Railway tunnel environment monitoring system and method based on Internet of Things

Abstract

The invention discloses a railway tunnel environment monitoring system and method based on the Internet of Things, and relates to the technical field of data monitoring and management.The railway tunnel environment monitoring method includes the steps that potential risks can be recognized in advance by analyzing historical monitoring data and evaluating the dynamic environment abnormal risk of a tunnel; acquiring a risk prediction result in real time and performing early warning by training an anomaly prediction model; when new monitoring data is input, abnormal risk parameters are captured through automatic comparison, and early warning information is output; by marking the abnormal risk and evaluating the risk level, the severity of the risk can be clearly identified, the sweep range and the weight of the abnormal risk are set based on the risk level, various processing strategies are set, different degrees of abnormities are effectively dealt with, and the dealing efficiency is improved. Automatic monitoring and intelligent management of the railway tunnel are realized, so that the monitoring precision and risk early warning capability of the tunnel dynamic environment are effectively improved, safe operation of the tunnel is ensured, and accidents are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of data monitoring and management, and in particular to a railway tunnel environment monitoring system and method based on the Internet of Things. Background Art

[0002] With the continuous advancement of transportation construction at this stage, the number of long tunnels and extra-long tunnels is increasing. With the increase in traffic volume in tunnels, the concentration of tunnel pollutants has also increased year by year. The traditional tunnel operation control method can no longer meet the needs. In order to save the operating costs of railway tunnels, it is necessary to collect environmental parameters in tunnels to realize intelligent operation control of tunnels. In addition, the collection and processing of environmental parameters of railway tunnels is related to the safe operation of tunnels, and plays an important role in realizing intelligent transportation in tunnels and ensuring driving safety.

[0003] During the operation of the public mobile network along the railway, the public network equipment cavern is an important infrastructure in the environmental monitoring of the railway tunnel. The stability of its dynamic environment is directly related to the operating efficiency of the public mobile network along the entire line. Traditional monitoring methods mostly rely on manual inspections, which are not only inefficient, but also difficult to achieve real-time monitoring of tunnel environmental parameters and rapid response to abnormal situations. With the development of technology, automated and intelligent monitoring systems have gradually become the mainstream of railway tunnel monitoring. The railway tunnel environmental monitoring system based on the Internet of Things proposed in the present invention improves monitoring efficiency and accuracy through centralized monitoring and analysis and processing capabilities, thereby ensuring the stable operation and safety of railway tunnels.

[0004] In summary, how to more accurately monitor the abnormal risk parameters of the railway tunnel dynamic environment and respond to abnormal situations in a timely manner is an issue that needs to be urgently solved and optimized in the railway tunnel environment monitoring system based on the Internet of Things. Summary of the invention

[0005] The present invention provides a railway tunnel environment monitoring system and method based on the Internet of Things, which solves the technical problem of how to improve the monitoring efficiency and accuracy of the railway tunnel dynamic environment and respond to and handle abnormal situations in a timely manner.

[0006] In order to solve the above technical problems, the present invention provides a railway tunnel environment monitoring system and method based on the Internet of Things. The specific technical solutions are as follows:

[0007] In a first aspect, a railway tunnel environment monitoring method based on the Internet of Things comprises:

[0008] Obtain historical monitoring data of railway tunnels to obtain abnormal risk parameters of the dynamic environment;

[0009] wherein, based on the historical monitoring data, a variety of power environment parameters are obtained;

[0010] Set a variety of abnormal risk indicators;

[0011] Comparing the power environment parameter with the abnormal risk index to obtain a comparison difference parameter; the comparison difference parameter is the potential abnormal risk parameter;

[0012] The potential abnormal risk parameters are evaluated to obtain the abnormal risk parameters of the power environment; wherein, when there is an error in the monitored potential abnormal risk parameter data, the real abnormal risk parameters are obtained by comparing the difference parameters, and the abnormal risk degree is evaluated according to the set threshold range;

[0013] Based on the abnormal risk parameters, abnormal risk marks are respectively marked; risk level assessment is performed on abnormal risk parameters with different abnormal risk marks; based on the assessment results, abnormal level data of the abnormal risk parameters is obtained;

[0014] Among them, the electromagnetic vector field is obtained through sensors and tunnel boundary conditions, and the wave mode cladding is constructed to obtain the charge density and current density on the dielectric interface to obtain the electromagnetic wave propagation constant; when the propagation constant is close to 0 and the direction is perpendicular or parallel to the ground, the tunnel propagation is judged to be abnormal and the dynamic environment risk is evaluated;

[0015] Construct a data set with historical monitoring data and multiple abnormal risk parameters to train an abnormal prediction model; obtain the abnormal risk prediction results of the tunnel dynamic environment through the abnormal prediction model; respond to the preset warning threshold according to the prediction results and output warning information;

[0016] Based on the prediction results and early warning information, the scope of abnormal risk parameters is determined and the abnormal risk weight is obtained; based on the abnormal risk weight, a variety of abnormal handling strategies are formulated.

[0017] As a further optimization scheme of the present invention, the tunnel electromagnetic vector field is obtained by combining the sensor with the boundary conditions of the tunnel; according to the obtained tunnel electromagnetic vector field, the railway tunnel is constructed into a wave mode envelope; in the wave mode envelope, the charge density p and the current density j are equal, that is, ; In the formula, k represents the spatial frequency of the radio wave, represents the partial differential symbol, and t represents the current time node;

[0018] According to the equality of the charge density p and the current density j, the unit normal vectors of the interface between the two media of charge density and current density are obtained; according to the unit normal vectors of the two media, the free charge surface density and the conduction current surface density on the interface between the media are obtained;

[0019] According to the free charge surface density P and the conduction current surface density J, by ; to obtain the propagation constant of electromagnetic waves in free space; where k0 represents the propagation constant of electromagnetic waves in free space, represents the wavelength of electromagnetic waves, k P represents the spatial frequency of the free charge surface density, k J represents the spatial frequency of the conduction current surface density;

[0020] When the electromagnetic wave propagation constant approaches 0 during free space transmission and propagates approximately perpendicularly or parallel to the ground, the electromagnetic wave propagates normally in the railway tunnel environment; otherwise, the normal propagation of electromagnetic waves in the railway tunnel environment is questionable, which will cause the wireless channel state to be in a risky state; and then the abnormal risk parameters of the dynamic environment are obtained.

[0021] As a further optimization scheme of the present invention, the power environment parameters are compared with the abnormal risk index to obtain comparison difference parameters, including:

[0022] The dynamic environment parameter represents various parameter data of the environmental operation status in the railway tunnel; the abnormal risk index represents the risk standard value of abnormality in various parameter data of the environmental operation status in the railway tunnel;

[0023] Preprocessing a plurality of the dynamic environment parameters to obtain a standardized data set;

[0024] The railway tunnel operation data at each time node of the standardized data set is , to obtain a comparison difference parameter, wherein a plurality of the comparison difference parameters constitute a difference index;

[0025] In the formula, Di represents the ith comparison difference parameter, n represents the number of dynamic environment parameters, and x i represents the ith dynamic environment parameter, y i Represents the abnormal risk index corresponding to the i-th dynamic environment parameter.

[0026] As a further optimization scheme of the present invention, the potential abnormal risk parameters are evaluated to obtain abnormal risk parameters of the power environment, including:

[0027] When there is an error in the monitoring data and a comparison difference parameter is generated, the obtained comparison difference parameter is obtained through , to obtain the real abnormal risk parameter, which is the abnormal risk parameter of the power environment; R t represents the true abnormal risk parameter, w i represents the real abnormal weight, and n represents the number of comparison difference parameters; the comparison difference parameters are the potential abnormal risk parameters;

[0028] By setting the abnormal risk threshold range [T i , Tj ],pass To obtain the abnormal risk degree of the abnormal risk parameter of the power environment; where R t (T) represents the abnormal risk degree of the real abnormal risk parameter, K represents the abnormal risk degree assessment weight, and t represents t real abnormal risk parameters;

[0029] When R t (T)<T i , then the abnormal risk of the abnormal risk parameter of the dynamic environment is at low risk; when T i <R t (T)<T j , then the abnormal risk of the abnormal risk parameter of the dynamic environment is at medium risk; when R t (T)>T j , then the abnormal risk degree of the abnormal risk parameters of the dynamic environment is at high risk.

[0030] As a further optimization solution of the present invention, the abnormality prediction model includes:

[0031] Constructing a data set of historically acquired monitoring data and a plurality of abnormal risk parameters to generate structured data, encoding the structured data into sequence data to train the abnormality prediction model;

[0032] The sequence data is input into the abnormal prediction model; the abnormal prediction model includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, and the intermediate representation data of multiple hidden layers are transmitted to the output layer, and the output layer output represents the abnormal risk prediction result of the railway tunnel dynamic environment;

[0033] At least one data item in the newly acquired railway tunnel monitoring data is input into the abnormality prediction model, and the output layer outputs the abnormal risk prediction result of the dynamic environment parameter in the newly acquired railway tunnel monitoring data.

[0034] As a further optimization scheme of the present invention, in response to a preset warning threshold, and outputting warning information, the method includes:

[0035] Based on the prediction results of the abnormal prediction model, and according to different abnormal risk levels of the power environment abnormal risk parameters, a warning threshold is set; based on the preset warning threshold, a corresponding alarm response mechanism is designed to quickly respond to abnormal situations and issue a response alarm;

[0036] When in a low-risk abnormal situation, the alarm response mechanism flashes the alarm light once every preset time interval, and continuously monitors the abnormal risk state of the power environment parameters at the node where the alarm light flashes. When the low-risk abnormal situation has an upward trend in risk at the tth time node, the preset time interval of the alarm light flashing is shortened;

[0037] When in a medium-risk abnormal situation, the alarm response mechanism flashes the alarm light at no time interval, accompanied by an alarm sound at a preset time interval, and records the abnormal risk parameter information at the current time node, and regularly evaluates the risk trend of the acquired abnormal risk parameter information at a preset time period to determine whether there is a deteriorating risk situation at the t+1 time node;

[0038] When in a high-risk abnormal situation, the alarm response mechanism sends out early warning alarms at no time intervals through alarm lights and sirens, sets high-risk abnormal railway tunnel sections, closes the railway tunnel sections corresponding to the current time node, and conducts secondary surveys to avoid frequent abnormal risks in multiple sections of the railway.

