Intelligent early warning type comprehensive pipe gallery environment monitoring method and system
By deploying comprehensive monitoring networks and machine learning algorithms within the pipeline corridor, a multi-classified risk prediction model is built, detection resources are dynamically allocated and alarm thresholds are set, and an adaptive learning mechanism is introduced, which solves the single monitoring parameters and early warning models in the existing technology. The inaccurate problem has achieved comprehensive monitoring and efficient early warning of the pipeline corridor environment, and improved the safety and efficiency of pipeline corridor operations.
Patent Information
- Application Number
- CN202411180042.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-12-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing technology has single monitoring parameters in pipeline corridor monitoring, which cannot fully reflect the operating status of the pipeline corridor, the early warning model is not accurate enough, the false alarm rate and missed rate are high, the system integration is low, and it is difficult to achieve interconnection with other systems.
By deploying a comprehensive monitoring network within the pipeline corridor, wireless communication is used to transmit data to the data center, combining historical data and machine learning algorithms to build a multi-classified risk prediction model, dynamically allocate detection resources, set dynamic alarm thresholds, and introduce an adaptive learning mechanism Optimize early warning models and emergency strategies, and display the status of the pipeline corridor through three-dimensional visualization.
It has achieved comprehensive and accurate monitoring and early warning of the pipeline corridor environment, improved the safety and efficiency of pipeline corridor operations, reduced on-site inspection work, reduced operation and maintenance costs, and enhanced the early warning and response capabilities of safety hazards.
Smart Images

Figure CN119071799A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of information technology and the Internet of Things, and specifically relates to an intelligent early warning integrated pipe gallery environment monitoring method and system. Background Art
[0002] With the acceleration of urbanization, the integrated pipe gallery, as an important infrastructure of the city, carries the safe operation of key pipelines for water supply, drainage, electricity, and communication. However, the pipe gallery faces many risks and safety hazards in the long-term use process, such as leakage and loss problems. These problems may lead to safety accidents and have a significant impact on the operation of the city. In order to timely discover the safety hazards in the pipe gallery, it is necessary to be able to comprehensively monitor the environment, equipment operation status, and gas composition in the pipe gallery. The traditional pipe gallery monitoring method mainly relies on manual inspections, which is not only inefficient, but also difficult to achieve real-time monitoring and early warning. With the development of modern technology, it is possible to deploy various sensors to achieve real-time monitoring and data transmission of environmental parameters in the pipe gallery, or use machine learning and deep learning technologies to intelligently analyze and predict monitoring data to achieve early warning functions.
[0003] For example, the patent with publication number CN116659579A discloses a cable corridor comprehensive environment monitoring and early warning device, including a shell, in which an audio sampling unit, a vibration sensing unit and an image acquisition unit are arranged; the audio acquisition unit and the vibration sensing unit are respectively connected to a data analysis and processing module, the data analysis and processing module performs feature matching on the pre-processed audio samples and vibration samples, the data analysis and processing module is connected to a controller, and the controller controls the image acquisition unit to start working. This technical solution uses audio sampling, vibration sensing and image acquisition sensors to conduct comprehensive detection of the cable corridor environment, realizes the complementarity of data between multiple sensors, and thus accurately judges the hidden dangers and accidents of the power infrastructure, realizes all-round protection of the power infrastructure, and improves the operation level. Effectively improve the safety and stability of facilities, and create a safer and more reliable power grid environment.
[0004] Although existing technologies have been able to achieve monitoring and early warning of pipeline corridors to a certain extent, the following problems still exist: for example, the monitoring parameters are single and cannot fully reflect the operating status of the pipeline corridor; the early warning model is not accurate enough; the false alarm rate and missed alarm rate are high; the system integration is low and it is difficult to achieve interconnection with other systems. Summary of the invention
[0005] In view of the shortcomings of the prior art, the present invention proposes an intelligent early warning comprehensive pipeline corridor environment monitoring method and system, which constructs a comprehensive monitoring network inside the pipeline corridor, adopts wireless communication to transmit data to the data center, and after preprocessing, combines historical data with machine learning algorithms to build a multi-classification risk prediction model to accurately predict the environmental status of the pipeline corridor; based on the prediction model, dynamically allocate detection resources to high-risk partitions, and intelligently assess risks, set dynamic alarm thresholds, and automatically trigger emergency responses; the system introduces an adaptive learning mechanism, continuously optimizes the early warning model and emergency strategy, and displays the pipeline corridor status through three-dimensional visualization to ensure the accurate operation of the monitoring equipment, thereby improving the intelligent level of pipeline corridor management, enhancing the early warning and response capabilities of safety hazards, and improving the safety and efficiency of pipeline corridor operations.
