data; A data transmission module, used for transmitting the multi-dimensional original data to a cloud server; A data analysis module is used to align the multidimensional raw data in time and space on a cloud server, assign weights to the multidimensional raw data according to the reliability and accuracy of the different monitoring systems, and perform data fusion to obtain fused data; and, through the fused data, update the multidimensional raw data, classify and / or linearly predict the updated multidimensional raw data, and obtain a risk classification result and / or a risk linear prediction result; The risk monitoring module is used to generate a risk report based on the risk classification results and / or risk linear prediction results.

2. The system according to claim 1, characterized in that The differences in the monitoring systems include: sensor type and data collection method, data model and representation method, communication protocol, and / or business logic and application scenario.

3. The system according to claim 2, characterized in that The sensor types include: strain gauges, displacement gauges, crack gauges, anchor stress gauges, convergence gauges, temperature sensors, humidity sensors, gas sensors, water level sensors, video surveillance cameras, noise sensors, and / or vibration sensors.

4. The system according to claim 1, characterized in that The data analysis module is further used to: perform data verification, anomaly detection, and / or redundancy processing on the multi-dimensional raw data before aligning the multi-dimensional raw data; The data verification includes: performing format verification based on a preset data format, performing integrity verification based on the integrity of the data packet, and / or performing logic verification based on business rules; The anomaly detection includes: detecting anomalies with a preset threshold, detecting deviations with data dispersion, and / or detecting abnormal fluctuations with time series prediction results; The redundant processing includes: comparing the same sensor data of different monitoring systems in the multi-dimensional original data, and if the difference exceeds the normal range, triggering an alarm and discarding the data.

5. The system according to claim 1, characterized in that The objects of the data fusion include: different data from sensors of the same type, data from sensors of different types, and / or sensor data of different time periods.

6. The system according to claim 1, characterized in that The data analysis module is further used to: perform cleaning processing, standardization processing, and / or feature extraction processing on the updated multidimensional original data before classifying or linearly predicting the updated multidimensional original data; The cleaning process includes: removing noise from the updated multi-dimensional raw data, filling missing values, and / or smoothing curves; The standardization process includes: converting sensor data of different scales into a unified standard; The feature extraction process includes: extracting the mean, variance, rate of change, skewness coefficient, and / or kurtosis coefficient of the updated multi-dimensional original data.

7. The system according to claim 1, characterized in that The process of classifying or linearly predicting the updated multi-dimensional original data is specifically as follows: Classifying or linearly predicting the updated multidimensional raw data by using a random forest algorithm, a support vector machine algorithm, and / or a long short-term memory network algorithm; Based on the risk classification results, confirm whether there are structural anomalies and / or environmental anomalies in the tunnel; and / or, Based on the risk linear prediction results, confirm whether there are risks of structural abnormalities and / or environmental abnormalities in the tunnel.

8. The system according to claim 1, characterized in that The risk report includes: risk level, risk impact scope, and / or possible cause of the risk.

9. The system according to claim 1, characterized in that The risk monitoring module is also used to: display the updated multi-dimensional original data and / or the risk report in real time through a front-end large screen and / or a mobile terminal device through a visualization tool; return the updated multi-dimensional original data to the back end through the RPC protocol, call the corresponding tunnel, geological structure, and / or support model, and generate a corresponding two-dimensional or three-dimensional model.

10. A tunnel risk management method based on the Internet of Things, applied to the tunnel risk management system based on the Internet of Things as claimed in any one of claims 1 to 9, characterized in that: include: Through standardized data interfaces, sensor data collected by different monitoring systems in the tunnel are obtained to obtain multi-dimensional raw data; Transmitting the multi-dimensional raw data to a cloud server; The multidimensional raw data are aligned in time and space on the cloud server, and weights are assigned to the multidimensional raw data according to the reliability and accuracy of the different monitoring systems to perform data fusion to obtain fused data; and the multidimensional raw data are updated through the fused data, and the updated multidimensional raw data are classified and / or linearly predicted to obtain risk classification results and / or risk linear prediction results; A risk report is generated based on the risk classification results and / or risk linear prediction results.

Images