[0039] As a further optimization scheme of the present invention, based on the prediction results and warning information of the abnormal prediction model, the abnormal risk scope of the abnormal risk parameter is obtained, including:

[0040] The actual abnormal risk parameter is To obtain the abnormal risk impact measurement value corresponding to the real abnormal risk parameter; where, Indicates the abnormal risk and measurement value, The normal dynamic environment parameters representing the predicted results, Indicates the dynamic environment parameters;

[0041] Establish three-dimensional spatial coordinates in the railway tunnel, obtain any number of spatial coordinate points in each quadrant of the coordinate system, and respectively , to obtain the three-dimensional space abnormal risk spread range of the abnormal risk spread measurement value;

[0042] In the formula, represents the scope of abnormal risk, K represents the spatial kernel function, N represents the number of spatial coordinate points, and x r ,y r and z r They respectively represent the three-dimensional coordinates of the r-th coordinate point.

[0043] As a further optimization solution of the present invention, the abnormal risk scope of the abnormal risk parameter further includes:

[0044] when is abnormal if and only if ;Right now , to obtain the abnormal risk spread time node range of the abnormal risk spread measurement value; where, Indicates the scope of abnormal risk at the tth time node, represents the normal risk parameter threshold of the power environment; t i and tj Represent the i-th and j-th abnormal risk time nodes respectively;

[0045] Based on the three-dimensional space abnormal risk spread range and the abnormal risk spread time node range, according to , to obtain the upper and lower limits of the abnormal risk range, according to Adjust the factors to dynamically adjust the upper and lower limits of the abnormal risk range.

[0046] As a further optimization scheme of the present invention, according to the abnormal risk spread range, the abnormal risk weight of the abnormal risk parameter is determined, and according to the abnormal risk weight corresponding to the abnormal risk parameter of the power environment, a plurality of abnormal handling strategies are set, including:

[0047] Based on the extent of the impact and severity of each risk factor, Abnormal risk weights are assigned to the severity of different risk factors; where: represents the abnormal risk weight of the abnormal risk parameter pi, Represents an exception enabling function;

[0048] Plan an exception handling strategy based on the abnormal risk weight, abnormal risk impact scope and abnormal risk parameter level;

[0049] The exception handling strategy includes: for low risk levels, monitoring, recording and early warning measures can be taken, and no immediate intervention is required; for medium risk levels, manual monitoring is increased, system parameters are adjusted or local repairs are performed; for high risk levels, an emergency response mechanism is activated, global intervention, shutdown or isolation of the faulty area is performed.

[0050] In a second aspect, the system is provided with an electronic device including a memory, a processor, and a railway tunnel environment monitoring method program based on the Internet of Things stored in the memory and executable on the processor, wherein the railway tunnel environment monitoring method program based on the Internet of Things implements the steps of a railway tunnel environment monitoring method based on the Internet of Things when executed by the processor, and the system includes:

[0051] Data acquisition module: It is used to obtain historical monitoring data of railway tunnels to obtain abnormal risk parameters of dynamic environment;

[0052] Data identification module: it is used to obtain multiple power environment parameters based on historical monitoring data; set multiple abnormal risk indicators; compare the power environment parameters with the abnormal risk indicators to obtain comparison difference parameters; the comparison difference parameters are potential abnormal risk parameters; evaluate the potential abnormal risk parameters to obtain power environment abnormal risk parameters; based on the acquired power environment abnormal risk parameters, mark abnormal risk marks respectively; evaluate the risk level of abnormal risk parameters with different abnormal risk marks; based on the evaluation results, obtain abnormal level data of abnormal risk parameters;

[0053] Early warning response module: It is used to construct a data set with historically acquired monitoring data and multiple abnormal risk parameters to train an abnormal prediction model; obtain new monitoring data and input the new monitoring data into the abnormal prediction model to obtain the abnormal risk prediction result of the tunnel power environment; respond to the preset early warning threshold according to the abnormal risk prediction result of the tunnel power environment and output early warning information;

[0054] Abnormality handling module: It is used to obtain the abnormal risk scope of the abnormal risk parameters based on the prediction results and warning information of the abnormal prediction model; to judge the abnormal risk weight of the abnormal risk parameters according to the abnormal risk scope; and to set a variety of abnormality handling strategies according to the abnormal risk weight corresponding to the abnormal risk parameters of the power environment.

[0055] The present invention has at least the following beneficial effects: by analyzing historical monitoring data, the present invention can accurately extract potential abnormal risk parameters, and evaluate the abnormal risk of the tunnel's dynamic environment based on these parameters, which helps to identify possible risks in advance.

[0056] By training the abnormal prediction model, the abnormal risk prediction results of the tunnel's dynamic environment can be obtained in real time. When new monitoring data is input, the system can automatically compare and output warning information, thereby achieving early warning and dynamic monitoring, reducing the possibility of sudden events.

[0057] Marking abnormal risks and assessing their risk levels can help more clearly identify the severity of different risks. Determine the scope and risk weight of different abnormal risks based on risk levels, and provide a quantitative basis for subsequent risk management and processing.

[0058] According to the weights corresponding to the abnormal risk parameters, a variety of targeted abnormality handling strategies can be set to ensure that preventive measures are taken for abnormalities of different degrees and improve response efficiency.

[0059] By establishing an abnormality prediction system based on historical data and models, the automated monitoring and intelligent management of railway tunnels are realized, the decision-making process is optimized, and the management efficiency and safety are improved. This method can effectively improve the monitoring accuracy of the tunnel dynamic environment, enhance the risk warning capability, provide a scientific basis for tunnel management, reduce the possibility of accidents, and ensure the safe operation of railway tunnels. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a schematic flow chart of a railway tunnel environment monitoring method based on the Internet of Things provided by an embodiment of the present invention;

[0061] Figure 2 Schematic diagram of a railway tunnel environment monitoring system based on the Internet of Things provided by an embodiment of the present invention;

[0062] Figure 3 It is a model diagram of railway tunnel monitoring points provided by an embodiment of the present invention;

[0063] Figure 4 is a schematic diagram of connection between a monitoring device and a monitoring host provided by an embodiment of the present invention;

[0064] Figure 5 This is the processing flow when the monitoring platform provided by the embodiment of the present invention detects an abnormal situation. DETAILED DESCRIPTION

[0065] The present application is further described in detail below in conjunction with the accompanying drawings. It is necessary to point out here that the following specific implementation methods are only used to further illustrate the present application and cannot be understood as limiting the scope of protection of the present application. Technical personnel in this field can make some non-essential improvements and adjustments to the present application based on the above application content.

[0066] This embodiment provides a railway tunnel environment monitoring system and method based on the Internet of Things, and the specific implementation methods are as follows:

[0067] like Figure 1 As shown, a railway tunnel environment monitoring method based on the Internet of Things includes the following steps:

[0068] Step 11, obtaining historical monitoring data of the railway tunnel to obtain abnormal risk parameters of the power environment;

[0069] Step 12, wherein a plurality of power environment parameters are obtained based on historical monitoring data;

[0070] Set a variety of abnormal risk indicators;

[0071] Comparing the power environment parameter with the abnormal risk index to obtain a comparison difference parameter; the comparison difference parameter is the potential abnormal risk parameter;

[0072] Evaluating the potential abnormal risk parameters to obtain abnormal risk parameters of the power environment;

[0073] Based on the acquired power environment abnormal risk parameters, abnormal risk marks are respectively marked;

[0074] Conduct risk level assessment on abnormal risk parameters of different abnormal risk markers;

[0075] Based on the evaluation results, abnormal level data of abnormal risk parameters are obtained;

[0076] Step 13, constructing a data set with historically acquired monitoring data and a variety of abnormal risk parameters to train an abnormal prediction model; obtaining new monitoring data, inputting the new monitoring data into the abnormal prediction model to obtain a tunnel power environment abnormal risk prediction result; responding to a preset warning threshold according to the tunnel power environment abnormal risk prediction result, and outputting warning information;

[0077] Step 14, based on the prediction results and warning information of the abnormal prediction model, to obtain the abnormal risk impact range of the abnormal risk parameter; according to the abnormal risk impact range, to determine the abnormal risk weight of the abnormal risk parameter; according to the abnormal risk weight corresponding to the abnormal risk parameter of the power environment, set a variety of abnormal handling strategies.

[0078] like Figure 4 As shown, in step 11, multiple environmental sensors, power consumption detection devices, perimeter intrusion alarms, and image acquisition devices are installed in the public network equipment cavern and equipment monitoring port of the railway tunnel, so that multiple monitoring devices can effectively cover all effective areas in the entire cavern;

[0079] The environmental sensor is used to monitor the temperature, humidity, air pressure, wind speed and other environmental parameters in the cave; the power consumption detection device is used to monitor the power consumption of public network equipment in the cave; the perimeter intrusion alarm device is used to detect whether there is any illegal intrusion around the cave; the image acquisition device is used to monitor the situation in the cave in real time and record video data;

[0080] The environmental sensors include temperature and humidity sensors, water immersion sensors, intelligent air conditioning sensors, meteorological sensors, liquid level sensors, and smoke sensors. By monitoring various environmental parameters in the tunnel in real time, the environmental conditions in the cavern can be fully understood. The intelligent air conditioning sensor can automatically adjust the operating status of the air conditioner according to changes in temperature and humidity to maintain a constant temperature and humidity environment in the cavern cabinet. The meteorological sensor is used to monitor meteorological changes outside the cavern, such as wind speed, air pressure, etc., so as to adjust the environment in the cavern in time. The liquid level sensor is used to monitor the water accumulation in the cavern. Once an abnormality is found, the drainage system can be immediately activated to prevent damage to the equipment. The smoke sensor is used to monitor in real time whether there is a fire risk in the cavern. Once smoke is detected, the alarm system will be immediately activated to ensure the safe evacuation of personnel.