[0006] To achieve the above object, the present invention provides the following technical solutions:
[0007] An intelligent early warning integrated pipe gallery environment monitoring method, comprising:
[0008] Step S1: deploy a comprehensive monitoring network inside the tunnel, and set up a set of environmental detectors at fixed intervals in each fire zone, integrating the video monitoring system and sensor network, and using image recognition and pattern analysis methods to monitor the internal environment of the tunnel in real time and detect anomalies;
[0009] Step S2: The pipeline corridor data collected by the monitoring network is transmitted to the data center in real time through wireless communication, and the received pipeline corridor data is preprocessed and feature extracted. A multi-classification risk prediction model is constructed in combination with historical data and machine learning algorithms to predict the pipeline corridor environment status;
[0010] Step S3: Set up a partition detection strategy, dynamically select the partitions that need to be detected in detail based on the confidence of the multi-classification risk prediction model and real-time environmental data, and estimate the remaining partitions through the selected partition data. At the same time, conduct a risk assessment on the prediction results, and determine the warning level and warning range based on the prediction results and risk assessment results, set a dynamic alarm threshold, and automatically generate warning information if the corridor data reaches the warning level and warning range, and automatically start the emergency response strategy through the fire linkage control device;
[0011] Step S4: Introduce an adaptive learning mechanism to optimize the warning model, zoning detection strategy, and emergency response strategy based on historical warning conditions and disposal effects, visualize the processed corridor data in three dimensions, and regularly maintain and calibrate the monitoring equipment.
[0012] Specifically, the specific steps of step S3 include:
[0013] S3.1: Use neural networks to build a multi-classification risk prediction model and input real-time collected pipeline corridor data Make predictions, where Indicates the temperature data in the pipe gallery. Indicates the humidity data in the pipe gallery. Indicates the gas concentration data in the pipeline gallery. Indicates the vibration data in the pipe gallery;
[0014] S3.2: Set the partition detection strategy rules and the number of partitions to be detected each time;
[0015] S3.3: Set risk threshold h i , i = 1, 2, 3, 4, obtain the prediction results of fire, flooding, vibration and dangerous gas in each partition from the trained neural network model Y = {y 1 ,y 2 ,y 3 ,y 4} and its confidence, and compare the prediction results with the set risk threshold;
[0016] If Y<h i , there is a small risk and normal monitoring continues;
[0017] If Y>h i , there is a higher risk, and a risk assessment is performed on the prediction results.
[0018] Specifically, the specific steps of step S3 also include:
[0019] S3.4: According to the preset detection strategy, select the partition with lower confidence for detection, and use the data of the selected partition, combined with the assumption or model of the environmental correlation between the partitions, to estimate the status of the remaining partitions;
[0020] S3.5: Conduct risk assessment on the prediction results. According to the risk assessment results, divide the risks into five warning levels: very low, low, medium, high, and very high. Based on the warning level, determine the warning range in combination with the risk's spread, impact range, and emergency response factors. Dynamically adjust the alarm threshold based on historical data, real-time data, and risk assessment results.
[0021] S3.6: If the tunnel data reaches the warning level and warning range, the warning information will be automatically generated, and the emergency response strategy will be automatically initiated through the fire linkage control system.
[0022] Specifically, the risk classification formula in S3.3 is:
[0023]
[0024] Among them, Risk scoreIndicates the risk assessment score. Level = 1 indicates very low risk, level = 2 indicates low risk, level = 3 indicates medium risk, level = 4 indicates high risk, and level = 5 indicates extremely high risk.
[0025] Specifically, the emergency response strategy in S3.4 includes: emergency evacuation, emergency lighting, starting the fire extinguishing system, opening the smoke exhaust system, starting the drainage equipment, and formulating a team action plan.