[0081] The power consumption detection device includes power on / off monitoring, intelligent circuit breaker monitoring, voltage-stabilized power supply monitoring, power meter, smart meter, and battery monitoring. Power on / off monitoring can monitor the current and voltage changes of the power supply system equipment in the cave in real time to ensure stability and safety. The intelligent circuit breaker monitoring device can monitor the on / off status of the circuit in real time. Once an abnormality is found, the power supply can be cut off immediately to prevent the circuit fault from expanding. The voltage-stabilized power supply monitoring device ensures the stability of the power supply voltage to avoid damage to the equipment due to voltage fluctuations. The power meter and smart meter are used to accurately measure power consumption, which is convenient for energy management and cost control. The battery monitoring device monitors the charge and discharge status of the battery in real time to ensure that the battery can provide a stable backup power supply in an emergency. Through the comprehensive use of these power consumption detection devices, the centralized monitoring system for the dynamic environment of the public network equipment cave in the railway tunnel can effectively prevent and reduce power failures.

[0082] The perimeter intrusion alarm device can cover the entire area around the cavern to ensure timely detection and response to any illegal intrusion. The device usually includes a door magnetic switch, sound and light alarm, infrared microwave detection, infrared beam, vibration detection, electronic fence, etc., which can detect different types of intrusion and send alarm information to the monitoring platform. In addition, the system may also be equipped with an access control system to further enhance security protection. The access control system can record the information of people entering and leaving the cavern to ensure that only authorized personnel can enter the cavern, thereby improving the overall safety management level.

[0083] The monitoring range of the image acquisition device is the key area where the public network equipment chamber of the railway tunnel and the equipment installed therein are located.

[0084] All monitoring devices are connected to the monitoring host through the port. The monitoring host is the IoT data acquisition gateway terminal, which is responsible for collecting and processing the data sent by the field equipment. The host has functions such as video and data acquisition, data processing, protocol conversion, linkage control, and alarm management. It supports wired networks and can still run independently, store data, and perform linkage control when the network is interrupted. The data acquisition terminal uploads the collected data, processed results, alarm information, etc. to the monitoring platform equipment.

[0085] The monitoring host has powerful data processing capabilities and can analyze the collected environmental parameters, power consumption data, and image data in real time to detect abnormal situations in a timely manner. The monitoring host also has a remote control function and can automatically adjust the operating status of the equipment according to the monitoring data, such as adjusting the air conditioning temperature, starting the drainage system, etc., to adapt to environmental changes. In addition, the monitoring host can also transmit data and alarm information to the remote monitoring center in real time through the network to achieve remote monitoring and management.

[0086] The monitoring data obtained from multiple data interfaces are sent to the monitoring platform via the front-end monitoring host. The monitoring platform is used to summarize the data sent by the monitoring hosts in all caverns in the area to achieve data sharing and system integration. At the same time, it has intelligent analysis functions, which can predict potential risks and issue early warnings based on historical data and real-time data.

[0087] The monitoring platform has a user-friendly interface that can intuitively display the environmental conditions and equipment operating status of the tunnel, making it easy for operators to quickly understand the on-site situation. The monitoring platform also has data storage and historical data analysis functions, which can record and analyze long-term monitoring data to provide a scientific basis for the maintenance and management of railway tunnels. Through data mining and pattern recognition technology, the monitoring platform can identify abnormal change trends in environmental parameters and provide support for preventive maintenance.

[0088] In the implementation of the present invention, based on the power environment monitoring data obtained in step 11, a plurality of power environment monitoring data are preprocessed to obtain standardized monitoring data;

[0089] Define abnormal risk indicators based on pre-processed historical monitoring data and experience values. For example:

[0090] Set threshold ranges: Based on statistical methods (such as the 3σ rule) or domain knowledge; define specific danger zones or fluctuation standards; abnormal risk indicators can be divided into univariate and multivariate:

[0091] Univariate: Based on independent assessment of each dynamic parameter;

[0092] Multivariate: Consider the interactive relationship of multiple dynamic parameters.

[0093] Set the univariate abnormal risk index T, through ; In the formula, μ represents the mean vector of the parameters, σ represents the standard deviation, and k represents a constant (usually 2 or 3);

[0094] Multivariate indicators through ; In the formula, X represents the dynamic environment parameter vector,

[0095] Σ represents the covariance matrix; D 2 represents the multivariate abnormal risk indicator;

[0096] Compare the power environment parameter vector X with the risk index T one by one; if X>T or X<T, record the abnormal difference; the comparison difference parameter is expressed as ΔX=XT; if X exceeds the upper and lower threshold ranges, it is considered abnormal and the ΔX comparison difference parameter value is recorded; the comparison difference parameter ΔX in the previous step is used as a potential abnormal risk parameter; these parameters are preliminarily screened and classified to determine their sources.

[0097] Further analyze potential abnormal risk parameters to determine their severity and scope of impact; use statistical analysis, machine learning or model prediction methods to assess their possible consequences;

[0098] According to the abnormal risk parameters of the power environment, set risk tags (such as low risk, medium risk, high risk); this can be achieved through rules or classification algorithms;

[0099] Based on the risk markers, a specific assessment is made of its level; the assessment can be based on multiple dimensions, such as: frequency of occurrence, degree of impact, and controllability; based on the aforementioned assessment, the assessment results are output for subsequent decision support or exception handling.

[0100] Step 13 obtains the pre-processed power environment historical monitoring data and various abnormal risk parameters through step 12, and establishes a training data set including input features and corresponding abnormal results.

[0101] Input features: including tunnel dynamic environment parameters (such as vibration, acceleration, temperature, pressure, displacement, etc.); target variables (labels): abnormal risk parameters (such as fluctuations exceeding the threshold, abnormal levels, potential risk markers); the data set is used to train the machine learning model after feature engineering (such as feature selection, dimensionality reduction, and normalization).

[0102] By using historical data to reflect actual conditions, the model can more accurately predict future risks; by combining multi-dimensional parameters and historical samples, the model can adapt to complex environments and predict more potential anomalies; by using RNN (recurrent neural network) or LSTM (long short-term memory network), it is suitable for time series data prediction;

[0103] Real-time monitoring data (such as the latest data obtained by sensors) is used as input and substituted into the trained anomaly prediction model for inference; the model outputs the abnormal risk prediction results, including: the possibility of abnormality (such as probability value or classification result); abnormality level (low risk, medium risk, high risk); through the rapid prediction of new data, abnormality identification can be completed in a short time; the trained model is automatically updated and continuously optimized according to the dynamic monitoring data; based on the prediction results, it is determined whether to trigger an early warning. Set multi-level early warning thresholds: low-risk early warning: prompt potential risks, medium-risk early warning: recommend preventive measures, high-risk early warning: enforce emergency handling; if the prediction result exceeds the early warning threshold, output early warning information: including abnormal parameters, degree of abnormality, possible scope of impact; risk avoidance: take effective measures before the problem escalates; flexible response: different levels of early warnings allow hierarchical processing to improve resource allocation efficiency. According to the prediction results, combined with the distribution characteristics of abnormal parameters in space or time, estimate the scope of abnormal impact; determine the scope of impact through models or rules:

[0104] Spatial scope: the geographical area or equipment range affected by the abnormal parameters (such as the specific location of the tunnel);

[0105] Time range: The time window during which the anomaly may persist.

[0106] It can help you to know the scope of abnormal impact more clearly and avoid false positives or false negatives. It can help you to find the problem area quickly and reduce the response time. It can calculate the abnormal risk weight by combining the abnormal scope, abnormal level, and probability of occurrence: ; In the formula, W represents the abnormal risk weight, P represents the probability of abnormal occurrence (the probability value predicted by the model), S represents the scope of the abnormality (such as the area of ​​the spatial region or the number of affected devices), and I represents the degree of abnormal impact (such as the possible economic loss or the degree of equipment damage); the higher the risk weight, the higher the priority of the processing strategy is required, and resources are allocated according to the weight to deal with the most critical risks; multiple factors are introduced through the calculation of multiple risk weights to make the decision more reasonable.

[0107] Develop treatment strategies based on risk weights, including: low risk: observation or lightweight treatment (such as adjusting parameters), medium risk: preventive intervention (such as increasing monitoring frequency, strengthening inspections), high risk: emergency treatment (such as immediately stopping construction, initiating emergency plans); allocate limited resources to where they are most needed; dynamically adjust treatment plans based on real-time predictions and weights.

[0108] The above steps work together to accurately extract potential abnormal risk parameters and evaluate the abnormal risk of the tunnel's dynamic environment by analyzing historical monitoring data, so that possible risks can be identified in advance. By training the abnormal prediction model, the risk prediction results can be obtained in real time and early warning can be issued to reduce the occurrence of emergencies. When new monitoring data is input, the system can automatically compare and output early warning information to achieve early warning and dynamic monitoring. By marking abnormal risks and evaluating risk levels, the severity of the risk can be clearly identified, and the scope and weight of the abnormal risk can be set based on the risk level to provide a quantitative basis for subsequent management. In addition, according to the abnormal risk weight, a variety of processing strategies can be set to effectively respond to different degrees of abnormalities and improve response efficiency. This method realizes automated monitoring and intelligent management of railway tunnels by establishing an abnormal prediction system of historical data and models, optimizes decision-making processes, improves management efficiency and safety, and effectively improves the monitoring accuracy and risk warning capabilities of the tunnel's dynamic environment, ensures safe operation of the tunnel, and reduces accidents.