[0026] An intelligent early warning integrated pipe gallery environment monitoring system, comprising: a monitoring network module, a risk assessment module, an optimization module, and a maintenance module;
[0027] The monitoring network module is used to establish a monitoring network and collect environmental data in the integrated pipe gallery in real time;
[0028] The risk assessment module is used to conduct risk assessment on the environmental conditions of the integrated pipe gallery based on the data collected by the monitoring network module to determine whether there are safety hazards or potential risks;
[0029] The optimization module is used to optimize and adjust the operation status of the integrated pipe gallery based on the results of the risk assessment module;
[0030] The maintenance module is used to perform regular maintenance and management of the integrated pipe gallery.
[0031] Specifically, the risk assessment module includes: a risk prediction unit, an early warning setting unit, and an emergency response unit;
[0032] The risk prediction unit is used to perform risk assessment and prediction on the environmental conditions of the integrated pipe gallery based on the data provided by the monitoring network module, and identify safety hazards and risk points by using big data analysis and prediction models;
[0033] The warning setting unit is used to set corresponding warning thresholds and conditions according to the results of the risk prediction unit. Once the monitoring data reaches or exceeds the warning threshold, the system will automatically trigger the warning mechanism;
[0034] The emergency response unit is used to automatically perform emergency processing according to a preset emergency response plan when an emergency occurs.
[0035] Specifically, an electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of an intelligent early warning integrated pipeline corridor environment monitoring method when executing the computer program.
[0036] Specifically, a computer-readable storage medium stores computer instructions, which, when executed, execute the steps of an intelligent early warning integrated pipeline corridor environment monitoring method.
[0037] Compared with the prior art, the present invention has the following beneficial effects:
[0038] 1. The present invention proposes an intelligent early warning integrated pipe gallery environment monitoring system, and optimizes and improves the architecture, operation steps and processes. The system has the advantages of simple process, low investment and operation costs, and low production work costs.
[0039] 2. The present invention proposes an intelligent early warning integrated pipeline corridor environment monitoring method. By deploying a variety of sensors and monitors inside the pipeline corridor, it can obtain real-time and comprehensive environmental data in the pipeline corridor, including temperature and humidity, gas concentration, water level, and vibration. Combined with the video monitoring system, through cloud computing and edge computing, combined with image recognition, pattern analysis methods, and partition detection strategies, the pipeline corridor can be monitored in different areas, which can detect abnormal situations in time and ensure the safe operation of the pipeline corridor.
[0040] 3. The present invention proposes an intelligent early warning integrated pipe gallery environment monitoring method, introduces an adaptive learning mechanism and a remote monitoring and fault diagnosis method, improves the system's prediction and early warning capabilities, realizes remote management and maintenance of monitoring equipment, and reduces the workload of on-site inspections; at the same time, establishes an equipment health file and a fault early warning system, which can monitor the operating status of the equipment in real time, promptly discover and handle potential faults, and improve the reliability and service life of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] Figure 1 A schematic diagram of an intelligent early warning integrated pipe gallery environment monitoring method according to the present invention;
[0042] Figure 2 This is a working diagram of an intelligent early warning integrated pipe gallery environment monitoring method of the present invention;
[0043] Figure 3 This is a multi-classification risk prediction flow chart of an intelligent early warning integrated pipe gallery environment monitoring method of the present invention;
[0044] Figure 4 This is an architecture diagram of an intelligent early warning integrated pipe gallery environment monitoring system of the present invention. DETAILED DESCRIPTION
[0045] Example 1
[0046] See also Figure 1-Figure 3 , an embodiment provided by the present invention: an intelligent early warning integrated pipe gallery environment monitoring method, comprising the following steps:
[0047] Step S1: Deploy temperature and humidity sensors, gas monitoring sensors, water level monitors, and vibration monitors inside the tunnel to form a comprehensive monitoring network, and set up a set of environmental detectors at fixed intervals in each fire compartment, integrating the video monitoring system and sensor network, and using image recognition and pattern analysis methods to perform real-time monitoring and abnormality detection of the internal environment of the tunnel. Among them, the gas monitoring sensor can monitor carbon monoxide, methane, oxygen, and hydrogen sulfide.