[0109] Another preferred implementation of the present invention includes: obtaining the tunnel electromagnetic vector field by combining the boundary conditions of the tunnel through the sensor; constructing a wave mode envelope for the railway tunnel according to the obtained tunnel electromagnetic vector field; in the wave mode envelope, the charge density p and the current density j are equal, that is, ; In the formula, k represents the spatial frequency of the radio wave, represents the partial differential symbol, and t represents the current time node;

[0110] According to the equality of the charge density p and the current density j, the unit normal vectors of the interface between the two media of charge density and current density are obtained; according to the unit normal vectors of the two media, the free charge surface density and the conduction current surface density on the interface between the media are obtained;

[0111] According to the free charge surface density P and the conduction current surface density J, by ; to obtain the propagation constant of electromagnetic waves in free space; where k0 represents the propagation constant of electromagnetic waves in free space, represents the wavelength of electromagnetic waves, k P represents the spatial frequency of the free charge surface density, k J represents the spatial frequency of the conduction current surface density;

[0112] When the electromagnetic wave propagation constant approaches 0 during free space transmission and propagates approximately perpendicularly or parallel to the ground, the electromagnetic wave propagates normally in the railway tunnel environment; otherwise, the normal propagation of electromagnetic waves in the railway tunnel environment is questionable, which will cause the wireless channel state to be in a risky state; and then the abnormal risk parameters of the dynamic environment are obtained.

[0113] In the implementation of the present invention, sensors are arranged in the tunnel to monitor the electromagnetic field data in the tunnel in real time. These sensors can measure electromagnetic vector field components in the tunnel, including but not limited to electric field and magnetic field. These data will be transmitted to the computing system for analysis. The electromagnetic field in the tunnel is affected by the geometry, material, and surrounding physical environment of the tunnel, and can therefore reflect the electromagnetic wave propagation characteristics of the tunnel.

[0114] Constructing a wave mode envelope: Based on the obtained tunnel electromagnetic vector field, a wave mode envelope model is established. In this model, there is a balance between charge density and current density, that is, the charge and current are equal in the wave mode envelope model; especially in the process of electromagnetic wave propagation, the distribution of charge and current will affect the propagation characteristics of the wave. This is based on the wave theory of electromagnetic waves, that is, the coupling relationship between charge density and current density, which reflects the dynamic characteristics of the electromagnetic field in the tunnel; according to the wave equation of the electromagnetic field, the relationship between charge density and current density is processed in the model. This involves solving the propagation mode of electromagnetic waves in different media, where the equal relationship between charge density and current density provides the basis for the subsequent derivation. The stability and regularity of electromagnetic wave propagation are ensured.

[0115] The relationship between charge density and current density is used to determine the interface between two different media. The unit normal vectors between these interfaces are very important for subsequent calculations. They can help further describe the behavior of electromagnetic waves at the junction of different media, especially at the interface between the tunnel wall and the surrounding air. The free charge surface density and conduction current surface density on the interface are further obtained through the unit normal vector. The free charge surface density is usually the number of free charges per unit area, which indicates the distribution of charges on the surface of the medium; the conduction current surface density is the intensity of the flowing current per unit area, which indicates the distribution of current on the surface. It reflects the distribution of electromagnetic waves inside and outside the tunnel, and helps to describe the intensity of the electric and magnetic fields at the interface and their interaction.

[0116] Using the spatial frequency of the free charge surface density and the conduction current surface density, the spatial frequency usually refers to the frequency that changes periodically in space, indicating the rate of change of the wave mode in space. The spatial frequency of the free charge surface density and the current surface density involves the distribution of the electromagnetic field in the wave mode, which can usually be obtained by solving the Maxwell equations and performing Fourier transform on the electric and magnetic fields; or the boundary conditions, the properties of the medium (such as dielectric constant and conductivity) and the wave equation can be used to derive the spatial distribution characteristics of the charge density and current density, and then obtain their spatial frequencies;

[0117] pass Obtain the propagation constant k of electromagnetic waves in free space; the propagation constant is a key parameter of electromagnetic wave propagation characteristics, affecting signal attenuation, reflection and transmission efficiency; according to the propagation constant of electromagnetic waves, the propagation of electromagnetic waves in the tunnel can be judged. In the formula, f represents the frequency of the electromagnetic wave, which is the spatial frequency, and c represents the propagation rate of the electromagnetic wave. Represents pi; when the propagation constant of electromagnetic waves in free space approaches zero, and the propagation direction of electromagnetic waves is close to vertical or parallel to the ground, it means that the electromagnetic waves can propagate normally in the tunnel. If the propagation constant deviates from this feature, it means that there is an abnormality in the propagation of electromagnetic waves, which may cause the signal quality of wireless communication to decrease or the interference to increase; by analyzing the changes in the electromagnetic wave propagation constant, the propagation state of the wireless signal in the tunnel can be further obtained. If the electromagnetic wave propagation constant is abnormal, it means that the electromagnetic wave propagation in the tunnel environment is abnormal, thus entering a "risk state", which may cause wireless signal instability or communication interruption. At this time, the system will output the "dynamic environment abnormality risk parameter" to prompt the need to take preventive measures, such as adjusting communication equipment, improving tunnel structure or strengthening signal enhancement.

[0118] This method uses sensors to monitor the electromagnetic field in the tunnel in real time, and can timely identify abnormal electromagnetic wave propagation in the tunnel environment, providing data support for the maintenance and optimization of communication equipment in the tunnel; by obtaining the electromagnetic wave propagation constant, the state of the wireless channel can be evaluated. If the signal propagation is abnormal, it can be discovered and adjusted in advance, thereby improving the reliability of wireless communication in the railway tunnel and ensuring the safety and smoothness of train operation; by monitoring the electromagnetic wave propagation, it can predict problems such as signal attenuation, reflection or interference, and issue risk warnings in time to reduce the occurrence of wireless communication failures. Especially in scenarios with extremely high communication requirements such as high-speed railways, it can effectively reduce communication failures caused by electromagnetic interference; this technology can provide a scientific basis for the design, construction and maintenance of tunnels. For example, factors such as tunnel wall material, shape, and equipment layout can be optimized through this technology to improve the propagation characteristics of electromagnetic waves and improve the communication quality in the tunnel; risk assessment of the electromagnetic environment in railway tunnels helps to improve the foresight of potential communication failures, strengthen the safety management of tunnel operations, and avoid safety accidents caused by communication interruptions.

[0119] In a preferred implementation of the present invention, the step 12 compares the power environment parameter with the abnormal risk index to obtain a comparison difference parameter, and further includes:

[0120] Step 121, the power environment parameter represents various parameter data of the environmental operation status in the railway tunnel; the abnormal risk index represents the risk standard value of abnormalities in various parameter data of the environmental operation status in the railway tunnel;

[0121] Step 122, preprocessing the plurality of power environment parameters to obtain a standardized data set;

[0122] Step 123, the railway tunnel standardized data set at each time node operation data, through , to obtain a comparison difference parameter, wherein a plurality of the comparison difference parameters constitute a difference index;

[0123] In the formula, Di represents the ith comparison difference parameter, n represents the number of dynamic environment parameters, and x i represents the ith dynamic environment parameter, y i Represents the abnormal risk index corresponding to the i-th dynamic environment parameter.

[0124] In the implementation of the present invention, step 121 mainly defines a number of key data indicators of the operating status of the tunnel environment, such as temperature, humidity, pressure, air velocity, air composition, etc. These parameters reflect the basic conditions of the tunnel environment and are the basis for evaluating the safe operation and operational efficiency of the tunnel.

[0125] The abnormal risk index has established some standardized risk values ​​to indicate the abnormal risks that may be caused when the dynamic environment parameters deviate from the normal range. For example, when the temperature, humidity, etc. exceed the set safety threshold, it may indicate that there are problems with the ventilation, drainage and other facilities of the tunnel, or there are safety hazards.

[0126] By clearly defining various dynamic environmental parameters and abnormal risk indicators, a unified standard can be provided for subsequent monitoring, analysis and early warning. This enables tunnel managers to pay attention to changes in environmental parameters in real time during operation and take timely response measures to ensure the safe operation of railway tunnels.

[0127] Step 122: In order to ensure that multiple dynamic environment parameter data collected at different time points can be effectively compared and analyzed, the data needs to be standardized. Preprocessing may include steps such as noise removal, filling missing data, and smoothing data to remove interference factors and make the data more reliable. Standardization converts parameter data from different sources to the same scale so that they can be compared and calculated on the same platform. Common standardization methods include converting data to a standard normal distribution with a mean of 0 and a variance of 1, or normalizing data to a specific range (such as the [0,1] interval).

[0128] The beneficial effect of preprocessing and standardization is that it can eliminate the impact of data differences under different equipment, different time and different measurement conditions, and ensure the accuracy of subsequent analysis and model training. At the same time, standardized data can improve processing efficiency and facilitate automated analysis and comparison, thereby effectively improving the real-time and accuracy of risk assessment.

[0129] Step 123 compares the tunnel environment data of each time node with the previous historical data or standard operation data in the data set standardized in step 122, and calculates the difference. These difference parameters are defined by comparing the deviation between the standardized data and the reference data; based on the calculated comparison difference parameters, a difference index is constructed. The difference index is a measurement value used to comprehensively measure the changes in environmental status at different time nodes. If the difference index value is large, it means that the environment in the tunnel has changed to a large extent, and there may be safety risks. On the contrary, if the difference index value is small, it means that the environmental changes are small and the risk is low.