[0048] Furthermore, the specific steps of the image recognition and pattern analysis method in step S1 include:
[0049] S1.1: The video images inside the tunnel are captured in real time by cameras installed inside the tunnel. The camera coverage area includes the entrance, corners, and main equipment of the tunnel.
[0050] S1.2: De-noising, enhancing and cropping the collected video images through histogram equalization and filtering to improve image quality;
[0051] S1.3: Automatically identify the target by detecting its shape, color, and texture features, and track it using its motion trajectory information;
[0052] S1.4: Use pattern recognition methods to learn the normal behavior patterns of targets in the tunnel, monitor the behavior of the targets in real time, and compare it with the normal behavior patterns. When the behavior of the targets deviates from the normal patterns, the alarm system is triggered to indicate the occurrence of abnormal behavior.
[0053] S1.5: Monitor multiple areas simultaneously, and use image stitching to stitch images from multiple cameras to form a large picture to avoid blind spots.
[0054] Step S2: The pipe gallery data collected by the monitoring network is transmitted to the data center in real time through wireless communication. The data center uses cloud computing and edge computing methods to preprocess and extract features of the received pipe gallery data, and combines historical data and machine learning algorithms to build a multi-classification risk prediction model to predict the environmental status of the pipe gallery. The wireless communication method refers to a dedicated wireless communication network. The dedicated wireless communication network selected by the present invention has the characteristics of low power consumption, long-distance transmission, and self-organizing network, and is suitable for data transmission in complex environments. At the same time, the edge computing method is the prior art content in this field, and is not the inventive solution of the present application, and will not be repeated here;
[0055] Step S3: Set up a partition detection strategy, dynamically select the partitions that need detailed detection based on the confidence of the multi-classification risk prediction model and real-time environmental data, and estimate the remaining partitions through the selected partition data. At the same time, conduct a risk assessment on the prediction results, and determine the warning level and warning range based on the prediction results and risk assessment results, and set a dynamic alarm threshold. If the corridor data reaches the warning level and warning range, it will automatically generate warning information, sound and light alarms, and automatically start the emergency response strategy through the fire linkage control equipment;
[0056] Step S4: Introduce an adaptive learning mechanism to optimize the warning model, zoning detection strategy, and emergency response strategy based on historical warning conditions and disposal effects, visualize the processed corridor data in three dimensions, and regularly maintain and calibrate the monitoring equipment.
[0057] Among them, monitoring equipment maintenance and calibration include: 1) regular inspection of monitoring equipment, including the appearance, connection status, and power supply of the equipment; 2) testing the various functions of the monitoring equipment to ensure that it can work normally and accurately collect data; 3) calibrating equipment that needs to be calibrated, such as temperature and humidity sensors, gas monitoring sensors, and making necessary adjustments and maintenance to the equipment based on the test results to ensure its stability and accuracy.
[0058] Furthermore, the specific steps of introducing adaptive learning mechanism to optimize early warning model and emergency response strategy include:
[0059] (1) Data collection: Collect historical warning data, including warning trigger time, warning type, and warning level; and collect historical disposal effect data, including disposal response time, disposal measures, and disposal results;
[0060] (2) Data preprocessing: Clean and organize the collected historical data to ensure the quality and accuracy of the data, and perform necessary conversion and formatting on the data to meet the needs of the adaptive learning algorithm;
[0061] (3) Model training and optimization: The present invention selects an adaptive learning algorithm of a decision tree to train the early warning model, and adjusts and optimizes the parameters and structure of the model based on historical data to improve the prediction accuracy and robustness of the model;
[0062] (4) Adjustment of emergency response strategy: Adjust the emergency response strategy based on the optimized early warning model.
[0063] Step S5: Introduce remote monitoring and fault diagnosis methods to remotely manage and maintain monitoring equipment, and establish equipment health records and fault warning systems to conduct real-time monitoring and warning of the equipment's operating status.
[0064] The specific steps of step S3 include:
[0065] S3.1: Use neural networks to build a multi-classification risk prediction model and input real-time collected pipeline corridor data Make predictions, where Indicates the temperature data in the pipe gallery. Indicates the humidity data in the pipe gallery. Indicates the gas concentration data in the pipeline gallery. Indicates the vibration data in the pipe gallery;
[0066] S3.2: Set the partition detection strategy rules and the number of partitions to be detected each time;
[0067] S3.3: Set risk threshold h i , i = 1, 2, 3, 4, obtain the prediction results of fire, flooding, vibration and dangerous gas in each partition from the trained neural network model Y = {y 1 ,y 2 ,y 3 ,y 4} and its confidence, and compare the prediction results with the set risk threshold;
[0068] If Y<h i , there is a small risk and normal monitoring continues;
[0069] If Y>h i , there is a higher risk, and a risk assessment is performed on the prediction results.