[0130] By comparing difference parameters and constructing difference indexes, it is possible to monitor the operating status of the tunnel environment in real time and quickly identify possible abnormal changes. Difference indexes can serve as early warning signals to reflect potential risks or hidden dangers in advance and help managers take appropriate intervention measures. Analysis based on difference indexes can also provide a scientific basis for decision-making and improve the safety and reliability of tunnels.

[0131] The above steps work together to achieve efficient monitoring, real-time analysis and risk warning of the railway tunnel environment. Specifically: Step 121 ensures that the goals of data collection and monitoring are clear by defining key environmental parameters and abnormal risk indicators; Step 122 ensures the quality and consistency of data through data preprocessing and standardization, making subsequent analysis more accurate; Step 123 provides an effective means for timely detection of abnormal changes and potential risks through comparison and calculation of difference indicators; thereby improving the safety management level of the tunnel, preventing potential safety accidents, and improving the operating efficiency and reliability of the railway tunnel.

[0132] In a preferred implementation of the present invention, the step 12 evaluates the potential abnormal risk parameter to obtain the power environment abnormal risk parameter, and further includes:

[0133] Step 124: when there is an error in the monitoring data and a comparison difference parameter is generated, the obtained comparison difference parameter is obtained by , to obtain the real abnormal risk parameter, which is the abnormal risk parameter of the power environment; R t represents the true abnormal risk parameter, w i represents the real abnormal weight, and n represents the number of comparison difference parameters; the comparison difference parameters are the potential abnormal risk parameters;

[0134] Step 125, by setting the abnormal risk threshold range [T i , T j ],pass To obtain the abnormal risk degree of the abnormal risk parameter of the power environment; where R t(T) represents the abnormal risk degree of the real abnormal risk parameter, K represents the abnormal risk degree assessment weight, and t represents t real abnormal risk parameters;

[0135] Step 126, when R t (T)<T i , then the abnormal risk of the abnormal risk parameter of the dynamic environment is at low risk; when T i <R t (T)<T j , then the abnormal risk of the abnormal risk parameter of the dynamic environment is at medium risk; when R t (T)>T j , then the abnormal risk degree of the abnormal risk parameters of the dynamic environment is at high risk.

[0136] In the implementation of the present invention, in step 124, during the actual monitoring process, the collected monitoring data may have certain errors due to various factors (such as equipment errors, environmental interference, etc.), which will affect subsequent analysis and judgment. In order to ensure the accuracy of risk assessment, these data need to be corrected.

[0137] First, by comparing the tunnel environmental parameters with historical data or standard operating data, the "comparison difference parameters" are calculated. These differences reflect the deviation between the monitoring data and the standard data, which may indicate potential abnormal risks; after error correction, the comparison difference parameters are further processed to obtain the real abnormal risk parameters. The real abnormal risk parameters represent the corrected risk values, which can more accurately reflect the abnormal risks in the tunnel environment; the real abnormal risk parameters are obtained by comparing the weighted average of the difference parameters or other methods; the data after error correction is more accurate: by correcting the errors in the monitoring data, the calculated real abnormal risk parameters are more credible, avoiding false alarms and misjudgments caused by errors, and ensuring the reliability of the risk assessment results; by correcting the comparison difference parameters, the assessment of abnormal risks can be made more accurate, reducing possible omissions and false alarms.

[0138] Step 125 Abnormal risk threshold range [Ti, Tj]: In this step, two thresholds are set to divide different levels of abnormal risk. These thresholds are set based on historical data, safety standards of the tunnel environment, risk tolerance and other factors. The division of the threshold range is usually based on experience, statistical analysis or expert knowledge, and the abnormal risk of the environment is calculated by comparing the abnormal parameter value with the threshold range [Ti, Tj]. Through this calculation, the current risk level of the tunnel environment can be determined; by setting a clear risk threshold range, different risk levels can be accurately distinguished, so that managers can have a clearer understanding of the current safety status of the tunnel and take appropriate countermeasures; threshold setting can help quickly determine whether the tunnel environment needs special attention, ensuring timely response when potential risks are discovered to prevent accidents.

[0139] Step 126: Low risk, medium risk and high risk classification, intuitive classification of risk levels: By classifying the real abnormal risk parameters, the risk status of the tunnel can be intuitively obtained, which is convenient for managers to make decisions quickly; this step helps identify potential dangerous areas and time periods, and through hierarchical management, it avoids being caught off guard when the risk is too high. The high-risk stage can trigger timely emergency response to prevent the situation from further deteriorating; according to different risk levels, managers can allocate resources in a targeted manner to avoid excessive or insufficient response. For example, for low-risk status, only routine inspections may be required; for high-risk status, emergency rescue forces need to be deployed.

[0140] In a preferred embodiment of the present invention, the abnormal prediction model in step 13 further includes:

[0141] Step 131, constructing a data set of historically acquired monitoring data and a plurality of abnormal risk parameters to generate structure data, encoding the structure data into sequence data, so as to train and obtain the abnormal prediction model;

[0142] Step 132, inputting the sequence data into the abnormality prediction model; the abnormality prediction model includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, transmitting the intermediate representation data of multiple hidden layers to the output layer, and the output layer output represents the abnormal risk prediction result of the power environment of the railway tunnel;

[0143] Step 133, at least one data item in the newly acquired railway tunnel monitoring data is input into the abnormality prediction model, and the output layer outputs the abnormal risk prediction result of the dynamic environment parameter in the newly acquired railway tunnel monitoring data.

[0144] In the implementation of the present invention, step 131 extracts various types of data of the railway tunnel from the historical monitoring data, including dynamic environmental parameters such as temperature, humidity, pressure, vibration, displacement, etc.; combines the acquired historical monitoring data with abnormal risk parameters (such as specific abnormal thresholds, environmental pressure indicators, etc.) to construct a comprehensive data set. This data set is the basis for training the abnormal prediction model.

[0145] The constructed dataset is converted into structured data by some means (such as time series, feature engineering, etc.), and further encoded into sequence data. This step converts the original monitoring data into a format suitable for model processing, usually time series data, so that the model can capture patterns and changes in the time dimension.

[0146] Through data structuring and coding, we ensure that the data has been standardized and preprocessed before entering the model to avoid noise interference from the original data; by combining historical monitoring data with abnormal risk parameters, the model can comprehensively capture the potential abnormal risks in the tunnel dynamic environment and enhance the accuracy of the prediction.

[0147] Step 132: Input data to the anomaly prediction model: Input the above data encoded as sequence data into the anomaly prediction model. The model is generally a deep neural network (such as a multi-layer perceptron, MLP), which includes multiple layers (such as an input layer, multiple hidden layers, and an output layer).

[0148] Model structure: Input layer: receives processed data (such as sequence data) as input to the model.

[0149] Hidden layers (first, second, and third layers): Multiple hidden layers are used to gradually extract high-level features from the data. Each layer learns a more complex pattern than the previous layer, thus being able to capture the temporal nature of the data and complex nonlinear relationships.

[0150] Output layer: Finally, all intermediate representations (hidden layer outputs) are passed to the output layer, where an anomaly risk prediction result is calculated.

[0151] Through the design of multi-layer neural networks, the model can extract deep features from the data, learn complex and implicit rules, and improve the accuracy of abnormal risk prediction; nonlinear relationship processing: multiple hidden layers can process nonlinear relationships in the data, which are usually crucial to accurate risk prediction.

[0152] Step 133: Input new data: When new monitoring data (such as real-time data in the tunnel) is obtained, at least one data item (such as temperature, pressure, etc.) will be input into the trained abnormality prediction model; Model output: The new input data will be processed by each level of the model, and the final output layer will generate a new prediction result, which represents the predicted value of the abnormal risk of the dynamic environment of the railway tunnel corresponding to the new data.

[0153] In this way, the model can receive new monitoring data in real time and make instant predictions, providing dynamic abnormal risk warnings; respond to potential anomalies in a timely manner: once new data is input, the system can respond in a timely manner based on the results of the model's predictions, take necessary preventive or treatment measures, and reduce potential risks; as the data is continuously updated, the model can continuously adapt to new data features, so that its prediction accuracy can be improved over time.

[0154] like Figure 5 As shown, in a preferred implementation of the present invention, the step 13 responds to a preset warning threshold and outputs warning information, and also includes:

[0155] Step 134, based on the prediction result of the abnormal prediction model, and according to different abnormal risk levels of the power environment abnormal risk parameter, a warning threshold is set; based on the preset warning threshold, a corresponding alarm response mechanism is designed to quickly respond to abnormal situations and issue a response alarm;

[0156] Step 135, when in a low-risk abnormal situation, the alarm response mechanism flashes the alarm light once every preset time interval, and continuously monitors the abnormal risk state of the power environment parameter at the node where the alarm light flashes. When the low-risk abnormal situation has a risk increase trend at the tth time node, the preset time interval of the alarm light flashing is shortened;

[0157] Step 136, when in a medium-risk abnormal situation, the alarm response mechanism flashes the alarm light at regular intervals, accompanied by an alarm sound at a preset time interval, and records the abnormal risk parameter information at the current time node, and regularly evaluates the risk trend of the acquired abnormal risk parameter information at a preset time period to determine whether there is a deteriorating risk situation at the t+1th time node;

[0158] Step 137, when in a high-risk abnormal situation, the alarm response mechanism sends out a warning alarm at no time intervals through the alarm light and the alarm sound, and sets the railway tunnel section with high-risk abnormal situation, closes the railway tunnel section corresponding to the current time node, and conducts a secondary survey to avoid frequent abnormal risks in multiple sections of the railway.