[0070] Specifically, the specific steps of step S3 also include:
[0071] S3.4: According to the preset detection strategy, select the partition with lower confidence for detection, and use the data of the selected partition, combined with the assumption or model of the environmental correlation between the partitions, to estimate the status of the remaining partitions;
[0072] S3.5: Conduct risk assessment on the prediction results. According to the risk assessment results, divide the risks into five warning levels: very low, low, medium, high, and very high. Based on the warning level, determine the warning range in combination with the risk's spread, impact range, and emergency response factors. Dynamically adjust the alarm threshold based on historical data, real-time data, and risk assessment results.
[0073] S3.6: If the tunnel data reaches the warning level and warning range, the warning information will be automatically generated, and the emergency response strategy will be automatically initiated through the fire linkage control system.
[0074] The present application sets up a partition detection strategy first, dynamically selects the partitions that need detailed detection based on the confidence of the multi-classification risk prediction model and real-time environmental data, and estimates the remaining partitions through the selected partition data, thereby reducing the number of partition detections and greatly improving the detection speed. The solution based on the present application can also ensure detection accuracy, thereby providing rapid warnings and improving the response speed of environmental monitoring.
[0075] Among them, the warning information includes: event type, warning level, warning range, and recommended response measures, while the triggering sound and light alarm device sends an alarm to on-site personnel through sound and light signals.
[0076] The risk classification formula in S3.3 is:
[0077]
[0078] Among them, Risk score Indicates the risk assessment score. Level = 1 indicates very low risk, level = 2 indicates low risk, level = 3 indicates medium risk, level = 4 indicates high risk, and level = 5 indicates extremely high risk.
[0079] The emergency response strategies in S3.4 include: emergency evacuation, emergency lighting, activation of fire extinguishing system, opening of smoke exhaust system, activation of drainage equipment, and development of team action plan.
[0080] Example 2
[0081] See also Figure 4 Another embodiment provided by the present invention is an intelligent early warning integrated pipe gallery environment monitoring system, comprising:
[0082] Monitoring network module, risk assessment module, optimization module, and maintenance module;
[0083] The monitoring network module is used to establish a monitoring network and collect environmental data in the integrated pipe gallery in real time. It can achieve full coverage and all-weather real-time monitoring of the pipe gallery to ensure the accuracy and real-time nature of the data.
[0084] The risk assessment module is used to conduct risk assessment on the environmental conditions of the integrated pipe gallery based on the data collected by the monitoring network module, determine whether there are safety hazards or potential risks, and provide real-time and accurate risk assessment;
[0085] The optimization module is used to optimize and adjust the operation status of the integrated pipe gallery based on the results of the risk assessment module. Through real-time optimization and adjustment, it can ensure that the environment in the pipe gallery is always kept in the best state, thereby improving the safety and stability of the integrated pipe gallery;
[0086] The maintenance module is used to carry out regular maintenance and management of the integrated pipeline corridor. Through remote monitoring and automated management, it can reduce operation and maintenance costs, improve equipment reliability and stability, and at the same time, reduce the frequency and danger of manual inspections and improve work efficiency.
[0087] The monitoring network module includes: a sensor unit, a wireless communication unit, and a preprocessing unit;
[0088] Sensor units are used to collect real-time environmental data in the utility tunnel, including temperature, humidity, gas concentration, and vibration;
[0089] A wireless communication unit, used to transmit the data collected by the sensor unit to the system center through wireless communication to ensure timely transmission of data and reliable communication;
[0090] The preprocessing unit is used to perform preliminary processing on the raw data collected by the sensor unit, such as data cleaning and format conversion.