[0159] Specifically, when the monitoring platform detects an abnormal situation, the exception handling unit attached to the platform can classify different types of abnormalities and take preventive measures, such as sending alarms, automatically adjusting the equipment operating status, or notifying maintenance personnel. In addition, the exception handling unit also has a self-diagnosis function, which can detect its own operating status and ensure timely response in abnormal situations. This combination of centralized monitoring and exception handling can effectively improve the safety and reliability of the dynamic environment of the public network equipment chamber of the railway tunnel.

[0160] The abnormality handling unit includes an intelligent alarm system and a remote maintenance system. The intelligent alarm system can automatically select the appropriate alarm method, such as SMS, phone, email, etc., according to the type and severity of the abnormal situation, to ensure that relevant personnel can receive the alarm information in time. The remote maintenance system allows maintenance personnel to remotely log in to the monitoring platform to diagnose and maintain the equipment, improve maintenance efficiency, and reduce the number and cost of on-site maintenance.

[0161] In the implementation of the present invention, step 134 can identify abnormal situations of different risk levels based on the prediction results of the abnormal prediction model. According to different abnormal risk parameters, the corresponding warning threshold is set. This threshold is used to determine when to trigger an alarm response; design an alarm response mechanism to ensure that it can effectively respond and issue an alarm under different risk levels; through the prediction results of the abnormal prediction model, the warning threshold can be dynamically adjusted to ensure that the alarm is triggered only when there is a real risk, thereby avoiding excessive alarms; design a special response mechanism for each risk level so that timely and effective responses can be made under different risk conditions.

[0162] Step 135: When the system detects a low-risk abnormality, the alarm light flashes once every set time and continuously monitors the abnormality. If the abnormal risk shows an upward trend at a certain point in time, the time interval between flashing of the alarm light is shortened to improve the warning effect; when the risk is low, only the alarm light flashes to remind, which will not disturb the operator excessively and keep the normal operation of the working environment; as the abnormal risk increases, the alarm frequency increases, which helps to promptly remind the operator to pay attention to potential problems and avoid further expansion of risks.

[0163] Step 136: In the case of medium risk, the alarm response mechanism not only flashes the alarm light, but also has regular alarm sounds. At the same time, the system records the current abnormal risk parameter information and periodically evaluates the risk trend. By comparing the risk changes at the current and future time nodes, it is determined whether there is a risk of deterioration. The coordination of the alarm light and the alarm sound ensures that the operator can detect abnormal situations in time and take action; by regularly evaluating abnormal risk parameters, the potential risk of deterioration can be determined in advance, which helps to formulate response measures and prevent the spread of risks.

[0164] Step 137: In the case of high-risk abnormalities, the alarm lights and sirens will continue to work without interruption, sending out strong early warning signals. In addition, the system will immediately close the tunnel section according to the high-risk railway tunnel section information and conduct a secondary survey to prevent possible larger-scale risks; the continuous and uninterrupted alarm lights and sirens can quickly attract the attention of operators to ensure that no potential threats are missed in high-risk situations; closing the high-risk section and conducting a secondary survey will help avoid catastrophic events, reduce personnel and equipment losses, and ensure railway safety.

[0165] In a preferred embodiment of the present invention, the step 14 is based on the prediction results and warning information of the abnormal prediction model to obtain the abnormal risk scope of the abnormal risk parameter, and further includes:

[0166] Step 141: The actual abnormal risk parameter is To obtain the abnormal risk impact measurement value corresponding to the real abnormal risk parameter; where, Indicates the abnormal risk and measurement value, The normal dynamic environment parameters representing the predicted results, Indicates the dynamic environment parameters;

[0167] Step 142, establish three-dimensional space coordinates in the railway tunnel, obtain any number of space coordinate points in each quadrant of the coordinate system, and respectively connect the plurality of space coordinate points through , to obtain the three-dimensional space abnormal risk spread range of the abnormal risk spread measurement value;

[0168] In the formula, represents the scope of abnormal risk, K represents the spatial kernel function, N represents the number of spatial coordinate points, and x r ,y r and z r They respectively represent the three-dimensional coordinates of the r-th coordinate point.

[0169] In the implementation of the present invention, in step 141, the current actual abnormal risk parameters are first obtained. These parameters are obtained through a prediction model and are usually closely related to the state of the dynamic environment (such as temperature, humidity, pressure, speed, etc.) and other related dynamic factors (such as vehicle status, equipment operation in the tunnel, etc.); the corresponding abnormal risk impact measurement value is calculated using the actual abnormal risk parameters. This measurement value reflects the spread and impact of the abnormal risk in space, indicating the impact range of the abnormal event on the surrounding environment; by obtaining the difference between the actual parameters and the predicted parameters, the severity of the abnormal environment parameters is estimated; this measurement value helps quantify the risk and predict the impact range of the abnormal event.

[0170] By obtaining the abnormal risk spread measurement value, the propagation intensity and scope of the abnormal event can be accurately assessed, providing a scientific basis for subsequent emergency response; as time goes by, the system can monitor the changes in risk parameters in real time and update the risk spread measurement value, thereby providing dynamic risk assessment; by quantifying the abnormal risk spread measurement value, the possible consequences of the abnormal situation can be more clearly understood, so as to make reasonable decisions.

[0171] Step 142: First, a three-dimensional space coordinate system is established inside the railway tunnel. This coordinate system is used to represent the positions of all spatial points in the tunnel. Each spatial point can be identified by a coordinate point (x, y, z); then the three-dimensional space is divided into several quadrants (or regions) through the three-dimensional coordinate system. There can be multiple spatial coordinate points in each quadrant. These coordinate points represent points at different positions inside the tunnel, and each point has a potential abnormal risk spread measurement value; the propagation range of the measurement value in the three-dimensional space is calculated through the known abnormal risk spread measurement value. The spatial expansion of abnormal risks can be predicted by some mathematical model or simulation method (such as diffusion model, thermodynamic model, etc.). This calculation will produce a three-dimensional spatial range, indicating the area that the risk may affect in the tunnel.

[0172] By establishing a three-dimensional coordinate system, the abnormal risk status of each area in the tunnel can be clearly known, which helps to locate the risk source and potential high-risk areas; marking the scope of abnormal risk in three-dimensional space can help operators and managers understand the spatial distribution of risks more intuitively, so that they can make decisions and take precautions in a timely manner; instead of relying solely on a single risk point, the risks in the entire tunnel are spatially modeled, which improves the comprehensive perception of risks in complex environments; based on the calculation results of these spatial coordinate points and the scope of impact, managers can scientifically assess the risk level of each area and carry out targeted resource allocation and emergency response according to the spatial distribution of risks. For example, if an area is severely affected, it may need to be closed immediately for personnel evacuation or equipment inspection.

[0173] In a preferred embodiment of the present invention, the abnormal risk scope of the abnormal risk parameter in step 14 further includes:

[0174] Step 143, when is abnormal if and only if ;Right now , to obtain the abnormal risk spread time node range of the abnormal risk spread measurement value; where, Indicates the scope of abnormal risk at the tth time node, represents the normal risk parameter threshold of the power environment; t i and t jRepresent the i-th and j-th abnormal risk time nodes respectively;

[0175] Step 144, based on the three-dimensional abnormal risk spread range and the abnormal risk spread time node range, according to , to obtain the upper and lower limits of the abnormal risk range, according to Adjust the factors to dynamically adjust the upper and lower limits of the abnormal risk range.

[0176] In the implementation of the present invention, an "abnormal" risk situation is defined in step 143. Generally, an abnormal risk event refers to a risk that exceeds a certain preset threshold. The threshold is usually a normal risk parameter obtained through analysis of historical data and a risk assessment model; a normal power environment risk parameter in the absence of an abnormal event, and a risk parameter that exceeds a certain set threshold is considered "abnormal".

[0177] In step 143, our goal is to determine the changes in the "abnormal risk impact measurement value" at different time nodes and the spread range of abnormal risks in the time dimension. When the normal risk parameter threshold of the abnormal risk impact range is obtained, that is, only when the abnormal risk impact measurement value exceeds the threshold, it will be regarded as a true abnormal risk parameter.

[0178] Time nodes: By tracking the abnormal risk impact measurement value, the start and end time points of the abnormality are identified. On the timeline, the i-th and j-th time nodes mark the time boundaries of the abnormal risk impact range.

[0179] Changes in the time dimension reflect the start and end of the risk impact, thereby determining the time range of the abnormal risk impact. By analyzing the time node range of the abnormal risk, the specific moment when the abnormal event occurs can be accurately captured. This allows for more effective early warning and intervention; as time goes by, the system can dynamically adjust risk assessments based on new data to ensure the real-time and accuracy of risk management strategies; by accurately determining the time node range of the risk impact, relevant managers can initiate emergency responses at critical time points, thereby reducing potential losses.

[0180] In step 144, the system no longer performs risk assessment based solely on the static spatial dimension, but combines the interaction of the time dimension and the spatial dimension to dynamically adjust the upper and lower limits of the risk impact range. This means that not only the scope of the abnormal event in the three-dimensional space should be considered, but also the trend of the risk over time; the abnormal risk impact range in the three-dimensional space has been obtained in step 142, and now these ranges need to be adjusted according to the new time node and risk impact metric value. For example, over time, the risk may expand or shrink to other areas of the tunnel. Adjustment factors (such as environmental changes, changes in risk sources, etc.) will affect the upper and lower limits of the risk impact range.

[0181] Through the influence of the time dimension, the duration of abnormal risks can be identified. Combined with this information, the spatial scope can be adjusted dynamically. For example, if the abnormal risk increases in a certain period of time, it may be necessary to expand the spatial scope of risk prevention and control; if the abnormal risk decreases in another period of time, the scope of impact can be reduced; the adjustment factor is a coefficient dynamically calculated based on variables such as the time, environment, and tunnel status of the risk impact, which is used to adjust the scope of abnormal risk impact in real time. The adjustment factor is usually calculated based on the following factors: environmental changes (such as temperature, humidity, etc.); equipment status (such as the health status of monitoring equipment in the tunnel); changes in traffic flow and train speed; changes in risk sources (such as train failures, fires, etc.); by combining these factors, the adjustment factor can reflect changes in the environment and adjust the spatial risk impact range accordingly.

[0182] By dynamically adjusting the upper and lower limits of the risk scope based on a comprehensive analysis of time and space, the risk of a certain area in the tunnel can be assessed more accurately to ensure that appropriate response measures are taken; when an abnormality occurs in the tunnel, the system can dynamically adjust the coverage and response speed of emergency measures based on the latest risk scope. For example, if the risk scope of a certain area expands, it may be necessary to dispatch resources in advance for evacuation or strengthen safety monitoring; in the complex environment of the tunnel, the spread of risk may be affected by many factors. By dynamically adjusting the risk scope, the system can respond to emergencies more flexibly and avoid delayed response due to overly static risk prediction; through accurate adjustment of the risk scope, relevant departments can reasonably allocate resources and avoid waste of resources. For example, in time periods and areas with a smaller risk scope, the investment of emergency resources can be reduced, while in high-risk time periods, efforts can be concentrated on emergency response. In short, this process not only enhances the spatial and temporal understanding of abnormal risk events, but also provides a flexible adjustment mechanism for actual operations, making the risk management of railway tunnels more intelligent and real-time.

[0183] In a preferred implementation of the present invention, in step 14, the abnormal risk weight of the abnormal risk parameter is determined according to the abnormal risk spread range, and a plurality of abnormal handling strategies are set according to the abnormal risk weight corresponding to the abnormal risk parameter of the power environment, which also includes:

[0184] Step 145, based on the scope of impact and the severity of each risk factor, Abnormal risk weights are assigned to the severity of different risk factors; where: represents the abnormal risk weight of the abnormal risk parameter pi, Represents an exception enabling function;

[0185] Step 146, planning an exception handling strategy according to the abnormal risk weight, abnormal risk impact range and abnormal risk parameter level;

[0186] Step 147, the abnormality handling strategy includes: for low risk levels, monitoring, recording and early warning measures can be taken, and no immediate intervention is required; for medium risk levels, manual monitoring is increased, system parameters are adjusted or local repairs are performed; for high risk levels, emergency response mechanisms are activated, global intervention, shutdown or isolation of fault areas are performed;

[0187] In the implementation of the present invention, the scope of impact in step 145 refers to the breadth or degree of the impact that the risk may have on the system. For example, a certain fault may only affect a single module, or may affect the entire system.

[0188] Assess the consequences of the risk if it occurs, such as data loss, service interruption, system crash, etc.

[0189] Abnormal risk weight indicates the weight or priority of each risk factor in an abnormal state. This weight reflects the urgency and priority of the risk factor. The calculation of the weight can depend on a variety of factors, such as the scope of impact, severity, probability of occurrence, etc.

[0190] By assigning weights to risk factors based on their scope and severity, the risk management process can be made more detailed and scientific; this step helps determine which anomalies are most urgent and which can be handled later, providing a clear basis for subsequent decision-making.

[0191] Step 146 plans the abnormality handling strategy based on the abnormality risk weight, the scope of impact, and the abnormality risk parameter level assigned in step 145; the abnormality risk parameter level refers to the risk level calculated based on the weight, such as low, medium, and high risk levels; different handling measures are formulated for different risk levels. Lower risks may not require immediate response, while higher risks may require emergency handling; by formulating different response strategies for different risk levels, resources can be reasonably allocated to avoid overreaction or waste of resources; according to different risk scenarios, appropriate response measures are selected so that the system can flexibly respond to various emergencies.

[0192] Step 147 adopts different abnormal handling measures for different risk levels according to the plan of step 146: for low-risk abnormal events, usually adopt measures such as monitoring, recording, and early warning. Through real-time monitoring and recording, the evolution trend of risks can be discovered in time, but there is no need to take intervention measures immediately.

[0193] Medium risk level: For medium risk levels, manual monitoring is usually increased, system parameters are adjusted, or local repairs are performed. At this time, the risk is high and some intervention measures need to be taken, but there is no need for a global response; High risk level: For high risk levels, the system needs to activate the emergency response mechanism, conduct global intervention, shut down, or isolate the fault area to ensure the stability and security of the system.

[0194] Taking different response measures according to different risk levels can avoid overreaction and waste of resources, while also ensuring that necessary emergency measures are taken in high-risk situations; through targeted treatment of different risk levels, the normal operation and security of the system can be better guaranteed; monitoring and early warning can be carried out when the risk is low, so as to discover potential problems in advance, and emergency measures can be initiated in time when the risk is high to prevent catastrophic consequences.

[0195] like Figure 2 As shown, a railway tunnel environment monitoring system based on the Internet of Things includes:

[0196] Data acquisition module: It is used to obtain historical monitoring data of railway tunnels to obtain abnormal risk parameters of dynamic environment;

[0197] Data identification module: it is used to obtain multiple power environment parameters based on historical monitoring data; set multiple abnormal risk indicators; compare the power environment parameters with the abnormal risk indicators to obtain comparison difference parameters; the comparison difference parameters are potential abnormal risk parameters; evaluate the potential abnormal risk parameters to obtain power environment abnormal risk parameters; based on the acquired power environment abnormal risk parameters, mark abnormal risk marks respectively; evaluate the risk level of abnormal risk parameters with different abnormal risk marks; based on the evaluation results, obtain abnormal level data of abnormal risk parameters;

[0198] Early warning response module: It is used to construct a data set with historically acquired monitoring data and multiple abnormal risk parameters to train an abnormal prediction model; obtain new monitoring data and input the new monitoring data into the abnormal prediction model to obtain the abnormal risk prediction result of the tunnel power environment; respond to the preset early warning threshold according to the abnormal risk prediction result of the tunnel power environment and output early warning information;

[0199] Abnormality handling module: It is used to obtain the abnormal risk scope of the abnormal risk parameters based on the prediction results and warning information of the abnormal prediction model; to judge the abnormal risk weight of the abnormal risk parameters according to the abnormal risk scope; and to set a variety of abnormality handling strategies according to the abnormal risk weight corresponding to the abnormal risk parameters of the power environment.

[0200] like Figure 3As shown in the figure, railway tracks are displayed in the tunnel, and multiple monitoring devices (such as sensors) are arranged along the tunnel, which may be used to monitor the structural health of the tunnel, environmental parameters (such as humidity, temperature, smoke) or train operation status; the monitoring equipment is connected to the local monitoring station through wireless communication to form a regional monitoring network; the local monitoring station is located near the tunnel and collects data from the equipment in the tunnel through wireless signals; the local monitoring station processes or stores the monitoring data and communicates with the higher-level control center through the railway dedicated communication network; the functions of the local station may include: monitoring the operation status of the tunnel, preliminarily analyzing the data, detecting anomalies, and uploading the data to the remote center; the railway dedicated communication network, the cloud-like area in the figure represents the railway dedicated communication network (such as the railway optical fiber network, wireless communication network), which acts as a transmission bridge; through the railway The railway dedicated communication network transmits monitoring data from local sites to a higher-level monitoring and control center to ensure the reliability and security of data transmission; the railway monitoring and dispatching center is the core node of the entire system, which is used to centrally process tunnel monitoring data and perform high-level analysis and decision-making. It may have the following functions: remote real-time monitoring of tunnel and train operation, cross-regional abnormal event analysis (such as geological disasters, equipment failures, fires, etc.), and issuing control or dispatching commands to local monitoring sites on site; data flow and communication, the yellow lightning-shaped arrow in the figure indicates the transmission path of data and commands. Data is collected from monitoring equipment in the tunnel, transmitted to local monitoring sites, and then sent to the railway monitoring and dispatching center via the railway dedicated communication network; commands and instructions from the monitoring and dispatching center can also be sent to local monitoring sites and on-site equipment through the communication network.

[0201] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general intelligent device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code that implements the method or system. It should also be pointed out that in the device and method of the present invention, it is obvious that each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

Claims

1. A railway tunnel environment monitoring method based on the Internet of Things, characterized in that: The following methods are included: Obtain historical monitoring data of railway tunnels to obtain abnormal risk parameters of the dynamic environment; wherein, based on the historical monitoring data, a variety of power environment parameters are obtained; Set a variety of abnormal risk indicators; Comparing the power environment parameter with the abnormal risk index to obtain a comparison difference parameter; the comparison difference parameter is the potential abnormal risk parameter; The potential abnormal risk parameters are evaluated to obtain the abnormal risk parameters of the power environment; wherein, when there is an error in the monitored potential abnormal risk parameter data, the real abnormal risk parameters are obtained by comparing the difference parameters, and the abnormal risk degree is evaluated according to the set threshold range; Based on the abnormal risk parameters, abnormal risk marks are respectively marked; risk level assessment is performed on abnormal risk parameters with different abnormal risk marks; based on the assessment results, abnormal level data of the abnormal risk parameters is obtained; Among them, the electromagnetic vector field is obtained through sensors and tunnel boundary conditions, and the wave mode cladding is constructed to obtain the charge density and current density on the dielectric interface to obtain the electromagnetic wave propagation constant; when the propagation constant is close to 0 and the direction is perpendicular or parallel to the ground, the tunnel propagation is judged to be abnormal and the dynamic environment risk is evaluated; Construct a data set with historical monitoring data and multiple abnormal risk parameters to train an abnormal prediction model; obtain the abnormal risk prediction results of the tunnel dynamic environment through the abnormal prediction model; respond to the preset warning threshold according to the prediction results and output warning information; Based on the prediction results and early warning information, the scope of abnormal risk parameters is determined and the abnormal risk weight is obtained; based on the abnormal risk weight, a variety of abnormal handling strategies are formulated.