[0091] The risk assessment module includes: risk prediction unit, early warning setting unit, and emergency response unit;
[0092] The risk prediction unit is used to conduct risk assessment and prediction of the environmental conditions of the integrated pipeline corridor based on the data provided by the monitoring network module, and identify safety hazards and risk points by using big data analysis and prediction models;
[0093] The warning setting unit is used to set the corresponding warning thresholds and conditions according to the results of the risk prediction unit. Once the monitoring data reaches or exceeds the warning threshold, the system will automatically trigger the warning mechanism to remind the management personnel to take timely measures;
[0094] The emergency response unit is used to automatically carry out emergency processing according to the preset emergency response plan when an emergency occurs, improve the ability and efficiency of responding to emergencies, and reduce losses and risks.
[0095] The optimization modules include: adaptive learning unit and visualization unit;
[0096] Adaptive learning unit, which is used to optimize and adjust system parameters and models based on historical data and real-time data through machine learning algorithms, so as to improve the accuracy and adaptability of the system and enable it to better adapt to complex and changing environmental conditions;
[0097] The visualization unit is used to present the monitoring data and risk assessment results to managers in the form of graphics and tables, and provides a user interface and interaction method.
[0098] The maintenance module includes: equipment maintenance unit, remote monitoring unit, and health record unit;
[0099] Equipment maintenance unit, used to conduct regular inspection and maintenance of equipment in the integrated pipe gallery, timely detect and handle equipment failures and abnormalities, and ensure the normal operation and safety of the equipment;
[0100] Remote monitoring unit, used to monitor and manage the integrated pipe gallery in real time through remote monitoring technology, so that managers can remotely view monitoring data and equipment status information, and perform remote control and operation;
[0101] The health record unit is used to establish and maintain the health records of the integrated pipeline corridor and its equipment, and record the equipment's operating history, maintenance records, and fault information data.
[0102] Example 3
[0103] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of an intelligent early warning integrated pipeline corridor environment monitoring method when executing the computer program.
[0104] A computer-readable storage medium stores computer instructions, which, when executed, execute the steps of an intelligent early warning integrated pipe gallery environment monitoring method.
[0105] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in the field may also change, modify, replace and modify the above-mentioned embodiments without departing from the purpose and scope of protection of the present invention, and all of these are within the protection of the present invention.
Claims
1. An intelligent early warning integrated pipe gallery environment monitoring method, characterized in that: include: Step S1: deploy a comprehensive monitoring network inside the tunnel, and set up a set of environmental detectors at fixed intervals in each fire zone, integrating the video monitoring system and sensor network, and using image recognition and pattern analysis methods to monitor the internal environment of the tunnel in real time and detect anomalies; Step S2: The pipeline corridor data collected by the monitoring network is transmitted to the data center in real time through wireless communication, and the received pipeline corridor data is preprocessed and feature extracted. A multi-classification risk prediction model is constructed in combination with historical data and machine learning algorithms to predict the pipeline corridor environment status; Step S3: Set up a partition detection strategy, dynamically select the partitions that need to be detected in detail based on the confidence of the multi-classification risk prediction model and real-time environmental data, and predict the remaining partitions through the selected partition data. At the same time, conduct a risk assessment on the prediction results, and determine the warning level and warning range based on the prediction results and risk assessment results, set a dynamic alarm threshold, and automatically generate warning information if the corridor data reaches the warning level and warning range, and automatically start the emergency response strategy through the fire linkage control device; Step S4: Introduce an adaptive learning mechanism to optimize the warning model, zoning detection strategy, and emergency response strategy based on historical warning conditions and disposal effects, visualize the processed corridor data in three dimensions, and regularly maintain and calibrate the monitoring equipment.
2. The intelligent early warning integrated pipe gallery environment monitoring method according to claim 1, characterized in that: The specific steps of step S3 include: S3.1: Use neural networks to build a multi-classification risk prediction model and input real-time collected pipeline corridor data Make predictions, where Indicates the temperature data in the pipe gallery. Indicates the humidity data in the pipe gallery. Indicates the gas concentration data in the pipeline gallery. Indicates the vibration data in the pipe gallery; S3.2: Set the partition detection strategy rules and the number of partitions to be detected each time; S3.3: Set risk threshold h i , i = 1, 2, 3, 4, obtain the prediction results of fire, flooding, vibration and dangerous gas in each partition from the trained neural network model Y = {y 1 ,y 2 ,y 3 ,y 4 } and its confidence, and compare the prediction results with the set risk threshold; If Y<h i , there is a small risk and normal monitoring continues; If Y>h i , there is a higher risk, and a risk assessment is performed on the prediction results.
3. The intelligent early warning integrated pipe gallery environment monitoring method according to claim 2 is characterized in that: The specific steps of step S3 also include: S3.4: According to the preset detection strategy, select the partition with lower confidence for detection, and use the data of the selected partition, combined with the assumption or model of the environmental correlation between the partitions, to estimate the status of the remaining partitions; S3.5: Conduct risk assessment on the prediction results. According to the risk assessment results, divide the risks into five warning levels: very low, low, medium, high, and very high. Based on the warning level, determine the warning range in combination with the risk's spread, impact range, and emergency response factors. Dynamically adjust the alarm threshold based on historical data, real-time data, and risk assessment results. S3.6: If the tunnel data reaches the warning level and warning range, the warning information will be automatically generated, and the emergency response strategy will be automatically initiated through the fire linkage control system.
4. The intelligent early warning integrated pipe gallery environment monitoring method according to claim 3 is characterized in that: The risk classification formula in S3.3 is: Among them, Risk score Indicates the risk assessment score. Level = 1 indicates very low risk, level = 2 indicates low risk, level = 3 indicates medium risk, level = 4 indicates high risk, and level = 5 indicates extremely high risk.
5. The intelligent early warning integrated pipe gallery environment monitoring method according to claim 4 is characterized in that: The emergency response strategies in S3.4 include: emergency evacuation, emergency lighting, activation of fire extinguishing system, opening of smoke exhaust system, activation of drainage equipment, and formulation of team action plan.
6. An intelligent early warning integrated pipe gallery environment monitoring system, which is implemented based on an intelligent early warning integrated pipe gallery environment monitoring method according to any one of claims 1 to 5, characterized in that: include: Monitoring network module, risk assessment module, optimization module, and maintenance module; The monitoring network module is used to establish a monitoring network and collect environmental data in the integrated pipe gallery in real time; The risk assessment module is used to conduct risk assessment on the environmental conditions of the integrated pipe gallery based on the data collected by the monitoring network module to determine whether there are safety hazards or potential risks; The optimization module is used to optimize and adjust the operation status of the integrated pipe gallery based on the results of the risk assessment module; The maintenance module is used to perform regular maintenance and management of the integrated pipe gallery.
7. The intelligent early warning integrated pipe gallery environment monitoring system according to claim 6, characterized in that: The risk assessment module includes: a risk prediction unit, an early warning setting unit, and an emergency response unit; The risk prediction unit is used to perform risk assessment and prediction on the environmental conditions of the integrated pipe gallery based on the data provided by the monitoring network module, and identify safety hazards and risk points by using big data analysis and prediction models; The warning setting unit is used to set corresponding warning thresholds and conditions according to the results of the risk prediction unit. Once the monitoring data reaches or exceeds the warning threshold, the system will automatically trigger the warning mechanism; The emergency response unit is used to automatically perform emergency processing according to a preset emergency response plan when an emergency occurs.
8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of an intelligent early warning integrated pipeline corridor environment monitoring method as described in any one of claims 1 to 5 are implemented.
9. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed, the steps of an intelligent early warning integrated pipeline corridor environment monitoring method as described in any one of claims 1-5 are executed.
Citation Information
Patent Citations
Cable pipe gallery comprehensive environment monitoring and early warning device
CN116659579A
A big data visualization system and method for an underground comprehensive pipe corridor
CN109408686A
Comprehensive pipe gallery equipment state monitoring and management system
CN110428135A
Safety production accident potential early warning system based on artificial intelligence
CN118333411A
Intelligent pipe gallery remote monitoring and intelligent management method based on Internet of Things
CN118469498A
Cited By
Real-time monitoring and early warning method for leakage state of long-line public facility
CN119515112A
Cross-platform remote power transmission channel forest fire monitoring and early warning system and method
CN119810994A
Cross-platform remote power transmission channel forest fire monitoring and early warning system and method
CN119810994B
Multi-sensor equipment AI early warning system applied to bulk grain system line
CN119919038A
Emergency communication linkage system and method based on network security early warning
CN120166386A