2. The method for monitoring railway tunnel environment based on Internet of Things according to claim 1, characterized in that: The electromagnetic vector field of the tunnel is obtained by combining the sensor with the boundary conditions of the tunnel. According to the obtained electromagnetic vector field of the tunnel, a wave mode envelope is constructed for the railway tunnel. In the wave mode envelope, the charge density p and the current density j are equal to obtain the unit normal vector of the interface between the two mediums of charge density and current density. According to the unit normal vectors of the two media, the free charge surface density and the conduction current surface density on the medium interface are obtained; according to the free charge surface density P and the conduction current surface density J, the propagation constant of the electromagnetic wave in the free space is obtained; When the electromagnetic wave propagation constant approaches 0 during free space transmission and propagates approximately perpendicularly or parallel to the ground, the electromagnetic wave propagates normally in the railway tunnel environment; otherwise, the normal propagation of the electromagnetic wave in the railway tunnel environment is questionable, causing the wireless channel state to be in a risky state; and then the abnormal risk parameters of the dynamic environment are obtained.

3. The method for monitoring railway tunnel environment based on Internet of Things according to claim 1, characterized in that: The power environment parameters are compared with the abnormal risk index to obtain comparison difference parameters, including: The dynamic environment parameter represents various parameter data of the environmental operation status in the railway tunnel; the abnormal risk index represents the risk standard value of abnormality in various parameter data of the environmental operation status in the railway tunnel; Preprocessing a plurality of the dynamic environment parameters to obtain a standardized data set; The railway tunnel operation data at each time node of the standardized data set is , to obtain a comparison difference parameter, wherein a plurality of the comparison difference parameters constitute a difference index; In the formula, Di represents the ith comparison difference parameter, n represents the number of dynamic environment parameters, and x i represents the ith dynamic environment parameter, y i Represents the abnormal risk index corresponding to the i-th dynamic environment parameter.

4. The method for monitoring railway tunnel environment based on Internet of Things according to claim 3 is characterized in that: The potential abnormal risk parameters are evaluated to obtain abnormal risk parameters of the power environment, including: When there is an error in the monitoring data and a comparison difference parameter is generated, the obtained comparison difference parameter is obtained through , to obtain the real abnormal risk parameter, which is the abnormal risk parameter of the power environment; R t represents the true abnormal risk parameter, w i represents the real abnormal weight, and n represents the number of comparison difference parameters; the comparison difference parameters are the potential abnormal risk parameters; By setting the abnormal risk threshold range [T i , T j ],pass To obtain the abnormal risk degree of the abnormal risk parameter of the power environment; where R t (T) represents the abnormal risk degree of the real abnormal risk parameter, K represents the abnormal risk degree assessment weight, and t represents t real abnormal risk parameters; When R t (T)<T i , then the abnormal risk of the abnormal risk parameter of the dynamic environment is at low risk; when T i <R t (T)<T j , then the abnormal risk of the abnormal risk parameter of the dynamic environment is at medium risk; when R t (T)>T j , then the abnormal risk degree of the abnormal risk parameters of the dynamic environment is at high risk.

5. The method for monitoring railway tunnel environment based on Internet of Things according to claim 4 is characterized in that: The abnormality prediction model comprises: The monitoring data acquired historically and a plurality of abnormal risk parameters are used to construct a data set to generate structured data, and the structured data is encoded into sequence data to train the abnormal prediction model; the sequence data is input into the abnormal prediction model; the abnormal prediction model includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, and the intermediate representation data of the plurality of hidden layers are transmitted to the output layer, and the output layer output represents the abnormal risk prediction result of the dynamic environment of the railway tunnel; Inputting at least one data item in the newly acquired railway tunnel monitoring data into the abnormality prediction model, and the output layer outputs the abnormality risk prediction result of the dynamic environment parameter in the newly acquired railway tunnel monitoring data; Based on the prediction results and warning information of the abnormal prediction model, the abnormal risk impact range of the abnormal risk parameters is obtained; according to the abnormal risk impact range, the abnormal risk weight of the abnormal risk parameters is judged; according to the abnormal risk weight corresponding to the abnormal risk parameter of the power environment, a variety of abnormal handling strategies are set.

6. The method for monitoring railway tunnel environment based on Internet of Things according to claim 5, characterized in that: In response to the preset warning threshold, the system outputs warning information, including: Based on the prediction results of the abnormal prediction model, and according to different abnormal risk levels of the power environment abnormal risk parameters, a warning threshold is set; based on the preset warning threshold, a corresponding alarm response mechanism is designed to quickly respond to abnormal situations and issue a response alarm; When in a low-risk abnormal situation, the alarm response mechanism flashes the alarm light once every preset time interval, and continuously monitors the abnormal risk state of the power environment parameters at the node where the alarm light flashes. When the low-risk abnormal situation has an upward trend in risk at the tth time node, the preset time interval of the alarm light flashing is shortened; When in a medium-risk abnormal situation, the alarm response mechanism flashes the alarm light at no time interval, accompanied by an alarm sound at a preset time interval, and records the abnormal risk parameter information at the current time node, and regularly evaluates the risk trend of the acquired abnormal risk parameter information at a preset time period to determine whether there is a deteriorating risk situation at the t+1 time node; When in a high-risk abnormal situation, the alarm response mechanism sends out early warning alarms at no time intervals through alarm lights and sirens, sets high-risk abnormal railway tunnel sections, closes the railway tunnel sections corresponding to the current time node, and conducts secondary surveys to avoid frequent abnormal risks in multiple sections of the railway.

7. The method for monitoring railway tunnel environment based on Internet of Things according to claim 6, characterized in that: Based on the prediction results and warning information of the abnormal prediction model, the abnormal risk scope of the abnormal risk parameter is obtained, including: The actual abnormal risk parameter is To obtain the abnormal risk impact measurement value corresponding to the real abnormal risk parameter; where, Indicates the abnormal risk and measurement value, The normal dynamic environment parameters representing the predicted results, Indicates the dynamic environment parameters; Establish three-dimensional spatial coordinates in the railway tunnel, obtain any number of spatial coordinate points in each quadrant of the coordinate system, and respectively , to obtain the three-dimensional space abnormal risk spread range of the abnormal risk spread measurement value; In the formula, represents the scope of abnormal risk, K represents the spatial kernel function, N represents the number of spatial coordinate points, and x r ,y r and z r They respectively represent the three-dimensional coordinates of the r-th coordinate point.

8. The method for monitoring railway tunnel environment based on Internet of Things according to claim 7, characterized in that: The abnormal risk scope of the abnormal risk parameter also includes: when is abnormal if and only if ;Right now , to obtain the abnormal risk spread time node range of the abnormal risk spread measurement value; where, Indicates the scope of abnormal risk at the tth time node, Indicates the normal risk parameter threshold of the power environment; t i and t j Represent the i-th and j-th abnormal risk time nodes respectively; Based on the three-dimensional space abnormal risk spread range and the abnormal risk spread time node range, according to , to obtain the upper and lower limits of the abnormal risk range, according to Adjust the factors to dynamically adjust the upper and lower limits of the abnormal risk range.

9. The method for monitoring railway tunnel environment based on Internet of Things according to claim 8, characterized in that: According to the scope of the abnormal risk, the abnormal risk weight of the abnormal risk parameter is determined, and according to the abnormal risk weight corresponding to the abnormal risk parameter of the power environment, a variety of abnormal handling strategies are set, including: Based on the extent of the impact and severity of each risk factor, Abnormal risk weights are assigned to the severity of different risk factors; where: represents the abnormal risk weight of the abnormal risk parameter pi, Represents an exception enabling function; Plan an exception handling strategy based on the abnormal risk weight, abnormal risk impact scope and abnormal risk parameter level; The exception handling strategy includes: for low risk levels, monitoring, recording and early warning measures can be taken, and no immediate intervention is required; for medium risk levels, manual monitoring is increased, system parameters are adjusted or local repairs are performed; for high risk levels, emergency response mechanisms are activated, global intervention, shutdown or isolation of faulty areas are performed.

10. A railway tunnel environment monitoring system based on the Internet of Things, characterized in that: The system is provided with an electronic device including a memory, a processor, and a railway tunnel environment monitoring method program based on the Internet of Things stored in the memory and executable on the processor. When the railway tunnel environment monitoring method program based on the Internet of Things is executed by the processor, the steps of the railway tunnel environment monitoring method based on the Internet of Things according to any one of claims 1 to 9 are implemented. The system includes: Data acquisition module: It is used to obtain historical monitoring data of railway tunnels to obtain abnormal risk parameters of dynamic environment; Data identification module: it is used to obtain multiple power environment parameters based on historical monitoring data; set abnormal risk indicators; compare the power environment parameters with the abnormal risk indicators to obtain comparison difference parameters; the comparison difference parameters are potential abnormal risk parameters; evaluate the potential abnormal risk parameters to obtain power environment abnormal risk parameters; based on the acquired power environment abnormal risk parameters, mark abnormal risk marks respectively; evaluate the risk level of abnormal risk parameters with different abnormal risk marks; based on the evaluation results, obtain abnormal level data of abnormal risk parameters; Early warning response module: It is used to construct a data set with historically acquired monitoring data and multiple abnormal risk parameters to train an abnormal prediction model; obtain new monitoring data and input the new monitoring data into the abnormal prediction model to obtain the abnormal risk prediction result of the tunnel power environment; respond to the preset early warning threshold according to the abnormal risk prediction result of the tunnel power environment and output early warning information; Abnormality handling module: It is used to obtain the abnormal risk scope of the abnormal risk parameters based on the prediction results and warning information of the abnormal prediction model; to judge the abnormal risk weight of the abnormal risk parameters according to the abnormal risk scope; and to set a variety of abnormality handling strategies according to the abnormal risk weight corresponding to the abnormal risk parameters of the power environment.

Images